NoR sponsored projects

ESA will organize a training course in Riga, Latvia, from 27 June – 1 July 2022, in collaboration with the Ministry of Education and Science of the Republic of Latvia, the Institute of Environmental Solutions, and Riga Technical University. Objective: The training is designed to promote and disseminate EO data and information-based solutions in various scientific and industrial fields. The program will provide theoretical information followed by practical computer exercises and feature the use of Copernicus Sentinel-1 data (SAR sensor) and Copernicus Sentinel-2 data (optical sensor). Audience: The course is intended for researchers, students, Ph.D. students, and young professionals who use EO technology within their research or work and want to improve their knowledge of remote sensing. Preference will be given to applicants from Latvia and other Baltic countries. Main topics: Introduction to ESA EO missions; SAR & optical data for land cover applications, including climate change impact; SAR & visual data for forestry, including climate change impact; SAR & optical data for agriculture, including climate change impact; InSAR data, including terrain motion due to gas; SAR for ship detection; Integrated applications.

In the first virtual workshop ‘Spring School of the 3D Earth project’ organised by the Kiel University, it is presented the outcomes of 3D Earth. The participants learn which data products are available from the project and how they can use them. The workshop is a mixed format of lectures and exercises (each 50 %). It is set in a virtual environment with a Jupyterhub kernel, which makes it possible for all students to execute the exercises in their browser. As all are still located at their home spots, this helps us, to have good control that the technical part works flawlessly and that all participants can follow the exercises even if they have low budget hardware. The workshop has about 50 participants. Therefore, we selected from the Nor Shopping cart the “Medium Computing and Storage by Hour” by Cloud Ferro with the virtual machines for 200 hours of execution time. Some exercises are computationally expensive, in which cases several instances will run in parallel.

This PhD research project aims to analyze land degradation in traditional and mechanically-constructed mountain terrace landscapes in Cyprus. Project objectives are:

1. To enhance existing models for evaluating the stability of terraced hillslopes.

2. To implement such models on large areas using GIS techniques.

3. To develop guidelines for the design and construction of new bench terraces. Those guidelines are expected to address the full spectrum of terrace design and construction (terrace geometry, land utilization, fill/cut percentages, dry-stone wall dimensions, vehicle access roads, field drainage, irrigation network, construction methodologies etc.) on a more practical view.

4. To develop models and methodologies for evaluating the stability of terraced hillslopes.

4DMED-Hydrology aims at developing an advanced, high-resolution, and consistent reconstruction of the Mediterranean terrestrial water cycle by using the latest developments of Earth Observation (EO) data as those derived from the ESA-Copernicus missions. In particular, by exploiting previous ESA initiatives, 4DMED-Hydrology intends: 1) to demonstrate how this EO capacity can help to describe the interactions between complex hydrological processes and anthropogenic pressure (often difficult to model) in synergy with model-based approaches; 2) to exploit synergies among EO data to maximize the retrieval of information of the different water cycle components (i.e., precipitation, soil moisture, evaporation, runoff, river discharge) to provide an accurate representation of our environment and advanced fit-for-purpose decision support systems in a changing climate for a more resilient society.

This project assesses the use of cloud-based artificial intelligence to detect early indicators of water stress across several grass species most common for golf courses and public surfaces. Near-infrared images from Planet scope imagery will be collected. Cropped images of plants in no, low, and high-water stress conditions are split into four-fold cross-validation sets and used to train models through IBM Watson’s Visual Recognition service. Watson generated models can detect indicators of stress after 48 hours of water deprivation with a significant to marginally significant degree of separation. Two models are also able to detect indicators of water stress after only 24 hours, with models trained on images. Ease of pre-processing, minimal amount of training data required, and outsourced computation make cloud-based artificial intelligence services such as IBM Watson Visual Recognition an attractive tool for golf and public green surface agriculture analytics. Monitoring using Sentinel-1 Data Optical imagery can provide invaluable insights into crop growth and development but is severely hampered by cloud cover. This project illustrates the potential value of Sentinel-1 for golf course and public green surfaces. Time series of radar backscatter from the European Space Agency’s Sentinel-1 Mission are analysed and compared to ground measurements including phenological stage and height. Temporal variations in backscatter data reflect changes in water content and structure associated with phenological development. Emergence and closure dates are estimated from the backscatter time series and validated against a photo archive. Coherence data are compared to Normalized Difference Vegetation Index (NDVI) and ground data, illustrating that the sudden increase in coherence is a useful indicator of harvest. The results are presented here that demonstrate that Sentinel-1 data have significant potential value to monitor growth and development golf and public green surfaces.

Urban land cover (ULC) is an essential input in various urban research studies focusing on urbanization trends, land cover change, and urban climate. While urban land surface and climate models use ULC as the main input to evaluate surface energy terms in cities (which are driver of atmospheric dynamics), such models still use ULC data with naive representation of urban areas i.e. MODIS (MODerate resolution ImagingSpectro-radiometer) data that are usually used in Weather Research and Forecasting (WRF) model. Such data does not capture the spatial variability of land cover in cities leading to incorrect prediction of surface energy terms. In addition, they usually do not account for informal settlements areas in the outskirt of cities. Therefore, it is vital to have a precise enough urban land cover data. In the recent years, the emergence of satellite imagery with the help of image processing and machine learning techniques has made it possible to have a better prediction of land cover globally. However, due to the heterogeneity of the land cover fractions in urban areas, it is difficult to distinguish between various surface types in cities (e.g. building roofs, paved surfaces, and soil). One way to address this challenge is to combine the satellite imagery and prediction techniques with the available urban data sets such as building and urban footprints. Therefore, this project introduces a general framework for obtaining the land cover for urban areas by combining the land cover prediction from satellite imagery, and other urban related data sets. It uses Sentinel 2 images to predict the general land cover over urban areas, then it combines the prediction outcomes with global urban footprint data set (GUF) and urban building data sets (e.g. Open Street Map) to obtain a more accurate urban land cover fraction. The aim of the project is to design a pipeline (which will be finally released as an open-source Python package) for obtaining an accurate land cover fraction of a desired urban area. The OSEO OGC services make the design of this pipeline possible due to their available easy-to-use interface. The pipeline contains:

1) using the OSEO OGC interface (more specifically WCS service due to available high-resolution images) to retrieve the necessary Sentinel-2 bands for the first step urban land cover prediction,

2) the predicted land cover is integrated with the available urban footprint data sets in order to distinguish the urban areas from other lands, and

3) finally, building footprint data of the desired urban area is integrated to the previous step to classify the built areas to more categories (buildings, roofs, and roads).

Note that one of the objectives is to make this pipeline automated and easy to use so it is possible to eventually have a global urban land cover fraction. Therefore, OSEO OGC interface and API is a necessity for this project. The final land cover fraction of cities obtained by this pipeline is assessed using the available land cover fractions data for cities like London and Shanghai. The deliveries of the project are an open-source Python package as well as peer-reviewed journal publications.

This study intends to estimate crustal deformation in the form of land subsidence from vertical displacement and velocity maps from SAR products and investigate sub-surface processes using gravity modelling techniques (2D modelling from GOCE products). Sub-surface structures are being modelled from gravity anomalies, and the displacement map from SAR differential interferograms will be obtained from the GEP platform. Although this study is limited by the absence of subsidence rates and uplifts, Bouguer anomaly data from the GOCE satellite data repository was acquired and separated into residual and regional anomalies. Forward modelling of sub-surface structures was achieved from residual Bouguer anomaly, while delineation of faults was done from the total horizontal derivatives of the gravity anomaly. The approach in this study will contribute to the knowledge base on remote sensing applications for crustal deformation studies in sedimentary basins within Nigeria and Africa as a whole.

Furthermore, the integration of GRACE and InSAR will improve the monitoring accuracy of crustal deformation detection as the separation of sub-surface densities modelled from the Bouguer anomaly and the faults delineated from the anomaly gradient corroborate the vertical displacement determined from the InSAR. This supports further probing of the sub-surface interactions that lead to deformation and subsidence in Nigeria and Africa. The objectives of this study will be summarised: To generate displacement and surface velocity maps for the last ten years using interferometric synthetic aperture radar (InSAR) datasets such as the Sentinel-1, ENVISAT, and RADARSAT. The deliverables will be further analysed with gravity anomaly distribution in the study area.

A major challenge facing African agriculture is the lack of field boundary (i.e. parcel) maps. Field boundary maps provide the foundations for understanding the characteristics and extents of agricultural systems and how these are changing. This information is essential to organizations that provide services that smallholder farmers need to improve their yields and access to markets, and to adapt to a rapidly changing climate. This project will develop a comprehensive, high-quality set of labels digitized on PlanetScope imagery over Africa intended for training generalizable, regionwide field boundary mapping models, and for refining and validating models for specific regions and years. The labels will be freely available under a Creative Commons license and hosted on Radiant MLHub, from where they will be easily ingested into machine learning pipelines. To date, no such labeled dataset exists, despite the growing interest across the public and private sectors in mapping field boundaries in Africa.

The primary objective of this project is to quantify surface deformation in the village of Stropones, located in Evia, Greece. Our focus is on validating the accuracy of our differential Global Navigation Satellite System (dGNSS) measurements and solutions by comparing them with displacement values derived from a comprehensive timeseries associated with multiple reference points. In conjunction with our dGNSS measurements, our research team has extensively covered the area using Unmanned Aerial System (UAS) flights and acquired images for the generation of multi-temporal Digital Surface Models (DSMs). The intention is to conduct spatial comparisons between these DSMs and validate the displacement rates obtained through a different methodology. A key aspect of our investigation involves comparing Synthetic Aperture Radar (SAR) remote sensing methodologies with close-range remote sensing techniques. By integrating SAR data into our analysis, we evaluate and cross-verify the surface deformation measurements obtained through different remote sensing approaches. This comprehensive approach not only enhances the reliability of our results but also provides valuable insights into the synergy and complementarity of diverse remote sensing methodologies for monitoring and quantifying ground deformation in the Stropones village area.

The primary objective of this project is to develop, implement, validate, and showcase advanced AI-based methods to automatically map and characterize the spatial extent of slums from Earth Observation (EO) data. This objective is framed and informed by the data needs of national and local governments and civil society to monitor progress on SDG indicator 11.1.1 on the proportion of the urban population living in slums, informal settlements, or inadequate housing. Furthermore, the objective is linked to the information needs of a diverse group of stakeholders that engage in understanding and improving local living conditions.

The primary objective of this project is to develop, implement, validate and showcase advanced AI-based methods to automatically map and characterize the spatial extent of slums from Earth Observation (EO) data. This objective is framed and informed by data needs of national and local governments, as well as the civil society, to monitor progress on SDG indicator 11.1.1 on the proportion of the urban population living in slums, informal settlements or inadequate housing. Furthermore, the objective is linked to the information needs of a diverse group of stakeholders that engage in understanding and improving local living conditions.

The purpose of this Master Thesis is to demonstrate, through a non-commercial and automatic way, how to map out large-scale accumulations of products by using modern techniques and accessible data.

The primary objective in both zones is to identify and quantify tectonic ground deformations (and volcano-tectonic ground deformations in the case of El Salvador) by combining INSAR analysis and GNSS data from geodetic networks that are installed around the main active faults and volcanoes of the region. In the case of SE Spain, the study will focus on the active faults of the Eastern Betics Shear Zone (EBSZ) bounding the Guadalentin tectonic depression: the Alhama de Murcia and Carrascoy faults, both faults with high seismic hazard in the Iberian Peninsula. We have been establishing a continuous GNSS network around these faults since 2016 (Staller et al. 2018), and until now, four campaigns have been carried out. GNSS velocities will be used to validate the InSAR results. In the case of El Salvador, our main objective is to estimate the deformation field across El Salvador volcanic arc to determine spatiotemporal variations of the slip rate along the El Salvador Fault Zone (ESFZ). Geodetic estimates of slip rates along the ESFZ have been published by Staller et al. (2016) using 30 GPS campaign stations measured from 2007-2012

The objective(s) of this project are the following: (1) Identify factors that differentiate micro and small enterprises (MSEs) that can successfully integrate digital technologies in their business operations from those that don’t. (2) Deepen understanding of the exposure of MSEs to climate shocks and their resilience to climate impacts, as well as the role of digital adoption in risk management and risk coping. (3) Identify the key challenges faced by women-owned MSEs, including their ability to leverage opportunities offered by digital technologies. Learnings from this research will be made public and be used to influence investors, financial services providers, and policymakers.

The objective is to offer a comprehensive, efficient and cost-effective approach to quantify the economic impacts of the Covid-19 crisis for ADB in developing countries in Asia using Earth Observation (EO) data where conventional data sources are insufficient, not up to date or if data is not available. To do so, Earthlab AI data science team uses EO data from Copernicus program and PlanetLabs commercial data when available as a proxy for economic indicators such as GDP, Manufacturing Output, Production Output, Tourism Activities. The aim is to find correlation between insights generated from EO data and economic indicators. With these correlations, it is possible to provide more frequent forecast of the economic activities of a region. As deliverables there are the country level dashboard with quarterly, monthly, and weekly reports of various insights agreed upon with ESA and ADB teams. Showing historical data as well as forecasts updated daily.

The objective of this project is to provide training and high-resolution NDVI and NDMI maps to facilitators of the Alito Training Center in Uganda (who manages the Alito Farm) in order to optimize farm inputs, maximize yields, and to promote sustainable agriculture practices.

This project aims to:

• Review and evaluate existing remote sensing methodologies used in forest health assessment, including their strengths, weaknesses, and applicability under different forest conditions.

• Identify gaps in the existing methodologies for assessing forest health using remote sensing techniques.

• Propose an advanced remote sensing technique or set of techniques that could be used to better assess forest health, addressing the gaps identified in objective 2.

• Develop a prototype or pilot study applying the proposed advanced remote sensing techniques to a specific forest or set of forests.

• Evaluate the effectiveness of the proposed techniques by comparing the assessment results to those of traditional methods and/or ground-truth data.

• Propose guidelines for implementing the advanced techniques on a broader scale and discuss potential applications and implications for forest management and conservation.

The primary objective of this project is to accurately determine the authentic positions of moving targets, specifically ships, in maritime environments. We plan to integrate advanced Deep Learning technologies with Synthetic Aperture Radar (SAR) signal processing techniques to achieve this. One of the key challenges in using SAR for maritime surveillance is the positional distortion that occurs when detecting moving targets like vessels. Traditional SAR-based ship detection methods often yield inaccurate positions due to the Doppler shift effect. This is a significant issue as it compromises the reliability of the ship detection data, which in turn affects maritime security, environmental protection, and navigational safety. Therefore, two distinct analyses are essential for effective vessel detection. Firstly, a vessel identification algorithm is needed. The purpose of this algorithm is to detect vessels, thereby enabling us to select the specific objects for which we need to extract precise positional data accurately. Accurate identification is the cornerstone upon which the subsequent steps of the project are built.

Secondly, a position restoration algorithm is required. This algorithm will be implemented based on the results of the vessel identification process. Its primary function is to determine the authentic position of the vessel by calibrating azimuth shifts that occur in high-resolution SAR data. The algorithm aims to provide a more accurate and reliable representation of a vessel’s true location by correcting these shifts. This breakthrough stands to revolutionize maritime surveillance in multiple ways. The system will bolster environmental protection and navigational safety by delivering precise, real-time vessel positions. Accurate data will enable more effective monitoring of illegal activities such as unauthorized fishing and oil spills. In contrast, real-time positioning will mitigate the risk of maritime accidents like collisions.

The objectives of the project are:

• Continue to update the Web base Mapping Applications with improved accuracy and usefulness to the avocado industry and build on the solid progress.

• Yield forecasting model supporting other benchmarking project and crop forecasting and continue to allow investigation into the relationship between climate and yield to inform the remote sensing climate-based yield prediction model.

• Expand testing and structured feedback process to allow for improved decision-making and orchard management by producers using the CropCount Mobile Application as a means of improving productivity.

• The CropCount Moblie Application will also support avocado growers with new plantings or no historical data (that would be used in the time series analysis).

Investigate (propose a solution) how sustainable agriculture can be achieved in the African continent under drought conditions by co-developing innovative scientific EO-based and state-of-the-art modelling solutions with African experts. The project aims at increasing experts’ knowledge and capacity, developing an operative platform and database for results visualization and sharing with end­users.

The AFRI-SMART project will tackle this challenge in Morocco.

Objective 1. EO-based solutions addressing sustainable agriculture and drought monitoring for Morocco:

• Estimating water availability and crop irrigation water needs under a changing climate at multiple spatial scales at present and forecasted times;

• Improve water management at the national scale for present and forecasted water availability.

Objective 2. Agile development along all project phases to maximize the impacts and to guarantee that the final output is responsive to necessities. Sharing project approaches and activities, defining the output indicators, and customizing the web tool, so that uptake will be easily promoted in the stakeholders’ habits. Data repository and a web dashboard.

Objective 3. Integrated use of multiple earth observation data with hydrological – crop modelling schemes at different spatial and temporal resolutions (from SMOS soil moisture data to Landsat/ECOSTRESS land surface temperature and Sentinel-2 vegetation information).

As part of AGEO-INTERREG project, several Citizens’ Observatory pilots on geohazards (landslides, rockfalls, floods, peat movements, earthquakes, coastal hazards, geotechical risks) are being launched in France, Portugal, Spain, Ireland and UK. The use of EO processed products will be useful to analyze the hazard as a process through the estimation of deformation rates, flooded areas and geomorphological parameters, which will be extremely useful in the risk management tasks. Moreover, AGEO aims to encourage the local use of innovative EO products and services provided by European data infrastructures.

The project aims to face food insecurity using modern technologies, including remote sensing. The number of people worldwide affected by hunger increased in 2020 under the shadow of the COVID-19 pandemic. After remaining virtually unchanged from 2014 to 2019, the prevalence of undernourishment ascended to around 9.9 percent in 2020 from 8.4 percent a year earlier. In terms of population, taking into consideration the additional statistical uncertainty, it is estimated that between 720 and 811 million people in the world faced hunger in 2020. Considering the middle of the projected range (768 million), 118 million more people were facing hunger in 2020 than in 2019 – or as many as 161 million, considering the range’s upper bound.

Unless bold actions are taken to accelerate progress, primarily measures to address significant drivers of food insecurity and malnutrition and the inequalities affecting the access of millions to food, hunger will not be eradicated.

So we should use all of our tools to face this dilemma, and we, as gis and remote sensing and artificial intelligence experts, should use our techniques.

We believe we should develop applications that provide helpful information for the leading players in the field of agriculture who make food for us. In addition, we need to make our agricultural procedures more innovative and intelligent.

So the added value of our project would be providing valuable insights for agriculture sector players to help them make more efficient decisions.

Copernicus Sentinel data are used to detect irrigation on agricultural fields in Austria by the Environment Agency Austria to understand water usage in time and space. This helps to prepare and inform current and future water management policies and measures in the country. Together with the support of EODC we work on processing workflows to integrate Earth Observation data into our ongoing project activities. Austria has been and is likely to remain a water-rich country overall, although the degree of water supply varies from region to region. For example, the water-poor region of Pannonia in eastern Austria is expected to suffer more often from severe water shortages in the future. As farmers are currently dependent on irrigation, they will be the first to suffer from increasing scarcity. Against this background, the Environment Agency Austria (UBA) has been investigating how remote sensing and EO data can help to better identify where and when irrigation takes place, supporting the Federal Ministry of Agriculture, Forestry, Regions and Water Management to prepare future-proof water management policies. This will support better management of permits for water use of farmers, considering future climatic changes such as new precipitation patterns and prolonged droughts in Austria.

Agriculture Virtual Laboratory strives to make an attractive offer to the science community for implementing and executing end-to-end workflows with EO data and derived products. Embracing open science principles, AVL enables researchers to access, share, visualise, process and validate a variety of relevant data sets. Moreover, algorithms and workflows c developed within the virtual laboratory may be published and shared, thus fostering collaboration at all stages of research. To this end, the AVL system integrates several components:

– A web-based Workspace including a Jupyter Service, a visualisation service, the interface to the Thematic Processing Subsystem, and an overview of own data and algorithms,

– the Thematic Processing Subsystem offering an engine for numerous common workflows and tools for agriculture research, e.g. Sen2Agri and Sen4CAP but also generic tools such as SNAP, gdal, and Orfeo,

– the Exploitation Subsystem providing convenient access to all data in a common analysis-ready format thus greatly facilitating the development and execution of complex workflows involving multiple datasets.

– The data access layer, connecting heterogeneous data sets from different sources to AVL, hence greatly decreasing, the burden of data management for researchers.

AVL is intended to be a community-based, long-term initiative facilitating the continuous development of expertise and knowledge in agricultural monitoring and modelling based on the evolving Earth Observation (EO) capabilities. The activity has recently entered the pre-operational phase and a first set of Early Adopters have been onboarded to implement their research projects. According to the Early Adopters’ proposals, substantial thematic processing will be required. To this end, AVL offers a scalable Thematic Processing Subsystem, for which the computational resources are requested here.

The CCN 1 of the Agriculture Virtual Laboratory (A VL) project aims at supporting the

continuation of some activities from the previous Sen4CAP project. The Sen4CAP project developed, validated and demonstrated an open-source toolbox (Sen4CAP system), which can automatically process Sentinel-I SLC and Sentinel-2 LIC or L2A time series into a set of products which are relevant for the new Common Agricultural Policy. The main users of this toolbox are national Paying Agencies (and/or their sub-contractors specialized in EO), but also the private sector and researchers. The system is available on the web (http://esa-sen4cap.org/) and was already downloaded more than 330 times at the end of the project. The Sen4CAP project fully relied on CREODIAS for the EO processing and was already supported by NoR.

The activities included in this A VL CCN I cover four different aspects:

1. Continue supporting the users of this Sen4CAP toolbox

2. Continue organizing webinars to inform the Sen4CAP user community about the toolbox itself

but also, about all technologies related to the new CAP

3. Supporting the system’s evolution: maintenance and development of new functionalities

4. Supporting the definition of a roadmap for the Green Deal policy-related future Applications

development.

Farms invest time and money to improve yields, but available solutions help by only 10-30% and are insufficient for rising food demand. Our company provides the first autonomous irrigation and fertigation system with recorded yield improvements of 200%+ and significant water and nutrient conservation enabled by a proprietary soil optimization algorithm. Our AI solution continuously collects real-time plant and soil data, determines precise irrigation and fertigation commands, and executes them on demand to maintain an ideal soil environment around the clock. Farms using Agrinoze can implement unique agrotechnical, and regenerative farming approaches incompatible with typical irrigation regimes, minimizing environmental and economic costs of food production. Agrinoze transforms farms into efficient and profitable local producers while paving a sustainable path to global food security. Access to satellite imagery will help us further optimize Agrinoze’s monitoring capabilities, leading to more significant yield improvements and resource-use efficiency. We are looking to implement satellite imagery to increase accuracy in two main areas:

1. Monitoring vegetation to improve our irrigation algorithm, which is currently based solely on in-field sensors.

2. Monitoring proper functioning of the irrigation system (lack of water, leakages etc.) to reduce waste of precious resources such as water and fertilizer and eliminate production loss.

This project aims to map the spatial and temporal evolution of micro agro-urban landscapes which have emerged within – and as an unintentional result of – the rapid urban expansion in the cities of Guangzhou and Wuhan, China. Composed of individually cultivated vegetable and crop gardens, these landscapes were established by ordinary citizens in urban spaces which they consider to be “wasted”, e.g. stalled or stagnant construction sites, mismanaged green spaces, unused spaces underneath elevated viaducts. In these spaces, without any form of overt organization or institutional support, people are slowly, but cumulatively, converting urban land into rural landscapes. From an initial study of Wuhan conducted through Sentinel-2 data, the physical impact of this seemingly scattered practice at the urban scale was shown to far exceed existing expectations. While this phenomenon may superficially be interpreted as a symptom of the various failures of rapid urbanization, an hypothesis is that it also provides an opportunity to examine an alternative urban future of the city as a rural-urban.

Objectives: Agriculture is one of the few sectors that humanity can not live without, where the climate impact is large (20% of total emissions in Sweden) and furthermore assumed to be difficult to do something about it. However, increased agricultural productivity, i.e. more photosynthesis, results in positive climate effects which IPCC does not fully count. Huge amounts of CO2 are caught by crops that, in turn, generate huge amounts of O2. The yearly agriculture carbon dioxide binding capacity is approximately 15 tons per hectare (crop harvest, straw and roots) The operational understanding of what really happens in a field when crops are growing are clearly lacking in spite of the tremendous amounts of data that modern agriculture equipment is gathering. This results in suboptimal decisions for land use, crop selection, machine usage, fertilization and irrigation for both economic productivity and the climate. Remarkable is that the very detailed harvest data (measurements every fifth second) which have been collected by harvesters for many years is hardly used for operational feedback at least not in Sweden. The project will use AI to quantify limiting agriculture factors, to optimize crop growth in a climate beneficial way and long-term agriculture productivity. Hushållningssällskapets existing

platform markkartering.se will be used for operational usage of the results by the farmers as prescription files for the agriculture equipment.

Extensive field, soil, satellite and sensor data will be used as input to model algorithms driven by Al /ML and spatial analysis (GIS). These algorithms will over time be used to create prescription files to control inputs and other actions in the fields as efficiently and climate friendly as possible. The project objectives are:

#To create a climate positive prescription file model as a decision tool for the next level of precision agriculture. In the end, the result will be presented as prescription files for field equipment, including autonomous vehicles. The results can also be obtained in table form, text or as an interpolated map.

#Expand and enhance Hushållningssällskapet (the Rural Economy and Agricultural Societies) web- based decision support system Markkartering.se (that today has over 2000 active users, about 800 000 hectares) to support as climate friendly and operationally efficient production of food as possible. This will optimize the agricultural climate-affecting factors in multiple ways: #Enhance crop growth and thus bind more carbon into the soil that slowly heals high levels of greenhouse gases;

#Optimize agricultural machine usage and driving;

#Optimize inputs like fertilizers and pesticides;

#New governmental directives that focus on long-term sustainable climate improvements.

The result of our project will be gender neutral however we will try to develop a tool that will change the values of agriculture and in the long-term increase equality both in agriculture and in AI. The project potential of an increased gender balance for farmers is to offer an advanced decision basis that is easy to learn and use for all genders.

Today, we live in an age of frequent disasters, such as the Türkiye-Syria earthquake, and many other disasters that occur every year. However, the “memories of disasters” are overwritten and forgotten with time. To make the most of these “memories of disasters” and the people’s experiences to the next generation, it is necessary to share and pass on the memories of disaster victims to society. However, such precious memories of individuals will eventually be lost due to aging and death. To share “individual memories” and preserve them as “social memories”, it is necessary to create a system to preserve and record the memories that have happened and will occur again in the future. In this sense, “digital archives” are important as a foundation for preserving and sharing such memories and passing them on to the future. The Hidenori Watanave Laboratory has been developing and operating a “Digital Archives Series”. However, they have been developed and operated mainly with annual research funds, and there are concerns about their sustainability. In addition, we would like to incorporate advanced technologies such as virtual reality and artificial intelligence into these archives with the cooperation of many people to develop more user-friendly archiving systems. We have released many web applications. And it’s getting a lot of attention in the media in many countries.

The AI for the Arctic (AI4ARCTIC) project applies deep learning, in particular deep convolutional neural networks, for Earth observation applications within the cryosphere, focusing on sea ice and snow. The project trains deep-learning systems from relevant training data and tests and demonstrates the capability of deep learning by applying it to a large-scale inference of cryosphere-related variables. The project focuses on two use cases, one on snow mapping in Scandinavia and the other on sea ice charting in the waters around Greenland.

Land management and management of cultivated land plays a central role globally to sustain economic growth and will play an ever-important role in reducing the impact of climate change. Earth Observations (EO) information is particularly suited for land management applications, as it provides global coverage at high spatial resolution and high revisit frequency. In particular, data from the Sentinel-2 satellites, freely available through the Copernicus programme, have opened up new and unique opportunities. This challenge aims at exploring novel Artificial Intelligence (AI) methods to push the limits of Sentinel-2 time-series beyond its 10-meter pixel resolution. In particular, the challenge will focus on cultivated land, given its paramount importance for sustainable food security and global subsistence. This activity is part of AI4EO.eu project funded by ESA, managed by Phi-Lab. The aim of this challenge is to create AI methods that can exploit the temporal information of Sentinel-2 images to enhance its spatial resolution. The task to be solved by challengers will be to estimate a cultivated land binary map at 2.5 metres spatial resolution given as input a Sentinel-2 time-series at 10 metres spatial resolution, therefore resulting in a 4x spatial resolution enhancement. We are looking into how to make the challenge more “user-friendly” by exploiting various existing services provided by Euro Data Cube. All Sentinel-2 data will be streamed using Sentinel Hub, the labels will be ingested either in Sentinel Hub (using BYOD) and/or geoDB. The challenge’s “starting point” will be prepared in Jupyter Notebook (JN), published on EDC Marketplace (free offering, useful also beyond the challenge’s duration). There is the option for the participants to make use of Xcube features within the JN and of EOxHub Workspace hosted processing (with or without GPU-powered resources).

The AI4FOOD project investigates advanced Artificial Intelligence (AI) and Machine Learning (ML) techniques to develop new algorithms for the creation of fused (with a focus on Sentinel-1 SAR and Sentinel-2 optical) continuous data streams and evaluate aspects such as time series predictability over different land environments. A consortium of industry experts on data fusion and time series techniques, and open-source implementation and operational service provision to users do this. Within AI4FOOD, the consortium strives to create an open-source, modular, extensible, and reusable toolbox called fuseTS. To support the fusion of complementary EO data streams and time series analytics, relevant algorithms will be integrated into the toolbox as a service.

Next to the FuseTS Python library, which can be installed locally, the AI4FOOD toolbox will also be available as a cloud-based on-demand service. Existing operational services, such as the OpenEO platform and Euro Data Cube, will be used for the actual deployment. This cloud-based implementation will lead to a scalable software-as-a-service (SAAS) approach, ensuring that a wider group of users can implement data fusion and time series analytics techniques to develop EO-based services. The algorithms that are included in the toolbox are demonstrated through 3 real-life use cases:

• Subtle Land Cover Change Monitoring (FAO)

• Cropland Phenology Indicators (ITACyL)

• Agriculture and Land Management Activities Identification (Agency for Agricultural Markets and Rural Development, Slovenia)

As part of our Corporate Social Responsibility initiatives, we are working on a use case concerning whales. Overall, this use case would like to support remote detection of the whales and enable a lower rate of collision between whales and ships, to safeguard these whales. Whales are one of the most important species of and for our ecosystem. Yet, humans are primarily responsible for endangering this species, as many whales die from collisions with ships that cross their seasonal paths. We intend to automatically detect the whales’ locations by using AI algorithms within VHR satellite imagery and, depending on the training data quality, to detect the species of it. For training data, we have the logs of a few organizations that are also freely available. Manual detection of these animals in vast areas through satellite imagery is time-consuming and prone to error. By utilizing VHR satellite imagery of different areas, especially in the regions that whales usually cross, we want to identify the location of whales (in near-real time). After detecting their location, this information would be communicated to ship captains and respective organizations. Through this, we want to decrease the number of collisions and contribute to saving the species of whales and ensure their existence. Through our use case, we want to contribute indirectly to maintaining and improving our fragile ocean ecosystem.

ARGANS Ltd is sub-contracted to INDRA to deliver use case 3 in the GDA Disaster Resilience project. This use case will supply innovative products to support coastal change analysis and investment decisions. Use Case 3 will monitor coastal trends along the Volta Delta, including Keta & Songhor Lagoons in Ghana (reaching just across the border with Togo) to support the WACA program.

This use case will support Ghanaian institutions in assessing how natural events, including climate change and human intervention along the coast (such as coastal engineering and sand extraction), have affected coastal dynamics (or morphologies), so they can advise on their significance.

The main objective is to provide coastal change indicators derived from Earth Observations. One of the key user requirements is to optimise how many images can be made available, i.e. cloud free in the coastal area. In addition, one of the tasks will be to provide customer-ready co-registered waterlines and shorelines seasonally covering 25 years with enough examples to “bracket” any severe weather events or anthropogenic events such as harbour developments or sea defence construction.

The AIOPEN project will combine and extend the existing frameworks ASB (Automated Service Builder), EOPEN (Open Interoperable Platform for Unified Access & Analysis of EO Data), and EOEPCA (EO Exploitation Platform Common Architecture) with new and innovative services based on operationally mature AI /ML software capabilities to build a new platform that supports the end-to-end AI model development lifecycle.

This research aims to overcome critical limitations in air pollution monitoring by leveraging satellite data and machine learning techniques. Existing street sensor-based measurements suffer from spatial scarcity, hindering accurate pollution assessment. Satellite remote sensing offers a solution, but its coarse resolution hampers source identification. Addressing these gaps, this study will utilize Sentinel 5P satellite data, Sentinel 2 satellite data, ground-based sensors, Open Street Map API, and traffic data to estimate air pollution with fine resolution across Europe. Ultimately, this research will advance the understanding of urban air pollution dynamics, and contribute to environmental science, remote sensing, and machine learning domains

Our Agriculture Innovation using Remote Sensing (AIRS) project intends to combine the areas of artificial intelligence and remote sensing to create a technological solution to monitor the grape leaves in vineyards using satellite images obtained by the European Space Agency. The correct assessment of these variables allows for sustained decisions to be made with an impact on the management of agricultural areas. Furthermore, implementing precision agriculture practices enables the reduction of pesticides and waste or irrigation water, resulting in a more sustainable agricultural system and the development of rural communities. The AIRS project’s innovation consists of using artificial intelligence to use high-resolution images acquired by Unmanned Aerial Vehicles to increase the resolution of images coming from the Sentinel-2 satellite. The project foresees the implementation in the vineyards of the members of Adega Cooperativa de Pinhel, with the results later made available to the agricultural community through an online platform.

The objectives of this project are to further our understanding of (i) associations, (ii) causal effects, and to enable (iii) prediction of the impacts of the environment on human health.

Understanding their impact on human health becomes increasingly crucial as extreme weather events become more frequent. However, the utilization of Earth Observation to effectively analyze the environmental context concerning health remains limited. This limitation is partly due to challenges in obtaining appropriate environmental indices across different geographical levels and timeframes.

We conducted a preliminary investigation for 2020 (the first year of COVID-19), for which we collected spatio-temporal indices for all Lower-Layer Super Output Areas in England. These indices include indicators such as prescriptions associated with five medical conditions (metabolic, respiratory, and mental health issues), opioids and total prescription prevalence, as well as environmental factors (totalling 42 point features and four seasonal satellite images, resulting in 44 composite satellite image bands) and sociodemographic characteristics (over 100) linked to these health conditions in existing literature.

We evaluated the plausibility of our dataset for modelling population health by predicting the prescription prevalence associated with various conditions with models such as Spatial Lag Model (SLM) and LightGBM. These models can explain 35% to 61% of variance in prescriptions for different situations. We also demonstrated the usability of our dataset for modelling health disparities and inequality across England.

Precise county-wide crop yield prediction provides valuable information for regional agriculture planning. However, it remains challenging for such an accurate forecast due to the effect of complicated weather and soil factors. The short-term weather variations, governed by the meteorological data during the growing season, and the long-term climate change, headed by historical aspects, are among the critical factors that dictate crop yields simultaneously. This project plans to develop deep learning-based solutions for predicting crop yields at the county level across the United States by using the visual Sentinel-2 satellite imagery data and the numerical data computed from the Weather Research and Forecasting with High-Resolution Rapid Refresh (WRF-HRRR) model. We first produce suitable datasets for any location of interest (e.g., a county/ parish) for model developments. Then, the transformer­based solutions will be developed to capture the direct impact of short­term weather variations on crop growth, learn the high-resolution spatial dependency among counties for precise crop tracking, and capture the effects of long-term climate change on crops. This project will result in a set of location-specific datasets available for public downloading to broadly impact the research community in data science, artificial intelligence, meteorology, and agriculture, among others. In addition, the developed deep-learning models will be packed into software toolkits or application portals for stakeholders (including farmers) to use.

This development aims to align multiplatform SAR data in time and space, although not limited to SAR data alone, and to label reference data as the input of the data training in machine learning. In this way, it will meet the scientific needs defined by ESA and synergize the platform with existing ΕΟ platforms as requested by ESA. To do so, we propose to 1) maximally extract and well document the key parameters and signatures, e.g. metadata, and generate standard products and tailor-made products, such as radar indices/indicators for SAR and machine learning applications, of historical and new SAR data acquired particularly from open access missions; 2) develop and implement methods to provide high-accuracy SAR benchmark data, and align time x space SAR data, when these data, the area of interest and time interval are pre-defined by the users. Note that our team has been devoted to this endeavour as we developed a spatiotemporal SAR alignment method based upon probabilistic analysis and Monte Carlo simulation; 3) develop a tool to accurately convert available geospatial data from other sources such as Lidar, GPS and cadastral archives, to a uniform coordinate reference grid; 4) develop relevant quality control metrics; and 5) develop and append relevant functions of the processing operators, user-defined functions, and provide demonstrations and examples.

This project aims to implement a demonstrator for a Digital Twin Earth precursor, establishing the Destination Earth vision with a focus on the Alps. The developed solution will enable a holistic representation of some significant physical processes specific to the Alpine context, powered by a unique combination of Earth Observation data analytics, machine learning algorithms, and state-of-the-art hydrology and geohazard models. The resulting Digital Twin Earth precursor will provide an advanced decision support system for actors involved in observing and mitigating environmental risks and impacts in the Alps and integrating resource management. The implementation of the demonstrator in the scope of this project will enable the creation of a development roadmap to support the migration from currently available capabilities and merging developments to complete the development and implementation of the DTE.

Europe Union is one of the more significant cocoa and coffee buyers, and most of these crops today are managed by smallholder farmers (less than 4 ha). Nevertheless, new considerations have been developed for approving buying these crops from farmers, mainly focused on forest conservation, which today is a barrier for small farmers to prove their conservation activities without incurring expensive certification costs. That’s why we want to develop a scalable way to help farmers demonstrate their work and efforts, looking for these objectives:

• Develop an algorithm using temporal data and low resources algorithms to detect deforested, reforested and conserved areas with confidence higher than 80%.

• Develop a scalable, low-cost service to help smallholder farmers validate their conservation efforts.

• Generate proofs of conservation to help cocoa farmers adapt to new Europe legislation for forest conservation.

Emissions of ammonia to air from the agricultural sector have large negative societal impacts. Ammonia contributes to eutrophication and acidification of terrestrial and marine ecosystems and loss of biodiversity. Despite its central role in many environmental threats, the uncertainty in agricultural ammonia emissions is large. This project aims to improve the quantification of agricultural ammonia emissions at European scale using earth observation and meteorological data which will increase insight in the temporal dynamics of agricultural practices and emissions over the year. The contribution of the agricultural sector to nitrogen deposition in Europe will thus be quantified, being a crucial product in view of biodiversity impacts. The overall objective of AMARETTO is to quantify the impact of agriculture on loads of ammonia at European scale based on the optimization of a dynamic agricultural emission model within LOTOS-EUROS through earth observation products. Specific objectives of AMARETTO are to:

1. Improve the understanding of processes and mechanisms that induce the variability in ammonia emissions, concentrations and deposition;

2. Develop methodologies and parameterizations to detail agricultural emissions with remote sensed information on practices, vegetation growth, surface conditions and atmospheric concentrations; 3. Provide novel ecosystem specific nitrogen deposition distributions based on detailed ammonia emissions and assimilation of satellite data.

The quantification of agricultural ammonia emissions at European scale are improved using earth observation and meteorological data which will increase insight in the temporal dynamics of agricultural practices and emissions over the year. The atmospheric ammonia budget is modelled using LOTOS-EUROS. The novel emission product is verified using ammonia column data from IASI and CrIS and in-situ observations. Finally, ammonia emission strengths is inverted from the IASI data with LOTOS-EUROS. More in detail, the activities are:

1. Improvement of spatial and temporal allocation based on available models

1.1. Inclusion of spatial allocation with INTEGRATOR

1.2. Inclusion of time dependent housing and application emissions: agricultural activity timer

2. Improvement of spatial and temporal allocation in available emission models

2.1. Improvement of the spatial allocation of farming practices by using crop classification with Sentinel-1 and Sentinel-2 remote sensing data

2.2. Improvement of the temporal allocation in farming practices.

The main reason to use Sentinel-hub is the amount of data involved. The project focuses on land classification, first focus on the Netherlands and Germany, then apply it to other region in EU. The spatial domain is rather large so it takes very long time to download on Copernicus data hub, especially for multiple years. Moreover, there is no need to use all bands of Sentinel-2 data for classification, but use and explore combinations of selected bands and various vegetation indices. Therefore, Web Coverage Service (WCS) is very useful, since it makes possible to extract calculation results directly without downloading all bands, which saves a lot of local computation power and processing time. The output of this work is ammonia emission data with high spatial details and temporal dynamics. Four papers were planned to be published. The project fund comes from Netherlands Organisation for Scientific Research (NWO).

The primary objective of the AMoKI project is to develop a machine learning (ML)-based semi-autonomous system for monitoring excavation sites using satellite and governmental data. This system can enhance the precision and efficiency of land use and excavation volume monitoring, providing a robust tool for sustainable land management and resource security. The project will create a reliable system for accurate land use change detection and 3D volume calculations, essential for effective excavation site management. By combining Sentinel-1 and Sentinel-2 satellite data with governmental data, comprehensive and up-to-date monitoring solutions can be delivered. Automating the data collection and analysis processes reduces manual efforts, increases transparency, and ensures consistent data quality. Government authorities can improve tools for monitoring, planning, and decision-making in land management and resource allocation. Mining and excavation companies can benefit from more efficient regulatory compliance and better planning data. Environmental organizations and communities have access to more transparent and accurate information, facilitating better environmental protection and community engagement. The results are made publicly available for research and educational purposes. Key data sets, the trained ML model, and project documentation are accessible on public repositories such as GitHub under open licenses. A web-based demonstrator tool is also available online, allowing stakeholders and the general public to explore the project outcome.

The project aims to introduce the training process on specific platforms such as EO BROWSER, Google Earth, and QGIS. Calculations of the volume of salt harvest in the province of LA PAMPA during 2016-2021. Develop a theoretical, practical, and methodological approach to address a control between calculated and declared minerals. The work will include the location, recognition, and digitization of salt harvest beaches from 2016-2021. This will allow a calculation of the annual production volume that will be compared with the volumes declared by the production companies, thus developing a virtual control technique. The images used are those provided by the EO BROWSER platform, which will be digitized with QGIS, and from this, the calculation of harvest areas and volumes will be carried out.

This research aims to understand the quantity and properties of landslides that can be predicted to likely occur given a particular typhoon level or rainfall event and landscape. This will help establish the basis for increased landslide disaster resilience through early warning.

1. To map and characterise multiple landslides triggered by various meteorological events in several areas in the Philippines, contributing to the build-up of inventories for typhoon events;

2. To utilise existing automatic methods of landslide mapping, i.e. ALADIM-HR: Automatic LAndslide Detection and Inventory Mapping from multispectral HR (S2 or L8) data; and/or the NDVI equation in QGIS;

3. To assess the impact of antecedent rainfall vis-à-vis triggering rainfall (threshold) vis-à-vis soil moisture in multiple landslides;

4. To assess other geomorphologic factors that influence particular slopes to be susceptible to landslides.

The project is part of the broader research activity currently underway for the archaeological areas of Gabii and Villa Adriana, carried out by the University of Rome Tor Vergata. Although numerically abundant, the preservation of the archaeological sites on the outskirts of the town is often placed in the background compared to that of the “central” archaeological areas. However, natural phenomena linked to normal soil transformation processes are often accelerated by atmospheric phenomena caused by ongoing climate change. The risk of hydrogeological disruption of many ancient sites is one of these. The archaeological area of Gabii, active from the Iron Age to late antiquity, is an excellent example. It is mainly located along a ridge of tuff rock that bordered an ancient lake. It is currently in a precarious geomorphological situation, already witnessed by traces of visible lesions on the ground. Therefore, the study is necessary for three purposes:

• Understand whether a geological movement exists in the areas close to the archaeological remains.

• Quantify this movement over time.

• Identify a trend whereby information can be provided to the competent authorities so that action can be taken within the time required to preserve archaeological remains. In addition, results will be provided to local authorities for better decision-making on the risk associated with the ground motion of the archaeological features. The objective is to allow local authorities to familiarise with the usage of the available online Earth Observation Services and support them with the assimilation of these new services in the daily monitoring and forecasting routine.

The study focuses on the Almería-Oran Front (AO) in the Alboran Sea, formed by the interaction of fresh Atlantic waters and saline Mediterranean waters. To enhance sub-mesoscale studies (1-10 km), the research incorporates variables such as Sea Surface Temperature (SST), Chlorophyll-a concentration (CHL), Sea Surface Height (SSH), and salinity (SSS) using Copernicus products. The objective is to create a comprehensive dataset, integrating these variables for improved analysis and correlation. The XCUBE will facilitate monitoring of the Alboran Sea dynamics, providing insights into physical and biological variables on the surface. Furthermore, the study aims to integrate products from the Land Surface Temperature Monitoring (LSTM) with a high spatial-temporal resolution thermal infrared sensor. Landsat data will be used as a proxy, requiring research on storing and integrating this information into XCUBEs. The project also plans to test re-sampling procedures like DINEOF (or other ML approaches) to build a dataset with higher detail (approximately 100 m) in the specified area of interest. Overall, the objectives include advancing sub-mesoscale studies, creating a comprehensive dataset, and integrating additional data sources for a more detailed understanding of the Alboran Sea’s physical and biological dynamics.

This research project investigates the potential of a satellite radar technique called Fully Focused Synthetic Aperture Radar (FF-SAR) for mapping flood extents in wetlands. The project specifically focuses on utilizing data from the CryoSat-2, Sentinel-3, and Sentinel-6 satellites to assess the effectiveness of FF-SAR in these areas. The primary objective is to determine if FF-SAR data can accurately delineate the boundaries of flooding in shallow floodplains with dense vegetation cover. The Biebrza Wetlands in northeastern Poland serve as the test case for this investigation. While current methods for flood extent mapping in this region rely on data from the Sentinel-1 Interferometric Wide swath (IW) instrument, this approach has limitations, particularly in areas with significant vegetation. The researchers hypothesize that despite the potential shortcomings of FF-SAR technology, the ability of radar waves to reflect off water surfaces will yield superior results compared to the backscatter measurements obtained by Sentinel-1. This project seeks to evaluate the validity of this hypothesis by comparing flood extent maps generated using FF-SAR data with existing maps derived from Sentinel-1 data, particularly in the heavily vegetated areas of the Biebrza wetlands. The beneficiaries are Floodplain managers and emergency responders, environmental researchers and conservationists, and water resource management agencies.

The ambition of the ANIN project’s team is to develop a drought early warning system for preparedness, mitigation, and response with the following characteristics:

• Generating quality data to support a drought early warning system by combining meteorological, agricultural, and hydrological indices.

• Customizing EO information for specific user needs by answering practical questions for the users.

• Enhance drought capacity and decision-making mechanisms to bring drought forecasts to the grassroots level.

• Integrating EO information with other information resources such as real-time weather forecasting, seasonal forecasts, and in-situ data from existing network information.

• Perform enhanced analytics and modeling to provide information that allows better decision-making.

• Facilitate decision-making by providing drought monitoring by providing an open visualization platform.

The objective is to set up an automated processing service that maps the changes over the main Antarctic ice shelves (e.g. Pine Island Glacier, Thwaites Glacier) within the AntarctICE project. This in follows up a recent paper titled “Damage accelerates ice shelf instability and mass loss in Amundsen Sea Embayment”, where it combines Sentinel-1, Sentinel-2 and Landsat to map the rapid changes. This proposal, continues this work by setting up an automated email service that emails the latest images over the focus areas to all interested users. This allows a rapid response in case of changes over the focus areas and should allow to respond to questions of research/media over the area as satellite images over regions enter the media news cycle regularly with Stef Lhermitte and his twitter account as well-known sources. By using the sentinelhub-python scripting approach, the service automatically checks for new Sentinel-1, Sentinel-2 and Landsat images over the focus areas and converts them to a production ready image that are emailed to the interested users. As deliverables there are automated scripts for processing and emailing Sentinelhub images over regions over interest and email service NOR cloud order.

As part of the understanding of the hydraulic behavior of the condo river and especially in the lower reach , as well as the protection of islands in this area, this study also aims environmental and economic aspects in the area , as it is already known, the pool Malebo is a strategic area concerning river transport (navigation), irrigation and agriculture, fishing, etc the protection of the morphological degradation of they is also one of the challenges in this work , for this purpose our study aims to master all the scientific information on the hydraulic and hydrological level in order to serve other economic activity and

environmental ,This prompts us to launch the main questions as follows: How can we develop an agent-based simulation model (ABMS) for navigation chart in the lower reach exactly in the stanely pool that includes (hydraulic, hydrological and socio-economic aspects), with this complexity, to find scenario optimal of navigation in the pool male boo , and if we can generate this approach in all the Congo river ? What are the assumptions, approaches and data needed to develop this model?

The increasing number and intensity of natural disasters in the past few years have had severe consequences in terms of human lives that were impacted, but also in terms of structural damage and economic losses. In years to come, extreme events will no longer be exceptions. Uganda is regularly affected by multiple natural hazards, including droughts, earthquakes, floods, landslides, and volcanoes. Flooding, particularly in low-lying areas, presents the largest risk. Each year, floods impact nearly 50,000 people and over $62 million in gross domestic product. Climate change is likely to increase average temperatures in Uganda up to 1.5 degrees Centigrade by 2030 and 4.3 degrees Centigrade by 2080. Rainfall variability and rising temperatures are expected to lead to higher incidences of droughts, and water scarcity but also extreme weather-related events which will likely increase population exposure to hydro-meteorological disasters such as heavy rainfall, floods and landslides (GFDRR 2017). Geospatial information technology (GIT) including satellite imagery analysis and data visualization plays a vital role in understanding the geographic extent and severity of disaster events. Nevertheless, the ability of national and regional authorities as well as disaster management experts to seamlessly collect, integrate, and analyse geospatial information in a comprehensible and easy-to-use format remains a challenge that needs to be addressed with ad-hoc training and capacity development programmes. To meet these challenges, UNITAR-UNOSAT UNITAR-UNOSAT and UN Technology Bank offered a 1-week introductory technical training course in the use of Geo-Spatial Information Technology to support operational planning and decision-making for emergency response and post-disaster recovery. This training also included dedicated sessions on how to trigger satellite imagery acquisition mechanisms following major disaster events such as the International Charter Space and Major Disasters. During one session, the participants created a training landslide inventory to be tested with ALADIM for Sentinel-2 algorithm for automatic landslide mapping on GEP (guided by Dr. Romy Schlogel, an expert in remote sensing applied to landslide hazard mapping). The course was designed to accommodate selected participants from line ministries and national/regional disaster management authorities.

For my master thesis I am investigating the application of InSAR for glacial lakes in the Himalaya. In order to check the InSAR results I am using optical imagery – sentinel 2, which is why I would like access to the sentinel hub.

In this work, we have become increasingly convinced about the need to strengthen the quality and depth of meteorological data accessed to adequately capture crop primary production patterns. In particular, we identified (crop) evapotranspiration – ETc and radiation as variables of crucial importance. Unfortunately, we cannot publish an operationally viable service due to constraints and inadequate access to such meteorological data. The key result of our work is going to be a set of novel tools which enable monitoring of crop productivity at various spatial scales and are coupled with the already available SatAgro precision agriculture tools, in result enabling individual farms to map the profitability of particular crop fields and crop fields’ sections, also before the harvest. As with other SatAgro tools, the motivation to create these new functionalities is to optimize crop production and, in turn, increase the farm’s fitness and reduce its environmental impact simultaneously.

This project aims to study the application of transfer learning techniques on hyper-dimensional remote sensing data. Here is the list of specific objectives. Objective 1: Learn about the hardware in remote sensing data (e.g., aircraft types, sensors). Objective 2: Learn about image characteristics (e.g., wave bands, image distortions). Objective 2: Learn about different challenges that can be solved using remote sensing data. Objective 2: Learn about the structure of remote sensing data and the statistical methods used to interpret and correct it. Objective 3: Train convolutional neural networks on high dimensional remote sensing data. Objective 4: Test the viability of using the transfer learning technique to train prediction models on datasets with insufficient data to train prediction models from scratch. Objective 4: Document the work process and results in a graduation thesis. This project will be the final project of a bachelor’s degree program in Mathematics and Computer Science. Suppose the transfer learning technique will prove efficient in building prediction models on smaller datasets. In that case, it can be used for future applications (e.g., tracking invasive species in smaller areal surfaces, land cover changes, unsanctioned object building, etc.). This could be especially beneficial for countries like Slovenia, where datasets are significantly smaller due to the smaller land surface. Transfer learning would enable us to train prediction models using remote sensing data of other countries and use this knowledge (parts of the mode) as a starting point to build a highly accurate model using Slovenian data, which otherwise may not be possible due to insufficient data.

APEx will secure continuous access to ESA Earth observation project results. This includes primarily algorithms, workflows, and value-added products, all accessible through the creation of a dedicated online portal. APEx will offer access to so called instantiation and propagation services to support ESA EO projects and the broader EO community. The instantiation services will provide dedicated IT components including project websites, data visualization tools, workspaces, development environments, and more. Offered as Software as a Service (SaaS) products, projects can instantiate these components as cloud-based environments on demand, and tailor them to align with their specific needs. These instantiated environments are hosted on the infrastructure that is requested through this NoR request. The APEx propagation services are geared towards ensuring the continuous availability, enhancement, and upscaling of algorithms, thereby increasing their utilization and adoption in the EO community.

This project is to support a doctoral thesis, and it is a synergy of space technology and terrestrial methods for interpretation and validation with geotechnical modelling. The entities currently involved are the Geomatic Survey Laboratory of the Department of Civil, Building and Environmental Engineering (DICEA) of the University of Roma la Sapienza, Italy, also the Department of Civil Engineering of the University of Concepción, Chile, (Geotechnical Division). The field of study is civil infrastructures and buildings in Chile. The motivation for this study is the great seismic activity of the territory. The effects induced by the earthquakes in Chile have made it possible to carefully analyze the region and some cities, studying the behaviour and response of structures to seismic phenomena. The objectives are to use DInSAR and ground-based methods by quantifying ground deformation and structural stability. Specific goals are to identify the critical infrastructures, using the DInSAR satellite technology, in the areas and infrastructures after the earthquakes (3 bridges, primary infrastructures and buildings), validate the P-SBAS technique, using a round-based method, and map the sections and critical components of the infrastructures with the data obtained from the DInSAR and cross-referencing the types of soil. Finally, we want to develop new geotechnical and structural indicators by analyzing and comparing the results of the DInSAR and ground-based methods.

Seafood fulfills approximately 10% of the global animal protein demand, serving as a cornerstone of global food security. Presently, every second fish consumed originates from aquaculture, establishing it as a major supplier of protein. Despite its significant role and provision of livelihood to millions, the sector largely remains untouched by modern technological advancements. The predominant challenges are low awareness, a steep learning curve, a lack of transparency, and an inefficient value chain.

Aquaconnect’s “AquaSAT” initiative seeks to harness the potential of satellite remote sensing and Artificial Intelligence (Al) to introduce transparency and efficiency into the seafood value chain. By offering real-time insights into culture operations, AquaSAT aims to address and overcome the fundamental challenges hindering the aquaculture industry.

Core idea: Utilizing satellite imagery of ponds combined with deep learning Al algorithms, AquaSAT aims to:

– Democratize pond boundary recognition.

– Differentiate between fish and shrimp ponds.

– Provide near real-time predictions on the days of culture

Leveraging this intelligence, our Al models are designed to:

– Forecast the demand for farm inputs.

– Predict harvest supply.

– Offer near real-time monitoring capabilities, including disease prediction, production statistics, resource utilization, and traceability.

By harnessing satellite technology, our approach scales seamlessly from individual ponds to villages, states, and even on a national level. In the broader perspective, these models empower us to create efficient market _ linkages, aiding farmers in accessing essential farm inputs and optimizing their harvest sales. Conversely, for stakeholders like retailers, our platform provides insights for purchase planning, market potential identification, and business strategy. For seafood buyers, this translates to advanced procurement planning and logistical optimization. By bridging technology and aquaculture, we’re not only improving an industry; we’re enhancing food security and livelihoods on a global scale.

The research aims at the archaeological interpretation of the landscape by reading anomalies detected in the ground visible in optical data and radar data from satellites linked to climate-changing events like summer fires. The identified areas of interest are the archaeological areas of Gabii and Villa Adriana (UNESCO Cultural Heritage), located in Italy. The research aims to understand whether the archaeological interpretation of the landscape through the study of surface anomalies can change due to the occurrence of natural phenomena related to climate change. The archaeological area of Gabii, active from the Iron Age to late antiquity and currently consisting of about 70 hectares of countryside, could be an excellent place to test it: from a preliminary analysis already carried out using optical Google images dating back to August 2020, when much of the Archaeological Park was affected by a large fire that also involved the ancient remains, it emerged that the archaeological reading of vegetation anomalies might be different concerning the reading and archaeological interpretation of the vegetation anomalies visible in the same areas prior to the event. The study is necessary for the following purposes:

• understand how weather phenomena linked to climate change can change the perception of vegetation or ground moisture on optical and (possibly) radar data;

• starting from this study, satellite data will be used to perform pre- and post-event analysis on the area and set up a methodology for the forecasting monitoring to identify a Fire Risk Index through the integration of Artificial Intelligence technologies at a later stage;

• multi-temporal satellite data will be used to establish a vegetation index (NDVI time series) useful to understand lifetime changes in vegetation visibility linked to the average rise of temperatures.

Archaeological prospection in Saruq al hadid is of significant interest to find the complete story of prehistoric settlements lived in Dubai, United arab emirates. Located at 50 km in the southeast of Dubai at the north of al Rub’al khali desert, Saruq al Hadid (SA) archaeological site is discovered since 2002. More than 15 000 artifacts have been identified after more than 20 excavations. The location of this site in the middle of desert between the dunes is mysterious because there is no available close freshwater critical for human survival and raw material sources critical for metallurgical industry. The use of remote sensing satellite high resolution radar and multispectral images enhance widely the possibilities of archaeological prospection. This project aims to prescreen potential buried archaeological sites in that desert region. This work is the first attempt made until now in evaluating the detectability of archaeological remains using satellite images data in United Arab Emirates. The outcomes are important to guide and help the excavation missions and the archaeologist for the planning of future excavation campaigns.

At ArchAI, we use ΑΙ to detect archaeological sites on LiDAR and satellite imagery automatically. We have shown the success of this technology with LiDAR data, detecting thousands of previously unknown sites, and our customers include the Forestry Commission and the National Trust. On LiDAR, we specifically look for earthworks (humbs and bumps in the landscape). However, most housing development occurs on farmland where ploughing has levelled earthworks, and satellite imagery is a more reliable source. In addition, archaeology is revealed on satellite imagery in agricultural fields through crop stress revealing sub-soil walls and ditches. Innovations in Satellite imagery have increased the frequency of high-resolution (<1m) information, meaning that a sufficiently trained ΑΙ can now derive archaeology from big data.

Our initial tests on aerial imagery have shown that the results are variable, depending on crops, seasonality, and weather. As such, we require to develop our technology further to account for this and create a higher volume of training data. Satellite imagery has higher temporal revisits, allowing for wider choice and availability of potential training data.

If our research is successful, we will be able to sell these assessments to our customers in the construction industry. It is a legal requirement to consider archaeology before development. However, archaeology is an unknown risk in projects, and it currently takes 6-24 months to reach high accuracy, which involves several stages of fieldwork and even costly excavations. Using satellite imagery and the SentinelHub, our proposed workflow could allow for instant assessment of construction project archaeological risks.

ARSET – Crop Mapping using Synthetic Aperture Radar (SAR) and Optical Remote Sensing is a collaboration between ARSET, Agriculture and Agri-Food Canada (AAFC), European Space Agency (ESA), University of Stirling, University of Ljubljana, and the CEOS Working Group on Capacity Building & Data Democracy (WGCapD). NASA’s Applied Remote Sensing Training Program (ARSET) has opened a new online advanced webinar series: Crop Mapping using Synthetic Aperture Radar (SAR) and Optical Remote Sensing. This three-part training is open to the public and builds on previous ARSET agricultural trainings. Here we present more advanced radar remote sensing techniques using polarimetry and a canopy structure dynamic model to monitor crop growth. The training will also cover methods that use machine learning methods to classify crop types using a time series of Sentinel-1 & Sentinel-2 imagery. This series will include practical exercises using the Sentinel Application Platform (SNAP) and Python code written in Python Jupyter Notebooks, a web-based interactive development environment for scientific computing and machine learning.

ArtEO (www.arteo.earth) is an independent, non-profit arts and education initiative, established by Imperative Space, focused on making it easier for artists (and others involved in creative, outreach and educational activities) to work with satellite Earth observation (EO) and related data and imagery. It provides a range of free tools and support services, bringing data and experts closer to the artists, and providing showcasing opportunities for emerging artworks. Artists and creatives work with EO at varying resolutions and scales and with the ability to show change over time, at any location on Earth. Guidance about the data and assistance in researching specific imagery and datasets is provided. It also connects artists with experts in climate science, ecology and conservation. To support this, access to selected data portals, visualization tools and curated collections of data is needed. Working with the ADAM platform greatly enhances the service, creating a more responsive opportunity to the interests and creative curiosity of the participating artists, science communicators and educators.

The 5Vs characterising big data (Volume, Variety, Velocity, Veracity, Value) are well-matched with EO data. Massive amounts of data describing the Earth are being transmitted by the currently operating satellites. As a result, computational and storage challenges are emerging and the necessity of having novel methodologies to analyse these amounts of datasets increased. Simultaneously, artificial intelligence (AI) has witnessed significant successes in terms of solving well-defined problems for which high-quality big data is available. While AI algorithms have been developed and deployed in several application domains, it is yet to receive the same level of adoption and impact in remote sensing and EO applications. Currently, limited EO applications such as land-cover classification are addressed using rather simplistic AI algorithms such as Random Forests and SVM. This is predominantly attributed to the lack of high-quality EO datasets that are ready for use by the non-EO experts in the AI community that develop the algorithms and models. Furthermore, despite the availability of AI algorithms that could be used out-of-the-box to start developing practical applications, the EO community lacks clear standards, guidelines and tools to prepare their EO data for use by the AI algorithms. Not to mention that the integration of EO datasets with those from other application domains and sources is also severely hindered by a couple of datasets/models for building integrated systems. The creation of a labeled training dataset is a time and cost-consuming process which is not affordable to the majority of data science and remote sensing communities and practitioners. In addition to the time and cost and despite the incredible power of AI and its applications for EO data, there remain a lot of questions about the fundamentals, like how to create an accurate, qualified, high quality, transferable, accessible, interoperable and reusable training dataset. Planned phases and activities:

CR1 – Research, develop and formulate dataset specifications and best-practice guidelines that define what constitutes AIREO training datasets.

CR2 – Develop a set of pilot datasets into AIREO compliant format, expose this to the user community, and analyse and incorporate feedback. Understanding of the main technical objectives of the RFP/ITT:

1. Review existing methodologies for training datasets.

2. Engage key stakeholders to aggregate requirements in training datasets.

3. Develop community-driven dataset specifications and best practices for AIREO training datasets.

4. Develop pilot AIREO training datasets.

5. Engage key stakeholders to use pilot AIREO training datasets, by following the below tasks:

o Community building, stakeholder consultation and comprehensive technical review

o Initial formulation of the AIREO specifications and best-practices

o AIREO pilot datasets, community assessments and Python library

o Stakeholder and community consultation and review of the AIREO v.0 specification

o Final AIREO v.1 specifications, best-practices, datasets and outreach.

More than half of the global population lives in cities and by 2050, two-thirds of all humanity will be urban. Furthermore, cities occupy just 3 percent of the Earth’s land but account for approximately 70 percent of global carbon emissions. Sustainable development cannot be achieved without significantly transforming the way we manage our urban spaces. This involves investments in many different sectors such as mobility, green areas, renewable energy, waste management, etc., between others. Therefore, the project explores novel and innovative applications of high-resolution satellite imagery in the urban planning field. The main objective is to provide development and management assistance for urban sustainability and climate resilience. Thus, the feasibility study proposes the state-of-art artificial intelligence and computer vision techniques to deliver constant urban forest monitoring. Automatic object detection is used to identify flora features (localization, health status, species) to constitute an arboreal system census of the area object of study. Specifically, trees play a vital role in the functioning of the city and provide environmental, social and economic advantages such as improving air quality, climate control, water cycles regulation and noise pollution reduction. Therefore, the trees catalogue not only assists flora monitoring and maintenance but also allows potential estimation of several benefits such as CO2 and PM absorption, mitigation of urban temperatures, erosions and floods prevention, biodiversity increase as well as potentially monitoring side effects and impact of trees on the built environment (e.g. tree roots growth damaging street pavements or threating buildings). The experimental set up selects the city of Rome as testing ground for the entire study with the option of potentially scaling the approach to other cities. Finally, the investigation is proposed as a preliminary work for participating to the ESA open invitation tender “EO Science for Society”.

The broader research context of my thesis is represented by Short and Mid-Term Fire Danger prediction using EO Data, coming from both VHR and SR images like Pléiades, WorldView, and Sentinel-2 Imagery. The dissertation would explore novel and innovative applications of satellite imagery in the field of Short and Mid-Term Fire Dangers and Fire Forecasting. The proposal’s main objective is to provide development and management assistance for “Civil Protection” for deploying units, use controlled fires to cope with destructive fires, and aid States and local governments to cope with climate change to augment forest resilience.

The long-term goals of the ArtiMATE project are to combine a small number of ground-truth labelled images from global DNA-annotated soil microbiome sampling sites for semi-supervised and active learning to build a model of two challenging learning tasks in agriculture, namely the prediction of:

i) Spatio-temporal patterns in satellite imagery of soil microbiome sampling sites across planet Earth, and

ii) the causal interactions between microbe sustaining soil microbiomes of various categorized environments inferred from DNA barcodes.

The project thus aims to vastly extend our understanding of the causal factors underlying microbial networks in diverse soil environments with the ultimate goal of supporting sustainable smart farming. With the focus on developing sustainable smart farming, the research project is addressing the UN sustainability development goals 2 and 15. The project seeks to uncover new pest management ‘drug’ targets and plant growth-promoting natural chemistries within agriculture. Through the ArtiMATE project, satellite imagery would be applied in combination with DNA datasets to:

1. Investigate the association between the abundances of operational taxonomic units (OTUs) and crop health and growth via satellite image data.

2. Investigate the association between the environment and the OTUs at specific sampling sites.

The project objective is to target vegetables and fruit agriculture to:

• Reduce up to 50% CO2eqT emissions (reduction and caption) in agriculture.

• Reduce farming costs by up to 30%.

• Increase crop yield by up to 20%.

• Improve crop value by up to 50%.

• Time management improvement.

As a Seeds company, Syngenta invests in breeding research programs for field crops. In these programs, field trials are necessary for evaluating the performance of new plant varieties in real-world conditions. These trials allow breeders to assess the traits of the new variety, such as yield, disease resistance, and quality, and compare them to existing varieties. Field homogeneity is critical for breeding trials because it ensures that the environmental conditions are consistent across the entire field, which reduces the variability in the performance of the plants being tested. This allows breeders to more accurately assess the genetic potential of the plants and make informed decisions about which ones to select for further breeding. Satellite imagery can be used to identify and characterize patterns of variability within the field such as areas with different levels of vegetation growth or soil moisture. These patterns can then be used to assess the field’s homogeneity. The objective of our project is to develop a methodology implemented in a prototype that allows breeders and trialing teams to assess the homogeneity of all the fields in an area containing multiple fields to help them select the most homogenous field in the targeted area.

The objective of the project is to focus on sustainable resources in Africa, assessing deforestation in countries like Gabon, Ivory Coast, Uganda etc. This will help in understanding the potential risk of deforestation and high risk areas, so that we can take necessary measures to manage the phenomenon. Moreover, this will help us as a company to attain our sustainable goals for the future.

The objective(s) of this project is/are to assess the Sphagnum moss coverage of specific peat land areas in Ireland, Canada and Denmark, assess the changes that have occurred over time here in terms of Sphagnum moss coverage and from this with data gained from peat land protection agencies. Correlate the difference this new Sphagnum moss has made to peat land Carbon capture ability. This will show how much of a difference the Sphagnum moss inoculation technique is having on Irish peat lands which will aid Bord na Mona and other teams in terms of where funding should go for further peat land restoration projects.

In recent years, cities worldwide have undergone significant urban transformations characterized by shifts in population demographics, changes in housing affordability, and alterations in neighbourhood landscapes. London, in particular, has experienced notable changes over the past decades. Understanding these changes is crucial for policymakers, urban planners, and community stakeholders to address issues such as gentrification, displacement, housing affordability, and health disparities. Previous studies have assessed urban transformation through changes in sociodemographic attributes and land uses in small city areas but have not identified changes at a very fine local level, such as new or lost green spaces, alterations in the built environment, or infrastructure changes. Additionally, while past research has examined housing prices and other forms of urban transformation, it has not linked those changes to health outcomes, which are

likely to be affected. This Masters Project, part of the Consumer Data Research Center (CDRC)

Masters Dissertation Scheme from the UK Economic and Social Research Council (ESRC), aims to investigate neighbourhood changes in London over time using a multidimensional approach that incorporates census data, satellite imagery analysis, and prescription records. This project is a collaboration between the London School of Economics (LSE) in London, UK, and Nokia Bell Labs in Cambridge, UK.

Hot and dry compound events affect millions of people yearly and can potentially cause substantial damage to hazard-susceptible objects such as buildings, crops, or automobiles. Nevertheless, the knowledge about the quantification of their interactions evolving in cascade events remains limited (Tilloy et al., 2019). As a result, the total effects resulting from the interaction of multiple hazards can be underestimated as they lead to a more significant impact than the sum of single hazard effects (Terzi et al., 2019). In this study, we would like to focus mainly on hot and dry compound events, including droughts, fires, dust storms, and heat waves. The main objectives are: (i) To assess the risk regionally (by analyzing the vulnerability, exposure, and past hazards), (ii) to identify and quantify single natural hazards with the help of satellite data (For early warnings and needs for assistance during disaster events), (iii) to apply tracking algorithms on satellite data to reconstruct and to forecast individual natural hazards h trajectories, (iv) to combine (i),(ii) and (iii) to assess the total impacts from the hazards interactions. In this project, two principal datasets will be used: ERA-Interim fields and satellite data for detecting and tracking natural hazards.

The objective of our study is to use high-resolution satellite altimetry to assess wave renewable energy potential on the French coasts, with a particular focus on the coastal zone where the energy can be cropped. The novelty is to take advantage of the increased temporal and spatial coverage of high-resolution satellite altimetry data products from the Sentinel-3 mission and use the SAMOSA+ state-of-the-art retracker (Dinardo et al. 2018, Dinardo 2020). This retracker, differently from the SAMOSA2 retracker currently adopted for the generation of the official Sentinel-3 WAT products, allows obtaining more valid geophysical estimates near the coast where contaminated data are typically acquired. Moreover, the customisable processing options available at the SAR processing level and quality flags provided in SARvatore products can be efficiently used to refine the analysis and for filtering purposes to strengthen the analysis. The study period shall cover 1 December 2018 to 30 July 2022 to provide sufficient data to perform the study and indicate possible limitations. An assessment of the wave energy potential will be given for the coastal zone, which is characterised by high energy swell generated by remote westerly wind systems, which is also affected by the strong wave-current interactions that take place in the area where tidal currents are of the order of 2 m/s. The feasibility of high-resolution satellite altimetry-based assessment of wave renewable energy potential in the coastal zone is examined, taking advantage of the increased time and spatial coverage guaranteed by the Sentinel-3 high-resolution satellite altimetry data.

The project aims to develop and ensure a neural network for the detection of wildfires using satellite images. The focus is on coordinates, times and dates of fires all over the world during the first week of September 2018. Research is carried out by staff and students at the University of York (UK). Funding has been secured from the Lloyd’s Register Foundation, a charitable organisation supporting research to improve the global safety of people and infrastructure.

The research aims to characterize climatic events (droughts) and extreme meteorological events (frosts) and their forecast to carry out agricultural planning and mitigation in the Central Table of Mexico and the North of Mexico. Specific objectives: a) Carry out a characterization of extreme meteorological events: frosts associated with the north in Mexico (Perez 1, 1996) or Tropical Cyclones (Perez 1, 1990), which have a greater incidence in our territory, as in the case of severe frosts North and Central Mexico, since 2011, which affected agriculture- b) Analyze the agroclimatic conditions (precipitation, minimum temperature, maximum temperature, and evapotranspiration) of the crops in the case study states in each of the meteorological characterizations mentioned ίn the previous paragraphs to determine the growing season of the crop, which will be determined based on the availability of water and favorable temperatures for the development of the crop in each phonological phase. Based on the temperature, potential evapotranspiration, and precipitation data, agroclimatic indices will be determined to pιan the most appropriate crop sowing and harvest date. c) Carry out an economic cost-benefit analysis of crops ίn the 5 High resolution topography data of the Mexican Republic. Mapping The available cartography will be analyzed to make Esri Story Maps. This web application allows authors to combine attractive maps with narrative text, impressive images, multimedia content, and videos. The apps are designed to be engaging and usable by everyone, making them ideal for education and outreach purposes, whether for the general public or a specific audience.

The project goal is to evaluate the accuracy of the atmospheric correction obtained with iCOR4S3 using in situ hyperspectral remote sensing reflectance and also a comparison with POLYMER reflectance data. The area of interest is focused on Lake Erie in North America. The results should contain the entire Sentinel-3 (S3A and S3B) OLCI data series for the Lake Erie area, processed with iCOR4S3. The results will benefit the academic community working on the Global Water Futures program and other researchers on similar topics.

Production of fertility maps, or “FMAPs”, which are, in essence, classified NDVI images, is essential to the functioning of our business. Soil sample locations are defined based on the field areas classified from low to high agricultural productivity. Based on soil sampling, we gauge the number of nutrients (Nitrogen, Phosphorus, Potassium) already in the soil. Our agronomists then provide variable rate fertiliser recommendations to grow a given volume of a particular crop. However, manual FMAP production is slow, labour-intensive and done field by field. Therefore, we need to automate and upscale the production of fertility maps, or “FMAPs”, to save time and money.

Along with the automation of the FMAP creation, we are also interested in synthesising a “peak green” image of a field for each of the five years. We rely on actual images taken close but not necessarily on the “peak green” day. Therefore, we are trialling using spatiotemporal interpolation to synthesise such an image. The interpolation process also relies on removing clouds and cloud shadows in the region of interest; that latter is a third objective and area of innovation. A fourth objective is automating geolocating the soil sampling sites within our client fields. Based on the produced FMAP, we are trialling a soil test point picking algorithm.

The objective(s) of this project is to automatically localize the photos from the Gateway to Astronaut Photography of Earth, which are photos taken by astronaut from the International Space Station (ISS). Although the position of the ISS is known at the time of taking the photos, the direction and orientation of the camera is not known, making it a challenging task to automatically geolocalize such photos. Nowadays only less than 10% of the images have been geolocalized, and with current methods it will take more than 30 compute years to automatically geolocalize them [1]. This project stems from the idea that such methods can be hugely sped up by the use of image retrieval methods for geolocalization, of which the project coordinator is one of the world’s leading expert, having published multiple papers in the last few years in the top computer vision conferences (e.g. CVPR, ICCV) on the topic.[1] Alex Stoken and Kenton Fisher, “Find My Astronaut Photo: Automated Localization and Georectification of Astronaut Photography”, Computer Vision and Pattern Recognition Workshops 2023Request ID

Agricultural field delineation is desirable for the operational monitoring of agricultural production and is essential to support food security; however, due to sizeable within-class variance of pixel values and small inter-class differences, automated field delineation remains challenging. Analyzing high spatial resolution Remote Sensing data permits the delineation of farm boundaries. Accurate delineation of farm boundaries is essential for planning and decision-making actions. First, it enables a better estimation of cropland area, which is important information for farmers and agricultural managers (e.g., ministries and private sector players). Farmers often use traditional measurement approaches to estimate the area of their farms, which sometimes leads to high under- or over-estimation. Accurate knowledge of farm boundaries (and, therefore, cropland area) will lead to efficient use of farm inputs such as seeds, fertilizers and pesticides. They may also help to optimize harvest logistics. Second, accurate information on farm boundaries can facilitate land registration and subsequent acquisition of land use rights for smallholder farmers (through a land tenure information system). Farmers, communities and the private sector are mostly deterred from investing in land resources due to unclear land use rights in rural areas. Developing an accurate parcel system through high spatial resolution remote sensing data is an essential first step towards creating a land tenure information system and, potentially, a land taxation scheme. Such a system will reduce land-related conflicts and encourage increased investment in agriculture. It can also improve farmer access to inputs and credits. Third, delineating farm field boundaries can improve crop type classification using object-based image analysis (OBIA) procedures.

Digital Surface Models (DSMs) are digital representations of the Earth’s surface that can be created using various technologies, such as aerial or satellite imagery, LiDAR (Light Detection and Ranging), or photogrammetry. Some typical digital surface model applications include urban planning, Agriculture, Natural resource management, Disaster response, Surveying and Mapping, Environmental monitoring, Archaeology and cultural heritage and Telecommunication. DSMs have a wide range of applications in various fields, and their usefulness is only expected to grow as technology advances. DSMs have the potential to benefit a wide range of stakeholders, including government agencies, businesses, farmers, environmental organizations, researchers, and educators. As an example Agricultural companies and farmers: DSMs can be used to monitor crop health and yield, as well as to plan irrigation and drainage systems, which can help increase efficiency and reduce costs. Satellite data can be a valuable source of information for generating DSMs, particularly for areas where ground-based data collection is difficult or impractical. Some potential benefits of using satellite data for generating DSMs are Wide coverage, Consistency, Timeliness, Cost-effective, and Remote areas. Unfortunately, some people in the above industries believe that only UAVs can answer their needs. Such a belief will limit satellite data usage, which will negatively affect the satellite data market. However, it is possible to produce higher-quality products using newer techniques like deep artificial networks. So this project’s initial goal is to make high-quality elevation models using high-resolution data (like 30 cm resolution and 50 cm resolution). Undoubtedly, high-quality products will change the attitude of different industries to satellite data and will positively affect the market.

This master’s degree project carried out by the University of Applied Sciences aims to improve the quality of cadastral data provided by governmental institutions. Exports of cadastral data provided by European countries provide accurate geospatial information about the location and geometry of buildings. This freely accessible data is used by researchers, companies and private individuals to perform analyses and evaluations that form the basis for decisions regarding the expansion of urban regions. While the data is of high quality in terms of geometric dimension, it is published at such long intervals that it reflects reality only to a limited extent, as there is a likelihood that changes in the building stock have taken place over time. The research aims to provide the missing component of temporal resolution using satellite data that has been consulted and to determine which buildings have been removed and which entries in the database are no longer representative. Applying the product to the dataset will maximize confidence in the data and provide end users with an approximation of the actual state. At the same time, users performing address-specific queries can be provided with an estimate of how far the answer can be trusted. Similarly, the models produced will be made available to government institutions so that, even before publication, there is an indication of where there have been demolitions of buildings and where construction work has taken place that may not yet be recorded in the database. The project serves as a support to the OpenData initiative of the EU, which enables a variety of different use cases regarding urban planning, energy-efficient construction and other areas in the building sector.

This research is one of the requirements to complete my studies at the State University of Semarang. The theme I took was the relationship between green open space and the level of thermal comfort, especially in the city centre of Semarang. Semarang City is one of the metropolitan cities in Indonesia with a high population density and, thus, a significant level of urban development. Continued development reduces green open spaces, even though these are crucial to improve the urban microclimate. This research aims at providing information to maintain the availability of green open spaces in Semarang City.

Thermal comfort level expresses the influence of microclimate on the human condition. The variables used in this study include the area of green open spaces, air temperature, humidity, vegetation density and the level of thermal comfort. This research will produce a map of the distribution of green open spaces, a map of vegetation density, a map of the distribution of the level of thermal comfort and how much green open spaces influence the surrounding temperature conditions. Besides that, from this research, it will be known which areas have a level of comfort that is classified as uncomfortable, a result that can be used as input to improve the local microclimate to provide comfort for the community in carrying out daily activities. It is hoped that this research can benefit the broader community regarding the importance of maintaining green open spaces in urban areas so that environmental conditions are maintained for comfortable living.

The workshop within the CCN 1 of the Agricultural Virtual Laboratory (AVL) aims to provide a good understanding and first hands-on training. The Sen4CAP project developed, validated and demonstrated an open-source toolbox (Sen4CAP system), which can automatically process Sentinel-1 SLC and Sentinel-2 L1C or L2A time series into a set of products relevant to the new Common Agricultural Policy. The primary users of this toolbox are national Agencies (and/or their sub-contractors specialized in EO), but also the private sector and researchers. The Sen4CAP project entirely relies on CREODIAS for the EO processing. The Panta Rhei conference aims to facilitate knowledge transfer between the agencies. This opportunity is unique to express the importance of the Sen4CAP system to its primary users. The workshop will focus on two main aspects:

1. communication of the main evolutions of the system up to now.

2. Performing hands-on training with the system for the newcomers (from the download of the images from the suitable dataset up to the generation of more advanced products) and a question and answers session for the more advanced users.

The objective(s) of this project is to provide data for artists to visualize how the northern shore of Lake Balaton has been built up, threatening the climate change adaptation of the region and the lake’s water quality while lowering the ecosystem services of the area. The final products will be showcased during the Balatorium events https://bazis.balatorium.hu/en. The result of our exercise will be given to various artists to transfer scientific images in a suitable form for the general audience. Our group of experts and scientists has already provided multiple data and knowledge for the Balatorium events to focus on local problems and solutions. Our work is based on our previous studies on how to increase the climate adaptability of the region. It is slightly connected to our present assignment for the Hungarian Academy of Sciences Working Group of Sustainable System’s National Program, where we study the lake’s socio-hydrology, focusing on its water level.

Spatial planning is a process that aims to mitigate the impacts of human activities and eventual improvement of the state of the environment through the coordination and implementation of various practices and policies. Thus, a critical action for improving the state of the Baltic Sea is to strengthen the territorial and maritime spatial planning capabilities of the organizations operating in the area. We aim to develop an integrated data approach to obtain a full view of the essential processes of land and coastal water areas by combining currently available satellite data sources, in situ observations, and model predictions about dynamic land cover and water quality characteristics.

The BalticAIMS project will reach this goal through the following technical objectives:

• Identify suitable environmental data and GIS materials.

• Integrate, process, and store thematic information.

• Create the data access, visualization, and analysis systems and tools.

The proposed research addresses two specific needs that characterise the Maltese Islands: an extensive survey of shallow seabed information and a time series on the submarine groundwater discharge within the coastal and nearshore setting. The Maltese Islands represent an ideal location to test out the viability of a workflow for obtaining a new bathymetric layer from satellite-derived information (Satellite Derived Bathymetry, SDB). This new information set will be acquired through the use of Sentinel-2 and Sentinel-3, two missions launched explicitly for the surveys of sea topography and sea-related properties. During the first stage of this proposed project, the team will select three study areas around the Maltese Islands where there are better chances for the satellite to acquire reliable images. Machine Learning techniques will be critical within this phase (Stage 1) for improving the classification of the depth of the seafloor. Validation of the method tested formerly on three areas will then be extended across the whole Maltese Archipelago. Within the area delimited by the new bathymetric fringe produced from satellite data, data acquired from the infrared sensors of Sentinel-3 will be used for identifying submarine groundwater discharges. This research objective will be attained during Stage 2 of this project. It will contribute to a better understanding of groundwater system migration from onshore through coastal systems in the nearshore or offshore setting. This research will allow Malta to be the first European country with the entire coastal and nearshore setting updated with Satellite Derived Bathymetry and to have shallow areas, which usually are poorly surveyed because of navigation issues, to be equipped with a novel workflow and data output. The capacity built with this research project enables the marine geology community of the University of Malta to learn to use and exploit satellite data. These skills have the great potential to be transferred to other multidisciplinary and interdisciplinary research projects that will entail handling and interpreting satellite data for bathymetric or topographic purposes and groundwater discharge monitoring.

The main objective of the project is to use the DaaS service provided by the CREODIAS environment to run the Sen4CAP system to:

• Compare the accuracy of EOStat and Sen4CAP crop type classifications.

• Verify the quality of the crop type classification using only one Sentinel-1 sensor.

• Complement EOStat products with Sen4CAP and uptake in ARMA business processes.

• Evaluate a backup solution for the operational CAP monitoring.

Accurate information pertaining to the spatial distribution of various tree species in a forest stand is crucial for better monitoring and management of boreal forests. Such wall-to-wall information is lacking from field-based forest inventories. Meanwhile, remote sensing techniques based on satellite and

Unmanned Aerial Vehicle (UAV) data promises to highly reduce this information gap. The end result would be a publication and/or technical note that describes how ESA’s satellite date can be used along with UAV image data for better forest tree species mapping in boreal conditions. The benefit of userready data available from processing platforms (like F-TEP) will also be highlighted in the document.

The beneficiaries of this research project will be forest stakeholders such as forestry companies and government agencies.

The primary objectives of the project are to:

• Support definition and cooperative implementation of Danube and Black Sea regional priorities.

• Achieve measurable progress in embedding EO-derived information into the strategies and cooperation actions within the Danube and Black Sea region.

• Enhance and promote the use of the EO platforms capabilities for regional-scale processing, data fusion and information delivery.

These shall be achieved by developing and delivering a customised set of EO-based information services that utilise scalable cloud computing-based processing resources, high-throughput computing capabilities, and fusion of large volumes of EO data from the Sentinel missions and other European EO missions. The implementation shall be based on a regional approach to information collection and delivery. Integration with non-EO data is also foreseen as an essential component, including the opportunity to exploit the potential for innovative service delivery (or new data access, processing and management solutions).

Bark beetle outbreaks are a significant problem in the EU, causing more than 3 billion euros worth of damage to forests each year. Climate change is making this problem worse, as dry and warmer weather conditions are causing the beetles to multiply rapidly. Unfortunately, large forest owners and government bodies are struggling to spot outbreaks on time, and there are no effective prevention measures.

To preserve the value of our forests, we must establish a centralised prediction and alerting system. This system would help government bodies and forest owners react more quickly to outbreaks, which are likely to become more frequent.

Our proposed platform would provide new opportunities for forest owners to be notified of outbreaks using near real-time satellite imagery monitoring. This would streamline the entire forest management pipeline, from regulatory bodies to forest management, forest owners, and the wood processing industry. A centralised system can quickly alert all parties to take action to mitigate the outbreak.

In order to be successful, the system must be able to detect outbreaks as early as possible. This requires advanced technologies such as remote sensing and machine learning. The system must also be able to process large amounts of data quickly and accurately. Additionally, the system must be user-friendly and easy for forest owners and government bodies to access and use.

Implementing a centralised prediction and alerting system for bark beetle outbreaks would be a significant step forward in protecting our forests and preserving their value. It would also provide new opportunities for forest owners to manage their resources more effectively and efficiently. We believe that by working together, we can make a real difference in the fight against bark beetles.

The primary objective of our project is to develop and deploy a user-friendly tool aimed at architecture students and investors. The project’s core focus is on the following purposes:

Facilitate Plot Search: the tool will streamline the process of identifying available building plots. Users will be able to input their requirements, such as location, size, and purpose, to find suitable options quickly.

Enhance Decision-Making: by providing comprehensive information about the available plots, the tool aims to empower architecture students and investors to make informed decisions about their investment in real estate.

Optimize Resource Allocation: the project seeks to contribute to resource optimization by matching user requirements with available plots, potentially reducing the time and effort required to find suitable building locations.

Promote Sustainable Urban Development: the tool may encourage users to consider environmentally friendly and sustainable options when searching for building plots.

The project’s results will bring substantial added value to several stakeholders, including Architecture Students(our main target). This tool will be a valuable resource for architecture students, allowing them to identify real-world examples for their projects and educational purposes. It can also aid in the development of innovative and sustainable architectural designs. The real estate sector will benefit from streamlined access to building plots that align with their investment objectives. This tool will potentially save them time and resources in their property search. Urban Planners can take advantage by contributing to sustainable urban development; the project’s results can assist urban planners and authorities guide the construction and expansion of cities more sustainably. Our results will be available for the Architecture department when we introduce some proper functionality with a user-friendly environment.

The EU Copernicus programme has established itself globally as the predominant spatial data provider, through the provision of massive streams of high resolution earth observation (EO) data. These data are used in environmental monitoring and climate change applications supporting European policy initiatives, such as the Green Deal and others. To date, there is no single European processing back-end that serves all datasets of interest, and Europe is falling behind international developments in big data analytics and computing. This situation limits the integration of these data in science and monitoring applications, particularly when expanding the applications to regional, continental, and global scales.

The proposed C-SCALE (Copernicus – eoSC AnaLytics Engine) project aims to federate European EO infrastructure services, such as the Copernicus DIAS and others. The federation shall capitalise on the European Open Science Cloud’s (EOSC) capacity and capabilities to support Copernicus research and operations with large and easily accessible European computing environments.

This project estimates tree growth and carbon sequestration along a 10-year period in four different ecosystems in western Mexico. The identification of species on the ground of selected trees allows us to estimate the growth rates of different forest species and their capacity for carbon capture. The main goals of the project are to provide accurate information on carbon storage capacity of the studied ecosystems and identify native species with high carbon capture for further reforestation efforts. The data obtained allows to assess the impact of environmental variables on carbon sequestration and enhance the accuracy of carbon stock estimation models. This project adds significant value by creating a comprehensive database of growth rates and carbon capture potential for key native species in these ecosystems, which can be used to inform sustainable forest management practices and climate change mitigation strategies. The results significantly benefit research on ecology and conservation and provide crucial information for forest managers. The results are available through academic publications and an online database with the estimated carbon capture per species.

“BACKGROUND: Canopy height is a fundamental geometric tree parameter in supporting sustainable forest management. Apart from the standard height measurement method using LiDAR instruments, other airborne measurement techniques, such as very high-resolution passive airborne imaging, have also shown to provide accurate estimations. However, both methods suffer from high cost and cannot be regularly repeated.

GOAL: In our study, we attempt to substitute airborne measurements with widely available satellite imagery. In addition to spatial and spectral correlations of a single-shot image, we seek to exploit temporal correlations of sequential lower resolution imagery. For this we use a convolutional variant of a recurrent neural network based model for estimating canopy height, based on a temporal sequence of Sentinel-2 images. Our model’s performance using sequential space borne imagery is shown in preliminary results to outperform the compared state-of-the-art methods based on costly airborne single-shot images as well as satellite images.

PREVIOUS WORK [1]: In our previous study, we adopted a neural network architecture to estimate pixel-wise canopy height from cost-effective spaceborne imagery. A deep convolutional encoderdecoder network, based on the SegNet architecture together with skip connections, was trained to embed the multi-spectral pixels of a Sentinel-2 input image to height values via end-to-end learned texture features. Experimental results in a study area of 942 km2 yielded similar or better estimation accuracy resolution in comparison with a method based on costly airborne images as well as with another state-of-the-art deep learning approach based on spaceborne images.”

This project is a collaboration between the University of Wollongong and Natural Hazards Research Australia. The project aims to develop a probabilistic wildfire rate of spread model based on observation of extreme wildfires that have occurred in eastern Australia. Observations of how fast past fires have spread will be based on fire perimeters mapped from images captured by fire agencies and available satellite data. This will be combined with weather and vegetation data, and Bayesian statistical techniques, to produce a probabilistic model. The model will be developed with regular feedback from fire agencies to ensure it can be operationalized. The project will provide a new empirically based probabilistic model to fire behavior analysts to better understand how a fire spreads, which will allow agencies to make better decisions about firefighting and community safety.

This project will serve as a pilot study focused on localizing beef and dairy farms in Germany. We want to use the high-resolution 50 cm Pleaides Stereo data to detect farms, land size, and localize buildings. The farms and facilities will be localized using Al techniques. By considering the number of cattle on each farm and modelling the emissions generated by these animals, the study can help identify emissions hotspots and evaluate the effectiveness of different farming practices in reducing carbon footprints. Understanding the carbon emissions from beef and dairy farms is of utmost importance for several reasons. Firstly, the agricultural sector, including livestock production, significantly contributes to global greenhouse gas emissions. Identifying and quantifying the carbon emissions, specifically from beef and dairy farms, can help us assess the overall environmental impact of these agricultural activities. By measuring carbon emissions from beef and dairy farms, we gain insights into their contribution to climate change. Methane, a potent greenhouse gas, is released during the digestive process of cattle.

Additionally, emissions from manure management, enteric fermentation, and farm energy use further contribute to the carbon footprint. Assessing the extent of these emissions allows us to develop effective emission reduction and mitigation strategies. Such localized assessments can assist policymakers, farmers, and researchers formulate targeted strategies to promote sustainable farming practices. This pilot study has the potential to serve as a foundation for future initiatives aimed at improving the environmental performance of beef and dairy farms in Germany and contributing to the country’s overall sustainability goals.

The JESAC project aims to develop a monitoring system from very high-resolution (VHR) data for at-risk areas and reforestation activities to cover the information gap in semi-arid regions. The monitoring system will detect individual trees, monitor their growth, and determine their increase in biomass over time, which can be translated into their capture of carbon dioxide (CO2) from the atmosphere. This technology would allow for an accurate understanding of such under-monitored areas. The first expected result is automatically detecting tree crowns from VHR imagery. Being able to perform such a task in an automated fashion with a trained model can aid local, regional, or National Forest Inventories in transitioning to a more digitized, less time-consuming protocol. It can also increase the frequency of monitoring, as the sole availability of cloud-free multi-spectral satellite imagery would be sufficient for the model to detect the trees. This technology could also help monitor agroforestry parcels’ daily activities while accounting for their trees’ health and growth. Another expected result is the estimation of carbon stock from each tree. It can be achieved by determining the biomass stored in the tree in the form of leaves, trunk, and roots. Pairing VHR data with carefully designed in-situ measurement campaigns can provide the requirements to calibrate the models to perform the estimation. The technology will then be used to monitor existing reforestation activities, ensure their correct development, and produce carbon offsets based on observations. Finally, vegetation indexes, crown sizes, and evolution of tree growth can provide the health status of individual trees and whole agroforestry parcels or forests.

As a vital vegetation type, trees dramatically contribute to carbon sequestration and mitigating climate change. Australia’s rangelands cover about 80% of the country’s area. Trees in rangelands are essential for both the interannual variability of the carbon cycle and local livelihoods. Therefore, accurately estimating the tree cover in Australia’s rangelands is fundamental for detailed landscape pattern analysis to manage and conserve trees. However, most public interest in trees is devoted to forests, and trees outside of forests are not well-documented, especially in Australia’s rangelands. This project aims to develop and implement a machine learning model to accurately map tree cover in Australian Northern Territory and Queensland rangelands using high-resolution satellite imagery. The outcomes will improve the monitoring of rangeland trees and understanding of their role in mitigating degradation and climate change.

The primary scope of the work covers the utilisation of the Euro Data Cube from an end-user point of view from the scientific community (e.g. meteorology or climatology).

The overall project aim is to access karst caves in remote places in Greenland and sample the speleothems (mineral precipitates on cave walls). From these can be extracted geochemical signals that relates to climatic variations at that location. The image analysis is to be used for planning a field expedition in the summer 2023. The main purpose of the field expedition is to collect speleothems from caves in East Greenland to provide unique data about climate variations in Greenland prior to the time interval covered by data from the Greenland ice-cores (~ 130.000 years). Such data are valuable for calibrating and improving climate models, especially for the Arctic region and the Greenland Ice Sheet (GIS). Traditionally the climate models rely on calibration data from marine sediment cores and ice cores. Recent developments in a suite of techniques (stable isotopes, radiometric dating, etc.) have provided scientists unprecedented opportunities to advance the understanding of mineral deposits in caves (so-called speleothems), although nearly exclusively such studies focused on temperate and subtropical regions (Fairchild & Baker 2012; Wong & Breecker 2015; Comas-Bru et al. 2020). Data from the Arctic are rare and until now only one single example from northern Greenland has been published (Moseley et al. 2021), covering a time-window of ~50,000 years dated at around 550,000 years ago. Additional data from Greenland cave speleothems may provide a better understanding of climate changes through the very important period from 2.5 million to 130,000 years ago including Pleistocene glaciations and interglacials, and will thereby serve to narrow uncertainty in the future predictions of the Arctic climate and the fate of the GIS under the progressively warming world. In order to plan and optimise fieldwork, satellite images will be used for the initial mapping of potential locations for cave entrances. The geochemical analysis data will be made publicly available and the results will be published.

The ESA River discharge Climate Change Initiative project is a precursor study. It aims to derive long term climate data records (at least over 20-years) of river discharge for some selected river basin (and some locations in the river network) using satellite remote sensing observations (altimetry and multispectral images) and ancillary data. It aims to provide a proof-of-concept for the feasibility for a potential River Discharge ECV product to meet the requirements for the Global Climate Observing System. The project results will be presented in a scientific article or outreach (publications of the main results of this project and user workshop foreseen in March 2024). Who will benefit from the project results: all the community interested in the long time series of river discharge.

The Arctic+ team intends to develop a new regional Arctic SMOS SSS product (follow-up version, Arctic+ Salinity v4) to enhance two fundamental components for calculating freshwater content in the Arctic, namely:

1. Effective spatial resolution: Algorithms for reducing the incoherent noise in the brightness temperatures will be applied, namely the Nodal Sampling (Gonzalez-Gambau et al., 2016) and the multifractal fusion of the brightness temperatures(Olmedo et al., 2021a).

2. Better characterization of the sea surface salinity dynamics: We plan to mitigate the different errors affecting the SMOS measurements without using salinity values in-depth as a reference for the temporal biases’ correction.

With this approach, we aim at keeping the surface dynamics and not masking it with the sub-surface one.

The European Continental Crop Map is a machine learning-based crop map that contains six crop types (summer cereals, winter cereals, maize, potato, sugar beet and winter rapeseed). Vito developed it using the openEO Platform. The map was created for a year at a spatial resolution of 10x10m. The map is based on Sentinel-1 and Sentinel-2 data, more specifically on time steps and basic statistics (standard deviation, percentiles) for B6, B12, VV, VH, VV/VH ratio, and seven indices (NDVI, NDMI, NDGI, ANIR, NDRE1, NDRE2 and NDRE5). The map is created using a Catboost model trained using GridSearch, using the LPIS dataset for training and testing.

CECOES 1-1-2 is the Emergency and Security Coordination Center of the Autonomous Community of the Canary Islands. Manage urgency and emergency calls to 1-1-2 from citizens by activating firefighters, ambulances, or police. In addition, in a significant emergency, such as a forest fire or flood, it coordinates the response in these emergencies. The provision of satellite images in real-time is of vital importance for decision-making in emergencies. For example, this information was used in the volcanic eruption on La Palma island just one year ago. The CECOES 1-1-2 has a GIS viewer to collect all the georeferenced information for emergency management. The main emergencies that are managed from the CECOES 1-1-2 are:

• Forest fires

• Floods

• Marine contamination

• Chemical risk

• Transport of dangerous goods by road

• Volcanic and seismic risk

The Civil Protection authorities require up-to-date information for decision­making. Therefore having access to satellite information, fire risk index, etc., has been very useful in the last emergency on La Palma island. However, having this information available in an emergency is not easy. It is necessary to download and process it for decision-making, which is why access to the latest available information is required. In addition, this entire process requires trained personnel with a high degree of specialization. During an emergency, all the operational procedures must be in place so that access to GIS information is easy.

The CERES project aims to develop a methodology and associated tools for detecting and monitoring chemical pollution from mining activities using satellite images. Specifically, the project aims to generate an automatic and precise mapping of polluted areas in soil and water, focusing on acid mine drainage, while simultaneously developing a quality assessment matrix to validate the satellite data processing methodology. The resulting datasets and data processing algorithms will be integrated into CybELE’s commercial products, designed to support both public and private entities in the raw material and mining communities. Integrating CERES technologies into CybELE’s products will provide significant value to these communities by enabling them to monitor and manage the environmental impact of mining activities more efficiently.

The urgency to develop methods capable of identifying specific drivers of forest disturbance events is highlighted in the UN REDD+ policy. Characterizing drivers is essential to understand the complex socioeconomic processes that cause forest loss. However, charcoal production across Sub-Saharan Africa is ineffectively monitored and regulated. This contributes to the uncertainties surrounding the ecological impact of the industry and makes it difficult to separate the drivers of forest degradation in the region. In addition, this limits our ability to grasp the effects on local processes and the shifting ecosystem dynamics. High spatiotemporal systematic observations of the Copernicus Sentinel-1 (S-1) synthetic aperture radar (SAR), with the intrinsic advantages of radar imagers, make it one of the most applicable sensors for detecting small-scale forest disturbances.

Furthermore, AI and cloud computing on EO Platforms (e.g., the Euro Data Cube) enable scalable exploration of deep stacks of SAR data at regional to continental scale. In this study, we demonstrate the potential for using S-1 SAR and other geospatial datasets with the help of AI to produce a methodology for scalable forest degradation monitoring of specific drivers in Sub-Saharan in an Open Science development framework. This will enable more effective management and protection of valuable woodlands and better inform policymakers on the extent of charcoal production across the region. Furthermore, it will allow one to understand better the shifting dynamics of these woodlands and their vulnerability to the changing hydrometeorological conditions within SSA. The second purpose the request will be used for is to prepare the tutorial notebooks in EDC for the RACE/EO Dashboard demo area at LPS 2022.

The project works on a machine-learning-based model to support the Paying Agency of the Republic of Slovenia with their Check by Monitoring introduction, in line with Common Agriculture Policy methodology. The project tests how various markers (crop classification, similarity, ploughing detection, land cover classification, etc.), which have been developed with Sentinel-2 data, work with Planet data time series. In case the algorithms (or at least methodology) prove to work on Planet data, the approach provides a solution for parcels, that are too small for Sentinel-2 data (e.g. less than a couple of full pixels within the parcel). The study covers 25.000 fields representing 15.000 ha of data. Weekly time series are needed over 6 months, which amounts to 5.800 sq. km.

Chlorophyll (chla), cyanobacterial counts, and cyanotoxins are not routinely monitored in coastal rivers and estuaries so an efficient approach to detecting blooms through remote sensing is needed to focus more detailed monitoring and to assess the environmental conditions (nutrients, temperature, flow regimes) associated with these blooms. Information on historical and near real-time frequency, occurrence, and magnitude of cyanobacterial blooms in lakes and reservoirs is being developed by the NASA-funded Cyanobacteria Assessment Network project (CyAN) based on remote sensing data from MERIS and Sentinel satellites (Clark et al. 2017). However, cyanobacterial blooms have been detected with increasing frequency in subtropical estuaries (Kramer et al. 2018), freshwater tidal systems (Tango and Butler 2008, Bukaveckas et al. 2018), and brackish water sites along the coast of southern California (Tatters et al. 2017). Puget Sound is potentially affected by freshwater-derived microcystins from upstream lakes and rivers, which are accumulating in Puget Sound shellfish to levels of concern and thus, could pose a health risk to tribes collecting local shellfish for food (Preece et al. 2015, 2017). The objective(s) of this project is/are to compare various chlorophyll algorithms (including machine learning) and atmospheric correction techniques (Acolite, Polymer) for estuaries and freshwater tidal rivers in the conterminous United States with Sentinel 2 data and to use these as inputs to predictive models for harmful algal blooms. Selection of the initial set of estuaries for time series analysis was based on the history of reported cyanobacteria blooms, stakeholder interest (e.g., NEP/NERRS sites), and availability of in situ monitoring data for ground-truthing.

This project aims to study image segmentation and classification for pattern recognition of forests, non-forests, and agricultural areas in the State of Pará (Brazil), including implementing Artificial Intelligence tools to assist in describing existing areas. The Centro de Inteligência Territorial (CIT) is an independent, non-profit organization with researchers specializing in land use modeling and public policy evaluation. CIT is a hub for Science and technology projects, connecting researchers, policymakers, decision-makers, and experiences in territorial intelligence. Reconciling production needs, ecological restoration, and social progress in a territory are challenging. Working at the frontier of knowledge is essential to face this and other challenges.

The project aims to assemble a knowledge aggregator that will provide a wider audience with convenient access to findings of rapidly progressing research related to climate change. The project’s primary goal is to create an open-to-public software platform that enables translating interdisciplinary geographical knowledge into a form of a climate action concept. We envision the materialization of climate change mitigation and adaptation ideas as state-of-the-art information on climate action indicators that can be easily verified, trialled, communicated, and implemented in the chosen area. The desired user group of the software solution is composed of active members of various climate action organizations. The platform will help them achieve their goals in approaching policymakers and the general public by providing unrestricted and free-of-charge access to near real-time access to a curated collection of climate readiness indicators. Calculated indicators will be served as maps, diagrams, and reports. Each platform artefact can be exported and utilized under CC BY-SA licenses. An example of platform usage would be creating a rich report on greenhouse gas emissions generated by deforestation of the specified area. This task could be achieved by analyzing satellite imagery to detect land-cover changes. An organization can then utilize the report to highlight the issue and prepare a solution with policymakers. For this to be possible, an urgent need is to integrate an analytical mechanism based on deep learning with various multi-modal data sources. The platform will heavily rely on remote sensing imagery to fulfil user requirements.

The objective(s) of this project is to study the behaviour of the sand reclamation artificial islands when exposed to climate change, regarding their physical and chemical environmental conditions. The sea level rise and excess concentration of CO2 in the seawater due to ocean acidification, impact the geological behaviour of the artificial islands. The correct assessment of the geo-hazards such as island liquefaction due to sand degradation, requires a proper evaluation of soil parameters using real calibration of the island component settlement, by using the satellite terrain motion readings. The soil parameters derived from the calibration of settlement equations of sand and rock fill will allow for correlated calculations of long-term settlement and liquefaction assessment results.

This initiative, led by the Asian Institute of Technology, is a capacity-building project that aims to enhance the abilities of the Asian Development Bank’s developing member countries (DMCs) in utilizing Earth Observation (EO) data for disaster risk reduction. The project will provide selected technical personnel from DMCs with the necessary skills to process satellite imagery. This includes a systematic approach to handling radar and optical data, which will subsequently be used for project planning and implementation. Participants gain hands-on experience in creating and deploying algorithms and models in a cloud environment. These tools process satellite data for disaster risk applications, thereby increasing the DMCs’ proficiency in using cloud based EO applications. The overarching goal is to support DMCs in their Disaster Risk Reduction strategies during both pre- and post-disaster periods. This capacity-building project empowers DMCs to better manage and mitigate disaster risks.

Evaluating Vineyard Stress with high resolution NDVIthis project is to assess vineyard stress levels in the renowned wine regions of Hermitage and Croze-Hermitage in France, in comparison to the vineyards in the Swartland region of South Africa, using the Normalized Difference Vegetation Index (NDVI). NDVI will serve as a key indicator of vineyard health and stress due to changing climatic conditions.Quantifying Impact through NDVI Analysis: We aim to quantitatively measure the impact of climate change and varying practical management strategies on vineyard health and vitality by analyzing NDVI data. This approach will provide a data-driven understanding of how climate shifts affect vineyards and how different management strategies influence NDVI trends.Request ID

CMIX II is the second edition of the joined ESA and NASA Cloud Mask Intercomparison eXercise activity in the frame of CEOS WGCV. It is an international collaborative effort aimed at intercomparing cloud detection algorithms for moderate-spatial resolution (10-30 m) spaceborne optical sensors. The focus of CMIX is on open and free imagery acquired by the Landsat 8 (NASA/USGS) and Sentinel-2 (ESA) missions.

Within the second addition of CMIX, dedicated reference datasets will be cerated to validate the participating cloud masking algorithms. One of these datasets is an expert pixel collection conducted on Sentinel-2 L1C and Landsat 8/9 Level1 data. Together with the participants, it was decided to provide information on cloud optical depth (COD) in addition to the expert classification, to have a numerical reference on different cloud transparency classes. To derive COD for any Sentinel-2 L1C or Landsat 8/9 L1 product, a surface reference is required. This reference can be a surface albedo or anything comparable.

In context of CMIX II an approach was developed using all S2 L2A data within an 18 day window of all years since the S2 launch, do derive a longterm average. The same is done for L8 L2 data. For this approach only the read and NIR band of the two sensors is needed, as well as cloud masking bands. The resulting product will called Land Surface Reflectance (LSR). The LSR can be used as a reference to estimate the COD. The reference dataset including the COD estimates will be published at the end of CMIX II. The reference dataset will comprise approx. 100 Sentinel-2 and 100 Landsat 8 products, the expert pixel collection and the COD estimates for all collected pixels.

This project aims to demonstrate the use of cloud technology in customized atmospheric correction for retrieval of estuarine water quality parameters. The results are beneficial for the research and management of estuaries, first and foremost for use by our peers, which are data scientists and water quality researchers and modelers, but also for managing the water quality of these water bodies. The latter is also in line with the advisory role of Deltares https://www.deltares.nl/en. Results will be presented to these stakeholders, and we will investigate the feasibility of publicly available the most interesting results.

Accelerated coastal erosion in the Arctic has been identified as a severe threat to the environment and the local population. Globally rising temperatures alter coastal erosion processes and rates with increasing velocities in the last decades. Coastal erosion processes have been investigated along the arctic coast of Russia, the United States of America and Canada, but little research has been done on the coast of Greenland. The aim of the project is to

i) identify specific sites prone to different erosion processes along the coast of Greenland,

ii) investigate the rate of change at the respective sites in the last decades,

iii) reveal the main drivers affecting coastal stability and

iv) determine future changes in the respective forms of coastal erosion under changing climatic conditions.

To achieve this, satellite-based remote sensing data is used to observe geomorphological erosion patterns and to calculate rates of erosion and deposition. Further, data from measurements during (and between) two planned field trips is analysed. Based on these in situ and remote sensing data, coastal erosion models are calibrated and evaluated and future erosion rates under global change scenarios are modelled. Spatial and temporal coverage of satellite imagery is relatively scarce in high latitudes. Therefore, it is crucial to combine all imagery available, to acquire the highest spatial and temporal resolution possible. Sentinel Hub makes Sentinel, Landsat, and other Earth observation imagery easily accessible for browsing and visualization of coastal erosion in Greenland. WCS services further allow data integration in local GIS platforms as well as mapping and data analysis for specific study sites. The results of this project will enhance our understanding of future changes on the coast of Greenland, providing valuable data to further investigate coastal erosion impact on land and ocean. Considering on-site effects, the acquired data is essential for the population of Greenland to manage and conserve their shorelines, to protect villages close to the coast. From a broader perspective, assessing the sediment eroded by coastal erosion processes is crucial to estimate an overall sediment yield for Greenland in combination with fine-grained sediment from glacial erosion, as the exact impact of terrestrial sediment loss and input into the marine ecosystem is not well understood and might have feedback for global biogeochemical cycles.

The objectives of the project include the feasibility study on the use of VHR optical data for coastal erosion studies and the production of coastal erosion rates from VHR optical data for selected areas along the north Dublin coastline. The results will be shared over the GSI web mapping services for free as an example of the use of VHR to monitor coastal erosion.

ARGANS Limited and its partners are engaged in a Coastal Erosion monitoring project funded by the Science for Society slice of the 5th Earth Observation Envelope Programme overseen by ESA/ESRIN. The partnership consists of an ΕΟ based information service provider group of Earth Observations and Data experts comprising ARGANS Ltd (UΚ/Fr), isardSAT (Spain), and adwaisEO (Luxembourg) who delivered to an authoritative public User Group of national representatives from the British Geological Survey, the British government experts, IΗ Cantabria in Spain on behalf of the Spanish government’s Ministerio para la Transiciόn Ecolόgica y el Reto Demografico (MITECO}, Geological Survey Ireland, the Irish Government experts, ARCTUS representing the Canadian academic world and the local communities of Quebec and the Italian Institute for Environmental Protection and Research.

The main objective is to provide coastal change indicators derived from Earth Observations, and one of the key user requirements is to optimize how many images can be made available (i.e., cloud light and usable to extract derived products) over the coastal strip.

The consortium is providing customer-ready co-registered waterlines and shorelines seasonally covering 25 years that have been validated by the leading technical geomorphological experts within the four partner nations. These products can be scaled to cover complete countries worldwide. Α land classification map has also been developed that describes the coastal strip, including urban waterfronts, marshes, dunes, and their inter-annual changes.

The goal of the project is the measure coastal erosion/shoreline change rates along the County Wicklow coastline in Ireland. The results of the project will allow us to give an up to date, accurate, and relevant synopsis of how the soft sediment coastline of Wicklow in the east of Ireland has changed over the last

two decades and what its current state of erosion/accretion is. Using orthophoto data collected in Ireland since 2000 it has been possible to gain an understanding on shoreline change over the timeframe 2000-2012, however the quality of data has improved significantly in recent times, which is a strong opportunity to understand more recent changes to Irelands coastline.

As a results, we are trying to access VHR commercial satellite data to digitize shorelines ( e.g vegetation line) between 2012-2022 and compare the results with the orthophotos. The coastal area in question is composed of three main environments exposed bedrock, lowland beach or marshland areas, and soft sediment cliffs, with some areas classified as Special Areas of Conservation by Irelands National Parks and Wildlife Service. As climate change and rising sea levels begins to take effect in the coming decades it is important to have a good baseline understanding of the fluctuation of shorelines, especially those in low lying areas that are vulnerable to coastal erosion or habitat loss. This stretch of coastline contains several significant urban areas which represents a significant anthropogenic influence on the project, as shoreline change/coastal erosion rates can help influence informed decision making along the Irish coastline with respect to This project can feed into ongoing coastal vulnerability and coastal erosion projects occuring in Ireland and throughout Europe.

Soil sealing – also called imperviousness – is defined as a change in the nature of the soil leading to its impermeability. Soil sealing has several impacts on the environment, especially in urban areas and local climate, influencing heat exchange and soil permeability; therefore, soil sealing monitoring is crucial, especially for the Mediterranean coastal regions, where soil degradation combined with drought periods and fires contributes to desertification risk. The project Mediterranean Soil Sealing, promoted by ESA European Space Agency, aims to provide specific products related to soil sealing presence and degree over the Mediterranean coastal areas by exploiting EO data with an innovative methodology capable of optimizing and scaling their use with other non-EO data. Such products must be designed to allow – concerning current practices and existing services – a better characterisation, quantification and monitoring within time of soil sealing over the Mediterranean basin, supporting users and stakeholders in monitoring and preventing land degradation. The targeted products are high-resolution maps of soil sealing over the Mediterranean coastal areas (within 20km from the coast) for the 2015-2020 period, at yearly temporal resolution with a targeted spatial resolution of 10m.

In this project, it is proposed to create a high resolution (<10m) coastal typology of the European coastline, which distinguishes land use / cover classes relevant to coastal flooding and erosion. During this sponsorship we will develop a methodology to classify the satellite imagery. Upon success we will scale this to the whole European coastline.

This project aims to research various implementations of machine learning algorithms in monitoring coastal waters and understand the potential implications of this research. The goal is to combine highly abundant remote sensing data with in-situ sensor data to monitor and predict water quality. Water quality measurements are used to determine the health of local ecosystems for wildlife preservation and food production, which are at risk due to harmful algae blooms (HABs). A trained machine learning solution can resist noise and incomplete data, often during a natural disaster event. The area of interest for this study is Biscayne Bay in South Florida due to ease of access to the site, the collected in-situ data, and the remote sensing data to be used from public online web services. A Python program is developed, and processes gathered in-situ data with remote sensing data from Sentinel Hub. The data is statistically analyzed, plotted, prepared, and used to train a machine-learning model. The model is cross-validated and performs to a certain degree. Recent literature investigation indicates several approaches for water quality measurement and estimation, many of which do not rely on a combined remote sensing and in-situ sensor data set. For example, certain developments use strictly in-situ sensor data or combine satellite remote sensing data with drone remote sensing data. Further investigation is necessary to improve the accuracy of the developed model; this includes a better selection of spectral satellite image source and bands, outlier and missing data handling, cross-validation parameters, and choice of machine learning modeling algorithms.

Omanos Analytics is a space technology start-up delivering bespoke space data knowledge to support the narratives of communities across the globe. Data is present in tailored, accessible formats in order to reveal impact on local environments and communities. The company has been granted ESA funding, through the EO Science for society programme, to develop a prototype for a highly flexible image-processing pipeline that can be adapted on a case-by-case basis to meet the needs and demands of the communities in target regions. The service under development demonstrates how EO data can amplify and validate local reporting, connecting communities to EO data and processing resources that are currently inaccessible to them. The service provides a systematic interface for merging EO data and community intelligence, ensuring traceability, scientific objectivity, and transparency in analysis and data presentation. The proof-of-concept work primarily used EO imagery from Sentinel 1 and 2 and the Landsat satellites. These provide spatial resolutions of 10-30m and temporal resolutions of a few days to a few weeks depending on weather conditions. The spatial and temporal resolutions required are assessed on a case-by-case basis. The resolutions provided by Sentinel and Landsat satellites has been found to satisfy the requirements of many cases but where higher resolution data is required this is accessed either free of charge through Google Earth Pro or, if necessary and where funds are available, commercially. The funded development of our Community Earth Observation Intelligence Service prototype builds on this proof-of-concept work. Preliminary work produces brief outlines of 2-3 case studies which are developed into full case study definitions through engagement and dialogue with clients. Then data analysis is performed, incorporating EO data and ground truth data from client and community testimony. Key deliverables from this project are case study product packs, formed of a primary and a secondary data product. The primary data product is a scientific write-up of all data and analysis performed and will form a rigorous and objective scientific foundation of the secondary data product. The secondary “customer facing” data product is a bespoke translation of the primary data product, tailored to the needs of the client. Feedback from clients is assessed and incorporated into an evaluation of the prototype procedure and a road-map for future deployment.

The coastal zone and its shorelines are potentially affected by sea level rise in the changing climate. However, shoreline changes are affected not only by absolute sea level rise but also by morphological changes and vertical land motion. So far, the individual contributions of these groups of shoreline changing processes are unclear. This thesis aims to separate these processes by quantifying their effects on shoreline changes. This project will use observations of retracted coastal radar altimetry, as applied here, and compare them with shoreline changes from optical remote sensing observations. Complementary data sets like tide gauges and GNSS observations will also be employed. The goal is to produce a time-variable shoreline attributed to sea level rise and morphological changes. This is initially done for a focus region (Terschelling, the Netherlands), but the methods will ultimately be applied worldwide.

Furthermore, it is planned to build an empirical model from these observations to predict future shoreline migration. It is expected that the results of this project will not only advance our observation-based understanding of coastal changes and the participating processes but will also serve as an essential observational input for coastal planning in light of climate change. Data and software will be publicly released on shared platforms such as Zenodo, GitHub and the Dutch Data Archiving and Networking Services (DANS) in line with the open science policies of the ITC Faculty of Geo-information Science and Earth Observation of the University of Twente.

The objective of this project is to develop and test a methodology to construct a dataset of beaches and beach attributes. The main intended use of the dataset is the study of tourism, including its economic and environmental consequences. The dataset will be composed of polygons of beaches with attributes such as the color/brightness of the sand. The dataset will be constructed from Sentinel 7 and Sentinel 2 products, which are used for a refined land cover classification along shorelines. The dataset can be used, for example, in econometric analysis of how the presence of beaches influences economic development in coastal areas.

This project is part of a PhD research that aims to explore the potential of interferometric products (interferogram, coherence), covering the period from 2015 to 2024, to compare and validate the coherence change detection with the detected changes in the 3D Earth surface, extracted from the photogrammetric approach (2015 – 2018), and with field observation data. The objectives of this project are to investigate coherence maps derived from interferometric products to detect changes in the surface over time, to compare interferometric-based surface changes to photogrammetric-based change detection, to compare the detected changes with field observation data to validate the accuracy of both interferometric-based and photogrammetric-based change detection methods.

The Mothership is an open innovation program where select teams engage in an 8-week prototyping period using their unique expertise to help vulnerable landscapes on Earth. The program is created to leverage the recent advancements in artificial intelligence and satellite technologies in support of the UN Sustainable Development Goals. Results deriving from the program are incubator-ready prototypes that will bring teams with more mature ideas to established support services like the ESA Business Incubation program, the Copernicus Accelerator or ESA Kickstart activities. For this Mission, we have been chosen as one of the selected Copernicus Hackathon organizers, a scheme which is funded by the European Commission. To this end, teams are developing applications with Copernicus Data. The landscape of focus for this Mission is the ocean, hence contributing to the UN 2020 Decade of Ocean Science aimed at reversing the decline in the ocean. In this mission, a total of 50 participants are utilizing Copernicus optical and radar data to solve ocean challenges such as Coral Reef S.O.S., Tracking Illegal Sand Networks or 3D mapping for inundation. A mixture of a kick-off event, webinars, process coaching sessions and dedicated calls with challenge owners and mentors will allow participants to arrive at useful, functional prototypes and associated business models aligned with the challenge owners’ requirements.

Results are presented to a judging panel on a Demo Day. The winning team gets a seat in the Copernicus Accelerator. The Mothership is run in a collaborative effort of 3 founding partners: Space4Good, AI Lab One and the World Startup Factory.

The objective of this project is to exploit and assimilate pre-calibrated Copernicus Sentinel-2 COG data collections, managed according to FAIR data principles, in order to provide a comprehensive solution for accurate and efficient canopy height mapping on a large scale. This service plays a pivotal role in ecosystem monitoring and sustainable forest management. By harnessing advanced end-to-end learning techniques, it uses space-borne multi-spectral images. Moreover, it leverages the power of multi-temporal data from image sequences to ensure precise and reliable canopy height estimations. The Canopy Height Service (CHS) empowers environmental professionals, forest managers, and conservationists, consultant companies with valuable insights, enabling informed decisions and application of proactive measures.

More than half of the U.S. population resides on or within 50 miles of the coast, even though coastal zones constitute only 18% of the total U.S. land area. The combined effects of natural and anthropogenic activities/processes alter the morphology of these land surfaces, increasing the threat of steady inundation from SLR and the possibility of sudden and abrupt flooding and erosion emanating from storm surges/high tides. Even outside the coastal environments, largely anthropogenic activity-driven surface deformation processes are gravely endangering human lives and infrastructure. The proposed study area, Southern United States and portions of the (north and east) Gulf of Mexico coast, despite being largely tectonically stable, is experiencing subtle surface deformation and change mainly attributed to human activity-driven (anthropogenic) processes and a lesser degree due to glacial isostatic adjustment processes. With the documented increasing recurrence and intensity of natural disasters mainly due to anthropogenic-led alterations to the environment and climate change, an integrated research approach based on various datasets and novel techniques would be beneficial for monitoring the occurrences and impacts as inducing processes that initiated their circumstances. The proposed study aims to quantify surface deformation processes using fused satellite- and ground-based datasets and generate a complete deformation field of the study area. The temporal deformation patterns will be assessed to detect precursory hazard indicators crucial for developing hazard early warning systems. In addition, the factors and processes that directly or indirectly contribute to the occurrence of the hazards will be determined. Who will benefit from the project results: Communities, policymakers.

Indicator SDG 2.4.1 is defined as the proportion of agricultural land area under productive and sustainable agriculture (FAO, 2019). While the denominator agricultural land area is arable land, permanent crops, permanent meadows and pastures, the numerator captures the three dimensions of sustainable agriculture: environmental, economic, and social. In collaboration with the Food and Agriculture Organization (FAO) – the agency responsible for this indicator – and Early Adopters (EA), this project has the objective of contributing to the achievement of the target set by 2030, i.e., to ensure sustainable food production systems and implement resilient agricultural practices that increase productivity and production, that help maintain ecosystems, that strengthen capacity for adaptation to climate change, extreme weather, drought, flooding and other disasters and that progressively improve land and soil quality. Furthermore, it should be kept in mind that agriculture is a proven driver of poverty reduction; in fact, GDP growth generated by agriculture is more effective in reducing poverty than growth in any other sector (IFAD, 2022). Consistent Rice Information for Sustainable Policy (CRISP) aims to scale up advanced and cost-effective Earth Observation (EO) solutions to provide information on seasonal rice planted area, growing conditions, yield forecast, and production at harvest. To achieve this objective and to ensure that the designed solution meets the needs of users, a user-oriented approach will be adopted. The active involvement of users is also essential to introduce them into the use of the proposed solution, and, even more, to understand its capabilities and limitations.

Previous research in a GIS Programming course requested teams of 2-3 students to develop a state-of-the-practice QGIS plugin (Anbaro#lu 2021). Consequently, students relied on Git to collaborate with each other while developing their plugins, did unit testing, provided language support and documented their plugins using Sphinx. Although, students learned valuable technical and practical skills, in order to have a critical spatial data science perspective, more theory should be integrated into teaching (Holler 2019, Kedron et al 2020). Therefore, the objectives of this experiment is to investigate how students utilise an open-source Python package, x2Polygons, to find the distance between georeferenced polygons. For this each student will digitise a number of polygons, with varying complexity – in terms of the number of edges each building possess and evaluate how different distance measures such as the Hausdorff distance; Chamfer distance, PoLiS distance (Avbelj et al 2021) and turn function distance correlate with each other. In this way, they will be able to assess the advantages and limitations of different distance measures.

The project aims to utilize satellite imagery from Sentinel-2 and PlanetScope, along with drone data, to:

• Analyze and identify crop-related issues such as diseases, pests, weeds, and waterlogging.

• Improve crop productivity.

• Understand the impact of crop diversity, flora, and ecological! Parameters on crop yield.

• Optimization of weed management.

• Monitoring crop health.

The Ministry of Agrarian Policy and Food of Ukraine communicated that they experienced in 2022 that satellite data makes it possible to monitor crop growth, as well as to visualize planted areas, yields and crop production. In addition, the harvest progress can be monitored at the national, regional and local levels. The Ministry recognizes this independent service as important and useful for the execution of tasks in the agricultural sector of Ukraine and would like to have a continuation. Because of the complicated financial situation, the Ministry of Agrarian Policy and Food of Ukraine requests international donors to consider the possibility of sponsoring such services. The requested service for the data processing shall deliver information on agricultural production using satellite monitoring based on Copernicus Satellite data (mainly Sentinel-2 and -1) and crop growth modelling. It shall provide independent, objective and highly detailed information on crop production and overall agricultural activity in Ukraine in 2023 as information to food security.

The project’s main objective is to use the IaaS service provided by the CREODIAS environment to classify crops and predict yields based on satellite and meteorological data available in the EO data repository. The secondary objective is to provide the generated results to the ESA WorldCereal project and the EO4UA initiative.

This project aims to study crops and their impacts in the U.S. Midwest. The corn and soybean row crop system in the U.S. Midwest, contributing to one-third of the world’s production, faces grand environmental challenges related to excessive use of fertilization, soil carbon loss, and water quality degradation. Understanding the historical and present crops and their impacts on crop yields is crucial for global food security. The accurate estimates of current and historical crop acreages are essential for understanding crop adoption status, evaluating the outcomes of incentive programs, and designing effective agricultural management. Multiple sensor datasets, including ESA’s Sentinels and NASA’s Landsat, are used for high-resolution and long-term crop mapping in the U.S. Midwest. Detailed crop fields with crop information will be generated for the whole U.S. Midwest, which is essential for agricultural stakeholders. The spatial and temporal patterns and trends of crop maps provide crucial details for policy-makers and sustainable agriculture, which further secure crop yields in this region. High-resolution crop maps at the field level are lacking for the whole U.S. Midwest. Thus, this project can serve as the benchmark for future crop mapping. The developed crop detection algorithms are scalable to regions with similar settings and can be performed locally and globally. The science foundation integrates the knowledge of crop plant physiology and remote sensing of different targets, gaining insights into agricultural remote sensing and laying solid foundations for other research.

The project aims to provide a service based on satellite and weather data to satisfy farmers’ needs. Several segments of the market can benefit from this service. Mainly and firstly, the target is farmers. Farmers can use this service via web-based or mobile applications and a lot of helpful information about their farmland and make more optimized decisions that use pesticides and similar inputs. In this way, not only does the farmer benefit because of lower consumption of such inputs(which will pay off the cost of the service), but they also will experience a higher crop performance. The second segment interested in the product is the insurance service providers. We can provide precious information based on satellite image analysis to them. Furthermore, we can help them to handle claims because we know what has happened to the farmland.

Our primary goal is to deploy digital and precision agriculture services for farmers, empowering them with data-driven insights to optimize every phase from planting to harvest. The sub-objectives of this initiative include:

– combining crop management strategies, Sentinel satellite data, climatic information, and artificial intelligence to create sophisticated monitoring tools that can detect Crop challenges related to pests, weeds, nutrient and water deficiencies

– Identification of hotspots within fields that require detailed inspection.

– Empowering farmers to apply inputs precisely where needed, reducing costs and minimizing environmental impact.

– Utilizing data to forecast yields at both the individual farm and broader regional levels.

– Providing policymakers with accurate, timely information about crop types, locations, and performance metrics to prepare data-driven agricultural strategies and decisions.

The main objective of this project is to study the complementarity of spatial optical imaging, structural information from Synthetic Apertuge Radar (SAR) and environmental characterization data to model maize and sunflower seed production by aggregating these observations of different spatial and temporal resolutions. The thesis work will be based on Syngenta’s plot network in several parts of Europe and North America, where some varieties of maize and sunflower are evaluated under different environmental conditions.

The Feature Engineering of satellite observations used in the development of machine learning models will seek to estimate varietal parameters-functional extracts-which define, on the one hand, the phenology, but also the different varieties’ response to abiotic stress, and mainly to water stress. In the case of phenology, we will study the parameters that determine the development response to temperature and photoperiod, and that predict specific crop stages. The functional traits that characterize the response to abiotic stresses will make it possible to identify, from multi-environment observations, the most efficient varieties, and to predict their behavior and yield.

Field crops (e.g. maize, soya beans, wheat, and sugar cane) are an important staple food in South Africa and the broader Southern African region. According to the latest “Census of Commercial Agriculture (2017)” by Stats SA, field crops make up 23% of South Africa’s total farming income (~Approx R69 Billion worth), and are a crucial resource in addressing the nation’s food security. They account for the largest portion of cultivated cropland in South Africa and employ ~16% of the total commercial agricultural workforce (some ~124 000 employees). Large farms (i.e. >R22.5M annual income) only make up 6.5% of the total number of farms, but contribute 51.4% and 67% of employment and income, respectively. This means the remaining small and medium-sized farming operations (~93.5% of farms) only contribute 33% of total income and 48.6% of total employment. This imbalance can be addressed, and reduced, through investment in innovative technologies that improve the efficiency of these small and medium-sized farming operations. Therefore, this project will particularly address the needs of small and emerging commercial farmers. Along with improved market access, increasing the efficiency (i.e. ‘doing more with less’) and crop outputs of a large number of farms, has the potential to not only address socio-economic aspects (e.g. poverty) of individual farmers but also improve the sustainability and competitiveness of the whole South Africa agricultural sector. The overarching aim of the project is to develop a unique precision agriculture information system (PAIS) that will provide actionable data to emerging, and existing commercial, farmers and industries along the agricultural value chain. The PAIS shall provide regular farm-level information on the spatial variability of crop growth conditions to desktop and mobile platforms to foster precision farm management. Using ground-based spectroradiometers, airborne drone imagery, and freely available medium-resolution satellite imagery, the CSIR in South Africa is actively working with several emerging (maize) farmers on the development of crop-specific remote sensing models (mainly based on Sentinel-2 data). Remote sensing algorithms have been established, regarding those for maize growth, with parameters including soil organic and nutrient content, crop height, number of leaves and leaf chlorophyll content. Having spent time calibrating and validating maize crop models, the next steps focus on developing a platform through which these various products can be delivered to farmers, and other stakeholders in the value chain. Cloud-optimized services (such as Sentinel-Hub), being able to offer scalable and ‘near real-time’ access to the satellite data, will form the backbone of the envisioned precision agriculture information system (PAIS).

The objective of the project is to leverage the high-resolution and multi-spectral data provided by Sentinel-2 to create detailed maps of crop distribution, which can help farmers make informed decisions about land use, crop management, and food security, which will enhance and lift the lives for many poor farmers. Furthermore, we want to unite the farmers and educate them regarding crop management and food security. We currently have a community of 50+ farmers, and we plan to make decisions on sessional crops, land decisions, soil management, and food security. Also, this will help us in the future in many ways.

Accurately determining crop growth progress and crop yields at the field scale can help farmers estimate their net profit and enable insurance companies to ascertain payouts, ultimately bolstering food security. At field scales, the trifecta of management practices, soil health, and weather conditions combine to impact crop growth progress, and this progress can be monitored in-season using satellite data. The project aims at creating field-scale results that will be made available to farmers and regional-scale results that will be available to policymakers via the NASA Harvest website and relevant peer-reviewed publications.

This project aims to design a system for the early yield prediction of crops in the Madhya Pradesh region of India with the help of Sentinel-2 satellite images. We want to apply deep learning techniques on satellite imagery to alleviate the problem of manual crop yield prediction and ensure food security in times of climate change in the Madhya Pradesh region, which has emerged as one of the largest wheat-producing states in recent years.

Indian economy is based on agriculture. More than 70% of the Ιndian population is involved in agricultural practice directly or indirectly. In 2015, the United Nations adopted the 2030 Agenda for Sustainable Development, including 17 Sustainability Development Goals. One of the goals concerns food security. Around 795 million people worldwide do not have adequate food to eat. According to an estimate, in the next 35 years, the world will need to produce more food than ever produced in human history due to the factors such as increasing population, climate change, rising incomes, and changing diets. Reliable and well-timed crop yield forecasting is essential in ensuring food security. Ιt can be helpful to the farmers, buyers, industry, and governments in several ways:

1. It helps the commodity brokers and farmers to manage and plan the selling and storage.

2. Early prediction of the expected yield helps the government and other buyers make necessary procurement arrangements, including workforce, transport, storage mapping, and gunny bags.

3. Ιt also assists the allied industries in strategizing the logistics of their business.

4. Yield forecasting is also helpful in minimizing damage in case of critical events. Early and reliable information on crop yield can help humanitarian agencies to organize emergency response and food assistance.

5. It helps the farmers to plan the crops accordingly, paving the way to precision agriculture.

Estimates suggest that India’s population will reach 1.7 billion by 2050. An increase in temperature with an increase in extreme heat days effect has been known to impact crop production and yield. This makes the precise and timely prediction of wheat yield even more critical.

This study aims to employ various vegetation indices and a deep learning system to estimate and predict yield in Bangladesh while accounting for spatial and temporal variations. Following is a list of specific objectives:

a) Estimate crop yield using vegetation indices and a deep learning algorithm.

b) Validate the estimation outputs by the utilization of ground-based observation.

c) Accurately predict yield within the context of smart and sustainable agricultural practices.

This project aims to develop methods for satellite-, model- and AI-based yield forecasting of crops in the context of Austrian agriculture. To achieve the project goal, the following technologies and methods will be combined or further developed:

• Sentinel 2 spectral data (satellite imagery) will be used as input for the AI component, the PROSAIL reflectance model and the iCrop growth model.

• The AI component will be trained to detect crops using manually labelled and existing training data from the Austrian and US regions. The trained model should be able to correctly classify the crops visible on the satellite images by 90%.

• With the PROSAIL reflectance model, possible reflectance values are calculated by discrete variations of the input values and stored in a database. The reflectance values seen in the satellite images are then matched with the values in the database to infer possible input value combinations and crops.

• The results of the AI component and the reflectance model are passed to the fuzzy logic classifier to determine the crop finally.

• The detected crop type and growth parameters (e.g. Leaf Area Index) derivable from the spectral data will be used to calibrate the iCrop growth model for yield prediction (as well as harvest timing, phenology, fertilizer and water requirements).

The developed methods should be able to determine the crop species on overgrown Austrian field pieces based on satellite data with about 90% accuracy and generate yield forecasts based on these data. For the Austrian area, such applications do not exist at present. In the international context, there are applications for detecting agricultural crops based on satellite imagery, but no approaches use this as a basis for calculating yield forecasts with growth models. The added value for the addressed user groups is the scalable generation of yield forecasts based on daily updated satellite data.

Training datasets (TDS) are understood to be an essential element of any application of Machine Learning (ML) or Artificial Intelligence (AI) in Earth Observation (EO). However, the general lack of TDS today is considered a major bottleneck hindering a widespread impact of innovative uses of AI in EO. This situation is especially severe for agricultural applications such as crop mapping, which demands timely (e.g., seasonal, multiple observations over the growing season), high quality and spatially exhaustive TDS. Therefore, there is a strong demand in the EO community and industry for capabilities that support the creation of TDS, especially for agriculture and in the absence of LPIS data. This activity combines the EuroDataCube (for pixel level data access and parcel delineation/segmentation) with crowdsourcing (Picture Pile app for parcel annotation) and citizen science (Street Level photography from Google Street View and MapPillary). Moreover, this activity is closely linked to the Earth Day EarthChallenge, which provides high public visibility and ensure the involvement of high numbers of participants to participate in parcel interpretation and annotation.

The project uses the TEP geohazards to make interferograms and time-series with SBAS to compare to the software ISCE and pi-rate time-series analysis). The aim is to teach InSAR researchers at the University of Pisa to use the current TEP capabilities and the ESA products to study and monitor our hazardous planet. Therefore, students (individually or in groups, for a max of ~ 5 users) can access the service and practice SAR processing and time-series analysis during the next 12 months. We aim to use Sentinel data to study crustal deformation in active key areas such as the Reykjanes Peninsula of Iceland. It is also planned to process Sentinel 1 and ALOS-2 interferograms over the volcano Changbaishan (China) to test whether short revisit times, as offered by Sentinel, and longer wavelengths, as employed by ALOS, work in monitoring vegetated hazardous areas like the Changbaishan volcano. A third study area is the Tuscany (Italy) region, in particular, the geothermal field of Larderello, as this site can also be directly observed and monitored with in-situ measurements by students at the University of Pisa. The deformation signals that we study are cycles of uplift and subsidence caused either by magma or geothermal fluid migration. The aim is to process the InSAR data to understand the relative importance of the two phenomena in the study areas. We also extract time series of cumulative displacement and assess whether a seasonality in the deformation pattern exists, which may suggest hydrothermal fluid migration. We will also test whether the observed deformations can be instead explained by magmatic source models (i.e. Mogi and Okada magma chambers).

Many strong active faults have developed within the Tibet Plateau, Tienshan and its adjacent regions, forming multiple seismic zones due to the collision and continuous extrusion wedging between the Indian and Eurasia plates. Those faults directly control the spatial distribution of severe disaster zones in mega-seismic areas. But the lack of quantified descriptions of geology and geodesy in this area makes it very limited to understand its geophysical environment and rupture process of active faults. This study focuses on strong active fault zones in Western China, especially in the central Qinghai-Tibet Plateau and Tienshan region. GPS and InSAR will be used to monitor the crustal deformation and to derive an accurate 3D velocity map of the area. We expect to densify the existing GPS network, form several profiles across those active faults, and then integrate the GPS and InSAR measurements to derive the velocity maps and geometry of different segments of the faults, cooperating with geology and geophysics data. It can elaborate the advantages of two means and get the fine fault monitoring and structure analysis to reveal the graben deformation characteristics, tectonics, deformation pattern and evolution mechanism of the studied regions. Finally, we will inverse the lock depth of different segments and investigate the relationship between crustal deformation features and strong earthquakes and the relationship between the lock depth and deep structure. It will improve the ability of earthquake forecast by revealing the kinematics pattern and dynamics and dynamics background of the continent deformation in China and its adjacent regions.

The Cryosphere Virtual Laboratory (CVL) project will develop, test and demonstrate a prototype community open science tool where EO satellite data and derived products can be accessed, visualised, processed, shared and validated. The tool will provide access and facilitate the sharing of relevant space and non-space data (aerial, UAV, coastal radar, in-situ, etc.). Following an Open Science approach, the CVL will mainly be designed to support scientists in accessing and sharing EO data, high-level products, in-situ data, and open-source code (algorithms, models) to carry out scientific studies and projects, sharing results, knowledge and resources. Within CVL, Polar TEP will act as the data processing engine and provide a rapid development and prototyping environment based on Jupyter Notebooks.

The Cryosphere Virtual Laboratory (CVL) project will develop, test and demonstrate a prototype community open science tool where ΕΟ satellite data and derived products can be accessed, visualised, processed, shared and validated. In addition, the tool will provide access and facilitate sharing of relevant space and nonspace data (aerial, UAV, coastal radar, in-situ etc.). Following an Open Science approach, the CVL will mainly be designed to support scientists in accessing and sharing ΕΟ data, high-level products, in-situ data, and open­ source code (algorithms, models) to carry out scientific studies and projects, sharing results, knowledge and resources.

In the polar regions, sea ice, glaciers and permafrost are subject to rapid changes. In order to keep up with the temporal and spatial scales of changes, Earth Observation (EO) data are instrumental. EO data can fill the spatial gaps between in situ measurements, but users are facing challenges as volumes are increasing rapidly with new satellite systems and sensors. In recent years spatial resolutions have moved from kilometre to metre scales. The number of satellite systems providing information is continuously increasing. While EO data create challenges in volumes, in situ observations which are necessary both for validation of the algorithms applied to EO data and to understand the long-term changes in processes, create another challenge – heterogeneity in data. Both in situ and EO data are now flowing at a higher pace than earlier, meaning scientists in the cryosphere domain are facing the challenges of Big Data, large volumes, large heterogeneity and large velocity of new data. This calls for new ways of working with data, where data, software and workflows are combined, taking advantage of new and existing technologies for workflow management, efficient data reduction and integration of data and software using the Internet. This way, data and software can be combined across physically distributed repositories and systems. The Svalbard Integrated Arctic Earth Observing System (SIOS) currently serves in-situ data and derived EO data time series from the Svalbard archipelago and surrounding sea areas. Within the CVL project, data available through SIOS is integrated with products from numerous EO missions, other relevant in-situ data, and other datasets relevant to Polar research. The CVL scientific development environment is launched as an integrated service in a cloud-based infrastructure, offering tools for data discovery, data access and data manipulation. CVL makes use of Polar TEP for some of its functionality. Data analysis (i.e., low-latency interactive operations on relatively small data amounts used in the development and testing of scientific algorithms) is performed on a virtual machine (VM) either on a local computer or hosted by Polar TEP. A user can download the VM configuration to a local computer and launch a local VM using freely available tools like VirtualBox and Vagrant, or log in to the Polar TEP web portal and launch a VM there. The user then can open a Jupyter Notebook (or login into the VM shell and run IPython) and work with Python for metadata search and data analysis. Visualization of data and results are performed using standard open-source Python libraries such as Matplotlib, Cartopy and Folium. In addition, Jupyter Notebooks will be integrated with the NGVOC (Norut Geo Visualization Open Core) 3D visualisation tool with the ability to pan, zoom and tilt the map, and to combine raster and vector information layers. Data processing (i.e., time-consuming and automated operations on large amounts of data to, e.g., derive time series using a pre-developed scientific algorithm) are performed only in a VM hosted by Polar TEP. The main processing chains (i.e., Python scripts) are prepared in the scientific use cases. In addition, users may also develop their processing chains. Each processing chain will contain relevant specifications of input data, processing steps and expected outputs. The results can then be uploaded to the CVL file servers, offering access and visualisation services for further re-use and visualisation.

The project’s main objective will be to demonstrate that it is possible to precisely monitor forest biomass to validate and certify La Belle Foret’s methodology to generate carbon credit thanks to high-resolution satellite data. More specifically, we want to carry out some ground measurements (LiDAR or manual forestry tree counting process) and combine them with satellite imagery to precisely estimate the aboveground biomass with only a few ground samplings using the allometric models that we developed in-house.

We are currently working with the french ministry of ecological transition to generate carbon credits certified by the French Label Bas Carbone, and we are laureate of the ΒΡΙ France Deep Tech sponsorship, which rewards our effort to set up deep tech solutions to finance the protection of the french forest.

We will mainly use Pleiade and Pleiade Neo Airbus data for this study (50 cm and 30 cm resolution over six spectral bands).

Since every methodology certified by Label Bas Carbone is made publicly available, the main results of this project may be publicly disclosed if it appears that satellite certification can take part in the overall certification process by the French Label Bas Carbone.

The project aims to monitor the cultural heritage sites in Libya, particularly the UNESCO WH sites that are facing many human and natural hazards and threats nowadays.

CYMS’s main objective is to scale υp an operational service for Tropical Cyclone (TC) monitoring based on existing C-band SAR missions (Sentinel-1 and Radarsat-2) in νiew of its potential integration as part of a Copernicus Service. CYM operational objectives include (1) the ordering of the SAR data to ESA and MDA to trigger acquisition over TC when operational Tropical Cyclones centres forecast a storm, (2) the near-real time processing and delivery of ocean surface wind field Level-2 products for TC occurring during the project and (3) the maintenance of an archive of all (including acquisitions over TC obtained before the project) Level-2 products processed with the most up-to-date algorithm. CYMS technical objectives include (1) the improvement of the existing near-real-time processing chain and (2) the investigation of new solutions for fast and remote reprocessing of the complete TC archive. (3) CYMS technical development also includes extending the activity to other types of storms such as Polar Lows, Medicanes and Extra-Tropical Cyclones. The project’s near-real-time part aims to provide information on TC vitals to end-users for short-term forecasting applications. The archiving part shall ensure a homogeneous processed Level-2 product data set for science applications and re-analysis of TC. One of the project objectives is thus to assess the potential of CYMS service for users, including applications over European waters. Communication actions and presentations of the service to users and national delegates are part of this task.

Danube Data Cube (DDC) is a regional data exploitation platform built on and follows the logic of the Euro Data Cube (EDC) infrastructure, a computational environment reflecting the Digital Twin Earth concept of the European Space Agency to support sustainable development. DDC is a cloud-based platform with data and analysis tools focusing on the Danube Basin. As a regional platform service, it demonstrates the data cube technology’s data storage and analysis capabilities, maximizing the benefit of the synergy of satellite and ancillary data with dedicated analysis tools. The DDC concept includes extensive Machine Learning capabilities, including analytical tasks and decision support algorithms. One of the key themes of the platform is water management, from regional strategy and public information to field-level irrigation management.

Currently, DDC works on a regional and a local (field-level) showcase. Both are related to water management.

This project is the second phase of the Danube Data Cube.

DDC is a regional data exploitation platform built on and follows the logic of the Euro Data Cube (EDC) infrastructure, a computational environment reflecting the Digital Twin Earth concept of the European Space Agency to support sustainable development. DDC is a cloud-based platform with data and analysis tools focusing on the Danube Basin. As a regional platform service, it demonstrates the data cube technology’s data storage and analysis capabilities, maximizing the benefit of the synergy of satellite and ancillary data with dedicated analysis tools. The DDC concept includes extensive Machine Learning capabilities, including analytical tasks and decision support algorithms. One of the key themes of the platform is water management, from regional strategy and public information to field-level irrigation management. Currently, DDC works on a regional and a local (field-level) showcase. Both are related to water management.

Timely and accurate forecasting of crop yields has important agricultural, economic, and societal implications. The primary tool for estimating crop yield has traditionally been field visits combined with crop growth models and/or weather inputs. Alternatively, remote sensing can be used to estimate crop yields by providing timely and continuous observations of canopy development over large areas at various spatial scales. Yet, remote-sensing based yield forecasting has not been operational to service local and regional governments in Central Europe to provide highly needed statistical and economic information in a timely manner. This project proposes to develop an operational and in-season crop yield forecasting service for Central Europe using remotely sensed observations and environmental inputs at multiple spatial scales. The approach is data-driven, exploiting the relationship between remotely sensed biophysical variables, weather conditions, soil water status, and management practices, using machine learning algorithms. As such, the approach is designed to bypass hard-to-parameterize crop models and being highly scalable using a cloud computing infrastructure. The proposed application has great potential for supporting government agencies, commodity firms, producers, and many other end users in planning market and trade activities, price discovery, and help determine the magnitude of supply by providing accurate and timely information on crop yield and production across large areas. At the present, a partnership with the Hungarian Agricultural Chamber – a distinguished end user in Hungary-, has been established.

Among the renewable energy sources, solar and wind are rapidly becoming popular for being inexhaustible, clean, and dependable. Meanwhile, power conversion efficiency for renewable energy has improved with great technological leaps. Following these trends, solar and wind will become more affordable in years to come and considerable investments are to be expected. As solar and wind plants are characterized by their high site flexibility, the site selection procedure is a crucial factor for their efficiency and financial viability. Many aspects affect site selection, amongst them: legal, environmental, technical, and financial. Today, information gathering for site selection assessments is a manual and time-consuming process. The main objective of this project is to develop a dataset of existing solar power plants* by applying computer vision on satellite imagery.

Objective 1 (O1): Achieve 90 % accuracy for a specific data layer* using SOTA deep learning models.

Research Question 1: Can the required accuracy be achieved with publicly available 10×10 meter

image resolution, or must higher resolution imagery be used?

Research Question 2: How can the training-data creation process be made for the specific data layer to

achieve the required accuracy?

Research Question 3: How can the training of the model be made for the specific data layer to achieve

the required accuracy?

Since the project is researching the process of site selection and the utilization of data for renewable

energy projects, the idea contributes to positively influence the UN’s Sustainable Development Goal 7;

Clean energy for everyone. For the region to be able to produce enough clean energy, it is necessary to

accelerate the development of renewable energy projects.

In the framework of the ESA Earth Observation for Sustainable Development – Climate Resilience (EO4SD CR) project, a large set of data-related services are going to be provided by the consortium partners to regional (e.g. Africa Risk Capacity, ARC) and global (e.g. the Climate Change unit of the World Bank) organizations so that they can serve their local users with climate risk analysis and adaptation support. To fulfil their needs the EO4SD CR is requested to provide data and services based on the following datasets:

– Copernicus ERA5 land (Surface air temperature, Runoff, Surface Air Relative Humidity, Potential Evaporation)

– Copernicus Land Global Services (Land water quality, Vegetation index, Soil Moisture, surface water explorer, global land cover 2015). Considering the data accessible via a DIAS platform, the cluster needs processing resources and storage space to generate, store and provide user-driven products based on the above-mentioned Copernicus data.

Through the Datafactor project, we intend to establish a reference centre for Data Science activities and services (for example, Big Data Analytics, Semantic Web) developed on national Open Data. This centre is conceived as enabling advanced data-driven solutions developed “in situ” and customised in favour of citizens, administrations, professionals, managers and companies. The primary objectives, understood as concrete results that the project will have to produce, concern both a strategic vision of the international scope of the group, as well as strong roots in the territory and a strong identification and awareness of the qualities of the country system:

• Enhance the information assets of national Open Data

• Reduce the complexity of using the powerful data technologies available today and make them more accessible and reusable by researchers, citizens and companies

• Allowing a substantial reduction in the execution times of data-driven decision-making processes of a diversity of subjects (decision-makers, managers, administrators)

• Integrate data of different natures, in particular satellite data. This source, not yet fully exploited, represents an excellent resource for the community, both in direct form and in the elaborated form: services based on satellite data have already been designed within Datafactor to be made available to individuals, PAs and companies, with significant positive effects on the quality of life and the environment.

• Increase the effectiveness of using the most modern data-based approaches and the measurability of the results. Any result will be available to citizens, public institutions and companies in the form of usable applications and reports based on web and phone apps, portals with search engines, tailorable profiles and easy to use infrastιυctιιres.

The project aims to develop innovative extensions for Jupyter and Visual Studio Code to allow the launch of remote Jupyter Kernels in the cloud. Furthermore, as part of our application, we want to demonstrate Proof of Concept of our offering.

We will also look at the security aspects (how to authenticate an external Jupyter server toward the EODC and how the fine-grained access rights to the datasets are implemented).

The objectives of the project are:

1. Assessment of decadal Mass Balance and Ice Thickness of glaciers of Sikkim Himalaya (Study

Area 1200 Sq. Km)

2. Estimation of Glacier Facies using GLCM and Random Forest Classification.

3. Movement analysis of glacier in Sikkim using PSI.

Statement on availability of results.

The results shall be available online through any suitable data sharing portal on request for research purpose only. It shall also be shared with nodal agency for sub-regional level policy response. Subregional policy requires concrete evidence especially in developing Nations like India.

The project objective is to create the decade data set for the land use map for India based on the NRSC classification scheme for 1995,2005,2015. Under this study, a methodology based on the CNN technique, which uses the yearly seasonal pattern to identify the LULC, will be integrated with the spectral response. The multi-temporal classification will lead to the level 3 classification data by applying the hierarchal classification technique. The decadal LULC will be analyzed for the temporal variability observed in different classes. The classified data will be used with the LULC prediction models to provide future integrated scenarios. The different LULCs will be integrated to give the weather models to analyze climatic variability due to LULC changes.

This system aims to provide advanced solutions for crop monitoring, disease detection, and yield optimization. By harnessing the power of AI and data analytics, the project seeks to enhance the efficiency and productivity of farming practices while promoting environmental sustainability. The specific project goals include:

– AI-Enhanced Crop Monitoring: to implement AI-driven algorithms that enable real-time monitoring of crop health and growth stages using multispectral drone imagery and satellite data.

– Disease Detection: to develop AI models capable of early disease detection in crops, thereby enabling timely intervention and reducing yield losses.

– Yield Optimization: to utilize AI-based predictive analytics to optimize crop yield by providing insights into irrigation, fertilization, and harvesting decisions.

The objective of this project is two-fold and the requested data can be used for both tasks while testing processing capabilities on The Food Security Platform (TEP). Firstly, we will demonstrate that it’s possible to do bottom-of-atmosphere (BoA) correction on Sentinel-2 Reflectance at Bottom of Atmosphere/VISTA Algorithm (available on TEP as ‘Vista_S2-L2A) using deep neural networks. We estimate that this can improve processing speeds by x100 to x500 while keeping accuracy high. This is inspired by an existing algorithm, developed for another project, that in production as a side effect efficiently fixed incorrect Sen2Cor bottom of atmosphere correction. This is in particular interesting on, important and frequently used algorithms with long processing times like BoA processing algorithms. The results will be avg. pixel error measured against ground truth imagery. We will also present the relevant processing speeds improvements and requirements to run said algorithm (eg. GPU accelerated processing). The results will be made available on TEP as ClearSky Vision demo data, and if possible produced on TEP. It will, furthermore, be measured against data in-sample and out-of-sample, and the project will be finished off by producing a tile unavailable on the platform. This project has the potential capability of greatly reducing required resources for BoA correction on Sentinel-2 imagery by doing it in

a fraction of the time (leaving data storage as the final limitation). Not only making it a fast and efficient process but it also makes near-real time monitoring more achievable.

ClearSky Vision has already developed an algorithm for cloudless Sen2Cor imagery (using deep learning and multiple satellites for data fusion). This approach won ClearSky Vision the Copernicus Masters Bay Wa competition in 2020. It combines Sentinel-1, Sentinel-2, Sentinel-3, and Landsat 8 into daily cloudless Sentinel-2 imagery. This project will further prove, to what degree cloudless results on Vista S2-L2A will match the accuracy from prior cloudless Sen2Cor imagery tests. The objective is to determine whether this (more complex) processing method will make the cloudless process more difficult or what’s more likely, improve the consistency of the output. The results will be made available on The Food Security Platform as ClearSky Vision demo data (10 spectral bands).

The arid and semi-arid regions of Africa (e.g. Chad) are fragile ecosystems where pastoralism is an important practice that induces the presence of large domestic mammal herds. The semi-nomadic nature of these herds leads them to cohabit with herds of wild animals within protected areas (PA) that are supposed to protect them. This cohabitation can lead to mutual transmission of epizootics, predation and competition for access to resources. Wildlife conservation relies on the reasoned and controlled presence of domestic herds within PA, involving continuous monitoring. The objective of this project is to evaluate the performance of recent Deep Learning (DL) algorithms to detect and count domestic herds in arid and semi-arid landscapes of Africa based on different remote sensing products, including very high-resolution satellites. The main study area is the Natural and Cultural Reserve of Ennedi (50,000 km²) located in Chad. DL techniques will be considered to create models for animal detection and counting. The tools developed will enable PA managers in arid or semi-arid zones to improve the monitoring of domestic herds and thus contribute to a better preservation of this natural heritage.

Urban expansion is giving rise to new challenges globally, especially in African countries badly affected by climate change, population, and, most importantly, economic growth. Government agencies must estimate cities’ growth, thus enabling better urban planning to meet challenges. Machine learning and Computer Vision techniques can allow government agencies to generate models which can control Urban expansion beforehand. So, this research focuses on using satellite images to tackle the Urban expansion of certain areas using deep learning techniques. For Urban expansion, I selected the area of Dakar, Senegal, one of the Seaports on the Western Coast of Africa. Dakar region also suffers from various development issues associated with environmental deterioration, such as the decrease of green areas, farmlands, and wetlands. Therefore, economic activities suffer from these problems. This research aims to provide a deep learning model which can predict Dakar’s urban expansion so the state can plan the land transformation and economic growth accordingly. Moreover, this project will also help all the sentinel hub users who want to work on satellite images or multi-temporal data to solve Urban expansion-related problems. This research will help them create a pipeline for using satellite images to develop a deep-learning model to predict the urban expansion of their desired area.

DeepESDL users or teams will be provided with individual subscriptions for external services to ensure that dedicated resources are available to them. The requested subscription is required for the first set of Early Adopters, which are currently onboarded, and their associated use cases as well as for the DeepESDL consortium to integrate the Sentinel Hub service, demonstrate and validate ts functionality and for using it in training sessions for new users.

Sinergise/Sentinel Hub have provided several code samples and instructions which make accessing/working with this data and API ‘easier’. Their EO-Learn libraries make it easier to prepare data for machine learning. This idea was launched at a NASA Space Apps hackathon in London in 2017, originally using NASA Aster data with 30m square resolution and combining satellite data (13 spectral bands) with ground-measured hydrogeological data. Specifically, using latitude/longitude records of existing drinking water locations, from national government records. We have over 1 million records of existing verified water wells, many with depth data. The combination of all the above reached to build a neural network with ~98% accuracy in determining the existence of water in a 10m square location (a binary yes/no classification). This was done using a smaller sample set of 10,000 existing water wells; by using the coordinates of the wells to cross reference and pull down Sentinel 2 satellite data with 13 spectral bands for each of the locations to train the neural networks. Several other ML techniques (including gradient boosting) have been used to verify our results. The next stage consists of training a regression neural network to predict/calculate depth of the 10m tile with presence of water. Each tile surface area is then multiplied by the predicted depth for that location and a volume of the water can be calculated. These prediction results can be verified using ground truths of government-known/verified well depths. The above work was used as a foundation to propose a flood prediction service.

The project aims at creating a Landcover semantic segmentation model to identify the changes in resources of Sri Lanka, such as forest cover.

The project will use differential interferometric Synthetic Aperture Radar techniques (DInSAR) to measure land deformation caused by earthquakes and land subsidence. Geological instabilities could cause the differential movement of ground at different depths. This phenomenon is a gradual settlement of soil that causes inundation of land, expansion of flooding areas, disturbance of drainage systems, changes in slopes, and damages to infrastructure foundations in urban areas. This study will also analyze the deformation’s behavior and cause of subsidence within the research area. Moreover, the study will try to understand the necessary connections and interactions between people and natural events to prevent or lessen the extensive social, economic, environmental, and infrastructure effects. Supporting information requires accurate and timely change detection on Earth’s surface to make better decisions about land deformation and the event’s temporal ramifications. To enhance the measurement of small-scale surface deformation using SAR Interferogram. The information, including detailed coseismic deformation based on the study’s interferometric results, will be helpful in the community’s disaster management and mitigation activities. The results will include the land deformation map and the Subsidence map of the study area. The aim is to provide information to urban planning and management authorities. Finally, the project will be used to gain expertise in using the Geohazard platform.

The objective of this project is to integrate image recognition technology for developing a small exploration rover that autonomously designs and guides its path using satellite imagery, detecting ruts, obstacles, and soil conditions. In recent planetary satellite missions, landing accuracy on the Moon and Mars ranges from a few hundred meters to several kilometers, needing guided navigation for rovers arriving at their destinations. For currently operational rovers on Mars, such as the Mars Curiosity Rover and Perseverance, personnel at ground stations determine intermediary waypoints necessary to reach their destinations based on images from satellites like the Mars Reconnaissance Orbiter. These rovers autonomously navigate to these waypoints by performing 3D scans with cameras positioned away from the body via arms, while guided by the personnel at ground stations that send the commands.

Current operational rovers on Mars, such as the Mars Curiosity Rover and Perseverance, autonomously navigate to these waypoints by performing 3D scans with cameras positioned away from the body via arms, but they need commands from the personnel at ground stations that determine the intermediary waypoints necessary to reach their destinations. These commands are based on information from images from satellites like the Mars Reconnaissance Orbiter.

However, small exploration devices have limited capabilities to perform extensive 3D scanning with cameras, unlike larger rovers. Furthermore, in traditional ARLISS competitions held in the United States (a competition for navigation and accuracy in reaching the goal of simulating a planetary exploration), many teams navigate using coordinates of the current and target positions without adequate consideration for ruts and obstacles on the terrain – as it happened in Black Rock Desert where it is held. Given their size and weight, small exploration devices are anticipated to play a significant role in future planetary explorations. If this technology is applied to satellite explorations, it could allow a few ground stations to monitor numerous small devices efficiently. Moreover, if new satellites enter the orbit of an exploration planet and enhance the resolution of images sent to these small devices, it could lead to improved exploration accuracy without the need to replace the devices.

The objectives of the project are to operationalize, deploy in operations and prepare for business the linked data e-Infrastructure that we have been developing within the PECS programme. We will conduct a pilot in-production deployment of ISMoSeDe at the Executive Agency for Exploitation and Monitoring of the Danube River after improving the functionalities of the current system with features that will allow the users to operate independently with and manage the system. Water resources management can vastly benefit from integrating earth observation data with other relevant for their monitoring data in web-based workflows. ISMoSeDe provides a cutting-edge web-based workflow that helps water resources managers, river and dam operators, higher level decision makers to better execute their duties in the critical domain of monitoring of water resources in dams and rivers by mixing earth observation, in-situ data, geospatial information and domain knowledge and enable superior interactivity multifaceted visualization, seamless extendibility, effective maintenance, optimal utilization of earth observation and in-situ data, combined with geospatial information from GIS and domain knowledge. It allows dashboard view, querying, reviewing, triggering alerts for upcoming overflows and droughts, changing the navigational conditions, predicting the power generation potential, etc. Our solution is a disruptive web-based workflow that uses a combination of AI methods that are put together to form a powerful e-Infrastructure for the benefit of water resources managers. It provides an instrument to sustainably exploit the water resources, prevent high impacts of disasters, and render the monitoring and assessment of the daily water-economic and infrastructure status optimal and efficient. While focusing on the Bulgarian segment of the Danube River for our pilot deployment, we are planning to extend the scope of coverage first to the entire Danube and secondly to any river or dam worldwide by capitalizing on the needs of water resources management worldwide and creating a business plan with a go to market strategy to go global.

The project Satellite-based economic flash estimation (Sat4Ec) is financed by EUROSTAT and supervised by the Federal Statistical Office of Germany (Destatis). Sat4Ec investigates how much information from satellite data can support early German gross domestic product (GDP) estimation at Destatis. Two indicators are envisaged: automobile productivity by monitoring production parking lots of automobile manufacturers and construction activity. For the first indicator, manufacturing parking lots of automotive production facilities are observed using the Synthetic Aperture Radar (SAR) instrument of the Sentinel-1 satellites. The main area of interest will be over central and western Europe.

The access to Earth Console is made in the frame of Proposal DETECT-B01, which is part of the Collaborative Research (CRC) 1502 of DFG (https://www.lf.uni-bonn.de/en/research/crc-detect). The main goal of DEECT-B01 is to estimate river discharge and water storage change from space using satellite altimetry. The central hypothesis of DETECT-B01 is that the new generation of space-borne altimeters, including Delay Doppler(DD), laser and bistatic SAR altimeter techniques, outperform conventional altimetry(CA) and in-situ measurements. They provide surface water levels and discharge of higher accuracy and spatial and temporal resolution thanks to the new river slope and width parameters. The better sampling will improve flood event detection and long-term evolution estimation, providing valuable further information to the overall CRC. In the first four years of its 12 years possible duration, two research questions have been addressed in the CRC:

1. How can we fully exploit the new missions to derive water level, discharge, and hydrodynamic river processes?

2. Can we separate natural variability from human water use?

Over the last decade, with SAR altimetry data, merging innovative space observations with in-situ data provides a denser and more accurate two-dimensional observational field in space and time compared to the previous two decades. This process allows better monitoring of water use’s impact and characterising climate change. River discharge and water storage change innovatively derived from the nadir and swath-altimetric measurements of river slope, height, and width will enable to validate the modelling (e.g. through budget studies) and will be used for assimilation in the IMS. A multi-sensor database will be built starting from 1993 and used in the Integrated Monitoring System (IMS) from other partners in the CRC. B01 will also monitor the exchange of water between rivers, lakes and reservoirs and the impact of natural and human disturbances, like water use. The project will contribute to the CRC’s key objectives in that it addresses the surface water compartments by improving new observation types and including them in the modelling.

The primary aim of this project is to utilize machine learning to detect reforestation and deforestation activities within the CRIMA Predio Putumayo y Andoque de Aduche REDD+ Project, a carbon sequestration project located in the Amazons within Columbia. To achieve this objective, we will construct multiple models using various sets of Earth Observation (EO) images spanning from the project’s inception to the present day. These models will then be stacked into a unified model, enhancing the overall robustness of our detection system. Our goal is to compare the outcomes of our modeling efforts with publicly available evaluations of carbon sequestration projects. This comparison will allow us to assess whether the forest carbon sequestration sites have successfully met their stated objectives of reducing deforestation and/or promoting reforestation in the designated areas.

Object detection is one of the mandatory steps in transferring imagery data into land cover information. Deep machine learning networks have shown automatic object detection capabilities and generated promising results. The patch-based Deep Neural Network (DNN) is one of the architectures designed for pixel-based object detection in aerial images.

Road extraction from remote sensing images is significant to urban planning, navigation, disaster assessment, and other applications. Although deep neural networks have shown a strong ability in road extraction, it remains challenging due to complex circumstances and factors such as occlusion.

Road extraction from remote sensing images is significant for updating geographic information systems (GIS), urban planning, navigation, and disaster assessment. In the past, the most widely used way to extract roads was through manual vision interpretation, which takes a lot of time and has a high labour cost, and the extracted results may vary due to the differences of interpreters. Automatic road extraction technology can improve the efficiency of road extraction, so it has become a hot issue in this field. This deep learning model is used to extract roads from high-resolution satellite imagery.

Road layers are useful in preparing base maps and analysis for urban planning and development, change detection, infrastructure planning, and various other applications.

Digitizing roads from imagery is a time-consuming task and is commonly done by digitizing features manually. However, deep learning models are highly capable of learning these complex semantics and can produce superior results. Furthermore, deep learning models can automate this process and reduce the time and effort required for acquiring road layers. My project is to train a model that can detect and build road networks anywhere in Egypt.

In the first stage as an early adopter user of GEP, several previously unknown landslides have been identified in the escarpments of the main faults of the Córdoba ranges, coincidentally in sectors where there is clear evidence of neotectonic activity. These landslides have been recognised by remote sensing techniques, geomorphometric analysis and field surveys, but they have not yet been characterised nor quantified in their rate of movement and speed. Results were exposed in the ARGENCON 2020 workshop, held in December 2020 in Argentina. This proposal aims to continue analysing gravitational processes in Sierras of Cordoba based on their geomorphometric parameterisation, with the estimation of its displacement obtained with DinSAR techniques. Quantifying the local relief through geomorphometric parameters has been done in combination with measures obtained after using the P-SBAS (Parallel Small BAseline Subset) algorithm through the services of the Geohazards Exploitation Platform (GEP). Displacement maps generated by this technique allowed the detection of active processes not previously registered. The sections of Sierra Grande and Sierra Chica fault scarps, which limit the San Alberto and Punilla valleys, respectively, and the Cerro Uritorco slopes, are the areas with the most significant evidence of displacement. Creeping, debris flow, collapses, and rock avalanches were recognised there. Results obtained via Early Adopter Program demonstrate that methods based on DinSAR can reveal morphologic features that otherwise could not be disclosed. In addition, it verifies that platforms based on cloud services that can process large volumes of data are beneficial for identifying and monitoring dynamic geomorphological processes and obtaining predictive information on areas with the potential to slide. The in-phase information provided by SAR images through a multitemporal analysis efficiently detects and evaluates possible new mass removal processes that are taking place or have taken place in recent years.

Several locations across the Czech Republic are known for creeping subsidence. Such subsidences are of various origin, most notably related to ongoing or former mining, drought or slope movements. These subsidences are often posing a risk to built-up areas and infrastructure and are causing property damages. However, most of these sites are not continuously monitored using any in-situ or remote sensing method. Using remote sensing is therefore of great use, in helping identify, locate and quantify processes at the studied sites. Among test sites, which will be studied using the GEP, there are case studies with in-situ reference data and test sites, where there is evidence from local residents, that actual subsidence has never been scientifically confirmed. One of the great benefits of using the GEP is the fast and easy processing of long-time series of radar data. This processing can allow to identify subsidence scenarios at each site quickly and enable us to set proper in-situ actions or evaluate the feasibility of further detailed InSAR time series processing using dedicated software. By exploiting the GEP for scientific purposes regarding geohazards it is possible to:

– Generate of time series of InSAR displacement products (FASTVEL service).

– Generate of velocities based on the optical data (Sentinel-2) (MPIC-OPT service).

Among scientific objectives are:

– Identification of surface subsidence related to mining, drought or slope movements, posing risk to infrastructure and property.

– Test FASTVEL results in comparison to commercial workstation-based InSAR processing software.

– Generate GEP services for landslide monitoring in case of densely vegetated landscape (a common type of landscape in the Czech Republic).

Agriculture is a vital sector in the West African economy, providing sustenance and income to millions of people. The timing of crop sowing is crucial in determining crop yield and quality. It is influenced by various factors such as weather conditions, soil moisture, and land preparation practices. Farmers’ practices determine the sowing date, and social constructs, such as traditions and beliefs, influence these practices. The project aims to produce country-wide maps for various phenological metrics using remote-sensed crop vegetation dynamics in West Africa. Notably, this study seeks to create multi-year sowing date estimation maps that will be valuable resources for understanding the spatial variability in sowing date strategies among different regions in West Africa. This approach will enable researchers to examine how environmental and social factors influence farmers’ sowing date decisions, leading to improved crop yield and quality and better management of West African agricultural systems. These maps will also be used as input layers in spatialized crop simulation models, contributing to the analysis of the impact of different factors, such as changing climate, genotypes, and agricultural practices, on crop productivity. As such, the study will provide valuable insights into how farmers can optimize their crop-sowing practices to achieve maximum yield. Time-series analysis of medium resolution optical remote sensing products will be performed to conduct this study. This analysis will target croplands detected from land cover/land use (LULC) products generated annually by stakeholders, such as ESA WorldCover. The project’s outcomes will be helpful for policymakers, agricultural extension workers, and farmers alike. By understanding the spatial variability in sowing date strategies among different regions in West Africa, stakeholders can tailor agricultural interventions and policies to the specific needs of different regions. By examining the impact of changing sowing dates on crop productivity, stakeholders can develop targeted strategies to enhance crop yield and quality.

This proposal intends to exploit the automated and unsupervised IREA-CNR N-SBAS processing tool integrated within the (GEP), to generate an up-to-date crustal deformation map of the country of Algeria by the mean of Sentinel-1 SAR data. The velocity maps will be generated for both ascending and descending passes so it will be possible to get the 2-D velocities (east-west and up-down) and resampled to 200 meters. The final results we will propose will be in the InSAR reference frame and ITRF.

The project, under the supervision of Prof. Jurgen Kusche, the head of APMG Institute of Geodesy and Geoinformation, University of Bonn, aims to determine the marine geoids of the West African coast using sentinel-3 data. To achieve the above aim, the following objectives will be used:

• To compute the Mean sea surface (MSS) in the West Africa region using sentinel-3, with SAR closer to the coast than before. This will aid the marine geoid in the region, where existing geoid models in West Africa are decades old.

• To compute Mean Sea Level (MSL) from the tide gauge.

• To determine an existing geoid model from the ICEGEM webpage.

• To calculate Mean Dynamic Topography (MDT) from Existing solutions based on stages 1 to 3.

• To compute Marine geoid by subtracting MDT from MSS.

Our project aims at developing a website that provides information about the impact of the Coronavirus and economic and social factors. First, starting from diverse data, we will investigate the global implications and the effects of the virus on economic and social life. After that, we will talk about rice and how it was affected by the weather conditions, investigating the Mekong River Basin.

The objective(s) of this project is/are to study the impact of the newly implemented Greenline BRt system in Karachi and its service area, along with the urban density and traffic congestion. The work also implements demographic indicators geospatially to deeply analyse the study area. The aim is to develop a resilient transport model for Karachi Pakistan considering its unique geography and circumstances. Moreover, there is a dire need to investigate the drainage channels over the satellite imagery temporally so that resilient measures may be developed for flood controls that lead to crippling congestion in the city. By examining the city’s urban landscape and its drainage channels it is possible to find a holistic solution for the chronic issues of urban sprawl and congestion in Karachi, which has been worsened by flash floods. Finally, newer models of transport analysis based on satellite imagery including modal shift will be suggested for future work.

The USeEO project ‘Development and verification of custom EO tools for resilience management in Poland’ addresses the need for resilience building by providing value-added satellite-based crisis information and establishing efficient and operational data flow lines between EO tool providers and decision-makers. It aims to develop and validate a set of customized EO-derived information products to support different stakeholders working in the resilience sector in Poland and verify the utility and benefits resulting from using these products. The customized EO-based products will be prepared based on High-Resolution Sentinel-1 and Sentinel-2 data. Also, it is planned to use Very-High-Resolution data to answer crises in which HR satellite data are not enough to fulfill the specific end-users’ needs. The solution is dedicated to the Government Centre for Security and the Regional (voivodeship) Management Centre in Rzeszów.

This research project aims to develop a robust rice identification tool designed explicitly for the Mekong Delta region in Vietnam. The primary objective is to create a new rice map for Dong Thap province and expand its coverage to encompass the entire Mekong Delta region. Accurate mapping of rice fields is essential for effective agricultural planning, resource management, and policy formulation. The current rice segmentation methods suffer from low accuracy and resolution, which hampers their reliability. This research seeks to provide precise and reliable information for decision-making in the region’s rice cultivation sector by developing an improved tool. The use of advanced remote sensing techniques, such as high-resolution satellite imagery and other geospatial data, will contribute to creating a more accurate and efficient tool. This will enable stakeholders to make informed decisions, leading to better agricultural practices, optimized resource allocation, and sustainable rice production in the Mekong Delta region.

The openEO API specification allows accessing Big Earth Observation Data cloud services using many different programming languages. Julia is an evolving language and well-suited for processing such datasets. The objective of this project is to develop a Julia client for openEO. This will give researchers access to well-established tools unavailable as native Julia packages elsewhere. This software will eliminate the need to query the server and convert the result data manually.

Moreover, results from openEO servers can be further processed in a local Julia environment, allowing fully customized workflows, including tailored visualizations. Developers writing clients for other web services in Julia can also use this project as an example. The software is open-source and can be downloaded from a public GitHub repository.

GEO Mountains (https://www.geomountains.org/) is an initiative of the Group on Earth Observations (GEO). Mountainous regions provide numerous goods and services to both highland and lowland populations globally. However, climatic and environmental changes, large-scale political and socio-economic transformations, and the unsustainable management of natural resources threaten this increasingly. Decisions on policy and investment, from the level of local governments to international agencies, must be based on knowledge that reflects both the generalities and specificities of mountainous regions. The paucity of observations from highelevation regions and associated major gaps in the understanding of mountainous systems thus represent key challenges that must be overcome. In October, GEO mountains released amajor iteration (v2) of the Inventory of In Situ Observational Infrastructure. This update includes many more researchoriented mountain observatories, operational stations, and locations where longterm monitoring is being undertaken. Looking ahead, GEO Mountains will consider providing data storage and linking for those sites that are not able to make their data available in an open repository otherwise. Also capturing extensive metadata for each site to facilitate a comprehensive, interdisciplinary “gap analysis” of in situ mountain observations (i.e. for many variables and with respect to geography, time, and elevation). The project will use the GEP services to develop improved inventories of past avalanches and landslides in remote mountain regions of the world, including the Andes, HKH, Central Asia, and East Africa.

ARTEMIS aims to develop a multi-modal service for processing satellite, terrestrial and available spatial data and the generation of products related to the quality, health and sustainable development of economic forests, with emphasis on chestnut forests. These products will be distributed through a dynamic and user-friendly online platform, which will support operations to facilitate monitoring and improvement of chestnut production and enhance actions for biodiversity protection against climate change. It is known that the Mediterranean chestnut forests in the region of Thessaly have been “degraded” despite being considered productive forests. Moreover, the long-term lack of planning for alternative crops and the insufficient policies for supporting mountain populations’ economic growth has hindered the production of chestnuts, especially in the forests of Mouzaki. Therefore, there is a need to develop modern practices and technologies that will support the continuous monitoring of natural and managed ecosystems and promote, in the long term, the growth of primary production while preserving biodiversity. The project will mainly address the forest health threats in selected areas, mainly caused by biotic factors (insects, diseases, etc.), thus resulting in gradual degradation and destruction of production. As many studies focus primarily on assessing damage driven by abiotic agents (fires, droughts) in forests, it is worth investigating and proposing solutions for the timely evaluation and management of early symptoms of decline, as well as the mitigation of further damage.

In Colombia, food production is given by two types of production, mainly conventional and organic. In organic production (without agrochemicals, certified) or agroecological (without agrochemicals, not certified), we have that its certification is challenging to access and expensive. Hence, its products and production are complex to credibility, so its sales are low. This new methodology, developed by multispectral images and which can be determined by different measurement indices, has been quite reliable for this determination. Supported scientifically and constantly determinable, they can add much value to your type of production. Therefore, applying this methodology to our network of local producers would be of great value and open up new markets. For this reason, a first approach with an experimental phase, training with the ESA in the procedure, will allow us to define the most appropriate methodology and analysis to apply to 3 organic/agroecological and three conventional crops, allowing us to extract and analyze the data. Once this experimentation is over, this tool and analysis may be available to Colombian and Latin American farmers who wish to have another organic and agroecological certification that is simpler, more accessible, and constantly monitorable.

Objectives of this project are: • Develop and validate methods for determining the stage and advancement of desertification via diffuse reflectance spectroscopy in the MIR aiming at obtaining prediction models for chemical and physical attributes in soils under intense degradation process. • Build a spectral library using the wavelengths observed in soil samples from the region, highlighting the distinction between the spectra observed in desertification area soil samples; • Understand the link between spectral attributes and chemical and physical attributes of the studied soils; • Prepare maps of the spatial variability of soil attributes, using the results obtained from analyzes carried out in the laboratory (measured values) and obtained by sensors (predicted values) in the study area. • Create land use and land cover maps using high-definition satellite imagery data provided by Sentinelhub.

The vision of the DE Africa is to provide a routine, reliable and operational service, using Earth observation to deliver decision-ready products enabling policy makers, scientists, the private sector and civil society to address social, environmental and economic changes on the continent and develop an ecosystem for innovation across sectors. The mission of the DE Africa is to process openly accessible and freely available data to produce quality products. Working closely with the AfriGEO community, DE Africa will be responsive to the information needs, challenges and priorities of the African continent. DE Africa will leverage and build on existing capacity to enable the use of Earth observations to address key challenges across the continent.

DE Africa portal: https://www.digitalearthafrica.org/

Africa has many agriculture challenges so monitoring and management was identified as high priority. Addressing these challenges requires better technology and policies to improve the management of small farms. Airbus Pleiades and SPOT have an impressive acquisition capacity that offers better earth observations of the area of interest and it is useful for monitoring of environmental practices and agri-environmental measures, which is very useful for the primary focus of the project: developing prototype crop delineation method as part of a Food and Agriculture Organization of the United Nations (FAO). The method is developed for country government users. The exact test area will likely be in Rwanda. For the small farms, higher resolution is desired.

Airbus Pleiades and SPOT high-res images were recognized as very useful for delineation of smaller crop fields.

Digital Gaia is an open intelligence and analytics platform that maximizes the environmental impact of regenerative projects and investments. Digitally­enabled, the Digital Gaia technology platform decentralizes impact assessment through a verification platform designed to enable high-integrity initiatives targeting regenerative effects in critical ecosystems. The open platform hosts a decentralized Natural Intelligence Network (ΝIΝ), which combines human expertise in ecosystem health and Artificial Intelligence to generate algorithmic impact assessments across all dimensions of natural climate solutions and associated investments. We will incorporate data layers from the farmers’ inputs, satellite imaging, remote sensing, climate modeling, and much more to create robust estimates for this project. This data aggregation into our active inference engine will result in tailored insights for the farmers, scientists, modellers and investors, ultimately increasing interoperability, transparency, and agility across the regenerative economy. The specific objective of this project is to create interactive, collaborative digital twins of 50 regenerative agriculture and agroforestry projects across Europe, Brazil, and the US. These digital twins will provide farmers, impact investors, scientists, and stakeholders with insights into these projects’ impact and actions for tangible improvement. The results will be free of charge to farmers and their nonprofit stakeholders through an interactive dashboard tracking the life of their project. These solutions scale up from the last mile of impact, where we focus on helping nature stewards and other innovators with the capacity to take action to optimize, demonstrate, and monetize their projects’ impact, creating clarity, trust and accountability for investors.

This project aims to determine the possibility of geological and lithological mapping of karst terrain using remote sensing methods, i.e., using available satellite (multispectral) images. After verifying the case of geological mapping, the geological potentiality of mineral resources would be determined. Generally, the potentiality of mineral resources in the Republic of Croatia is currently being defined based on the Basic Geological Map of former Yugoslavia SC 1: 100,000. Geological works for this map began in the late 1950s and ended in the 1980s. Mapping was performed οn worksheets SC 1:25,000, which was later reduced to 1:100,000. Individual sheets of the map were published between the 1970s and 1980s. The common feature of all the sheets of the map is that they were created in a Gauss-Κruger projection with three-stage zones, οn a Bessel ellipsoid 1841, with Greenwich as the initial meridian. Due to the above, these maps are now considered archival data.

Nowadays, it is assumed that such a principle of determining the potentiality of mineral resources is not precise enough, and the possibility of creating a new way of determining the geological potentiality of mineral resources is being explored. Α new approach would include the processing of available and commercial satellite images and other methods of remote sensing (UAV).

Several gypsum deposits have been identified within an area of 4 km2. The plan is to use these deposits as ground truth data for satellite images to examine a wider area with sizes up to 10 km2 in detail. In addition to archival materials and Sentinel-SA data, other remote sensing methods would be used to gain insight into the possibility of obtaining a geological/lithological map of large-scale 1:10,000 or a geological map of gypsum potential as a mineral raw material.

This project aims to apply DInSAR techniques with Sentinel-1 SAR images on Galeras and Chiles-Cerro Negro volcanoes in the southwest of Colombia using the SBAS technique to determine the deformation of these volcanoes in the last few years. Time-series of deformations will be compared with the GNSS data of those volcanoes. For this study project, I have already generated 86 interferograms, 86 unwrapped interferograms and 86 displacement maps with the ESA software SNAP. I want to complement the information I have with another technique like SBAS. This technique was proposed by Berardino and others in the year 2002, and it helps to give more accuracy to the deformation info and reduce problems of decorrelation and perpendicular baseline issues distance between the satellite images.

The project’s main objective is to build a nationwide dataset of slow-moving landslide deformation as the backbone of a national Early Warning System for Slow Moving Landslides. In many temperate countries, like Romania, the majority of active landslides are slowly moving, and the reactivations of inactive landslides are pretty frequent. Certain thresholds of precipitation represent the triggering. Therefore, building a Landslide Early Warning System (LEWS) requires at least a landslide inventory or a landslide hazard model besides the real-time rainfall data. We propose to use temporal landslide deformation from radar data obtained using DinSAR techniques and for training an AI model to predict landslide reactivation based on the trend of deformation and rainfall. Such a dataset and model can be used to implement the first LEWS for Romania, and the tested methodology could also be used for other areas.

The use of numerical weather prediction (NWP) models to drive snow cover models has recently become more and more investigated, thanks to the improved computer performances allowing to increase the spatial resolution and decrease the computational time. But still, some processes cannot be explicitly treated in the models because they are caused by phenomena happening at a fine scale. Thus the simulation of the snow cover is affected by the uncertainties of both atmospheric and snow cover models. Furthermore, the errors may increase if the simulations cover long periods; thus, the assimilation of observations in the snow models can help to reduce the simulation biases and make models converge to the observations. However, in situ observations of the snow conditions are usually done with automatic weather stations (AWS) and manual measurements. Thus they are sparse and insufficient to force a spatially distributed snow cover model. Instead, satellite data cover large areas at different resolutions and are the perfect candidates to correct snow cover models using gridded data from coarse to satisfactory resolutions. Optical data, for example, can give information on snow cover extent and albedo. At the same time, with DinSAR techniques, it is possible to estimate the snow height variation between different dates or even the snowpack liquid water content. Our project aims to develop an assimilation algorithm that will improve the snow cover model simulation quality using high resolution remote sensing data, to provide helpful information for avalanche warning services, hydrology services and even climates studies.

Today, we live in an age of frequent disasters, such as the Türkiye-Syria earthquake, and many other disasters that occur every year. However, the “memories of disasters” are overwritten and forgotten with time. To make the most of these “memories of disasters” and the people’s experiences to the next generation, it is necessary to share and pass on the memories of disaster victims to society. However, such precious memories of individuals will eventually be lost due to aging and death. To share “individual memories” and preserve them as “social memories”, it is necessary to create a system to preserve and record the memories that have happened and will occur again in the future. In this sense, “digital archives” are important as a foundation for preserving and sharing such memories and passing them on to the future. The Hidenori Watanave Laboratory has been developing and operating a “Digital Archives Series”. However, they have been developed and operated mainly with annual research funds, and there are concerns about their sustainability. In addition, we would like to incorporate advanced technologies such as virtual reality and artificial intelligence into these archives with the cooperation of many people to develop more user-friendly archiving systems. We have released many web applications. And it’s getting a lot of attention in the media in many countries.

IMPACT/REACH Ukraine is an international humanitarian NGO which provides information and mapping support for other NGOs, local authorities, and communities in conflict-related areas. Specifically, our team has produced several area-based risk assessment products for these areas to provide insights to reduce disaster risk there.

Currently we are running a project related to land subsidence risks in the Toretsk-Yenakievo area with a coal mining network. This area is located within the grey zone between government-controlled and non-government-controlled areas and thus is directly impacted by the ongoing situation in Eastern Ukraine. Only three coal mines are still operating, while the others continuously flood without adequate pumping and wastewater management. This situation is critical as up to 30 spoil tips of coal mines are located within 500 m distance to the residence areas, thus causing a significant damage risk to the buildings and infrastructure due to the land subsidence in the Toretsk area. We suggest using the SBAS algorithm using the Sentinel-1A platform with 94 relative orbits and descending orientation SLC images (IW mode) based on the images acquired from 2016 to 2019 (70-100 images) with a temporal baseline of 12 days. Those images fully encompass our study area. We suggest obtaining reliable raster products of land subsidence hotspots in the Toretsk area to address the most displacing locations associated with settlements and built-up infrastructure. This analysis is intended to be an essential product for justification of main areas where our partner humanitarian organization ACTED will collect soil and water samples and plan the priority activities for water supply and pumping networks.

This project investigates the direct and indirect deforestation due to oil palm expansion in the Peruvian Amazon. Direct deforestation associated with oil palm has been the focus of scientific literature, but the indirect deforestation aspect has not been studied. In this study, indirect deforestation is either:

a) forest loss intended for oil palm but is not realised,

b) adjacent deforestation for non-oil palm use that would not occur if oil palm was absent.

Examples of alternative land uses are cacao (to diversify income), worker housing or land prospecting. The majority of oil palm deforestation literature concerns the use of remote sensing data to detect large oil palm plantations, due to the limited spatial resolution of free satellite data e.g. Landsat, Sentinel-2. Large plantations can only be identified at these coarse resolutions due to the easily identified planting convention of rectangular grids with access roads. The oil palm canopy is not spectrally or visually different from the intact forest at these resolutions, so discriminating between the two is impossible. Oil palm cultivation is also practised on smaller parcels of land, often in unconventional patterns, and the agents of these are referred to as smallholders. The research questions are:

a) How much deforestation does smallholder oil palm contribute to the deforestation of the Peruvian Amazon?

b) Is indirect deforestation greater closer to oil palm? If so, this is known as a distance decay relationship – the further from the source (in this case, oil palm), the less the effect (deforestation) and vice versa.

c) What is the temporal relationship between indirect deforestation and oil palm?

Indirect deforestation likely exhibits a lagged response to oil palm expansion. Preliminary testing has shown that the distance decay relationship is restricted to < 1 km, as distance increases beyond 1 km there is interference from other deforestation drivers. Very high-resolution 2019 and 2015 PeruSat 0.7m imagery is freely available for viewing through Google Earth Pro for some of the project regions in North-West Ucayali, Peru. We have used this imagery to validate the land cover/land use of deforestation reported by the Hansen et al., 2001 – 2018 global forest loss dataset. However, much of the remaining imagery is not up to date or cloud-covered, preventing a full understanding of how indirect deforestation and oil palm plantations relate in this region.

The main objective of my work is to assess different domain adaptation techniques regarding geographical domain shifts in land cover classification. First, different deep-learning segmentation models will be trained on Sentinel-2 data with CORINE land cover maps as reference data. The Sentinel-2 input will probably be multi-spectral (but not multi-temporal), and the CLC map from 2018. The initial dataset, called the source domain, will only contain samples from a specific geographic region (like Germany or a federal state of Germany). After an architecture (probably U-Net) which shows acceptable performance on the source dataset is found, the model will be applied to different geographic regions (the target data set) in Europe. Due to the domain shift across different areas, the model’s performance is expected to drop. This domain shift arises from different class distributions and other spectral and spatial properties of the classes. Then, different domain adaptation techniques will be applied and compared to mitigate the performance decrease. The key idea behind domain adaptation is that there are only labels for the source domain (e.g. Germany) but not for the target domain (e.g. Greece). But this technique will still be possible to improve the performance on the target domain. Especially in remote sensing, where labels are rare and expensive to acquire, domain adaptation can help achieve valuable results even with fewer labels. So far, research on domain adaptation in remote sensing has focused mostly on high-resolution aerial imagery (ISPRS Potsdam and Vaihingen) with 3-channel inputs. Only a few works deal with medium-resolution satellite imagery. Still, in these cases, they primarily classify pixels based on their spectral and temporal properties without considering spatial information (the surrounding pixels with fully convolutional networks).

While drainage benefits farmers it carries adverse environmental impacts related to a.o. leaching of nitrogen, phosphorous, and agrochemicals to the aquatic environment, and CO2 and N2O emissions to the atmosphere. The goal is to construct a national map of agricultural areas that are drained using artificial subsurface drained systems in Denmark. This will be done with a UNet using multitemporal imagery from specific years and sensors. There have been proposed multiple methods for the detection of drained agricultural areas, but a high degree of uncertainty still exists in the derived output maps. This is a novel method using multitemporal image acquisition.

The pilot aims to develop a pan-European scale drought impact monitoring platform using the new CLMS service High-Resolution Vegetation Phenology and Productivity (HR-VPP) derived from Sentinel 2 images.

DEMs (including DSMs and DTMs) are critical in land-use planning, infrastructural project management, soil science, hydrology and flow-direction studies. Because DSMs characterize the bare Earth and its above-ground features, their use is widely applied in fields such as urban planning (i.e., in investigating how a proposed building would affect the views of residents and businesses, power line corridor inspections and aviation planning). DEMS and DSMs are powerful and efficient tools for applications in various sectors. There are different ways to generate DEMs, including satellite data processing. In this project, we want to apply deep learning-based algorithms to make high-quality digital surface models. There are several proposed added values if one can implement such a workflow.

One of the advantages will be that the amount of manual work will decrease significantly. This is important for processing steps like DTM and BHM (Building Height Model) generation. Previously, if someone wanted to have a high quality BHM, it would need manual work to filter the DSM and then finally make BHM. The main problem here is that the derived satellite-based DSM doesn’t include details compared to UAV-based DSMs. So the expert operator must manually examine the DSM and detect where the buildings are. Then, after the expert detects the feature is a building, he can filter that. As it is clear, the process is time-consuming. Now we want to use very efficient matching algorithms to provide a better initial point and then apply deep learning algorithms.

The objective(s) of this project is to maintain the platform developed under the Digital Twin Earth (DTE) Hydrology Evolution project. Specifically, the DTE Hydrology platform is currently used for training and educational activities under: (1) ESA courses (2) secondary school education (3) international workshops.

Our main technical and programmatic objective is to prototype an Information Factory (IF) that will enable data owners/administrators, analytics companies/model providers (this includes scientists) and end-users to host, find and ingest EO/spatial data to get them parsed into analytics pipelines/models and make them (and their derived products) available for direct integration and consumption in operational workflows at scale. The system we propose will enable people who are new to the ecosystem, or specialised in other aspects of data analytics, to use EO resources and automatically adhere to industry standards such as OpenEO and OGC protocols.

Earth Observation Advanced Science Tools for Sea Level Extreme Events (EOatSEE) is a project funded by ESA and proposed by a consortium of institutions and companies internationally recognized for their work in the Marine, Coastal, and Earth Observation topics. It aims to provide an advanced reconstruction of the relevant processes included in extreme sea level (ESL) events and their related coastal hazards by taking advantage of the novel capabilities and synergies offered by the latest advances in EO technology. Therefore, the solid scientific knowledge arising from EOatSEE shall enhance the fundamental scientific understanding and predictive capacity of such events and our potential better to assess the related risk and vulnerability of coastal zones.

CentraleSupélec – a French high school of engineering – organizes a course on Satellite Earth Observation dedicated to around 110 first year students, from the 22nd November to the end of January. This course is an introduction to optical and SAR remote sensing. It is based on the use and processing of ESA’s Sentinel images. The support of EOCARE is requested to allow the students to carry out mini-projects on 3 topics at the end of the course.

The project aims at providing a general background on the Sentinel remote sensing systems for Earth Observation from space-borne platforms and on data processing techniques. The EODA Sentinel Lab course provides an overview of the most critical applications and bio-geophysical parameters which can be retrieved. By proposing practical computer exercises, the essential techniques for data processing and product generation are analyzed with an overview of the main Sentinel satellite missions and the products they provide to the final user.

This project is part of a master’s Thesis in International Media and Computing at HTW Berlin University of Applied Sciences. The thesis’ scope is to explore the applicability of satellite data in data-driven journalism. The attempt is to reproduce prior scientific work using Copernicus data with a focus on topics of public interest and current relevance by analysing previous use of earth observation data in journalistic publications. The primary focus is the German federal states Berlin and Brandenburg, with the option of extending over the entire region of Europe.

The action focuses on integrating Earth Observation (EO) data from the European Space Agency (ESA) Copernicus Programme into the statistical production process for further analyses and projects within the fields of agriculture, forestry and environment. Critical aspects of the action are:

• the preparation and provision of required EO data and infrastructure;

• the methodological development for land cover classification using the EO data to gain spatially explicit data on different categories, focused on the needs of the statistical production process – namely woodland, grassland and cropland and the evaluation of a possible higher granularity within those classes;

• the dissemination of results and data and their further use for evaluating these integrations into statistical products and applications.

The EO4ALPS-snow regional initiative is a currently ongoing ESA-funded EXPRO+ project led by MobyGIS (IT), in collaboration with EURAC (IT) and Sinergise (SI). The project’s main objective is to provide a monitoring service of high-resolution snow variables in quasi-real time for improved management of available water resources at the Alpine scale. In particular, the project focuses on snow water equivalent (SWE), snow depth (SD) and fresh snow (HN), which are key products for policymakers, industry leaders and other private institutions in the Alps to manage the water resource. Although the most common method to monitor SWE, SD and HN is to organise measurement campaigns, this approach is costly and can only deliver information in a discrete number of locations. In response to the drawbacks of in-situ observations, physically based snow models were developed, with the advantage of calculating snow evolution by transforming meteorological data into snow accumulation or melting according to the mass and energy balance in the snowpack. However, models suffer from poor spatial accuracy and sometimes large uncertainties due to microclimatic disturbances in mountainous areas. Earth observation products are a promising alternative, as they offer a synoptic view of mountainous regions with high temporal and spatial resolutions. Nevertheless, current approaches to SWE estimation based on EO data only are limited by the low technological maturity and calibration issues.

The approach of the EO4ALPS snow project is based on a hybrid technology that merges the advantages of using a snow physical model with mid-resolution (10-20 meters) high-frequency (<5-10 days) EO snow products. The GEOtop snow model, which provides a dynamical snow depth mapping service with a resolution of 250m over the entire Alps, will be used upstream of the hydrological modelling chain. The model outputs will be corrected using a data assimilation scheme based on high spatial-temporal snow cover maps derived from open-access satellite data (optical and SAR). In addition, the corrected model outputs will be validated using an extensive network of ground stations data and UAV measurements. Downstream, the hydrological modelling process will calculate snow evolution and the final variables of interest by solving mass and energy balance on the snow based on meteorological data inputs (observations or forecasts).

The aforementioned approach, based on Python-based tools, is designed to run in a systematic manner of a cloud-based infrastructure. The project partners intend to leverage the services offered by the Euro Data Cube platform (EDC) in terms of access to satellite data, cloud-based processing, and dissemination of results. Firstly, the processing of the EO products to generate the snow cover maps will exploit Sentinel Hub services integrated into EDC. The time series of images provided by the optical and SAR sensors will be queried as Xcube datasets. Secondly, the development of the hydrological modelling workflow will be performed in the EOxHub computing environment. Finally, the results will be disseminated using the EDC marketplace and Bring-your-own-algorithm (BYOA) interfaces. The results will be made available to different categories of users, such as public agencies, hydropower companies or winter sports operators through a dedicated web application deployed within EDC’s marketplace. The implementation will also allow direct access to the data for advanced users via EDC API services (e.g. OGC).

The project will develop and showcase innovative EO approaches for producing indicators on the sustainable management of natural, semi-natural and planted forests, addressing the changes in forest extent and conditions for use in national and global forest assessment. The project will contribute to the international efforts to develop, validate, showcase and promote innovative EO approaches and methods for the evaluation and monitoring of sustainable forest management practices concerning SDG Target 15.2 to promote the implementation of sustainable management of all types of forests, halt deforestation, restore degraded forests and substantially increase afforestation and reforestation globally. The primary objective of the project is to develop, demonstrate, validate and showcase advanced EO solutions for the production of novel aggregated indicators/metrics on the sustainable management of natural, semi-natural and planted forests, which can be used in national and global forest assessment to monitor progress towards sustainable forest management that maintains and enhances the economic, social and environmental values of forests. The project will be conducted from the beginning until completion, with the principal objective to prepare for a transfer of the project outputs into SDG processes and systems.

The ESA Earth Observation for Sustainable Development Lab (EO4SD Lab) project’s goal is to procure an Earth Observation (EO) processing and e-collaboration environment (the Exploitation Platform) dedicated to Development Assistance. The primary objective is to help the Sustainable Development community make better use of satellite capabilities to improve the delivery of projects on the ground. The Exploitation Platform is based on online processing and provides a new solution for using satellite imagery complementary to conventional service provision methods. End users can connect to the EP to retrieve EO based information products. In addition, expert users can directly generate products on the EP and integrate and share their service chain. The project’s technical activities will initially focus on designing and deploying the pre-operational Exploitation Platform, a cloud-based portal enabling users to find and use EO-derived information, products, and services relevant to their needs. This portal will follow the concept of the Thematic Exploitation Platforms (TEPs) in that it brings together large EO data archives and processing and analysis capabilities within a cloud environment – hence removing the computing or technical barrier regarding the user’s systems and infrastructure. After the initial platform release, and in parallel with functional improvements, activities will focus on ensuring the Exploitation Platform can showcase the potential of EO through the execution of several service pilots – these will be individual projects run on the platform that create information or product that can help meet the specific needs of engaged end users.

The ESA Earth Observation for Sustainable Development Lab (EO4SD Lab) project’s goal is to procure an Earth Observation (EO) processing and e-collaboration environment (the Exploitation Platform) dedicated to Development Assistance. The primary objective is to help the Sustainable Development community make better use of satellite capabilities to improve the delivery of projects on the ground. The Exploitation Platform is based on online processing and provides a new solution for using satellite imagery complementary to conventional service provision methods. End users can connect to the EP to retrieve EO based information products. In addition, expert users can directly generate products on the EP and integrate and share their service chain. The project’s technical activities will initially focus on designing and deploying the pre-operational Exploitation Platform, a cloud-based portal enabling users to find and use EO-derived information, products, and services relevant to their needs. This portal will follow the concept of the Thematic Exploitation Platforms (TEPs) in that it brings together large EO data archives and processing and analysis capabilities within a cloud environment – hence removing the computing or technical barrier regarding the user’s systems and infrastructure. After the initial platform release, and in parallel with functional improvements, activities will focus on ensuring the Exploitation Platform can showcase the potential of EO through the execution of several service pilots – these will be individual projects run on the platform that create information or product that can help meet the specific needs of engaged end users.

A consortium led by KSAT and including Kongsberg Defence & Aerospace AS, T-Systems and Geocento got the contract and has since early 2020 developed the EOPORT platform that can take NRT EO data streams into an end-to-end processing system, get a dynamic set of processing steps done to the data, and deliver results in near real-time (NRT) to customers. This system is built and run on common cloud platform technologies that make internet scale designs possible. Platform customers shall be able to set up workflows to pick inputs, algorithms, and outputs to run as a service. The project’s first phase has been finished, and the consortium has entered into an extension phase with objectives to involve satellite owners, ground station operators, knowledge and methodology providers and service providers. This application aims to fund sufficient cloud infrastructure resources to cover the extension phase of the project.

The main objective is the development and demonstration of EO platform capabilities on a regional scale, which can respond to specific needs for: • Provision of cloud computing-based solutions and resources • Data processing of large amounts of EO data • Fusion and integration of multiple sources of information and products, from different satellite products to in-situ and ancillary information • Delivery to users (advanced visualization tools, products dissemination workflows, integration of results into users system).

Artificial Intelligence (AI) is the transformational technology of our era. Earth Observation (EO) will significantly benefit, as in other areas, from its application by lowering the cost of adoption and accelerating market uptake. The Earth Observation Training Data Lab (EOTDL) aims to develop open-source tools to create, curate, analyze and use AI-ready EO datasets. A European cloud-based repository of datasets and AI models will be created, maintained and improved. Training capabilities will also enable researchers, engineers, and non-expert users alike to efficiently train AI models in the cloud with the available datasets and keep track of state of the art. Many areas will benefit from this platform: having a repository of AI-ready EO datasets will strengthen industry capabilities for exploiting EO data as a whole and help accelerate EO market penetration. Furthermore, to enable Digital Twin Earth simulations, it is needed that quality datasets exist for researchers and engineers to use and build quality models and applications.

Space Agencies and other international organisations across the globe started promoting and are supporting FAIR and Open Science through dedicated programmes. ESA and the European Commission, have a long standing commitment to Open Science for example with the free and open provision of Earth Observation data from its Earth Explorer science missions and from the Copernicus Programme Sentinel missions.However, the Open Science commitment by ESA goes much beyond Open Data as ESA’s vision of Open Science shows which includes:Free, open, and linked data, algorithms, workflows, code, and documentationFully reproducible across platforms like cloudsLong-term free and open availability of researchTo achieve this vision the scientific community has to adhere to the same common and compatible practices when writing and documenting code, Request ID

The ECHOES Operation seeks to address cross-border challenges on the coastal bird habitats of the Irish Sea due to the effects of climate change that will impact our society, our economy and our shared ecosystems. ECHOES will promote climate change adaptation, risk prevention and management by providing tools for understanding climate change and potential impacts at site and regional levels. An important aspect of the operation will be engaging with local stakeholders in both Ireland and Wales, those tasked with managing or monitoring these coastal habitats and associated bird populations, as well as those stakeholders who live within and/or enjoy the coastal environment. Raising the awareness amongst stakeholders of climate change impacts and how we can monitor, manage and adapt to these impacts is our overarching priority. To increase capacity and knowledge of climate change adaptation for the Irish Sea and coastal communities. ECHOES Goals can be summarized in:

• To promote climate change awareness, adaptation, risk prevention and management and in doing so, to stimulate and encourage environmental citizenship;

• Increase the evidence base for the protection of these coastal areas and the decision-making and strategies required to manage them effectively for future generations;

• To increase knowledge of climate change adaptation for the Irish Sea and coastal communities based on lessons learned through a detailed study of Greenland White-fronted geese and Curlew;

• To provide an online platform and tools to assist policy-makers, managers and users of these coastal environments to better plan for, adapt to and manage the potential impacts of climate change;

• To achieve the result indicator of increasing levels of knowledge of adaptation to climate change amongst communities and stakeholders in the Irish Sea coastlines.

The primary outcome of this project will be a set of maps produced for farmers that highlight areas they can introduce sustainable interventions that improve their water management.

Ecolora is on a mission to help farmers unlock the most resilient version of their land. Our automated analysis informs farmers of sustainable interventions suitable for their land, such as reconnecting floodplains or creating wetlands.

Across the EU and the UK, for many farmers is critical to manage water and improve flood resilience. Flooding and poor water management can bankrupt farms. For many farmers, this data is out of reach or too expensive.

Answers to questions such as “How will my flood resilience improve if I convert this section of grassland to woodland?” or “A portion of my wheat crop gets flooded every year. What would be a better use of that land, and are there any grants that will offset my loss in yield?” cannot be easily answered by existing tools. While there are some fantastic hydrological models, they are largely not in the hands of farmers.

This project aims to build a platform that farmers and agronomists can use to investigate how their land has responded to past events.

The platform will derive actionable insights, and data farmers can use to develop a resilient farm strategy moving forward.

For example, a user on the Ecolora platform can look at the areas on their land that have been inundated in the past year. Ecolora recommends spatially explicit interventions such as establishing floodplain woodland or upstream leaky dams for those areas.

The maps from our analysis will be available to farmers on the Ecolora platform. The maps will be rendered in Mapbox with the option for farmers to export the results in GeoTIFF and png format.

Farmers with this data can make better-informed decisions when managing their water cycle, leading to better food security and more functional ecosystems.

Currently, our analysis is limited by the data we have available. We use Sentinel-1 radar data; however, our research can significantly improve by incorporating NDVI from Sentinel-2, PlanetScope’s frequent real color imagery, and Pleiades’ high-resolution images. Equipped with these datasets, we can unlock more advanced recommendations and enable farmers to work together on improving the water cycle across the landscape.

The primary objective of this project is to develop a generative model that predicts future satellite images based on historical satellite data and weather conditions. This model aims to fill the current gap in agricultural monitoring and modeling by providing realistic forecasts of satellite imagery under various weather scenarios. The specific objectives include:

– Data Integration and Processing: Collect and preprocess historical satellite images and corresponding climate data. Ensure data quality and alignment for accurate model training.

– Model Development: Develop a generative model capable of producing high-fidelity satellite images. Train the model using advanced machine learning techniques, leveraging both satellite and weather data.

Agricompas is developing a data analytics platform in an IPP (International Partnership Program) project funded by the UK Space Agency. EcoProMIS or Ecological Production Management Information System aims to provide all stakeholders involved in rice production with valuable insights in farmer and crop performance. Information is provided free to farmers (who are sharing in-situ data) to access information on crop management, soil and environmental conditions during the crop production cycle to improve decision making. Paid Analytics as a Service is provided to various stakeholders. A matchmaking platform will nurture stakeholder relations with safe and sound information of technical, economic, social and environmental processes. Farmers can place product and service requests with providers that can develop and tailor their offerings based on better farmer and field information.

EcoProMIS uses Earth Observation technology, especially from Sentinel satellites, to monitor maximal 500,000 hectares from up to 16,000 Colombian rice farmers in the four main rice production regions. Initial results of the project have included significant advances with the usage of Sentinel-2 imagery to derive various products, which monitor the situations on farms, and lead to direct knowledge which can be used to support decision making on the fields. The products derived from the Sentinel-2 imagery are also being used as inputs to crop models, allowing for predictions of important insights such as crop yields. We apply a two-way verification of crop performance. Bottom up with parameter data feeding into crop models and top down with satellite imaging. The two methods create a digital twin that with AI and machine learning leads to improved algorithms requiring less data while optimising crop monitoring and evaluation accuracy.

The objectives of this project are to calculate correction parameters for relative georeferencing error in ECOSTRESS imagery, and to develop an algorithm for automated improvement of absolute georeferencing accuracy of ECOSTRESS imagery.

With nearly 60% of the world’s total population, Asia is the world’s epicentre of economic growth, socio-economic change (e.g. urbanization) and increasing exposure to climate change (e.g. rising sea levels). These dynamics are particularly pronounced in major coastal and deltaic urban agglomerations. Against this backdrop, the region’s exposure to flood risk is poised to increase rapidly over the coming decades. Focusing on South-East and South Asia countries with middle-low incomes, over the past two decades, Myanmar, Lao PDR and Cambodia have suffered from flooding on multiple occasions. The eDrift (Disaster RIsk Financing and Transfer) Project, financed by ESA and led by CIMA Research Foundation (IT), enables easy and timely access to various services and products guaranteeing high computing capability and direct access to the EO datasets of the Sentinel constellation. Services cover several key areas of interest in the insurance market and of Countries that would like to transfer their sovereign risk. One of the stakeholders of eDRIFT is the World Bank Disaster Risk Financing & Insurance Group, with the SEADRIF program. SEADRIF is a regional platform that provides participating nations with advisory and financial services to increase preparedness, resilience and cooperation in response to climate and disaster risks. By increasing pre-disaster planning and post-disaster relief and reconstruction funding, SEADRIF protects people and their livelihoods. It also contributes to ongoing economic development and poverty reduction. In this context, a computational campaign is needed. eDRIFT services are hosted on the WASDI platform, that is running on the ONDA DIAS. The actual computational node is tailored to the execution of the automatic near real-time flood monitoring chain for the three countries of interest (Myanmar, Laos, Cambodia). The project aims also to realize a historical archive of floods for each country. To obtain this, the chain needs to be applied to all the available sentinel catalogues for each country. A dedicated computational node is the best option to achieve this goal and, also, to test the capability of the WASDI platform to scale up with new computational nodes.

The e-Drift (Disaster RIsk Financing and Transfer) Project, financed by ESA and led by CIMA Research Foundation (IT), enables an easy and timely access to various services and products guaranteeing high computing capability and direct access to the EO datasets of the Sentinel constellation. Services cover several key areas of interest of the insurance market and of Countries that would like to transfer their sovereign risk. One of the stakeholders of eDRIFT is the World Bank Disaster Risk Financing & Insurance Group, with the SEADRIF program. Using eDRIFT services a fully automatic flooded area detection service has been implemented and is now in place for Myanmar, Laos and Cambodia. The project aims also to realize an historical archive of floods for each involved country. To obtain this, the chain needs to be applied to all the available sentinel catalogue for each country. This archive allows the implementation of the so-called Flood Frequency Map: an historical statistical layer of the probability to be flooded for each pixel. The eDRIFT project has been extended with a CCN, that added a new Area of Interest for the flood Mapping (Indonesia) under the interest of the Asian Development Bank. During the regular project a NoR proposal has been submitted and approved to compute the flood Archive for Myanmar, Laos and Cambodia. During this computing campaign, many issues arose with the processing provider about the access to the S1 GRD images in the LTA: the time to retrieve a single S1 image grew from 20 min up to 2h making the goal of the project not feasible. It was only possible to finish the Myanmar archive, while Cambodia and Laos (and now Indonesia) are missing. In the meanwhile, other providers have been tested by the Consortium and the relative Data Providers have been added to WASDI to interface the different archives. EODC and CREODIAS demonstrated to be a better choice for the project requirements because there is no Long-Term Archive for the needed S1 GRD Images. Both providers have been tested with success using a dedicated WASDI computational node. The scope of this proposal is to compute the flood archives and the flood frequency maps of Laos, Cambodia and Indonesia.

The e-Drift (Disaster RIsk Financing and Transfer) Project, financed by ESA and led by CIMA Research Foundation (IT), enables an easy and timely access to various services and products guaranteeing high computing capability and direct access to the EO datasets of the Sentinel constellation. Services cover several key areas of interest of the insurance market and of Countries that would like to transfer their sovereign risk. The eDRIFT project has been extended with a CCN. Among the others, an activity of the CCN is about an automatic service to generate S2 Optical Indexes for Bolivia: CIMA Foundation has a strong background of collaboration projects in South America. One of these projects, funded by FAO, is called “Technical assistance programme for strengthening coordination and joint management of risk and increase resilience in Bolivia”. One of the main goals of the project is the implementation of a forest fire forecast and monitoring system at the national scale, with the integration of relevant tools and services in the myDewetra (www.mydewetra.world) application that is used in Bolivia as an Early Warning System platform. In this context a new service to use Sentinel 2 standard indexes and band combinations has been experimented as an expeditious way to detect on-going fires and to evaluate the status of the vegetation. This experimental activity has been considered an added value by the Bolivian Civil Protection that aims to test these data in their Early Warning System. The original context of the eDRIFT project is related to floods but must be considered that it has also the potential to create new services for the Insurance market linked to other natural hazards. This activity is considered an opportunity to enrich the Virtual Platform with other operational services that have already demonstrated to be appealing and may arise more interest and contacts with the insurance market. The scope of this proposal is to request the computational resources needed to compute to implement and test the pre-operative S2 Indexes service for the Bolivian Civil Protection and to create an historical archive of data for the same Area Of Interest.

The project consists of disseminating Copernicus values with data from Sentinel-2, Sentinel-1 and Sentinel-3. Spain is one of the countries in the Mediterranean basin where more forest fires occur, being one of the great problems of our forests. Our Public Educational Center trains future professionals in the extinction of forest fires. The project consists fundamentally in carrying out analyzes of forest fires that occur during the year, especially those that have an area greater than 500 hectares. The work will be published on social networks, specifically on Twitter, in the profile of @eforestal, and published on the website that I share with the students of the educational center: http://almazcara.forestry.es

Here you can see a sample of our publications this year using Sentinel-2 images for analysis of wildfires: https://e.forestry.es/GIF2021

The declared aim of the new “Vienna Geo Space Hub” innovation laboratory based in the Austrian capital is to fulfil a networking, communication and multiplication function within the nexus of geodata and satellite data and their innovative application for a green urban transformation. The innovation lab serves as an experimental space in which users are networked with solution providers and experts, innovative ideas are bundled, and creative ideas are developed into sustainable, data-based solutions. The innovation lab is intended to occupy a previously unoccupied field by offering added value for its users and customers. Building on intensive networking and communication work, the innovation lab offers a platform for project development through to the market launch of ideas. The main aim is to involve stakeholders from business, science, administration and civil society in the innovation process and in experimental spaces to facilitate new collaborations. It is therefore primarily about a research infrastructure for many stakeholders, such as research institutions or NGOs, who will find the solutions of tomorrow in open innovation with urban experts and infrastructure operators. In the future real-world laboratory, they will investigate the actual added value of AI-supported analyses of various data sets for a climate-neutral city in the coming years. On the one hand, the collective databases of multiple stakeholders are published for third-party users and thus help directly and indirectly with a transformation towards climate-neutral cities and urban policies. The form of the published data depends on the number of different projects and their specific outputs.

Within the Zambezi Basin, the Lunsemfwa River Catchment (12 620.17 km2) was chosen as a small-scale pilot area for the water-energy-food nexus analysis. Agricultural production is increased mainly through a transformation of land cover and land use to agriculture and intensifying use of inputs such as fertilizers and pesticides. With an increase in crop production, resulting impacts include nutrient and pesticide pollution in the environment. The Upper Lunsemfwa Catchment is of particular interest as it is a catchment in transition due to industrialization and expanding agriculture. Although agricultural activities in the form of crop cultivation have been increasing, the geographic extent of the expansion is not known. The main aim of the research is to evaluate effects of agricultural expansion and practices on water quality of the Upper Lunsemfwa Catchment. Specifically, the study seeks to determine the extent of agricultural expansion in the Upper Lunsemfwa Catchment from the year 2008 to 2020. Knowledge of the extent of agriculture in the Upper Lunsemfwa Catchment will help define the management of agricultural expansion in the catchment. In order to map agricultural expansion in the Upper Lunsemfwa Catchment, remotely sensed images (Sentinel II complemented with Landsat 8) are used for the spatial stratification of the land use and land cover and more importantly cropping domain. The Sen2- Agri system is used in this study. In situ data were collected through dedicated field surveys conducted in March 2019 and through personal interviews conducted with cooperating farmers with the aid of a closed-ended questionnaire. Information collected included crops grown, size of farms, size of cultivated portions, amount and rate of nutrient and pesticide applications. Deliverables for this investigation include general land cover maps, cultivated crop type maps for the region and maps defining agricultural practices in the area. These products are delivered in WGS84, the nationally accepted Coordinate Referencing System. The general land cover maps provide information on the different land covers present in the region of interest, including agriculture. The agricultural land will be further investigated to discriminate crop types and thereby indicate the status of crop diversification. The agricultural practices product aims at showing both nutrient and pesticide application on the identified croplands.

Natural vegetation in Southern Africa, including fynbos and grasslands, needs to go through natural fire cycles to promote regrowth.

Fynbos plants, such as proteas, need fire to release seeds and reproduce. In mature fynbos plants, fires stimulate them to release their seeds which then germinate. For example, when a protea burns, its seeds are released from what is left of the flower heads and begin germinating in cooler weather. Fire is a natural part of the grassland ecosystem and helps maintain its health and vigour. It warms up the soil and reduces the leaf litter that accumulates yearly, allowing sunlight to penetrate.

Fire, sometimes in combination with cattle grazing, is used to control trees, woody shrubs and invasive species and keep grasslands healthy. After a fire, grazing animals are attracted to the lush regrowth of grass and concentrate their grazing in that burned area. As new areas are burned, grazers shift to the most recently burned area, allowing previously burned areas to recover.

Unplanned or poorly-timed fires, however, can be detrimental, affecting natural habitats, damaging ecosystem functioning, endangering life and destroying property.

This study paper aims to assess how often this natural vegetation across the different biomes needs to burn for regrowth and at what point it becomes detrimental to the vegetation. With the results, we aim to release a paper showing what climate benefits and disadvantages fire can have in managing these biomes.

Objectives. The main aim of the research project is to evaluate effects of agricultural expansion and practices on water quality of the Upper Lunsemfwa Catchment. Specifically, for the NOR, the research seeks to determine the extent of agricultural expansion in the Upper Lunsemfwa Catchment from the year 2015 to 2020. The envisaged output of the project is to produce detailed mapping of the area of interest in terms of extent of cultivated area, specific crops and their intensity including:

• Production of the general land cover and land use maps of the;

• Production of the spatial extent of the agricultural domain i.e. annual binary crop/non-crop maps; and

• Production of maps of crop inventories of what, where and when crops are grown.

The format of the products envisaged include DIMAP format including GeoTIFF raster images, UTM – UPS/WGS 84 Projection, XML file meta data. Statistics of the to be classified crop areas will further be generated to quantify area coverage for each identified crop. The results of the project will be available to beneficiaries via peer reviewed open access scientific publications.

This request for NoR is an extension to the initial sponsorship that was given for Project ID 60792 for the period October 2020-February 2021. The extension is being requested to enable usage of the Sen-4CAP mapper that has the potential to map grassland and permanent crops which are a significant feature of the

area of interest. In addition, the ability to generate shapefiles documenting crop types observed and their associated attributes would add value to the product considering the end result desired i.e., relate crop type and fertilizer use to water of adjacent rivers and streams in the area of interest. Monitoring of agricultural practices i.e., crop planting and harvesting/clearing would aid in determination of cropping patters. The extension is further being requested to allow for the inclusion of additional in-situ data that was collected in the period March to May 2021. The additional crop field data was necessitated by the need to capture the fragmentation and heterogeneity of crop fields managed by peasant, small scale, and emergent farmers. Farming patterns of peasant, small scale and emergent farmers are fragmented and heterogeneous owing to management practices of the said farmers. Nonetheless, it is these farmers that provide for approximately 80% of the Zambian national food basket and hence contribute largely to the food security of the nation. Understanding the peasant, small scale and emergent farmers cropland extents, crop types, cropping patterns and cycles will lead to a better understanding of the arable land use and thus help ensure sustainability of agriculture while ensuring food security. This is envisaged in the production of timely, spatially explicit, and precise information that will aid decision making

Of the world’s rivers, 48% of their volume is moderately to severely affected by dams; if the dams that are planned or currently under construction are completed, this fraction could rise to 93%. With a surge in dam construction in recent years, understanding the ecological impacts of damming is essential for the security of the world’s water resources. Around 40% of the world’s population lives in watersheds of rivers originating from mountainous regions and many of these regions are glaciated. Glacial meltwater is high in glacial fines, giving rise to the characteristic cloudy, turbid appearance of many glacier-fed water bodies. Glacial fines are slow to settle which can reduce the depth to which light can penetrate, thereby decreasing the zone where photosynthesis can occur. The presence of glacial meltwater can, therefore, have important ecological consequences, influencing primary productivity and higher trophic levels. The goal of the present study is to examine the space-time variability of glacial turbidity in a hydroelectric reservoir. To this end, it has been selected a long and narrow glacier-fed reservoir located in south-central British Columbia: Carpenter Reservoir. The reservoir was part of a two-year field campaign in which in-situ data was collected. As part of monthly surveys, profiles of temperature, conductivity and turbidity were collected at several locations along the length of the reservoir. We observed longitudinal gradients in turbidity in the surface layer, which we attribute to a combination of natural dispersion and particle settling. Based on the field data, a simple model to predict variations of turbidity in the surface water it is been developed. While field observations agree favourably with this model, the dataset is limited both in period of record (two years) and in temporal resolution (monthly surveys). There is the possibility to extend this period of record and increase the temporal resolution by combining these in-situ measurements with remote sensing data. In 2020, with the Sentinel Hub sponsored account it was retrieved true colour images that revealed key physical processes in the shallow area of Carpenter Reservoir, an area that was inaccessible by boat during our field campaign. In particular, the images indicate that wind-driven upwelling may be an important mechanism introducing turbid water into the surface layer of the reservoir. The next step is to relate the normalised difference water index (NWDI) or variants, to in-situ turbidity measurements. By supplementing in-situ data with remote sensing data, to disentangle confounding factors influencing turbidity in Carpenter Reservoir, e.g., effects of reservoir operations, effects of wind events, seasonal variability, and year-to-year variability. The deliverable can be found in a publication in a peer-reviewed journal.

This project seeks to find relationships between the information obtained through SPOT satellite images and measurements in the field that allow advance recommendations and thus promote informed decision-making for beef farmers in Uruguay in the context of climate change and frequent droughts. It is proposed to evaluate the effect of drought in interaction with two grazing systems on the growth and forage quality of grasslands in Basalt soils in northern Uruguay. It is proposed to monitor drought’s impact in shallow and medium Basalt soils and its interaction with two grazing systems (continuous and rotating with 32 paddocks). It is proposed to calibrate SPOT satellite data (NDVI) with field measurements of grass quantity and quality (green and dry fraction). The variability of the production and quality of the forage will be evaluated depending on the type and depth of the soil, as well as the subsequent recovery after the drought of the grasslands according to the kind of soil and dominant plant communities. It is expected to have information that allows better decisions to be made in critical situations such as droughts, which are increasingly frequent in this scenario of climate change. Real-time monitoring of medium-high resolution images (SPOT 7) will allow establishing relationships with the measurements to be made on the pasture: grass cuts and height measurements to assess availability, separation of green and dry fractions to assess the actual pasture quality, etc. In addition, the response of the different plant communities in medium and superficial soils will be evaluated, as well as the effect of grazing systems on the recovery time of natural pastures after droughts.

Feral cats have caused the decline and extinction of many native species in Australia. There is also evidence that their impacts can be greater after fires when vegetation is removed, making it easier for them to hunt. In this project, we are using field experiments to assess the relative impacts of fire and predators on native prey populations, including identifying the post-fire period when prey are most vulnerable and determining how different management strategies could benefit native fauna (i.e. burning and cat baiting). The specific aims of the project are:

– Quantify changes in habitat structure in response to patch burning.

– Examine how patch burning by Indigenous Rangers of the Western Desert affects mammal and reptile communities in areas with and without predator control.

– Examine how predators (cats, dingoes) respond to patch burning.

– Determine if the severity and patchiness of burning affects wildlife populations, and whether these varies according to predator control.

The objectives of this project are to predict the biomass of tropical deciduous forests using Field inventory and Earth observation.

• Height prediction and its comparative analysis with field-measured results.

• Comparative analysis of Tree height with GEDI-derived tree height.

• Biomass prediction and comparative analysis of GEDI-derived, Pleiadas-derived, and Field measured biomass.

The aim is to highlight the efficacy of Pleiades 50cm (high spatial resolution) to predict biomass by providing the tree height. This study will use GEDI height and Field height for biomass prediction and compare the outcomes with Pleiades data using linear, logarithmic machine learning models. Results will provide a base to utilise optical data for different forest types. Also, managers/planners could utilise optical data for analysis.

The ALBIOM project (ALtimetry for BIOMass) proposes to derive forest biomass using SAR Altimetry Data from the Copernicus Sentinel-3 (S3) Mission. The Project is coordinated by Leila Guerriero.

Who will benefit from the project results: the scientific community and humankind. Results will be made available via: publications, abstracts, conferences

I’m researching at the University of Twente, Netherlands, on the Himalaya and Karakorum regions of the Indian sub-continent to understand/compare available elevation models and their variability/accuracy regarding glacial variations annually. Further, it aims to ascertain impacts of global warming on glaciers and the region.

This initiative, led by the Asian Institute of Technology, is a capacity-building project that aims to enhance the abilities of the Asian Development Bank’s developing member countries (DMCs) in utilizing Earth Observation (EO) data for disaster risk reduction. The project will provide selected technical personnel from DMCs with the necessary skills to process satellite imagery. This includes a systematic approach to handling radar and optical data, which will subsequently be used for project planning and implementation. Participants gain hands-on experience in creating and deploying algorithms and models in a cloud environment. These tools process satellite data for disaster risk applications, thereby increasing the DMCs’ proficiency in using cloud based EO applications. The overarching goal is to support DMCs in their Disaster Risk Reduction strategies during both pre- and post-disaster periods. This capacity-building project empowers DMCs to better manage and mitigate disaster risks.

Air Quality Modelling by The Finnish Meteorological Institute is a novel, operative, local-scale air quality model (a combination of Gaussian Puff & Plume) used in the Helsinki Metropolitan area and the city of Turku in Finland. The model was also used in foreign installation sites, such as Nanjing, China, during the Nanjing Air Quality Testbed project. The modelled pollutant species are NO2, NO, O3, PM2.5 and PM10, for which the model provides hourly average concentrations at a breathing height of 2 meters above the ground. Also, pollutant species and variables such as black carbon (BC), Lung Deposited Surface Area (LDSA), SO2 and CO are supported for modelling. Furthermore, the model incorporates a data assimilation algorithm to improve the urban scale modelling via measurement evidence; measurement data should be provided for each modelled pollutant species. In February 2022, a model description and evaluation paper about ENFUSER was submitted to the Environmental Modelling and Software journal (Elsevier) and is currently under review. Typically, the model predictions are updated several times per day, including a “now-casting” period with measurements (up to 24h in the past and a forecasting period in the future up to 48h). The modelling resolution is selected based on the size of the modelling area, down to 10 x 10m2. The model approximates the effect of urban elements such as street canyons with statistical approaches, which is less realistic than computational fluid dynamic modelling (e.g., a Large Eddy Simulation model).

The project is initiated to underscore the impacts of climate change over the Indian subcontinent region, with an ever-growing number of events occurring in this part of the world. The region has extremely dense human settlements, which count for 1/4th of the total world population. During the last El-Nino phenomenon around the globe, the subcontinent has experienced extremely hostile weather conditions. As a result, hundreds of millions of people are directly affected by climate change-related events. From the Glacial Lake Outburst Floods (GLOFs) in the Himalayas and Karakorum ranges to the cloud burst circumstances in the Indus river plains warrant in-depth analysis to understand the root cause from the climatic perspective. Furthermore, untimely and extreme heat waves during 2022 triggered stronger Pre-Monsoon and Monsoon spells (which resulted in unprecedented floods) over western Pakistan also require in-depth understanding of underlying causes to suggest remedial measures for future courses of action.

The habitat of Arctic polar bears is rapidly changing due to climate change, affecting their ability to find food and maintain the energy levels necessary for survival and reproduction. Previous research efforts conducted by Dr. Jody Reimer’s lab resulted in a developed model predicting the most energy-efficient paths for polar bears across a habitat characterized by a mosaic of ice and water. However, this model has only been applied to a highly simplified representation of the Arctic sea ice (a random matrix of ice and water), limiting the applicability of the results to real-world scenarios. This research aims to refine and enhance the inputs into this model by integrating advanced data science methodologies, satellite imagery, and sophisticated image processing techniques. Our primary objective is to transform high-resolution satellite images of Arctic Sea ice into binary data, classifying each location as ice or water using random forests, a machine-learning approach commonly used in landscape classification. This binary data will provide a more detailed and accurate representation of the landscape than the random patterns of ice and water currently used. By feeding this satellite-derived binary data into the polar bear movement model, we expect to significantly improve the realism of path predictions for polar bears, offering insights into movement patterns, associated energetic costs, and habitat use. This is an important step if we are to connect these models to polar bear movement data in the future. This research will help us analyze how changing Arctic conditions affect polar bear energetics and their ability to adapt to a rapidly warming climate. Understanding these impacts is crucial for conservation efforts and policy development. Our findings will contribute valuable data to the broader field of climate change research, emphasizing the impacts of environmental changes on Arctic wildlife and ecosystems.

EnviroLENS is a European Union’s Horizon 2020 (Grant No 821918). The goal of EnviroLENS is to demonstrate and promote the use of Earth Observation (EO) as direct evidence for environmental law enforcement, including in a court of law and related contractual negotiations. By using European satellite capacities, such as those provided by Copernicus, EnviroLENS responds to the demands of the environmental legal sector in the context of evidence-based decision-making processes. The EnviroLENS project further aims to deliver EO-based evidence on environmental incidences and/or environmental law violations to facilitate the data-gathering process as well as to reduce the number of expert field inspections. It addresses both the pro-active monitoring perspective to prevent damage to the environment, as well as the assessment of environmental violations for the enforcement of environmental law. EnviroLENS will also support environmental impact assessment procedures by providing information that supports contractual negotiations and discussions with clients. As such, EnviroLENS delivers three types of innovations:

1. Technological innovations: EO technology + Semantic data mining technology is used to merge two seemingly unrelated domains (EO and legal domain) into a joint environmental monitoring eco-system.

2. Conceptual innovations: EnviroLENS is delivering a cross-domain solution = not constrained by usage domain nor constrained by the type of EO service. The uniqueness of the EnviroLENS arises from its front-office capabilities; EnviroLENS can embrace any EO service and transform it by enriching it with new (LEGAL) added value.

3. Commercial innovations are based on enviroLENS open value chain strategy, the main idea being that anybody can contribute and receive benefit out of his contribution. An important part of the EnviroLENS service development is the combination of legal text materials, such as information on treaties, international soft-law and other non-binding policy and technical guidance documents, national legislation, judicial decisions, and law and policy literature with the power provided by state-of-the-art EO technologies. The envisaged satellite monitoring methods are mainly based on high-resolution EO (HR) data including optical and Synthetic Aperture Radar (SAR) data such as Sentinel 1-2-3. Within selected test areas, the HR data will be used for the development and execution of services such as temporal historical images, mapping of landscape changes, detection of unusual objects, etc. In the context of EnviroLENS, this data is accessed via the SentinelHub. In addition to HR data, VHR data are also of utmost importance as they have to provide reliable legal evidence, either for visual validation of violations or for detection of small-scale violations (such as illegal dumping sites, spatially refined marine pollution, agricultural violations, small scale illegal logging, …). This means, that within the OGC EO Interface Integration Service, the primary intention is to use additional VHR data such as PlanetScope, Airbus Pleiades or Airbus SPOT for parts of the selected test areas and check their suitability for the applications. The amount of VHR data required is 1000 km², divided into 8 regions, including actual and historical data. In order to be able to integrate the data optimally into the processing chains, it was necessary to access this data, like the HR data, via the Sentinel Hub service.

This project, namely an Environmental Information System (EIS) platform with a WebGIS interface, has two main goals:

1. To provide the user monthly aggregated satellite data of environmental variables for the whole extensions of the country of interest.

2. To allow the user to navigate through many years of satellite data in an easy way, allowing comparison of areas and periods, thus helping to understand environmental changes and identifying environmental “hot spots”.

In countries where local data is scarce and/or sparse, ensuring reliable and good quality satellite data can help to monitor key environmental variables at different scales and different dates. The United Nations, through the United Nations World Data Forum, emphasizes the importance of building trust in data platforms to promote open access to new sources of data -such as satellite data into decision-making. CIMA Research Foundation has developed the EIS platform for Iraq and Haiti. These two versions include satellite products made visible through a WebGIS interface. At the same time, a Dashboard module helps any type of user quickly understand the information shown in pre-compiled thematic maps, built with the satellite information available. Workshops and discussion rounds done in the first stages of these projects showed the potential uses of satellite data in these countries. We look forward to keeping improving sustainability and the availability of satellite images loaded in the platform, which will help to monitor environmental variables, aid decision- and policy-makers, provide centralized information for government institutions, NGOs, or other organizations, and raise environmental awareness among the population (from specific users as universities or schools to the general audience).

ENVISION aims to fulfil the need for continuous and systematic monitoring of agricultural land, shifting the focus from fragmented monitoring limited to specific fields and dates to territory-wide and all-year-round monitoring. It will make use of heterogeneous types of available data (EO-based, in situ, open data, and historical on-field check data) and state-of-the-art technologies and methodologies (automatic pixel/texture/object-oriented change detection and classification methods, machine learning, data fusion, multi-source and multi-temporal data management) for providing a fully-automated and scalable toolbox of services, built in close interaction with its future customers. ENVISION will fully exploit the wealth of data made available through GEOSS and Copernicus and its synergetic use with other data to develop data products such as Cultivated crop type maps; Soil Organic Carbon; Vegetation status; Crop growth (distinction of organic – conventional farming); Grassland mowing /ploughing; Soil erosion. The ENVISION toolbox will comprise a monitoring service of sustainable agricultural practices, tools that Pas & CBs can provide to farmers for adhering to environmentally friendly agricultural practices, and an Add-on Development Tool. The project will be tested and validated in a pre-operational environment by potential future customers of its products and services. ENVISION will have three categories of business cases (Monitoring of: multiple environmental and climate requirements of CAP, soil condition, and organic farming requirements) and will also be tested by a group of Lighthouse Customers. A market analysis, business model experimentation techniques and appropriate decision-making tools will determine the commercially viable business models for the services and products of ENVISION, define alternative business models, understand their implications and identify those that will create the most significant value. Role in the project ITC’s main tasks in the ENVISION project, together with the DIH AGRIFOOD, are linked to Dissemination & Exploitation management, where ITC will plan, draft and develop the Dissemination and Communication Plan as well as manage, coordinate and implement dissemination and communication activities according to this plan. Furthermore, ITC will increase the capacity of companies and organisations that offer commercial products to develop new and improved products and services by building up on the ENVISION solution. ITC will also be actively involved in commercialising and exploiting the ENVISION services and products and in identifying user requirements and needs.

Water Stress and Climate Indices for Africa (WaSCIA) service aim to deliver high-quality Water Stress and Climate Indices through an easy-to-use web interface to help the management of drought and water stress in Senegal. These are primary components of major climate risks for Africa, including demands on water resources, reduced crop productivity, adverse impacts on livestock, and biome changes. These, in turn, have significant consequences for undernutrition, migration, human conflict and wildlife welfare. The solution meets the principle characteristics of the EO Africa incubators ITT: “to deploy an innovative EO-based solution that realises benefits in drought management at a National scale while maintaining a user-focussed approach.” An effective drought monitoring solution’s benefits include detecting early onsets of water stress related to drought conditions, its severity and spatial extent.

ARIES is a project within ESA’s EO AFRICA research and development initiative. As such it focuses on building African-European R&D partnerships and the facilitation of the sustainable adoption of Earth Observation and related space technology in Africa. ARIES aims to create more detailed and timely information about drought conditions and crop water stress for African land use stakeholders. Thus, helping them navigate changing climatic conditions with unreliable rainfall patterns, that threaten food security. The consortium is developing EO products that shall deliver large-scale information on Ecosystem water stress as well as detailed information on plant water stress on the field level. These new products could help to evaluate the risk of drought for pastoral lands and entire farms and give information about the current plant conditions allowing detailed planning of actions. The products will therefore serve water resource management purposes and help ensure food security by helping farmers to raise healthy crops and feed their livestock. The information generated will also have the potential to inform drought policy frameworks in the respective regions. The utilization of hyperspectral and thermal will deliver important information for the design of future missions.

EO Africa R&D Facility is the flagship of the EO AFRICA initiative of ESA. The overarching goal of the Facility is to foster an African-European R&D collaboration enabling an active research community and creative innovation processes for the continuous development of EO capabilities in Africa. The R&D Facility will review the African EO research challenges and issue research calls for addressing the most relevant ones. Furthermore, it will offer the researchers modern cloud computing & digital tools and support various collaborative activities and initiatives between the African and European research communities.

EO Africa R&D Facility is the flagship of the EO AFRICA initiative of ESA. The overarching goal of the Facility is to foster an African-European R&D collaboration enabling an active research community and creative innovation processes for the continuous development of EO capabilities in Africa. The R&D Facility will review the African EO research challenges and issue research calls for addressing the most relevant ones. Furthermore, it will offer the researchers modern cloud computing & digital tools and support various collaborative activities and initiatives between the African and European research communities.

EO Africa R&D Facility is the the flagship of the EO AFRICA initiative of ESA. The overarching goal of the Facility is to foster an African-European R&D collaboration enabling an active research community and creative innovation processes for continuous development of EO capabilities in Africa. The R&D Facility will review the African EO research challenges and issue research calls for addressing the most relevant ones. It will offer modern cloud computing & digital tools for the researchers and support a range of collaborative activities and initiatives between the African and European research communities.

The long-term goal of “Land Use Intensity’s Potential, Vulnerability and Resilience for Sustainable Agriculture in Africa” (LUISA) is to build the resilience of smallholder farmers and pastoralists in Africa to land use intensification resulting from rapid population growth and climate change. LUISA will achieve this goal by developing a satellite-driven decision-support platform from which policymakers can deliver more effective and reliable carbon monitoring across Africa. Human Appropriation of Net Primary Productivity (HANPP) is a key environmental indicator that helps decision-makers understand the drivers and consequences of land use intensification on carbon dynamics on a pixel basis over large areas. There is a large disconnect between carbon monitoring platforms and the planning/decision-making they inform. The disconnect is due to poor communication, translation, and mediation on the side of system developers. Communication among knowledge users, clients, and platform developers helps to identify user needs while shifting perception away from “control” to “support.” The translation of SITS and scientific outputs in forms tailored to specific carbon monitoring applications encourages effective and sustained use of the platforms. Likewise, the integration of user feedback into the data processing cycle increases the quality and delivery of SITS and scientific outputs. LUISA is a 24-month project which has two main objectives:

(i) develop a remote sensing-driven HANPP monitoring framework for general land cover types (cropland, forest, rangeland, urban) in case study agroecosystems (Ethiopia, Mozambique, Senegal, Uganda) and

(ii) perform a massive scale out in space and time of the HANPP estimates for the African continent.

LUISA also establishes a graphical user interface (GUI) that contains a visual representation of HANPP and intermediary products (e.g., crop yield, carrying capacity). The GUI will be comprised of charts and other graphics that can be manipulated on the fly with a dashboard to facilitate users to understand the large volume of data in one centralized location. The platform developers of LUISA (ITC-University of Twente, VITO, University of Exeter, University of Natural Resources and Life Sciences at Vienna, GISAT) are defining the case studies jointly with the African partners (CSE, DATA4MOZ, Makerere and Bahir Dar University). The case studies are representative of the variety of landscape conditions encountered in Africa: Beira Agricultural Growth Corridor, silvopastoral area, highland region of Lake Tana and Mount Elgon Agroforestry Zone. First, the project will consolidate key user requirements, which is the foundation for the design of the HAN PP decision-support platform. The second body of work focuses on calibrating and validating a HANPP prototype in the case studies. It requires the collection, processing, and analysis of several sources of reference, Earth observation, and ancillary geoinformation data. A third major activity in the project is to transfer the prototype to a cloud-based computing environment to assess its stability, speed, scalability, and responsiveness. Eventually, the results will be disseminated to our partners in the case studies and to other interested decision-makers across Africa.

We just recently adapted this in-class project and founded a new student association, and we would like to resume our activities to promote space and earth observation, promote data extraction and popular science, and to push the limits of our different sub-projects, which we feel have barely scraped the surface of their potential.

Telespazio UK Ltd are the prime contractor for ESA’s “EO Exploitation Platforms Common Architecture (EOEPCA)” initiative. EOEPCA aims to facilitate adoption of a freely available common architecture that supports a paradigm shift from “bring the data to the user” (i.e. user downloads data locally) to “bring the user to the data” (i.e. move user exploitation to hosted environments with collocated computing and storage). This leads to a platform-based ecosystem that provides infrastructure, data, computing and software as a service. The resulting Exploitation Platform is where scientific and value-adding activities are conducted, to generate targeted outputs for end-users.

The focus of the Common Architecture is to define an open architecture using open interfaces that facilitate the federation of services in the “EO Network of Resources”, and to develop a Reference Implementation of the architecture for deployment as an operational service. The goal of the EOEPCA project is specifically tied to the goals of the Network of Resources (NoR). EOEPCA will define an architecture that facilitates the success of the NoR, comprising building blocks with well-defined interfaces based upon open standards. The architecture and its interfaces are designed to be reusable by third-parties provisioning platforms with the NoR. Use of the Common Architecture will encourage platform providers to have consistent interfaces with other platforms in the NoR ecosystem, and so facilitate interoperability that allows platforms to share their resources.

EOEPCA aims to facilitate the adoption of a freely available common architecture that supports a paradigm shift from “bring the data to the user” to “bring the user to the data”. This leads to a platform-based ecosystem that provides infrastructure, data, computing and software as a service. The resulting Exploitation Platform is where scientific and value-adding activities are conducted to generate targeted outputs for end-users. The focus of the Common Architecture is to define an open architecture using open interfaces that facilitate the federation of services in the “EO Network of Resources” and to develop a Reference Implementation of the architecture for deployment as an operational service. The architecture and its interfaces are designed to be reusable by third-parties provisioning platforms with the NoR. Using the Common Architecture will encourage platform providers to have consistent interfaces with other platforms in the NoR ecosystem, facilitating interoperability that allows platforms to share their resources. A Reference Implementation of the full architecture is being developed to prove the concepts and provide an off-the-shelf solution that can be instantiated by future projects to implement their EO Exploitation Platform, thus facilitating their ability to join the federated Network of EO Resources.

The objective of the “EO Exploitation Platform Common Architecture – Operational Uptake Support” project, headed by Telespazio UK, is to support the roll-out of the EOEPCA interoperability layer to independent infrastructure and platform operators. Operators are supported in migration to this new state-of-the-art of cloud-based platform interoperability. As a project subcontractor, and as the operator of the Forestry TEP platform, the objective for VTT in the project is to employ EOEPCA in building the architectural base for the next evolution of the platform.

This research project consists of the long-term monitoring of hazardous landscapes in high-mountain conditions (glaciers and related lakes), using EO data. The research presented here focused on high mountain areas where natural hazards are omnipresent. Within the current climatic context, global warming is responsible for the increasing melting and significant retreat of glaciers. As the glaciers retreat, the related proglacial lakes are growing, inducing an increase of slope instabilities, as well as a higher risk of glacial lake outburst floods (GLOFs), which menace populations downstream. Application site is the Terskey mountain range, Tien Shan, Kyrgyzstan, Central Asia (Petrov Moraine Lake Dam near the Kumtor Gold mine, Eastern Tien Shan, Kyrgyzstan, Central Asia). The Kumtor Gold mine is located at an altitude of 4000 m in the Eastern Tien Shan, in the South of Lake Issyk Kul. This mine, developed in the early years of this millennium, is currently still active. Due to the high altitude, it is affected by a series of high-mountain and geological hazards. The mine is located directly downstream from Lake Petrov, which formed more than 100 years ago behind the moraine left after the retreat of the Petrov Glacier. The size of the lake is constantly increasing, and destabilisation is also likely to occur due to permafrost retreat. The interest in this site is even greater since a recent landslide collapsed in December 2019, next to the Kumtor goldmine, increasing the risk of contamination related to the tailing. As soon as increased displacements can be observed, some risk mitigation measures must be applied. Other potential study sites are Pokot (Kenya, Africa), Kungai mountain range (Tien Shan, Kyrgyzstan, Central Asia), and the Patagonian Icefields (Chilean Andean Mountains, South America).

The main objective of this 6-year research project consists of the long-term monitoring of two hazardous areas in Central Asia and South America. To accomplish a complete monitoring, different sub-objectives are described as follow:

1. Large-scale inventory of glacial lakes in both study sites based on optical images (ERS + Sentinel 2, Spot 6-7, Google Earth).

2. Identification and monitoring of proglacial lakes and related hazards using optical and radar satellite imagery. For this first and main objective, a remote sensing database will be developed and processed using change detection techniques as well as multi-temporal interferometry (note the association of ascending and descending modes for 3D displacements).

3. Estimation of lake volume, determination of the rate of water level change based on ground displacements around the lakes using the difference of DEM and InSAR.

4. Comparison with climatic information to identify peaks of hazard occurrence or anomalies according to specific thresholds (comparison between in-situ and satellite data).

5. Reconstruction of the glacier conditions in the lake catchment and past climatic conditions of the mountain range by analysing historical data and meteorological data.

6. Evaluation of further risks of slope instabilities, GLOFs and other potential hazards (flow modelling).

7. Comparison between the two selected sites (and other potential sites presenting similar characteristics) to assess the ongoing geohazards and their trend in a climate change context (Terskey vs Kungai, Tien Shan, Kyrgyzstan).

8. Test of GEP services for landslide monitoring in case of densely vegetated landscape (a common type of landscape in the Czech Republic).

Implement a prototype of the Data Store for the EO Science Hub to complement the Discovey element under development for which a previous sponsoring request was submitted. It is meant to store EOP-SD science project outputs. The initial request is of 3 TB for one year but it will be extended as needed along the project.

The project aims to develop and deliver six services that respond to common challenges related to ecosystem mapping and monitoring in the Alpine region. These are: ecosystem mapping, forest disturbance, forest phenology, forest fire recovery, grassland management and grassland abandonment. The services have been developed addressing the specific requirements of national and regional stakeholders and delivered sufficiently large in scope and content to strengthen regional cooperation across Alpine countries. As a proof of concept, an area covering more than 50,000 km2 has been selected to demonstrate the adequacy and usefulness of the proposed services. In addition, the project also aims to demonstrate the added value of leveraging the open, non-monolithic and federated network of platforms paradigm developed by ESA with the Network of Resources initiative to provide state of the art processing at regional scale. The project aimed to setup in its first year an initial footprint for development and collaboration on top of EODC. The goal of the second year is to perform the actual service delivery on top of EODC.

EO4ALPS Applications – Ecosystems is an ESA-funded project that kicked off in January 2021. The project will develop and deliver six services that respond to common challenges related to ecosystem mapping and monitoring in the Alpine region: ecosystem mapping, forest disturbance, forest phenology, forest fire recovery, grassland management, and grassland abandonment. The services will be developed addressing the specific requirements of national and regional stakeholders and delivered sufficiently large in scope and content to strengthen regional cooperation across Alpine countries. The project will strongly engage critical national, regional, and international stakeholders active in monitoring Alpine ecosystems, starting with the Mountain Research Initiative and the Alpine Convention. Another objective of the project is to demonstrate the added value of an open and federated network of platforms to provide these services at the regional scale, in the spirit promoted by the Network of Resources. As proof of concept, an area covering more than 50,000 km2 has been selected to demonstrate the adequacy and usefulness of the proposed services. The project aims to set up an initial footprint for development and collaboration in its first year on top of an NoR resource and data provider. The second year’s goal will be to deliver the actual service on top of higher-level NoR services like the OpenEO Platform and Euro Data Cube.

The eo4alps snow project is based on a hybrid technology that merges the advantages of the physical model with high-resolution high-frequency Earth Observation snow products. The project focuses on implementing high-resolution quasi-real-time snow monitoring to improve water resource management. By combining the latest technology in snow monitoring, we want to improve the temporal and spatial aggregation of Snow Water Equivalent (SWE) monitoring techniques and provide high-resolution SWE monitoring in quasi-real time at the Alpine scale. The project takes advantage of the recent developments in physically-based snow modeling to improve the revisit frequency of the snow cover product. In addition, it is taking advantage of high-resolution binary snow cover maps from Sentinel-2, SAR data from Sentinel-1, and coarser resolution daily optical images (e.g., Sentinel-3). The core service is a snow water equivalent (SWE) product generated using a cloud-based processing environment to be delivered over the entire Alpine Arc region. The eo4alps team plans to engage users from public and private sectors, such as public agencies, research centers, associations, and hydropower companies.

The objective of this activity is to allow the eo4alps-landslides users (e.g., operational users in France, Italy, Switzerland, and Austria) to use the eo4alps­landslides services on GEP to generate landslide ground motion maps, landslide detection maps, and landslide models making full use of the eo4alps­landslides App on the Geohazard Exploitation Platform (GEP). The objective is also to support and train the users through CNRS-EOST, Terranum, Unimib, and AUTh members. This proposal is a component of the ESA contract eo4alps­landslides concerning the setup and operational exploitation of landslide­tailored services covering the critical areas of interest of landslide practitioners, science, and DRM communities seeking to assess hazard and risk better. The goal is to increase disaster resilience in mountain territories and support quality of life. It is based on the following:

• Allow the eo4alps-landslides users (maximum 15 users) to use the ΕΟ motion services, the ΕΟ detection services, and the landslide modeling services available on the eo4alps-landslides App on the GEP.

• Support training and validation activities by the eo4alps prime/co-prime and service owners for the operational users.

• Focus on publishing relevant processing jobs and data packages, promotion, and awareness-raising activities—the action of Copernicus Sentinels and third-party missions together with landslide models.

The integration of ΕΟ and models aims to provide services for the detection and monitoring of landslides, for updating landslide inventories, and to offer tools for forecasting landslide occurrences and intensity. The benefits are being implemented and exploited on the GEP.

The objective of this project is to produce the first pan-Greenland near-surface density time series derived completely from Earth Observation (EO) data. This will be accomplished through the joint analysis of satellite altimetry (ESA CryoSat-2, CNES/ISRO SARAL, EC Copernicus Sentinel-3) and passive radiometry (ESA SMOS) measurements for the 13 years between 2011-2023. Near-surface density has a direct role in converting observed changes in the volume of the Greenland Ice Sheet (through conventional repeat satellite altimetry) to a mass balance. Ice sheet mass balance is a critical parameter as it quantifies how the ice sheet has been changing through time and contributing to global sea-level rise. When using computer models to project how future melting in Greenland will contribute to sea-level rise over the coming decades and centuries, satellite-era (1990-present) mass balance observations are fundamental as they provide real-world observations of ice sheet behavior against which the simulations can be assessed. However, a current shortcoming in this approach (i.e., using observational data to validate computer models) is that there are no existing means of observationally measuring pan-Greenland changes in near-surface density. Instead, the computer models themselves are used to predict near-surface density across Greenland in response to modeled climate forcings (e.g., temperature, snowfall, etc.); thereby introducing additional uncertainty into the final mass balance estimates. This project is targeted directly at this limitation, to produce a unique observational dataset that ice sheet and sea-level rise modelers can use to refine their climate and near-surface models. At the end of the project, we expect to have produced monthly estimates of near-surface (top few meters) density across the Greenland Ice Sheet (in a 5-by-5 km grid) for the 13 years between January 2011 and December 2023. These results will be made available as a publicly accessible data repository (such as being hosted on DTU Data).

EO4HEALTH proposes to evaluate the suitability of Earth Observation (EO) imagery in the context of public health decision-making, scenario assessment and impact/risk evaluation. These objectives are being materialized by having science driving the project developments by current gaps and challenges, but at the same time, user needs from key stakeholders are taken into account to conceptualize a long-term initiative that can become useful in practice. The of goal EO4Health resilience is the development and implementation of added-value services, leveraged by the vast knowledge that was gathered in previous ESA-funded activities, which were focused on the capability of EO data and Artificial Intelligence methods to automatically identify patterns able to make accurate predictions of the spatiotemporal re-emergence and spread of vector-borne and waterborne diseases. The EO4Health services are being developed under two use cases, which are led by the scientific partners of the consortium: IZSAM – Istituto Zooprofilattico Sperimentale dell’Abruzzo e del Molise (vector-borne diseases) and PML – Plymouth Marine Laboratory (waterborne diseases). For the vector-borne diseases use case, the main goal will be the implementation of the model developed by IZSAM focused on the probability of circulation of the vector (mosquito) responsible for the circulation of the West Nile Virus. While this model has been developed for the Italian territory, in EO4Health resilience it is implemented for the entire Mediterranean basin and tested against existing ground-truth validation data that can be obtained from official institutions, such as the Portuguese Health Directorate. Still, in the scope of vector-borne diseases, the consortium, supported by ESA is engaging with relevant stakeholders such as the UN Food and Agriculture Organization (FAO), hoping to synergize with the work that FAO has been developing on vector-borne diseases, materialized as their web-based Rift Valley fever Early Warning Decision Support Tool (RVF DST). As for the waterborne diseases use case, the main goal to be achieved is similar, i.e., to scale up an existing predictive model focused on the prediction of Cholera outbreaks. This model has been developed by PML and is focused on mapping the risk of encountering the Cholera pathogenic bacteria in the water of the Vembanad Lake and its surroundings (India). As for the previous use case, for waterborne diseases, the idea is to test this model in another area of interest (The Baltic sea). However, the work is not limited to this, since also it is planned to:

i) examine the role of phytoplankton species or types in determining the relationship (positive or negative) between cholera bacteria and chlorophyll concentration,

ii) examine the role of surface water temperature in affecting the distribution of the bacteria and

iii) examine the role of green spaces, trees and built-up areas around the Vembanad lake in determining the transport of pollutants into the water by land drainage.

On the engineering side, this project also allows relevant advancements to the health community, via the setup of a “Resilience & Earth Observation Virtual Observatory” with Key Stakeholders, Public Authorities and Private actors. This virtual observatory, materialized under the form of a web platform that has been developed and implemented by project partners Brockmann Consult, acts as a one-stop shop for all project-related activities, not only gathering relevant EO and health-related data that can be used by health experts (e.g., data from previous activities focused on Non-Communicable Diseases) but also allowing the full implementation of the two use cases (considering all the required processing steps) and the integration of additional processing capabilities for the study of patterns associated with emerging diseases. The provision of all project data and outputs via the Resilience & Earth Observation Virtual Observatory allows non-EO and non-geographic data experts can access relevant data in a user-friendly environment, thus fostering the maximization of the uptake of the generated information.

In August 2023, major floods occurred in large parts of Slovenia due to heavy rain. Amongst others, the level of rivers Sava, Mura and Drava was exceptionally high. Several settlements and transport links in Slovene Littoral, Upper Carniola and Slovenian Carinthia were flooded. Severe rainfall event triggered more than 1,000 landslides, which caused a lot of damage to infrastructure and private properties. Due to the event, the National Flood Protection and Rescue Plan was activated. According to the Slovenian Environment Agency, the worst flooding was in the foothills of the Julian Alps, from ldrija through the Ljubljana basin to Slovenian Carinthia, where 150- 200 mm fell in 48 hours. At least seven people were killed during the floods. According to the Administration for Protection and Rescue data, 168 fire brigades participated in 1039 interventions within 12 hours. International support was requested through the European Union Civil Protection Assistance Mechanism (ERCC) and NATO’s Disaster Response Mechanism (EADRCC); several countries provided the help in different forms. The problem of the storm’s aftermath is being addressed at all scales and institutions, as the estimated damage has risen to 8-9 billion€. Slovenia has requested the activation of Copernicus EMS (EMSR680 and EMSR697) and received or is still receiving the products. In addition, aerial lidar scanning and orthophoto mapping have been realised for several areas.

The NoR sponsorship request support activities in the EO4MASRISK CCN project. Severe rainfall in May and August 2023 caused severe floods and over 8000 landslides in Slovenia. There is an urgent need for a landslide mapping methodology using VHR and HR optical and radar data to provide information on landslide extent, which is fundamental information for landslide risk assessment. In addition, automatic detection of flooded areas on optical and radar images using advanced ML is needed in Slovenia and worldwide. The main objectives of the activities performed in the NoR are:

– Monitoring landslides persistent motion with optical image time series,

– Landslides detection and inventory mapping with high and very high-resolution optical data,

– Deployment, integration, and hosting of the Sentinel-1 and Sentinel-2 flood detection service developed the team to mCube and GEP.

This will support the activities of GeoZS and other organizations in landslide mapping and the Space and Major Disasters users in flood detection.

As part of the EO4UA initiative, we will generate boundaries of agriculture polygons over Ukraine for six years to assess the impact of the current situation on agriculture activities. ΑΙΙ results will be released via the portal https://www. eo4ua.org/mapbender/application/eo4ua endpoint for use in the Ukraine damage analysis.

The Open Science Catalogue is one of the elements contributing to an Open Science framework and

infrastructure, with the scope to enhance the discoverability and use of products, data and knowledge

resulting from Scientific Earth Observation exploitation studies. This SAP activity aims to: enhance the Open Science Data Catalogue’s capabilities for data governance expand the catalogue with a data storage and long-term preservation component enhance interoperability and interconnectivity with the other open science and collaborative development systems enhance data indexing and discoverability in the cloud and enhance programmatic access to the catalogue.

The Open Science development team will work in an Agile way with ESA as the primary Product Owner supported by TPZ-UK. The bulk of the implementation is directly relevant to the Resource Management and is allocated to EoX and EOfarm.

The main goal of this research project is to make the most of the powerful Sentinel-1 Ground Range Detected (GRD) data. I want to use this data to create and use an Open Geospatial Consortium (OGC) Application Package on the innovative EOEPCA cloud platform. This project aims to push the boundaries of Earth observation and geospatial analysis by combining cutting-edge satellite data, advanced processing techniques, and state-of-the-art cloud infrastructure. A crucial objective is seamlessly integrating the processed Sentinel-1 GRD data into an OGC Application Package. By using widely-accepted data sharing and interoperability standards, I hope to encourage collaboration and allow different scientific fields to use our data products.

The ESA EOEPCA Common Architecture Project focuses on defining an open architecture using open interfaces that facilitate the federation of services and developing a Reference Implementation of the architecture for deployment as an operational service. The reference implementation will provide an operational service to obtain feedback on the Common Architecture from both platform providers and users. ESA and Telespazio VEGA UK have contracted Space Applications Services to establish an operational service based on the EOEPCA. Technically, the objective of the Operational Service is to integrate the building blocks developed by the Domain Experts, validate the resulting Service, and deploy the Service into production. Because the Domain Experts will implement new features in parallel to the Operators’ activity, incremental releases of the Service will be produced, deployed and evaluated.

The project aims to integrate the EO Exploitation Platform Common Architecture (EOEPCA) Reference Implementation building blocks developed by Domain Experts within a deployed exploitation platform to validate the common architecture in an operational context, collect feedback and support the Domain Experts developing the Reference Implementation.

As part of an activity to define an architecture for the Green Transition Information Factory, Telespazio will analyse how the EOEPCA building blocks, described in detail below, and the general architecture can satisfy the requirements of the Green Transition Information Factory (GTIF) use case for the Austrian GTIF demonstrator (GTIF-AT). The analysis will focus on showing the EOEPCA building blocks alongside the building blocks of the openEO platform, it will highlight any overlaps and functionality gaps, and also identify the openEO technologies that could be integrated into the EOEPCA reference architecture.

The consortium of the EOStat project for Statistics Poland proposes to implement the EOStat system of crop recognition and yield prediction in the territory of Ukraine. This will make it possible to estimate the yield losses for 2022 compared to previous years 2017 – 2021.

The project’s objectives are to identify ephemeral wetlands (Class 1 & 2) and differentiate these wetlands from Class 3, 4, & 5. The focus on ephemeral wetlands is because of their high risk for conversion (drainage) to agricultural production, as no laws are in place to protect them. Class 3 and higher class wetlands have various degrees of protection that reduce the risk of conversion. With this data, we hope to develop a project to incentivize landowners to protect ephemeral wetlands and, in turn, reduce the risk of transforming this vital ecosystem. The West Interlake Watershed (WIWD) strives to lead local watershed organizations, bringing a holistic and sustainable management perspective to surface and groundwater quality and quantity issues. Our not-for-profit company focuses on watershed health and how we can better mitigate risks associated with freshwater within our watershed.

This project aims to document the erosion of the Colorado River delta tidal flats with satellite images and analysis tools from the EO browser and Sentinel Hub. The erosion of the Colorado River delta tidal flats is initiated by the imbalance of the concurrent geo-processes of sediment deposition, erosion by tidal action, and tectonic extension in this plate boundary zone. The lack of sediment input to the delta due to the construction of dams along the Colorado River since the early XXth century has triggered the erosion to the tidal flats (31 20N, 114 56W) by the macro tidal regime in the upper Gulf of California with the persistent incursion and erosion of tidal currents. The trans-tensional tectonic regime in the region has created depressions or troughs with a slow but persistent downward movement of the surface, enabling the further incursion of the tides that the sea level rise trend will catalyze.

ESA Academy Earth Observation Remote Sensing Workshop 2022 (EORSW2022) is part of a series of training activities organized by ESA Academy for university students with three main objectives: To motivate and enable young people to enhance their literacy & competence in sciences and technology (STEM disciplines). Second, inspire and encourage young people to consider pursuing a career in STEM, particularly in the space domain. Third, contribute to increasing youngsters’ awareness of the importance of space research, exploration and applications in modern society and economy. More specifically, EORSW2022 will help university students get familiar with the current technology and missions on Earth Observation field and with all the products (and software) that those missions produce. Furthermore, students will get familiar with and practice using different mission products on different disciplines focusing on remote sensing, image visualization and analysis, and GIS applications.

Since the start of the Copernicus program and the launch of the two radar satellites Sentinel-1 a and b, whose data are freely available to any interested user, the general interest in radar remote sensing has increased. For this reason, extensive training materials on this topic have been compiled in close cooperation with proven experts in the respective field. ESA supported these activities with the ESA-funded projects “Land MOOC” and Echoes in Space”. These training materials are free to all interested users and can be viewed and downloaded at https://eo-college.org. This is accompanied by an annual summer school (free of charge), held as an online event due to the pandemic. To provide each user with a possibility for practical application of the theoretical knowledge in the field of radar remote sensing that meets the requirements, we want to give each summer school participant their VM for a limited time. The requested support with VMs is, therefore, an essential prerequisite for the successful realization of the summer school, which is organized in cooperation with ESA to course accompany the ESA projects “LandMOOC” and Echoes in Space”. Experience shows that such practical courses serve as multipliers in that the participants report on the course and the course content in their organizations. ln this way, different user groups can be opened up and won over to this area of remote sensing. Thus, Copernicus data from the Sentinel-1 a and b satellites will become increasingly widely used and will soon become an integral part of operational remote sensing analyses, e.g., for decision support, from which all citizens of the EU will ultimately benefit.

Objectives: The ESA “Sentinels for Agricultural Statistics” (Sen4Stat) project aims at facilitating the uptake of sentinel EO-derived information in the official processes of National Statistical Offices (NSOs), supporting the agricultural statistics. The project is working in four pilot countries: Spain, Ecuador, Senegal and Tanzania, thus addressing a wide diversity of both cropping systems and agricultural data collection protocols.

In close interaction with its pilot countries, the project conducted an in-depth review of how efficiently integrating EO data in their current NSOs workflow. National use case studies were defined: i. Coupling crop type maps with statistical ground surveys to derive crop area estimates; ii. Coupling crop type maps, biophysical variables, crop yield in situ data and district-level official crop yield statistics to derive crop yield and production estimates; iii. Using crop type maps, biophysical variables and statistical ground surveys to disaggregate the agricultural statistics to small administrative units and improve the statistics timeliness through the provision of early crop area and yield indicators; iv. Relying on cropland and crop type maps to build or update sampling master frames and optimize the sampling design; v. Supporting the official reporting of the SDG indicators 2.4.1. and 6.4.1. The project will develop validated algorithms and open source tools supporting these use cases and demonstrate them through the production of national products and best practices. It will also conduct training and capacity building activities on these tools and algorithms, thus supporting the uptake of EO technology by the NSOS.

The objective(s) of this ESA Sentinels for Agriculture project is to facilitate the uptake of Sentinel EO-derived information in the official processes for National Statistical Offices (NSOs) supporting agricultural statistics. The project works with five pilot countries: Spain, Ecuador, Senegal, Tanzania and Angola, thus addressing a wide diversity of cropping systems and agricultural data collection protocols. In close interactions with its pilot countries, the project conducted an in-depth review of how efficiently integrating EO data in the current NSOs workflow. National use cases were defined as:

1. coupling crop type maps with statistical ground surveys to derive crop area estimates;

2. coupling crop type maps, biophysical variables, crop yield in situ data and district-level official yield statistics to derive crop yield/production estimates;

3. using crop type maps, biophysical variables and statistical ground surveys to disaggregate the agricultural statistics to small administrative units and improve the statistics timeliness through the provision of early crop area and yield indicators;

4. relying on cropland and crop-type maps to build or update sampling master frames and optimize the sampling design;

5. supporting the official reporting of the SDG indicators 2.4.1 and 6.4.1.

The project is developing validated algorithms and open-source tools supporting these use cases and is demonstrating them through the production of national products and best practices. It is also conducting training and capacity-building activities on these tools and algorithms, thus supporting the uptake of the EO technology by the NSOs.

The objective of the Sen4CAP project is twofold:

1. Provide evidence of how Sentinel-derived information can support the modernization and simplification of the CAP in the post-2020 timeframe;

2. Provide validated algorithms, products, workflows and best practices for agricultural monitoring relevant to the management of the CAP.

The project has developed an open-source toolbox (Sen4CAP system), which can automatically process Sentinel-1 SLC and Sentinel-2 L1C or L2A time series into a set of relevant products for the new CAP. The primary users are expected to be national Paying Agencies (and/or their sub-contractors specialized in EO), the private sector and researchers. The system is available on the web.

The objective is to address two main scientific problematics:

– Assessment of the volume of oil seeps naturally expelled from the sediments compared to anthropogenic oil spills (pollution) in the Mediterranean Sea. The expected scientific improvements refers to the inclusion of oil seeps and oil spills in carbon cycles and a reassessment of carbon budgets that of the volume expelled naturally

– Evaluation of plastic pollution using remote sensing techniques: An overview in the Gulf of Lions (Mediterranean Sea). The aim is to compare the plastic detection efficiency for different imaging techniques (SAR, multispectral, hyperspectral, VHR).

The Blue Economy: Innovation Clusters, Atlantic Natural Resources Management and Maritime Spatial Planning project aims to complement the ESA Regional Atlantic initiative by providing insights and solutions in the Blue Economy theme. In this context, it is essential to consolidate EO and IT experience to design and build well-framed services that support information delivery to address the needs of new marine legal frameworks. Three principals must guide this information delivery: – The developed system simplifies the acquisition of information by the user, requiring a fit-for-purpose design focused on the user; – The developed system does not require the end user to be an expert in EO, though it can be reassured that the information they are acting on is transparent, quality-assured, and actionable; and – In the short term, developed systems fit within existing legal frameworks and information needs, whilst promoting and opening avenues to the development of new legal frameworks, capable of harnessing more novel advances.

Considering all these aspects, GMV, in the scope of the Blue Economy project, will develop a set of services focused on detecting and monitoring marine pollution in the form of plastics and/or marine spills. The services will explore EO data to verify and appraise models focused on maritime litter dynamics surveillance in support of MSPD ambitions. Analysis of merged data streams can provide evidence about the impact of MSPD and whether or not the evidence suggests negative trends are being improved. EO can complement such work by analysing the outcomes of these models in terms of impact (over tourism, environment) and survey looking for new contamination spots that can feed the models—taking into account the ICT Requirements for the marine pollution services to be developed.

Within the GEOGLAM pilot (pilot 1, showcase 1), part of the eShape project where VITO is leading the pilot, the aim is to provide a number of new services which are relevant for the wider agricultural monitoring community. Crop calendars as an Essential Agricultural Variable (EAV) were selected as new service. As GEOGLAM is targeting the global community, an important aspect is the geographical transferability of the monitoring service. This transferability refers to both the methodological as the implementation aspect, i.e. the method needs to be applicable at a global level, and the service needs to be available at the global level. The performance of the methods is evaluated in another component of the pilot, and this exercise focuses on the implementation of the service on a platform to ensure global availability. The scope of this exercise is to gain insights in the functionalities of the available platforms, in order to make a better-informed decision on where this GEOGLAM service could be integrated in a later phase. These functionalities encompass a range of possible variables, such data availability, ease of integration, ease of use, cost, processing speed, and reliability. In this document, we will provide an overview of the general approach of this benchmarking exercise, including the platforms used for evaluation, which variables will be compared, and how these results can be consolidated. This request focusses on the use of NextGEOSS service as part of this comparing exercise.

This request is part of a platform comparison exercise of the eShape project (https://e-shape.eu/). Within the GEOGLAM pilot, part of the eShape project where VITO is leading the pilot, the aim is to provide several new services that are relevant to the wider agricultural monitoring community. Crop calendars as an Essential Agricultural Variable (EAV) were selected as a new service. As GEOGLAM is targeting the global community, one important aspect is the geographical transferability of the monitoring service. This transferability refers to both the methodological and the implementation aspects, i.e., the method needs to be applicable at a global level, and the service needs to be available at the global level. This exercise focuses on the comparison of executing an algorithm/workflow on different platform providers.

Marine litter is a growing problem that has attracted attention and raised concerns over the last years. Significant quantities of plastic can be found in the oceans due to the unfiltered discharge of waste into rivers, poor waste management, or lost fishing nets. The floating elements drift on the surface of water bodies and can be aggregated by processes such as river plumes, windrows, oceanic fronts, or currents. The experiments demonstrate that harnessing the spatial patterns learned with a CNN is advantageous over pixel-wise classification using hand-crafted features.

As a follow up of the workshop organized in ESRIN Science Hub from 13-17 May 2024, we would like to give the young researchers (PhD students from University of Edinburgh and University of Leeds an opportunity to continue working on the platform, as they were given hands-on training on how to use it in their research. The workshop gave students a deep dive into exploring the scientific potential of Satellite Earth Observation together with data science techniques to transform the researcher’s findings into captivating stories. This was the 3rd edition of the event and as for the previous editions we would like the students to further use the platform by giving them possibility to work using the DeepESDL resources and datacubes until the end of the year 2024.

This hands-on training and workshop promise a deep dive into exploring the scientific potential of Satellite Earth Observation together with data science techniques to transform the researcher’s findings into captivating stories. After the big success of the Earth System Science Workshop organized last year, we followed up with the 2nd edition of the event in an exciting new setting. For this edition, the Science Hub collaborates with Sorbonne Université Paris, Académie Spatiale d’Ile de France, and IPGP and hosts the Earth System Science Hub Challenge, from February 26th to March 1st of 2024.

The objective of this hands-on training and workshop is to explore the scientific potential of Satellite Earth Observation together with data science techniques to transform the researcher’ s findings into captivating stories. This is the 3rd edition of the event in an exciting new setting. For this edition, the Science Hub collaborates with University of Edinburgh and University of Leeds and hosts the Earth System Science Hub Challenge, from May 13 to May 17, 2024.

The initial land cover national database of Lesotho was produced by FAO, mainly using manual techniques and very high-resolution orthophotos and RapidEye imagery. We are currently working on making a land cover product update using Sentinel-2 as primary input data and curating the old land cover data to use as training data to train a machine learning classifier. However, to create temporal composites for 2020, we would like to use the EDC Sentinelhub Batch service to quickly generate monthly or bi-monthly composites for the extent of Lesotho for 2019 and 2020. The EDC batch service is ideal as it provides a low-cost way of generating these composites for large areas. Once the land cover production exercise is complete, the plan is to develop vertical applications targeting specific land cover classes, mainly the agricultural ones, for vegetation vigour monitoring, monitoring of agricultural practices, soil properties measurements, etc. These vertical applications require monitoring over multiple years, and Sentinelhub Batch is once again the most cost-effective way of levering these long-time series of information.

Project objectives:The primary objective of this project is to estimate bathymetry from space using Sentinel-2 satellite data, with Maxar data serving as a validation benchmark. By implementing a sophisticated Convolutional Neural Network (CNN) method, we aim to accurately map underwater topography and enhance our understanding of marine environments. This approach leverages the high-resolution optical imagery from Sentinel-2, combined with the precision of Maxar data ( or other source ), to produce detailed and reliable bathymetric maps. The project will contribute to advancements in remote sensing technology, supporting sustainable marine resource management and aiding in the conservation of aquatic ecosystems.

This project aims at studying anthropogenic CO2 emissions as well as biological CO2 cycles from satellite observations using machine learning tools. The objectives are to develop algorithms to 1- Learn to detect plumes of CO2 emissions; 2- Estimate CO2 local emissions from plumes; 3- Predict monthly CO2 fluxes at a global scale. An exploratory subscription to Sentinel Hub will be very helpful, as easy to use data is basic for the project. The results of this project will be published in peer reviewed journals and presented at international conferences, the algorithms will be well documented and made public in GitHub.

The objective of the project is to estimate above-ground forest biomass in Europe. Biomass estimation is crucial to understand the amount of stored carbon in the forests and the carbon cycle. Accurate biomass estimation is a complex task, and there are several challenges of above-ground forest biomass estimations, such as the destructiveness of direct measurement methods, high cost, and time. Historical tree information, such as diameter at breast height (DBH) and tree height necessary for above-ground forest biomass calculations, are lacking spatially and temporally. Furthermore, countries do not have the same national inventory methods. Researchers use Synthetic Aperture Radar (SAR) data, such as Sentinel-1, and optical satellite data, such as Sentinel-2 and Landsat 8/9, to develop models for estimating forest above-ground biomass. The combination of preprocessed Sentinel-1 data and cloud-masked Sentinel-2 data from the Sentinel hub will be significantly helpful in developing a well­designed model to estimate forest above-ground biomass. Even though using remote sensing data can save a high cost and will consume less time than directly measuring the forest above-ground biomass, dealing with large areas using earth observation data would require lots of time to process the data. Sentinel-hub data would be beneficial to decrease this processing time. The project’s final result is one-year forest above-ground biomass raster data in 100 m resolution covering part of Europe. This forest above-ground biomass data could help researchers and scientists understand the distribution of stored carbon in forests and the carbon cycle. Foresters and forest managers could make reasonable decisions for sustainable forest management and stimulate conservation efforts. The result would be helpful for policymakers and governments to make environmental policies and regulations related to climate change and biodiversity protection.

Nowadays, it is found that Thai farmers live under challenging conditions. They face many problems, such as global warming, causing the temperature to rise, inclement weather, and severe drought. These factors directly affect agricultural productivity. In addition, farmers have to face the problem of falling agricultural prices. According to data from the Bureau of Agricultural Economics, in 2021, in-season rice had a purchase price of 8,306 baht per ton for farmers, while it had an export price of 15,730 baht per ton (data from the Thai Rice Exporters Association). The latter is approximately two times the farmers’ purchase price, causing them insufficient income. In addition, Thai farmers have relatively low yields per rai compared to Vietnam, a rice export competitor to Thailand. Data from knoema.com collects rice harvest data in Thailand with statistics of 0.47 tons per rai in 2020, while Vietnam, with a yield of 0.95 tons per rai, roughly double the product of Thailand. Therefore, it can be seen that when compared to Thailand, the world’s leading rice exporter, Thai farmers have very low yields per rai.

Therefore, I conducted a research study to develop an application to predict agricultural productivity, forecast farmers’ income from rice planting, and recommend the crops that should be planted to obtain the highest income each year. And in the future, the app will be able to monitor soil quality and provide fertilizer recommendations to help farmers save money on fertilizer purchases and get the most out of their farming. We plan to publish the first MVP at the end of 2023.

The aim of this research is to investigate and understand how multi-source satellite images can be used to monitor and analyze changes in the coastal zones caused by natural processes, and to consider the impact this has on cliff and shore platforms instability. This requires careful interpretation of remote sensing image interpretation results as well as micro-scale erosion determination by Transverse Micro Erosion Meter (T/MEM) and linking them to natural processes and geohazards. The methodology is used with the goal of monitoring, analysing and interpreting ground deformation, subsidence rates and mechanisms that lead to the erosion.The specific objectives include:

(i) Collection and processing of the long-term and short term of available data for coastal areas, including:

(ii) The Kaikoura coast, New Zealand with subsidence, shore platform erosion and cliff collapses.

(iii) The Otway coast, Australia, which covers both urban and rural environments with subsidence, shore platform erosion and cliff collapses.

The objective of this project is to classify rice fields and other agriculture fields with satellite images using an optimal model that performs semantic segmentation and deep learning in Indonesia. The project also seeks to classify the monthly growth phase to estimate and monitor growth from planting to harvesting by using satellite images from Sentinelhub. In addition, the model will be trained to estimate total production by combining survey data and big data with semantic segmentation deep learning and mass imputation. The final project’s goal is to show that satellite images and data can be used in daily life, as well as to support the government in making policies that focus on food security in Indonesia.

The objective of this project is to estimating the velocity, thickness, and volume of glaciers in the lndus Basin. This is crucial to assess the impact of climate change over time and its effects on the basin’s hydrosphere The Indus Basin is divided into upper and lower sections. Studying its glaciers is essential for understanding their current and future states. This knowledge enables sustainable water resource management, mitigates climate change impacts, preserves ecosystems, and supports hydrological modeling. These efforts are vital for ensuring the long-term viability of the basin’s water resources and for formulating strategies to cope with environmental changes.

The core objective of the EU Horizon project FAIRiCUBE is to enable players from beyond classic Earth Observation (EO) domains to provide, access, process, and share gridded data and algorithms in a FAIR and TRUSTable manner. To reach this objective, we propose creating the FAIRiCUBE HUB, a crosscutting platform and framework for data ingestion, provision, analysis, processing, and dissemination, to unleash the potential of environmental, biodiversity and climate data through dedicated European data spaces. Within this project, TRL 7 will be attained, together with the necessary governance aspects to assure continued maintenance of the FAIRiCUBE HUB beyond the project lifespan. This project’s goal is to leverage the power of Machine Learning (ML) operating on multi-thematic datacubes for a broader range of governance and research institutions from diverse fields, who at present cannot easily access and utilize these potent resources. Selected use cases will illustrate how data-driven projects can benefit from cube formats, infrastructure, and computational benefits. They will guide us in creating a user-friendly FAIRiCUBE HUB, which is tightly integrated to the common European data spaces, providing relevant stakeholders an overview of both data and processing modules readily available to be applied to these data sources. Tools enabling users not intimately familiar with the worlds of EO and ML to scope the requirements and costs of their desired analyses will be implemented, easing uptake of these resources by a broader community. The FAIR sharing of results with the community will be fostered by providing easy to use tools and workflows directly in the FAIRiCUBE HUB.

This is a request opened by Eric Doyle on behalf of Gordon Campbell who requests the use of a EDC Sentinel Hub licence for analysis – preparation of results.

The overarching objective of phase-1 of the EUROPEAN ECOSTRESS HUB (EEHPhasel, hereafter) project was to develop cloud mask (CM), land surface temperature (LST) and evaporation (ET) products (based on multiple LST and ET algorithms) for Europe and Africa using high spatial and temporal resolution information from numerous thermal infrared (TIR) bands of the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS).

The massive data volume of ECOSTRESS makes the seamless generation of LST and ET from models with different structures and parameterizations a challenging task. Due to such limitations, EEH-Phasel was developed in a centralized Food Security Thematic Exploitation Platform (FSTEP) system.

FS-TEP is connected to a Data Information and Access System (DIAS), a cloud-based system to store large volumes of data. Data products on CM, LST and ET for Europe and Africa from the EEH-Phasel were available through the FS-TEP.

The EUROPEAN ECOSTRESS HUB- update of the methodology (EUROPEAN ECOSTRESS HUB PhaSe 2, EURANUS hereafter) aims to develop and implement a novel temporal integration method for estimating daily evaporation (ET). Also, since the water use efficiency of an ecosystem indicates the amount of carbon assimilated as biomass produced per unit of water used by the vegetation, the estimation of water use efficiency is not straightforward. It needs further information on gross primary productivity. Therefore, to address the water use efficiency (WUE) of the ecosystems, EURANUS will test, validate, and simultaneously implement a new temporal integration method for estimating daily ET (from the instantaneous ET) and gross primary productivity (GPP) algorithms also to develop Europe and Africa wide GPP and WUE products. Furthermore, with the extension of the ECOSTRESS mission until 2028 and future recalibration of the ECOSTRESS radiances by NASA, EURANUS aims to reprocess all the data using the newly calibrated radiances for developing products of cloud mask, LST, daily ET, GPP and WUE for the entire ECOSTRESS mission.

In partnership with the national statistical offices and line ministries responsible for SDG implementation, the project EO Solutions for national SDG monitoring will develop innovative EO data processing and data analytics workflows exploiting EO platforms, integrating them within national systems and processes on SDGs, to showcase the adequacy of EO solutions for SDG monitoring.

From June 10-13, 2022, an atmospheric river produced approximately 13 to 130 mm of precipitation over the Absaroka-Beartooth Wilderness in Montana, resulting in an unprecedented extreme flood event with extensive hillslope and valley disturbance in parts of the Greater Yellowstone Ecosystem, including the Custer Gallatin National Forest and Yellowstone National Park. For example, in the East Rosebud Creek watershed, erosion and channel alteration significantly damaged infrastructure disrupted local economies, and altered ecosystems. Climate change exacerbates hydrological extremes and associated large-scale disturbances such as the June 2022 event, highlighting the need to understand landscape resilience. Resilience frameworks are often used to evaluate system responses to disturbances; in the context of rivers, a resilience approach provides a robust way of assessing how different fluvial units resist and adjust to floods and linking fluvial response to infrastructure, management, and restoration. Few studies, however, have quantified or modelled resilience pre and post-large flood. Using Machine Learning algorithms, we will predict how rivers on a reach scale will respond to significant disturbance events in the near future as climate change continues to become a more critical factor in environmental concern. This resilience model will aid in post-disturbance land and river management practices and restoration efforts to better understand how to prepare for future hydroclimatic extreme events.

This project aims to investigate whether we can benefit from using Sentinel-6A high-resolution RAW data for the computation of SAR spectra over certain areas where swells dominate. To this end, fully focused SAR RAW and RMC (nominal acquisition mode globally) L1b data will be analyzed as described in Altiparmaki et. al 2022. The tracks and cycle numbers to be processed have been selected so that both RAW and RMC data are available. In particular, the analysis is proposed to be extensive and focus on areas with various wave/wind conditions and relative propagation angles (i.e., wave direction concerning satellite azimuth) to study the potential limitations of the method. This request regards selected segments of five tracks in coastal areas for cycles 25-27 for processing of both RAW and RMC. We will use this dataset first to investigate whether we can adequately emulate RMC data using RAW. This step is needed as insufficient RAW data are available in the open ocean where swells mostly occur. More details, such as box boundaries and track numbers, have been provided by email. A further step regards the massive processing over two large boxes selected in a) Hawaiian islands and b) New Zealand. To validate our results we use in-situ data, where available.

Lakes are one of the primary sources of freshwater, and their size variations provide information critical to their sustainable management in the backdrop of seasonal and climatic changes. Due to topographic limitation and financial constraint, it will be difficult for any country to install gauges in the Lake ecosystem. Therefore, the Altimetry satellite can assist the government to

estimate water level which will be known as Virtual station. Satellite altimetry is an innovative method, currently being used to monitor water levels over oceans and inland water bodies. In this study, multi mission altimetry satellites are being used to study the water levels of Inland water. The Manchar Lake is significant for its ecological, social, and economic value but is not monitored regularly and hence cannot be managed well. Due to the unavailability of gauge data, it is challenging to calculate Lake’s water balance directly. Sentinel3A , the SRAL (SAR Altimeter) instrument mission with short historical data, provides the water level heights for our study area from July 2016 till April 2019.

In this study, Sentinel-3 altimetry data will be used for monitoring seasonal water levels of the Manchar Lake in Pakistan. After processing of Sentinel-3 data from Earth Console, further data will be processed in ArcGIS to estimate water levels of Manchar Lake. Sentinel derived water levels will be compared with Insitu data which assist in validation of sentinel 3 data. Who will benefit from the project results: irrigation department ,public health department, community water user, national disaster authority, water managers ,researchers , environmental protection agencies etc

Thanks to the Delay-Doppler technique, the SAR mode altimeters perform superior in the coastal zone. However, it can still be affected by the complex coastal topography (i.e., harbour, semi-enclosed bay) within 5 km of the coast. Here we want to investigate the improvement brought by the dedicated coastal trackers (i.e., ALES+, SAMOSA+ and Fully-Focused SAR) in the coastal oceans of the South China Sea (100-130°E, 0-26°N). The reason why we choose the SCS as the study region is as follows. The local wind forcing and atmospheric pressure dominates the seasonal sea level cycle of SCS. At the same time, the interannual-to-decadal variability is closely related to Rossby waves driven by wind stress curls associated with the ENSO signals. In addition, the sea level trends are more significant than the GMSL rise over the same period, varying between 4-5 mm yr-1. This is because the decadal variability dominated by the PDO and NPGO climate modes masks the long-term sea level trend in response to global warming. Therefore, it is necessary to consider the effect of climate modes to understand better the impact of global warming on the sea level variation of northern SCS, which would help us improve the ability to project the sea level rise in the future. Four major activities are conducted in this study: 1) assessing the data availability, precision and accuracy for SSH estimates from both open ocean and dedicated coastal retrackers; 2) analyzing the SSH bias between different retrackers and developing a bias-removing method; 3) using the reprocessed Sentinel-3A/B and Jason-CS data to derive the sea level trends of northern SCS over the last five years; 4) observing the variation of local sea states (i.e., Significant wave height).

The primary goal of this project is to conduct a comprehensive evaluation of the processing capabilities within the GEP platform, specifically focusing on SAR (Synthetic Aperture Radar) data derived from Sentinel-1 satellite imagery. This assessment will be primarily conducted using the SNAPPING tool, a specialized software designed for processing and analyzing SAR data. The company Geoapp, which is a regular user of commercial InSAR (Interferometric Synthetic Aperture Radar) products, is particularly interested in this evaluation. Geoapp’s objective is to determine the effectiveness and efficiency of the GEP platform’s services in handling SAR data. This evaluation will be carried out from both technical and business perspectives. The technical aspect will involve analyzing the accuracy, speed, and reliability of data processing, while the business perspective will focus on assessing the cost-effectiveness, scalability, and potential market value of the services offered by the GEP platform. This comprehensive evaluation will help Geoapp in making informed decisions regarding the integration of GEP platform services into their operational workflow.Request ID

Through the application of interferometry, the characterization of the phase and coherence variations, later the application of the STAMPS algorithm I intend to evaluate the surface variations in 3 high Andean salt flats of Chile, the first salt is the Coposa salt lake which maintains a close relationship with the surface hydrology and this can be distinguished in interferograms, so I seek to establish a mathematical relationship between interferometry and the intensity of precipitation events.

The second is the Salar de Atacama where anthropic activity related to lithium mining is considerable, so there is a relationship between deformation and surface and the extraction of lithium and underground water. Finally, I study the Salar de Llamara since this is a hydrogeological system very different from the previous ones, so it is possible to restrict and contrast the conclusions previously obtained.

Who will benefit from the project results: This is a research project leading to obtaining my degree in geology in Chile

-Results format: Through a PDF document validated by the university and free of charge through the university’s platform

Through the application of interferometry, the characterization of the phase and coherence variations, subsequently the application of the STAMPS alorithm, I intend to evaluate the surface variations in 3 high Andean salt flats of Chile, the first is the coposa salt flat that maintains a close relationship with surface hydrology and this can be distinguished in interferograms, so I seek to establish a mathematical relationship between interferometry and the intensity of precipitation events.

The second is the salar de atacama where anthropic activity related to lithium mining is considerable, so there is a relationship between surface deformation, lithium extraction and groundwater. Finally, I study the Llamara salt flat as this is a very different hydrogeological system from the previous ones, so it is possible to restrict and contrast the conclusions obtained previously. On the other hand, I will characterize the backscattering coefficient of the three salt flats to see how this characteristic can influence the results obtained, contrasting with LANDSAT 8 images. With this it is possible to obtain time series of deformation, phase, coherence and backscattering coefficient, which compared with the hydrological characteristics of the system speak of the dependence of these elements with the precipitation events, the change in the direction of the winds, the drainage network and in particular anthropic activity both associated with the extraction of minerals and the pumping of underground water. This research contributes to the understanding of the dynamism of the Chilean high Andean salt flats since these, due to their geological and hydrogeological characteristics, are an important source of water resources and understanding how their surface changes provides information on how the hydrogeological system changes and it is possible to interpret how the Climate change and variations in the intensity, duration and seasonality of rainfall affect them. On the other hand, due to the geographic location of the high Andean salt flats, their access is complex and dependent on many climatic conditions, so being able to obtain information remotely is essential.

The project will address a set of various use cases for the evaluation of various geological risks:

1. Ground deformation in the Canary islands;

2. Automatic identification and classification of deformation signals;

3. Ground deformation associated to Green Hydrogen injection;

4. Ground deformation for cross-border risk assessment at European level;

5. Ground deformation caused by groundwater extraction;

6. Volcanic deformation in El Salvador;

7. Geological risks in urban areas;

8. Ground deformation induced by underground mining in active mining

areas.

In this project, we want to analyze altimetry data to estimate water level variation over small inland water bodies like small lakes and narrow rivers. We have already developed retracking algorithms in full- and sub-waveform retracking and implemented them over several inland water bodies worldwide. We want to implement those algorithms included in Earth Console/Altimetry and evaluate the performance of different retracking scenarios in front of ground-based measurements. This evaluation will determine the most robust/accurate/precise retracking algorithm. To find reliable results, those algorithms need to be tested over many case studies worldwide. The priority is to select small inland water bodies that are very challenging even for monitoring the new generation of satellite altimetry. Based on this analysis of different altimetry mission data, one can see which mission/algorithm performs better and why.

The project aims to use the Sentinel imagery for two projects related to Vegetation management in Stormwater Treatment Areas (STAs).

1. Monitoring environmental restoration projects. Based on what has been seen during the trial membership, it seems possible to track the growth of vegetation in the wetlands, and key species can be distinguished, and area and expansion rates can be measured. This is possible with areas actively planted and managed and in larger areas experiencing natural recruitment.

2. One of the major challenges to STA management is invasive species management. Invasive species can grow in the cells and float in the water pumped to the STAs. These invaders are not only a threat to the downstream communities that the STAs were built to protect, but they can also interfere with the nutrient uptake capacity of the cells. I believe it is possible to manipulate the Sentinel images to highlight more harmful species before they reach the STAs, or deep inside the wetlands where ground monitoring is complex. Tracking the location and extent of the invasives will help us devise plans for capturing and or removing them in the water distribution network before they get to the STAs. Once invasive plant populations have been pumped into the STAs, the only viable remediation is herbicide treatment. This is problematic, as the STAs are a vegetation-based system. No matter how selective the herbicides may be or how carefully they are applied, there is collateral damage and downstream effects. My goal is to utilize the imagery to identify and trap the floating nuisance plants so they can be trapped and removed from the canal system and composted or used as mulch, biofuels, etc.

Exploiting the InSAR tools from the GEP Platform for ground deformation studies in geophysical and volcanic critical contexts (earthquakes and active volcanoes) will be carried out, as it was already done during the GEP Early Adopters program. The main focus of this activity will be ground deformation studies of the Campi Flegrei (Naples, Southern Italy) caldera, currently at the yellow alert level. Validation and comparison of processing results will be carried out with data from ground-based (GNSS) networks in the area. Coseismic deformations from strong earthquakes in the World will be evaluated as well.

The Mekong Delta, inhabited by over 20 million people, is among the world’s most biologically diverse waterscapes and agriculturally productive. Still, sea-level rise, land subsidence, upstream hydropower dams, and extensive delta-based water infrastructure have raised concern due to potential impacts on the region’s hydrology. Furthermore, most of the Delta is below 2 m of the sea level. It hence is highly vulnerable to the additive effects of regional pumping-induced land subsidence and sea-level rise due to global climate change. Therefore, we plan to use the INSAR SNAPPING service for subsidence estimation.

The main objective of this project is to develop methodologies based on artificial intelligence for inference of forest ecosystem characteristics in the northwest of Spain. Sentinel 2 imagery will be acquired and used for forest stand delineation and prediction of forest characteristics, such as species composition, diversity indexes and biomass stocks of study areas for which forest data from traditional surveys are available. At least one publication in a high-impact research journal is intended as the project’s main output. Although the scope of the project is mainly methodological, if the performance of the developed techniques is good enough, in the medium- or long-term, a potential transfer of knowledge can be proposed, mainly for collaborating with the regional government (Xunta de Galicia) and with consultancy companies of the provincial environmental sector.

NatureScot wishes to maximise the use and uptake of Sentinel 2 and Sentinel 1 in mapping and monitoring habitat changes across Scotland. A particular emphasis is the detection of wildfires and managed burning, but we also want to investigate whether other factors of habitat condition change can be detected. Methods will involve configuring Sentinel Hub WMS services to view areas of known change to investigate what types of changes can be detected (e.g., perhaps rewetting after peatland restoration). Deliverables will be a better understanding of how widely applicable S2 and S1 can be to addressing our information requirements.

The project aims to leverage satellite imagery to effectively showcase various use cases for tracking crop health. These solution accelerators are designed to empower farmers with swift and well-informed decisions, ultimately enhancing yield across diverse crops. The solution architecture incorporates supplementary accelerators such as Land Cover Detection, Crop Health Monitoring, Water Stress Monitoring, Deforestation Identification, and Wildfire Detection. By harnessing metrics such as NDVI (Normalized Difference Vegetation Index) and NDMI (Normalized Difference Moisture Index), the objective is to develop a machine-learning model capable of predicting crop yield based on these indices. Additionally, the project endeavours to provide a comprehensive suite of tools and insights to agricultural stakeholders, facilitating proactive management strategies. Through the utilization of satellite imagery and advanced analytics, the study seeks to enable real-time monitoring of crop health, allowing for early detection and mitigation of potential threats such as pest infestations, nutrient deficiencies, and environmental stresses. Furthermore, the aim is to establish a scalable framework that can be easily integrated into existing agricultural practices, fostering sustainability and resilience in the face of evolving climatic conditions and market dynamics. Ultimately, the project empowers farmers with actionable intelligence, thereby optimizing resource allocation, minimizing risk, and maximizing productivity across the agricultural landscape. The strategy involves positioning the solution as a pre-commercial offering during the initial marketing phase. Once potential clients are engaged and garner interest, the plan is to transition towards utilizing Sentinel subscriptions for ongoing satellite imagery access and data acquisition. This approach allows for establishing a strong foundation in the market, demonstrating the value proposition of our solution, and seamlessly integrate with Sentinel subscriptions to further enhance our capabilities and deliver sustained value to our clients.

need

This project aims to explore and identify various applications of Earth Observation (EO) technologies for Africa, focusing on addressing the region’s unique environmental and socio-economic challenges. The project aims to assess the potential of EO technologies for supporting sustainable development, natural resource management, disaster risk reduction, climate change mitigation, and other critical areas of concern for the African continent. The project will involve a comprehensive review of existing EO applications and technologies, an analysis of the current state of EO infrastructure and capacity in Africa, and the development of recommendations for improving access to and use of EO data and tools in the region. The project’s ultimate goal is to contribute to the development of a more sustainable, resilient, and prosperous Africa through the effective use of EO technologies.

This project revolves around the exploration and visualization of Earth System Data Cubes, where the primary focus is on predicting time series. In particular, the project explores temperature and precipitation patterns across diverse spatial and economic regions, to analyse patterns of climate anomalies and extreme events over time that may be subject to change due to climate change. The goal is to spot which regions of the world show the most significant change patterns. The project also serves to educate students on using programming languages and advanced techniques to analyse substantial spatio-temporal datasets via machine learning. Simultaneously, students develop an understanding of big data analysis while formulating a research question and seeking its solution through novel computational methods tailored to reveal patterns and insights from the data. In addition, students learn to apply for and efficiently utilize cloud computing resources to facilitate their analyses.

Customized EO Information Layers were designed, developed, tested, and implemented on ONDA DIAS for selected AOI in Burkina Faso. We discussed integrating previously developed services into UPMIS with our client in Uganda, the Ministry of Water and Environment, with a final goal of monitoring Sustainable Development Goals. The main reason for the change is that existing build-up services based on optical classification methodology need to be improved to support up to 1000 settlements already in UPMIS. Furthermore, we plan to upgrade the existing methodology with a machine-learning approach and select the most appropriate method. When monthly build-up products are calculated, we must integrate them into UPMIS. Therefore REST-API’s need to be further developed. The primary beneficiary of the project results is the Ministry of Water and Environment, Uganda, and later also the general population with improved drinking water supply services.

Extreme Citizen Science, or ExCiteS, is a research group at University College London which develops and contributes to the guiding theories, tools, and methodologies that will enable any community to start a Citizen Science project to address issues that concern them. Using an interdisciplinary research approach, ExCiteS aims to provide any user, regardless of their background or literacy level, with tools that can be used to collect, analyze and act on information according to agreed-upon scientific methods. Several of the ExCiteS projects focus on participatory sensing, monitoring, and modeling activities, with communities deciding what measurements are taken and how they are analyzed so that they can participate in and lead subsequent decision-making and actions. ExCiteS’s vision is to change the current state of the art by developing technologies to enable laypeople to understand and manage their environment with established scientific methods and models.

Extreme Citizen Science: Analysis and Visualisation project (ECSAnVis) is a five-year, €2.5M project funded by the European Research Council, which aims at the development of geographical analysis and visualization tools that can be used successfully by non-literate people and any other community in a culturally appropriate way, that further fit their needs and social practices. ECSAnVis case studies currently include # The Ju/‘hoansi in the Nyae Nyae Conservancy (Namibia), who collect data on a wide range of fauna and flora as part of their ongoing community-based natural resource management work; # Local fishermen in Pantanal wetlands (Brazil) where people collect data of their local fishing and other resource management practices; # Local farmers in Ghana, who collect data to capture and share their local knowledge of weather prediction; # Maasai pastoralists communities in Narok county (Kenya), which collect data of the medicinal and other properties of local indigenous flora. Small-scale farming communities in Elgeyo-Marakwet county (Kenya), which collect data on land uses and farming issues they face; # Baka and Bantu-speaking communities in Dja Biosphere Reserve (Cameroon), which collect data to tackle: wildlife crime, illegal logging, species monitoring, resource mapping, abuse by forest guards, and record births and deaths. # Agro-pastoralist communities in South Ethiopia.

The objective is to use high-resolution satellite imagery to map farmland habitats with high accuracy to assess habitat cover at a farm scale. Methods: Develop habitat mapping algorithms for use on higher resolution imagery (~1m) to create habitat maps at a farm scale. A polygon of the farm boundary will be obtained from the LPIS system, which will be used to create an AOI request for high-resolution imagery. The habitat mapping algorithm will then map the farmland habitats. We will derivable an app in which a farmer can request to have their farm mapped including the percentage cover of habitat on the farm as well as a breakdown of the different habitat types (woodland, wetland, grassland, etc).

Farm0C is a Science Foundation Ireland funded project to demonstrate that intensive Irish dairy farming can become climate neutral and biodiversity friendly. Life cycle assessment, remote sensed habitat mapping and digitalization will be combined to create an app that assesses a farm’s emissions and biodiversity. The app will further suggest best practice and technology needed to reduce farm emissions to climate neutrality while also providing bespoke recommendations as to how to increase farm biodiversity. Using high resolution satellite imagery (0.5 m- 10m resolution) it is possible to pick out linear habitat features on farms. Linear habitat features comprise a majority of on farm habitats in Ireland and so are essential to map in any farm-scale habitat mapping exercise. EU legislation (see EU Biodiversity strategy 2030) is moving towards requiring 10% of farm area to be managed as ‘high diversity habitat features’. Accurately quantifying farm habitats requires the development of high resolution habitat mapping that can reliably map linear features. The first objective of work package 2 of the Farm0C project is to develop and train machine learning algorithms to map farmland habitat at unprecedented resolution (0.5m – 10m) to allow for accurate habitat extent estimates. Remote sensed habitat maps will be tested and validated by comparison to on the ground farm habitat surveys. The deliverable of this objective is a scalable, reliable, farmland habitat mapping algorithm using high resolution remote sensed data to allow farm scale habitat mapping in Ireland. Once tested and validated in Ireland, it will be extended to other dairying and livestock systems in Europe. The second objective of work package 2 is to build farm scale natural capital accounts based on the SEEA ecosystem accounting framework. The habitat maps derived from remote sensed imagery will be used as habitat extent accounts. Condition assessments will be attempted based on remote sensed imagery using variables such as age, width and if possible, height.

Remote sensed condition assessments will be validated on the ground to assess the feasibility of remote sensed ecosystem condition estimates. Finally, ecosystem extent and condition accounts will be transformed into ecosystem service accounts. The main ecosystem services which will be investigated are carbon sequestration and storage, grass productivity, water pollution remediation and biodiversity conservation. Remote sensed imagery will be used to explore to what extent these ecosystem services can be measured remotely, the goal being to develop models that can reliable measure ecosystem services that can be scaled to many farms. The final deliverable of Farm0C project is the app. The farmer is the end user, such that the farmer can request that their farm be mapped, resulting in habitat extent and condition accounts of the farm being produced from satellite imagery using the models developed in the project. We also envision that our models and IT will be of interest to regulators, there will be a need to monitor compliance once area-based farmland conservation targets become part of the Common Agricultural Policy.

The primary objective of the project is to develop a comprehensive analytics tool that utilizes multiple crop health indices to create a growth stage-agnostic crop health score. This innovative tool aims to provide growers with precise and actionable insights into crop health, enabling them to optimize water and chemical usage, thereby reducing food production costs. The added value of this project lies in its potential to significantly enhance sustainable agricultural practices. By minimizing the unnecessary use of resources, the tool will help in promoting environmentally friendly farming while simultaneously improving crop yield and quality. This dual benefit will contribute to more efficient and cost-effective food production. The primary beneficiaries of this project will be growers and agricultural managers who will have access to this advanced analytics tool. They will be able to leverage the crop health scores to make informed decisions about irrigation and chemical applications, leading to better resource management and cost.

This project’s objective(s) is to deploy and test the Field Delineation project developed by Sinergise. In addition, we would like to see if it is suitable for Romania and if we could use it. The field delineation marker produces boundaries of the agricultural parcels by clustering the agricultural pixels according to spatial, spectral, and temporal properties. The delineated boundaries can aid the farmers in speeding up the declaration process and the paying agencies to better monitor changes in agricultural use. The marker automatically outputs polygon vectors defining agricultural parcels based on Sentinel-2 imagery, although the marker can be seamlessly adapted to work with any remote sensing imagery as an input. The marker was developed as part of the NIVA H2020 project and thus far has been used for generating parcels for paying agencies, insurance companies, and research centers for several regions in Europe and North America.

This project aims to investigate the added value of field delineation to my exploratory research in Personalized Agriculture. The study is funded by Interpretable AI, a research company exploring new ways of making data-driven practice recommendations to farmers across the globe. Solving the field delineation model would help us derive more accurate farmer recommendation models.

The objective of FieldAI is to create state-of-the-art Artificial Intelligence solutions to optimize yield in agriculture by utilizing satellite imagery. The project studies deep learning methods that capture the complexity of the factors influencing plant growth, in order to detect growth issues in farms during the growth period, predict yield on a per-field basis as well as on European scale, and provide actionable recommendations to the farmers. This work is an industrial PhD project running from 1. April 2019 to 1. April 2022, in collaboration with Aarhus University and FieldSense A/S, where the funding comes from Innovation Fund Denmark. The goal is to utilize ESA provided imagery for researching agricultural applications as part of the research project. The contribution from OSEO OGC is to provide access to an EO data repository containing a long-term archive of processed EO data, such as through the Sentinel Hub WCS. This would allow to easily access the data required for the research without the burden of data preprocessing and storage which is normally. In particular, the plan is utilizing Sentinel-1 and Sentinel-2 imagery from primarily Denmark, and to some extend the rest of Europe. This data serves as input for training neural networks in order to find effective network architectures that provide higher accuracies at different time steps during the growth cycle of crops. So far, it has been used raw Sentinel-2 from the AWS S3 bucket which shows promising results on a local test set, and afterwards it follows a further improve performance as well as the reliability of testing through direct and easy access to more EO data from other areas and satellites without the need for complexities such as mosaicking.

ToMap is a mapping and monitoring service developed for the Italian consortium of the tomato transformation industry, providing crop type classification and yield and phenology forecasts using machine-learning and simulation techniques. To deliver high-quality crop maps of interest and then carry on with the monitoring, manual digitizing of field polygons by photointerpretation is currently required in our workflow, which is indeed time and resource-consuming. Therefore, we intend to assess if the automated FieldDelineation service provided by Sentinel-hub through EuroDataCube can fully or partially replace the manual polygon drawing currently performed. If this method is proven to be a viable strategy, it will allow us to focus more resources on improving AI and modelling solutions and move faster towards our goals of involving in the platform also tomato producers by providing targeted farming insights.

The project aims at validating the MODIS automatic fire burnt areas for northern Australia using high-resolution satellite data such as Sentinel and Landsat. The fire burnt maps are used to operationally carry out early season fire activities by stakeholders such as indigenous rangers. The overall goal is to reduce carbon emissions.

The North Australia and Rangelands Fire Information (NAFI) website was developed in 2002 by the community of fire researchers and managers involved in the Tropical Savannas Cooperative Research Centre. Their objective was to facilitate access for the general community of northern fire managers to regularly updated maps of active fires and burnt areas in the open landscapes of the Australian rangelands. Active fires are shown via hotspots which are updated every few hours. Hotspots are produced by thermal (heat) sensors on several different satellites. They are usually accurate to within 1km of their actual location. However, due to how the heat image is converted into hot spot points, one large fire could show up as many hotspots, or many smaller fires could appear as one hotspot. Hotspots are sourced from Landgate Western Australia (from ΝΟΑΑ and NASA satellites) and Geoscience Australia (from NASA satellites). Burnt area maps show you what has already burnt and are updated weekly or so throughout the year. They are produced by comparing two different satellite images, generally 1-2 weeks apart, and identifying only the areas that have been burnt. On NAFI, the burnt areas are displayed in different colours depending on the month they occur. These data are produced via several satellites that pass over Northern Australia multiple times daily. Burnt area maps are derived from MODIS satellites. These sensors look at an on-ground pixel size of 250m, have a more significant spatial extent (covering the whole of the ΝΤ in one or two images), and pass over the same spot on the Earth’s surface twice.

This research is the first attempt to create a national-level burned area data set for spring-time burning for the Russian Federation. The participatory mapping will be made possible using a developed platform using recruited experts and volunteers. Additionally, we will calculate greenhouse gas, short-lived climate pollutants, and emissions that negatively impact air quality. The emissions will be reported at the regional level (oblast, okrug, and krai) and the monthly scale. The project is funded by Greenpeace Russia.

To adapt to climate change, environmental management practices could benefit from adopting a framework that accounts for increasingly extreme hydroclimatic events that threaten billions of lives and cost hundreds of billions of dollars in infrastructural damages. Fluvial geomorphic resilience provides a promising framework that describes the ability of a river to absorb natural or anthropogenic disturbance effects through intrinsic fluvial processes. However, this framework is still relatively new to the geomorphology field, with little to no study in relation to disturbance events (i.e., floods) impacting the fluvial environment. Drawing upon a framework proposed by Fuller et al. (2019), this project studies alluvial mountain rivers through the lens of a river system’s resistance and recovery to large flood events. By measuring geomorphic change through time, this project aims to predict which metrics best influence resilience using a Bayesian Multilevel Model. Leveraging extensive multitemporal high-resolution satellite imagery available through various geospatial platforms, river hydrographs, and other remote sensing data, we plan to gather a large dataset encompassing rivers affected by flood events worldwide including parameters such as slope, river type, geology, and potential bed-load transport. The analysis seeks to identify fluvial characteristics that could enhance or promote natural resilience for alluvial mountain rivers to contribute to strategic infrastructure planning along reaches susceptible to disturbance.

Vegetation and green open spaces in urban areas have a beneficial effect on human health and well-being. People perceive areas with an abundance of trees, parks, lawns and shrubs more favourably than areas with sparse elements. Cumulatively these effects are proven to have reduced stress hormone levels, lowered blood pressure, improved cognitive abilities and much more. Additionally, such areas improve property values, increase the revenue of adjacent businesses and attract tourists.

Using very high-resolution satellite imagery, we can create a grading framework for the restorative effects of outdoor environments by referencing them to on-ground survey information. This study will attempt to connect physical environmental features to qualitative aspects of the outdoor environment, specifically vegetation and green open spaces. The results will provide valuable insight into how we can use satellite imagery to locate such areas in the efforts to preserve and protect them. Due to climate change, urbanization and movement restrictions during the pandemic, such places have become of utmost importance in providing ecosystem services in densely populated areas. The project is a pilot study within collaborative efforts for continuous monitoring of the Swedish environment, aiming to expand further from agricultural, aquamarine and forest environment towards including the urban environments with qualitative aspects, as such indicators are essential for human well-being in cities. Depending on the success, it could develop a methodology for future assessments and monitoring and integrate it into the environmental monitoring routines.

The project aims to produce an application based on spot satellite data + supplementary data (like weather data) to provide useful information to management needs in agriculture. Various sections can benefit from this application. Mainly and primarily, the target is growers. Growers can use this service in different ways. The first platform which is going to be developed will be web-based. The second one is mobile-based. A lot of valuable information regarding the cultivated land would be delivered. Using this information, they would make better management decisions. These decisions eventually lower the use of different inputs, such as pesticides, herbicides, fertilizers, and so on. We also believe satellite data can help farmers with higher crop performance. Another group would benefit from this product: advisers and consultants. Using this system, the efficiency of advising would be increased because they have access to the same information and analysis. In addition, they would have all customers (which are farmers) and their fields on one convenient platform. Also, the costs of scouting may be reduced to a considerable extent.

The Forest Carbon Monitoring (FCM) project investigates the best approaches for forest biomass and carbon monitoring. It develops a system prototype meeting the requirements of different forestry stakeholder groups. The monitoring system will utilize the Forestry TEP platform, and it aims to provide means for forestry stakeholders to respond to increasing carbon monitoring and reporting requirements. Forestry companies may want to monitor carbon balance for forest sustainability requirements, carbon compensation schemes, forest certification or consumer demands. Administrative authorities can produce information for national and international reporting. The system will also enable European-wide analyses of distribution and changes in forest biomass and carbon. The system’s focus is initially in Europe but can be expanded to other continents. The project is funded by the European Space Agency (ESA) and lasts two years (July 2021-June 2023). It is coordinated by the VTT Technical Research Centre of Finland, with eight partners (AFRY, European Forest Institute, Gamma Remote Sensing, GFZ German Research Centre for Geosciences, Natural Resources Institute Finland, Satellio, Simosol and the University of Helsinki). Ten user organizations are cooperating with the project consortium to develop optimal monitoring approaches for different types of user groups. Private companies, regional and national agencies, and international organizations are represented. The demonstrations are designed to meet the needs of the users. After the initial stakeholder requirement review, the goal is to compare and evaluate several forest biomass and carbon monitoring approaches during the project’s first year. During the project’s second year, demonstrations from private company estates to European-level mapping will be conducted and validated. The partner companies will receive output products and analyses to meet their forest biomass and carbon monitoring requirements. The lists of products (incl. forest structural variable maps, biomass and volume increment maps, and change monitoring) were defined together with the user partners during the project’s first months. Overall, the aim is to develop a system that allows service providers in the future to provide forest biomass and carbon monitoring services using the forest carbon platform utilizing Forestry TEP. The platform will enable different types of users to request data that meets their purposes. The datasets will be produced with methods that best meet the users’ needs.

The Forest Carbon Monitoring (FCM) project (https://www.forestcarbonplatform. org/) has investigateci the best approaches far forest biomass and carbon monitoring and develops a system meeting the requirements of different types of forestry stakeholder groups. The focus of the system is initially in Europe, but it can be expanded to other continents in the future. The project is funded by the European Space Agency (ESA) and lasts far two years (July 2021-June 2023 ). Eight user organizations have been cooperating with the project consortium in the development of opti mal monitoring approaches far different types of user groups. Demonstrations were conducted far each of the user partners and user partner companies were provided with output products and analyses that aim to meet their forest biomass and carbon monitoring requirements. Overall, the aim was to develop a system that allows service providers in the future to previde forest biomass and carbon monitoring services using the forest carbon platform utilizing Forestry TEP. The platform enables different types of users to request data that meets their purposes. The datasets are produced with a selection of methods that best meet the needs of the users.

The Forest Carbon Monitoring (FCM) project (https://www.forestcarbonplatform.org/) develops a system to meet the forest biomass and carbon monitoring requirements of different types of forestry stakeholder groups. The monitoring system utilizes the Forestry TEP platform, and it provides tools for a wide range of forestry stakeholders (private, administrative, and international organizations) to meet their forest biomass and carbon monitoring and reporting needs. The project is funded by the European Space Agency (ESA). Following a two-year main phase, the 18-month continuation started on May 15th 2024 and lasts until November 2025. The continuation of the project addresses identified technical shortcomings and measures to close gaps between user expectations and the current approach. The overall approach is highly user-oriented. The system and algorithm improvements will reduce the barriers to onboarding the services highlighted by the users in the main project evaluation. All the work culminates in five use case demonstrations to be implemented in cooperation with five user partners. The project is coordinated by VTT Technical Research Centre of Finland, with seven partners. Terramonitor is responsible for the Sentinel-2 composite image tool implementation and mosaic creation.

The objective(s) of this project is to analyse the Sentinel-1 time series with the usage of Recurrence Quantification Analysis (RQA) for the detection of forest change. The methodology has been proven as promising on small scales and the aim of this project is to apply it for larger scales. https://doi.org/10.1109/JSTARS.2020.3019333This project is part of the C-Scale early adopter use case PangeoJulia and we showed, that the algorithm upscaling works for single tiles. We would like now to apply the change detection algorithm for the whole europe and single test areas in North America to detect the influence of the 2018 drought on the state of the forest. The overall aim is to provide a forest change detection product based on Sentinel-1 and to compare this against forest change maps based on Sentinel-2 data to confirm the forest loss in europe with an independent dataset.

Α range of natural and anthropogenic disturbances with various regimes and intensities affect forest ecosystems worldwide. Information, notably maps, of forest disturbances are of interest for at least two reasons: a basis for ecological studies and a tool in forestry decision-making and management. Forest disturbance is a global issue with implications for the sustainable management of forests, which is one of the aims of the United Nations Sustainable Development Goal. For example, Challenge L3 is related to better understanding the pressure caused by anthropogenic dynamics on land surfaces (use of natural resources and land-use and land-cover change) and their impact on the functioning of terrestrial ecosystems. The forest disturbance issues are particularly interesting in Bulgaria, where over one-third of the area is covered by forests. The main objective of the proposed ESA project entitled “FoReS” is to develop a set of forest disturbance prototype products, which provide specific and essential added value for the stakeholders, optimal for the national level inventory spatial resolution, namely: forest disturbance type product, post-fire forest regrowth product, and forest disturbance severity product. All map products will be focused on natural (abiotic and biotic) disturbance agents and used by national forestry authorities, enterprises, scientific organisations, and NGOs.

The current NoR Proposal aims at supplementing the EO-data workflows, which represent the core processing of the FoReS project. Namely, it aims at accessing, through the available APIs, the real-time processing capabilities of the cloud-based computing platform and specific datasets relevant to the FoReS project.

As a part of a teaching program from a public Vocational Training Center in Spain, the promotion and knowledge of Copernicus data is one of the objectives of the dissemination, publicly available from the eforestal Twitter account. The main study carried out within this program is the analysis of forest forest fires in Spain. The present project requests the service offered by EDC Sentinel Hub, as it is essential for fast and effective access to data.

The Forest Flux project (2018-2021) is funded by the European Union (Horizon 2020). The project creates and pilots cloud-based services for the prediction of structural forest variables and carbon assimilation. Forest Flux takes advantage of the rapid increase of Earth Observation data from the Copernicus program and developments of cloud computing technology. It implements a world-first service platform for high-resolution maps of traditional forestry variables (like height and basal area) together with forest carbon flux estimates (like net primary production). The services developed in the Forest Flux project are implemented in the Forestry TEP platform, allowing users to improve the profitability of forest management while taking care of sustainability. The project expands the platform service offering and allows web-based access to carbon flux modelling that is unrestricted by country boundaries. The platform enables easy commercial interactions with players of different sizes and backgrounds.

Our EU Interreg project operates within the region of Botnia-Atlantica in central Sweden and Finland. It supports regional businesses to develop opportunities within the “new space” economy and involves ecosystem-building support to commercialize existing space-based data. A component of our project is an end-to-end satellite mission technology demonstration process named “KvarkenSat”, having hyperspectral imaging, positioning, AIS and radio communication capabilities.

To bring the region’s forestry sector and new technological developments together, the “Kvarken Space Economy” project is organizing a “hackathon” in March 2022 called “KvarkenSat Innovation Challenge 2022 on Sustainable Forestry”. (https://ultrahack.org/kvarkensat-innovation-challenge-2022). This challenge will network the regions forestry sector actors with the latest ideas from research institutions in Finland and Sweden ( Luonnonvarakeskus (Luke) and Svenska Landsbruk Universitet (SLU), respectively). The individual, student and company start-up participants in the challenge will work with remote sensing observations and spatially dependent modeled results to address four research fronts important to the participating forest sector actors. The Forest-TEP platform will be demonstrated and offered as a platform for developing solutions during the challenge.

The four themes include supporting more timely estimations of soil moisture, preventing damages caused by spruce bark beetles, learning how to reduce damage to the forest ground caused by forest machines and developing new digital concepts for the forestry value chain.

The participating forest sector companies will have the possibility to work with the innovation challenge participants and their solutions and advance them within their companies.

The FORESTIFY project investigates the use of satellite imagery & blockchain technology to locate optimal locations for and monitor reforestation projects around the globe. Provides a solution to the deforestation problem by giving people, organizations and governments flexible and transparent tools to participate in reforestation projects in a transparent and trustworthy way. The specific challenges that try to solve with satellite imagery are:

– Can we assist in identifying sites under agriculture that should preferably be set aside for reforestation projects?

– How early after seeding/planting can we detect reforestation?

– Can monitor the regrowth of new forests and can we measure regrowth stages from seedlings over young forests till mature? Can we detect land use conversion from recently planted forests to agriculture?

The methodology is based on local/relative image analysis. The scope is to develop methods that are global by design. The main reason for opting for OSEO OGC services is the efficiency, as access to time-series of data for small areas and scattered globally is needed. OGC WCS services support very efficient data access allowing to focus on the strengths. The use of Scihub in the past made it possible to set up automated download & preprocessing (including ESA SNAP) using Python. The drawback of this approach is the relatively higher complexity of the code, the needed bandwidth and processing power to download full scenes and preprocess them. The tests were run using OSEO OGC WCS and a demo account to get a first impression of time-series of data for different regions in the world with promising results. OSEA OGC WMS was used to explore the imagery over time to assist in interpreting results and events (e.g. using QGIS plugin). Time-series of agriculture, reforested areas, young forests and old forests were extracted and compared. Land suitability for reforestation is based on multitemporal vegetation index analysis (e.g. cumulative VI). Spots are identified within the agriculture acreage that shows a systematic underperformance compared to its surroundings. Those sites are preferred locations for reforestation projects having minimal impact on productivity for the farmer while maximizing the environmental impact of the reforestation project (e.g. soil). Early detection of reforestation will be studied with both optical (spectral detection of vegetation) and SAR (land disturbance) imagery. For reference sites, time-series are analysed and multiple binary change detection methods are tested (e.g. logistic regression). In combination, monitoring of regrowth is studied based on regional comparison (similarity measure) with existing land-use types. This concept is driven by the fact that spectra-temporal signatures of different land use classes are location specific, eg. a forest in Brazil will have different characteristics compared to a forest in central Europe. FFT and/or wavelet decompositions are tested, combined with statistical similarity measures of pixel vectors in the newly created feature space. This methodology is also used to identify abrupt changes and red flag areas where the “reforestation signal” is lost due to reconversion to agriculture for example. The described research results in novel algorithms and operational methods that allow to use ESA Sentinel imagery to support the main goal: bring trust and transparency to reforestation initiatives.

High-resolution surface albedo is a key parameter that affects the Earth’s radiation budget. It is of critical interest to land-atmosphere interaction studies for weather and climate forecasts, and it is also a fundamental measurand for partitioning energy at the Earth’s surface related to the detection of water stress and soil moisture. Surface albedo products need to be generated on a regular basis, so that continuous measurements of the radiation budget can be ensured. The usual method for retrieving land surface albedo tries to populate the BRDF polar plane with as many observations as possible by either acquiring near-simultaneous multi-angle measurements such as from the NASA MISR instrument or from repeat measurements over a time window from different view and solar view zenith and azimuth angle from a sensor with a sufficiently wide swath-width such as Proba-V (2,250km), NASA MODIS (2,330km) or the NOAA/NASA VIIRS (3,060) instrument. However, all of these retrievals take place at a spatial resolution of 100-600m (Proba-V) which is too coarse for most land surface vegetation applications such as Forestry or agriculture. In this study, we employ coarse resolution BRDF/albedo (500m) from MODIS or VIIRS together with atmospherically corrected Sentinel-2 MSI to generate 10m/20m diurnal, daily, 2-3/daily or 5-daily retrievals of whole Sentinel-2 tiles over a limited time-frame (4 months) of 4 Sentinel-2 nominal scenes (100 x 100km). The processing chain includes innovations for deep learning-based cloud masks (up to F1=95%), Sensor Invariant Atmospheric Correction (SIAC) which uses the MODIS BRDF to generate a surface BRF with an associated uncertainty and a search for end members from each S2 multispectral scene using the 7 common spectral channels with MODIS or VIIRS to calculate an albedo-BRF ratio from the coarse resolution ratio which is then employed to generate albedo at the S2 resolution. GCOS 2016 specifies a measurement uncertainty of 5% and a spatial resolution of 50m. We are exploiting the 5-day repeat of S2A + S2B and the much higher resolution to generate a 10m/20m spectral and broadband (VIS, NIR and SW, shortwave). The processing chain and ATBD were completed recently, and a presentation was made of the overall system, its products and verification presented at the ESA VH-RODA workshop held online from 20-23 April 2021. The verification included a mixed forest and desert site for SW albedo and one of the two RADCALNET sites (Namibia Gobabeb) with a CIMEL-318T capable of making BRDF/BHR measurements simultaneous with every Sentinel-2 overpass for 18 months. The latter indicated agreement to within 6% for one sample date.

Forestry Thematic Exploitation Platform (Forestry TEP) enables commercial, research and public sector users in the forestry sector globally to efficiently access satellite data-based processing services and tools for generating value-added forest information products. As a newly established platform service provider on the NoR, we are looking forward to funding the required IaaS resources based on user-specific revenue in the future. We serve several user groups, including Forest industries and large forest owners; EO & Forestry Service Providers; Research Organizations and Universities; Intergovernmental Organizations and NGO’s; National Public Organizations. Our current key users are from projects such as the H2020 Forest Flux and the ESA Forest Digital Twin Earth Precursor, as well as many others.

The project aims to:

• Process and make available ten years of Geophysical Doppler shift from Envisat ASAR to the oceanographic community.

• Establish routines to enable future exploitation of SAR Doppler from Sentinel-1.

• Establish a time series of SAR Doppler from 2002 onwards.

• Investigate the possibility of, and the effect of, assimilation of SAR Doppler shift into METs ocean model.

• Deliver a new high-resolution dataset of the inter-annual, seasonal and monthly mean ocean circulation in the Nordic Seas that will:

o Advance the understanding of the relationship between surface circulation and the magnitude of ocean volume transport, particularly for dominant current systems and across straights and gaps.

o Provide new insight into the energy content and exchanges between the mean and varying ocean circulation.

Mapping land use and cover based on orbital images has several applications and is one of the main tools for agricultural monitoring. However, heterogeneity, temporal dynamics and cloud cover make mapping difficult. This work aims to merge the images of the Sentinel-1 and Sentinel-2 satellites at pixel level, for the mapping of agricultural areas, in two study regions with different characteristics, with crop and pasture rotations. The image resulting from the merger will be evaluated through statistical analysis and the Universal Quality Index. Machine and deep learning techniques are used for classification, time series classification of the Sentinel-1, Sentinel-2 images and the result of the merger between both. The image resulting from the merger intends to provide a better subsidy to the execution of the classification in both areas of study.

In light of the ESA project Gamma2Cloud and the recommendation of the technical office Marcus Engdahl, the present request ICT resources wants to test the Gamma Naught implementation in SNAP at three different pre-defined cloud providers (EODC, AWS and CREODIAS). The run and benchmark of the workflow on testbed VMs (Linux) uses 16 CPU, 64 GB RAM and 250 GB storage and would need access for one month. The results are used to report to ESA about the current gamma processing implementation in SNAP (with direct communication to the SNAP developing team) and provides a roadmap for better use of cloud resources.

• The overreaching project aims to assess the demographic properties of medium-sized wildlife species in space and time. The current project focuses on two gazelle species.

• Gazelles detection using very high-resolution satellite imageries via cross-referencing annotations with on-ground visual data detection in a controlled and enclosed area.

• Create a GT dataset of gazelle’s annotation in satellite imagery.

• Design a CNN model to detect and count gazelles in satellite images to evaluate population size in larger.

• Development of tools to assess gazelles’ population size and structure, using aggregation of satellite detection, on-ground detection, classification and identification data and updating and collected ecosystem knowledge.

• Propose a routine to adjust the developed methodology to detect and count additional medium-size species using very high satellite imagery.

Estimating wildlife population sizes is fundamental for conservation biology, yet challenging. Under the umbrella of the AIi4biodiversity project, this work focuses on enhancing the capacity to estimate gazelles’ population sizes in natural areas where their populations are unknown. We will study two gazelle species in a controlled and enclosed area in the southern desert regions of Israel, using Pleiades NEO satellite data with spatial resolution < 0.5m. To do so, satellite imagery will be aggregated and integrated with spatiotemporal on-ground visual data collected by motion-triggered cameras. The collected data is being used for training data of diverse CNN-based detectors (YOLO, Megadetector, DeepLabCut) aiming to refine the detection, classification and identification of local species and sub-species currently explored under the project framework. In the first phase, we seek to estimate the population sizes of two vulnerable gazelle species: Arabian gazelles (Gazella arabica) and Dorcas gazelle (Gazella dorcas) kept in the enclosed area. The next phase will extend this approach to free-roaming populations.

The GDA APP activity’s implementing consortium is being led by MEEO (Meteorological and Environmental Earth Observation), an Italian company devoted to the implementation and development of products and services related to remote sensing of the Earth-Atmosphere system. The consortium partners include: EarthPulse, an organization that utilizes Artificial Intelligence to simplify complex Earth Observation data; Geoville, a company focused on the development of new data processing systems for environmental monitoring based on satellite data; as well as GMV, a company specializing in applications and critical software solutions. This activity consists of designing and implementing a flexible and versatile analytical environment within the GDA program. Powered by European public cloud resources, this environment aims to target the specific requirements, information needs and working practices of International Financial Institutions (IFIs) and their clients and end-users in the context of international development activities.

We aim to develop our MVP application for implementing automated ecolabeling for the food identity of crops. This is a pre-commercial project for developing research and testing our technology development for building our prototype and advancing our Technology Readiness Level. We are expanding our prototype on remote monitoring utilizing high-definition satellite data for crop identification powered by zero-knowledge-proof blockchain technology.

Objectives:

Develop a prototype for integration of remote monitoring precision agriculture and blockchain Identity.

Enhance user interface and user experience UI/UX.

Ensure the solution aligns with market needs and user expectations.

Actions:

Develop prototype integration to HD Satellite API for full functionality and Food Identity traceability blockchain oracle using Polygon zkEVM infrastructure.

Identify areas of improvement based on user feedback, interviews, and market data.

Perform a preliminary assessment of data privacy compliance.

We aim to support small farmers globally by providing affordable technology solutions to increase crop yields and improve livelihoods by having an eco-label product to reach better markets. Economically, to improve farm incomes, stimulate local agricultural ecosystems, and reduce poverty and inequality. Environmentally, encourage sustainable farming practices, conserve resources, and support biodiversity—alignment with several UN Sustainable Development Goals, including poverty reduction, food security, and climate action. We express a willingness to help reduce the gender gap in agriculture, particularly benefiting women with access to technology.

The objectives of the project include: 1. Enhace the preservation, evaluation and use of olive genetic resources for improving the olive breeding and the delivery of new varieties

2. Leverage the information available through the development of a smart and user-friendly interface for the end-users 3. Predictions section: to provide information with regard to the predictable varieties’ behaviour in response to the different climate change scenarios – mapping the risked zones per each variety to avoid future economic losses.

4. We aim to determine and compare 30 olive genotypes’ behaviour in five different countries with very different environments and pedo-climatic parameters, in order to further develop breeding strategies taking into account the “environment-climate” variables. Furthermore, by knowing the Environment X Genotype interaction, we will be able to anticipate the climate change effects and select the olive progenitors for future breeding processes to obtain new resilient varieties. Specifically, we aim to: a. Determine and compare among 5 GBs the olive tree phenological parameters (blooming, fructification and maturation). b. Compare the varieties production and olive fruit and/or oil quality. c. Compare the

pests and diseases indexes – susceptibility scale in different zones and climates. d. Correlation of the aforenamed parameters with the climatic variables. e. Design breeding guidelines and strategies to face the future climate change scenarios.

5. Farmers section: i) to help determining the kind of variety to be planted in a specific geographic zone according to farmers’ necessities such as crop production, diseases risk, water availability and climate parameters; ii) to make available a free mobile app that will be able to determine the kind of disease that has affected the olive tree just by processing a mobile picture and to develop

online risk alerts for the rest of users by utilizing machine learning.

6. Breeders section: i) to provide in real time the best combination of olive progenitors for a specific breeding programme by implementing machine learning technology. ii) to provide a user-friendly but advanced mobile app that would be able to accurately identify through image processing an olive variety based on the morphological descriptors.

7. Development of a direct communication line between Germplasm Banks (GBs) and End-Users in order to ease the genetic material exchanging and speed up the collaboration between public and private sectors.

This project aims at an improved understanding and prediction of melt ponds occurring in the Arctic Sea ice using satellite data and Artificial Intelligence (AI) methods. Melt ponds have great importance in the context of climate change and the Arctic energy budget since they affect albedo and contribute to further ice melting. Given the current scarcity of this information, climate models or sea ice models could benefit from increased information on melt ponds. The main objective of this project is to produce melt pond fraction (MPF) products with high accuracy and high spatial and temporal resolutions. To this end, a multi-sensor approach, with a particular focus on Synthetic Aperture Radar (SAR), will be taken using machine learning to exploit and retrieve information from big data, as well as harnessing information on patterns and contributing factors to melt pond evolution. The use of AI has been chosen to allow for a data-driven and automatic technique that otherwise could not be achieved if relying only on human/manual labor.

The remote sensing application in the mining industry can serve to monitor and compute a spatial-temporal model of the mining activities. It is the main inputs to an environmental impact assessment of mining sites at both local and regional level. On the other hand, the mining industry affects variety

influences on humans and wildlife habitats, and there is a need to estimate its cumulative impacts on the surrounding environment. Therefore, the information derived from multispectral and temporal remotely obtained data and imagery at the landscape level is the key data for developing designs and

decisions at local, regional, and national levels. This satellite/drone-based smart research will provide a suitable model for rural landscape changes in Mongolia and all over the world. Problem statement: Mongolia is a landlocked country and located between Russia and China; also, it has a large territory but a small population with scattered life. The consumption of Mongolia is a rural landscape, especially agriculture and pastureland for livestock. The last decade, mining and its related development projects are significantly affecting economically and environmentally to rural landscapes of Mongolia. Therefore,

the development of mining and its related infrastructure development is of great economic and social importance in Mongolia’s rural area. There are many studies on these booming effects in Mongolian development. However, there are few studies based on landscape ecology modelling for sustainable

development using geo-spatial data and modelling. In summary, there is a need to produce a more detailed study of Mongolia’s rural landscape changes in the last two decades by economic development, mining, by combining satellite imagery and integrating social data.

In a tropical country like the Philippines, it is expected that the country is densely vegetated and cloud cover is prevalent. In fact, at least twenty five percent (25%) of the Philippines is covered in dense vegetation while cloud cover ranges, on the average, from twenty to fifty percent (20- 50%) on a monthly basis. This makes prospecting for and mapping of resources, like renewable energy and minerals, on a national and regional level using Remote Sensing challenging.

This study aims to address this problem by using high temporal (i.e. to address cloud cover) and high spatial resolution (i.e. for high resolution mapping of vegetation cover) multi-spectral satellite imageries from ESA, particularly SPOT, WorldView and Pleiades, together with publicly-accessible imageries from Sentinel and LandSat to create energy and/or mineral resource maps through Geobotanical Remote Sensing (RS). Geobotanical RS refers to the use of satellite remote sensing indetecting variations or anomalies in plant growth (i.e. size, color, form, spectral signature, phenology, etc.) in response to their geologic environment. Geobotanical RS has been proven to be an effective technique to map out areas where minerals and energy resources are present in previous studies, particularly in relatively recent work in Japan and India. For the Philippines, similar efforts were also made, but these studies were mostly done in the late 1990’s/early 2000’s and used low to medium spatial resolution (i.e. LandSat 4/5 TM) only. While resource maps based from in-situ observations do exist in the country, these are outdated and are created mostly in the 1970’s and are presented as smallscale maps only.

The objective is to perform fast investigations and assessments, and to obtain quick overview products, for a range of subsidence phenomena and slow ground deformation phenomena over the Italian territory, in support of scientific research and for the publication of scientific articles.

For autonomous driving vehicles, matching a camera image to a database of geo-referenced aerial imagery can serve as a method for self-localization. However, existing work on cross-view matching only aims at global localization and overlooks the easily accessible rough location estimates from GNSS or temporal filtering. Prior work has already demonstrated fusing the cross­view matching scores of a vehicle’s camera stream with real GPS measurements, a learned geographically local representation

In this study, we like to extend the geo-referenced aerial imagery database to geo-referenced high-resolution satellite images because aerial imagery is not always available everywhere. In addition, this study wants to use the multi-spectral images provided by the satellites.

In the broader region of the Gulf of Corinth, for about 30 years, a concerted effort has been made to understand better the geophysical processes (e.g. earthquakes, landslides, tsunamis) that take place in the region. The area is studied by research teams from all over Europe, and a network, the Corinth Rift Laboratory (CRL), has been established. The Gulf of Corinth is included as a Near fault Observatory (NFO) within the European Plate Observing Systems (EPOS) as Corinth Rift Observatory (CRO) and as a supersite within Geohazard Supersites and Natural Laboratories Group on Earth Observation initiative. Since 2016, every year in September, the so-called “School of the Corinth Rift Laboratory” (CRL School), which is the educational component of this natural Observatory, has been held in the area. So far (2021), around 50 acclaimed professors and researchers from European Universities and Research Centres have participated as lecturers/trainers in this school. About 70 students and 50 secondary education teachers have been trained. This school is being performed partly in the field, classes, and laboratories. The Space Component exists with the presentation and in-hand sessions of GEP, but we intend to strengthen it, partly using the outcome of the proposed request. For the CRL Observatory needs, GEP can provide routine monitoring by different services, with a double benefit for the Observatory: (1) no need to maintain computational resources and integrate sophisticated algorithms and (2) the capability to compare solutions obtained by different services. Our current efforts and activities are intended to strengthen the link to the GEP and strengthen the space component in the CRL NFO for research and educational activities. The utilization of GEP advanced InSAR services for monitoring terrain motion over the Gulf of Corinth, as a constraint using regional GNSS measurements, shall be demonstrated. To meet our objectives, access to both conventional DInSAR services (SNAP InSAR and DIAPASON) and advanced ones (PSBAS and SNAPPING) is required. The current investigation would pave the ground for future operational utilization of GEP within the CRL.

The project aims to explore the geotectonic position of Northern Kazakhstan using satellite images and confirm that the territory is characterized by a complex geological structure, represented by a combination of blocks of rocks of various ages, various geodynamic settings and a large-scale manifestation of intrusive magmatism. The ancient Kokchetav microcontinent represents the central part of the region with a consolidation age of 1.2-1.0 billion years, framed by Caledonian structures. In the northeast of the Kokchetav central massif is the East-Kokchetav zone, in the east Stepnyak, in the southwest Kalmykkul, and in the northwest Maryevskaya. The East Kokchetav zone is considered an offshoot of the large Seleta-Stepnyak zone, separated by the Eshkeolmessky uplift, representing a complex ensemble of island-arc (Stepnyak and Seletinskaya island arcs) terranes of Early Cambrian and Early Paleozoic age. All zones are composed mainly of Ordovician complexes with small tectonic blocks of Riphean and Cambrian rocks. Younger Devonian and Carboniferous deposits form separate graben-synclines superimposed on the Caledonids. The metallogeny of gold in this region is determined by two main epochs, the Riphean and Early Paleozoic. Small deposits and manifestations of the copper-pyrite and gold-pyrite formations characterize the Riphean and Early Cambrian metallogenic epochs. The Early Paleozoic age is characterized by the most extensive gold mineralization and is represented by deposits of several telluric-bismuth-arsenic-copper-gold formations. Regionally, many gold deposits are confined to the complexes of the Stepnyak zone (synclinoria), arcing the Kokchetav massif from the northeast, east and southeast, composed mainly of volcanogenic sedimentary and plutogenic rocks of Ordovician age.

The project aims to explore advanced aspects of some current issues in geomatics, including:

error and uncertainty analysis and visualization/communication in spatial data and analysis;

spatial decision support systems;

spatial interpolation and field models;

elevation modeling and data sources;

spatial pattern measurement or characterization;

spatial databases;

open data, data standards, and open source software development: impact and role in spatial data and analysis (standards, data exchange, open tools);

use of an EO data platform in the cloud (Polar TEP);

development of geospatial algorithms written in Python to accomplish some of the above tasks.

The objective of this project is the creation of a digital map platform for a region in north-eastern Germany that displays near real-time environmental data using Satellite imagery. The aim is to visualize environmental processes and changes concerning climate change, agriculture, forestry, water quality and urban development. Educational courses are planned for school children and adults, teaching the fundamentals of remote sensing and programming. This enables our community to conduct citizen science and develop processing tools that help to understand the dynamics of our environment by e.g. looking into methods to visualize lake water quality, algae blooms or agricultural drought challenges. Our educational and research work is conducted using Python and the Sentinel Hub API. The final product is a website that is used to visualize the data that was created during the courses on a Leaflet map. Certain rural areas in this German region will be struggling with the effects of climate change. Therefore, this platform supports policymakers in dealing with these changes and helps residents or tourists to understand the environment better. There is a collaboration with farmers to create a real-time environmental monitoring service that supports agriculture in the region as a free service. People can learn programming languages, look into their research questions and work creatively on new concepts of communicating knowledge. The results of our research and educational projects are available continuously on our website. Some research has been conducted and is implemented in a platform that can display the results without the current constraints due to the rate limitations of Sentinel Hub.

In the Framework of the ESA Georice Project, a method has been developed to monitor rice fields using Sentinel-1 time series. This submission is related to the implemention of the Georice algorithms on Sobloo DIAS.

The Geological Survey of Austria, as a state research organization, is responsible for preparing the landslide inventory and creating hazard warning maps and deformation maps regarding gravitational mass movements over the Austrian territory. Solid documentation of past and ongoing events is essential for managing the risks of possible extreme events in the future. InSAR has been a mature technology for monitoring geohazards for a decade. Several countries in the EU have full coverage of ENVISAT and SENTINEL satellite-derived ground movement guidance maps with medium resolution. Austria does not yet have such a service, so we would like to develop a strategic concept, review the method for Austrian conditions (lowlands to high mountains), and implement it in a later step. The engineering geology department already creates the algorithms and the workflow for the InSAR evaluation and has been successfully applied in several projects. An essential aspect in this context is the verification of the satellite data evaluations through motion measurements on the ground. For this purpose, we implement measurement data from the BEV and our own deformation measurements. The overall goal of this project is to evaluate current InSAR data for selected test areas in Austria to determine the current deformation behavior of the earth’s surface analysis. These analyses are based on the tools of innovative Geohazard-TEP applications and other open-source programs. This research uses the interferometric PSI (Persistent Scatterer Interferometry) technique and applies time series analysis to study the occurrence of terrain and object movement.

The aim of the project “GeoSciences IR: a Research Infrastructure for the Italian Network of Geological Services” is the creation of an innovative open cloud research infrastructure that include data, services, processing tools and training modules developed on geological topics identified as priorities by the Regional Geological Services within the Italian Geological Services Network – RISG. The main objectives of the project are the development and strengthening of the scientific knowledge of the Regional Geological Services to the geological themes considered a priority: geological and geo-thematic mapping and modelling; landslides and sinkholes; risk monitoring and management; monitoring of geo-resources and territories. Beneficiaries from the results are all users of the project, geologists, scientists.

This project’s objective(s) is/are to use contemporary satellite imagery within several educational opportunities (at all levels: grad, post-grad, and others) at the Aristotle University of Thessaloniki to demonstrate the operational use of EO in today’s society. Within three years, I will concern thousands of students across different Faculties (Science, Engineering, Geotechnical, and Law) who follow relevant courses at the graduate and post-graduate levels. The imagery will also be used within ESERO Greece, an ESA-funded project, to inspire teachers and pupils with appropriate ESERO activities like “Climate Detectives.”

EOINT4ENV is an action of the FPCUP program. It aims at initiating and developing activities supporting the investigation of public authorities and private entities’ information needs, as well as the performance of remote sensing and geospatial intelligence (GEOINT) methods, to answer those information needs (where, when, what, why, who) related to illegal activities affecting the environment taking into account the EU context and actions to improve environmental compliance and governance. FPCUP is the European Union’s Caroline Herschel Framework Partnership Agreement on Copernicus User Uptake under grant agreement No FPA 275/G/GRO/COPE/17/10042. The German Research Center for Geosciences (GFZ) Potsdam is in the lead on waste crime. In the summer of 2022, we hosted multiple events with users from both the private and the governmental sectors. Through this user dialogue, bilateral discussions, and meetings with individual users, we formulated concrete user needs. We then focused on a substantial use case provided by a governmental environmental agency to support their continuous monitoring efforts of waste sites. In this context, the GFZ Potsdam is now developing a remote sensing-based monitoring tool as per the requirements of a German state-based environmental authority (“Landesumweltamt”) to support the continuous monitoring of both legal and illegal small-scale (~0.2-0.5 sqkm) waste sites. This tool could be provided as a web service to any environmental authority or similar agency in Germany or beyond that currently does not have (sufficient) remote access to waste sites within their jurisdiction.

The objective of this project is to test OpenEO GFM’s capabilites in detecting floods and evaluate its potential use in Red Cross Red Crescent Movement’s disaster response. Specifically, the aim is to use GFM to quickly map flood extents immediately after the disaster happens, and use this to inform the teams on the ground on the most affected areas, estimated number of people and/or buildings affected, and potentially damaged infrastructure. The idea is to embed GFM into a web application that can be used by every (geo)data analyst of the Red Cross Red Crescent Movement, remotely or on the ground. The expertise of 510, the data & digital team of the Netherlands Red Cross, is leveraged to build and maintain a scalable application (see https://510.global).

The _bJect1vt.:(s) of this project are to improve the orgnn1zation’s capabil,cy to

investigate, document. and advocate around land rights and environmental

issues through the use of satellite imagery We have long consumed Sentinel

images through the EO Browser to complement our field investigations (e.g.,

January 2023’s statement on a new I:md concessions r, ·suiting in land loss and

deforestation httpsJ/www.l1cadho-cambodia.org/pressrelease.php?perm=S08)

When the free access to the EO Browser was reworked to permit less requests

per month, we found ourselves hitting the wall on most months, impacting the

efficiency of our work. As a non-profit, paying for the non-free account is

unfortunately not a possIbil.ty at this time. We are hoping our access can be

sponsored

The Gis-Co is a project that tend to invest in the data harvested from satellite through remote sensing and hydrological calculations to the welfare of residents in the Tunis city . this project at it’s first period is educational , the design zone would be in southern west of the gouvernerate of Ben Arous as the construction of a new industrial site has been taken place with a potential threat for the welfare of citizens . An initial mapping of the zone with a 30 meter spatial resolution free earth explorer maps is not sufficient for making precise and sophisticated calculation of the following parameters . This project tends to:

calculate the hydrological parameters of the Tunis watershed estimate the solid and liquid income within the 100-years life span relation to the reference terms of the industrial zones that built within Create an alert system for flood and fire hazard . Create a portal to navigate and explore the zone and it’s environmental characteristics . After rectification of the data and the creation of a automated A.P.I portal , the project would be open to new subject-study models like vegetation and the estimation of new parameters like vegetation and more. Thus , we wish that NoR would be our first demanded partner to achieve this dream and to sponsor our noble project that would save thousand of people and billions of investment by providing high resolution cards with 5 to 8 spectral bands .

Glaciers have been present in the Hindikush Karakorum Himalaya (HKH) region since the last ice age. The glacial region of HKH is considered as “water tower of Asia” because it stores water in ice and snow and supplies water in the world’s largest rivers. This is important for providing life, supporting sustainable agriculture, forest-based livelihood, and producing hydroelectricity. Climate change has been influencing the glaciated environment, causing the retreat of glaciers worldwide. However, glaciers extent in Karakorum has remained constant since the 1970s, and the number of reports has indicated that glaciers are advancing. The retreat or advance of glaciers in most areas of HKH has resulted in the formation of glacial lakes and the expansion of existing lakes. The frequency of glacial hazards has increased as a consequence of this situation. Unstable glacial lake dams discharge vast amounts of water and debris known as glacial lake outbursts flood (GLOFs). GLOFs have caused damage to property, agriculture, infrastructure and affected downstream communities. Therefore, monitoring glaciers and glaciers lakes must be monitored to reduce the challenges and risks while securing their potential benefits. Remote sensing techniques and satellite observations offer a flexible approach for spatial and temporal assessment and monitoring of glacial lakes and GLOFs. The research will be carried out in Western Karakorum, Gilgit Baltistan. The main aim of this study is to identify and classify glacial lakes in Western Karakorum, Pakistan, through remote sensing techniques and examine their expansion in relevance to their susceptibility to GLOF.

This project aims to develop an automated methodology to detect renewable energy projects worldwide, such as solar farms, wind farms, hydroelectric dams, geothermal power plants, etc. The goal is to track the growth of renewable energy adoption and better understand the distribution and scale of these projects across countries and regions. This project will use machine learning techniques like convolutional neural networks to detect and classify renewable energy facilities in satellite images by leveraging high-resolution optical and SAR satellites.

The models will be trained on existing facility images and detect new projects. Additional filters will be developed and applied to reduce false positives. The results will be a geospatial database and world map of newly detected renewable energy projects, with details on their type (solar, wind, hydro, etc.), size, exact location, and other attributes. This database will enable many valuable applications, such as monitoring renewable energy growth over time, progress toward policy goals, identifying future project locations, improving energy forecasts, and gaining market intelligence.

GlobWetland Africa (GW-A) is a large Earth Observation application project funded by the ESA in partnership with the Ramsar Convention Secretariat. The project was initiated to facilitate the exploitation of satellite observations (mainly Sentinel-1 and Sentinel-2, supplemented with Landsat) for the conservation, wise-use and effective management of wetlands in Africa and to provide African stakeholders with the necessary EO methods and tools to better fulfil their commitments and obligations towards the Ramsar Convention on Wetlands. GW-A has provided African users with an open source and free-of-charge software toolbox for the end-to-end processing of a large portfolio of EO products and the subsequent derivation of spatial and temporal indicators on wetland status and trends, from local to basin scales. The proof-of-concept and proof-of-value of the GW-A Toolbox has been provided through a set of use case demonstrations executed over +50 pilot areas spread across the African continent. During GW-A it has become increasingly apparent that there is a need to support countries in Africa to conduct full national wetland inventories to meet not only their obligations towards the Ramsar convention but also the monitoring requirements for the SDGs. Limited bandwidths in many parts of Africa prevent effective and instant access to the huge data amounts of data required to perform EO based national wetland inventories, and why cloud-based services should be promoted in order to bring the users to the data. In response to these requirements and challenges, the objective of the GlobWetland Africa – Extension on Wetland Inventory is to extent the toolbox functionality to the cloud and to provide countries with guidelines and tools to perform EO-based national wetland inventorying to meet their reporting requirements towards Ramsar and the SDGs. Beside the enhancement of the existing algorithms and product validation, the main activities focus on the review of data access options and conditions (i.e. via big data platforms), the implementation of an API/cloud-based processing scenario suitable for countries who lack the required ICT capacity for in-house processing, the implementation of post-processing workflows and reporting modules for users to correct the EO pre-inventory, testing the data access scenario as well as additional capacity building activities. Beside the “standard” deliverables like ATBD, Product Validation Report, and Technical Specifications, the project provides access to an online processing system (API-based) via a QGIS interface allowing users to trigger Sentinel data processing and getting access to derived wetland information products. These products are then refined and used for reporting purpose.

The project objectives are:

• Το frame an operational algorithm for a technological framework that would contribute to more sustainable agriculture practices by enabling precision agriculture locally and helping to provide consumers with a more consistent label of bio-products (Eco-label).

• Το evaluate available and select appropriate technologies to be applied in the defined technological framework, including, but not limited to, satellite data application, sensors displacement in the crop field, and Blockchain Technologies (ΒΤ).

• Το define a Multi-Criteria Decision Analysis (MCDA) method that can be implemented within the Geographic Information System (GIS) in a self-assessment tool for farmers linked to evaluating current practices and planning more sustainable agriculture practices.

• Το select a set of indicators for MCDA reflecting sustainable agriculture (i.e., environmental, economic and social dimensions) by implementing a Life Cycle Analysis (LCA) approach to construct a multi-dimensional index.

• Το set the foundation for forming an Eco-label based on the developed technological framework and self-assessment tool by implementing ΒΤ.

• Το develop an online platform (E-platform) which aligns with the technological framework and embeds the developed self-assessment tool.

• Το test and optimize the developed technological framework, self­assessment tool and E-platform based on a local pilot case study.

• Το ensure knowledge transfer to farmers using E-platform and promote sustainable agriculture practices.

• Το disseminate the study results through publications in scientific journals, conferences, and seminars for agriculture sector stakeholders and reports with policy suggestions for smart eco-labels.

The objective of the activity is to develop a stand-alone binary library (i.e. a toolbox) that provides the ability to efficiently utilize Graphical Processing Units (GPU-s) in cloud environments, for running and maintaining Earth observation (EO) algorithms. Such capability is required to increase the speed, scalability and cost-effectiveness of EO data processing, and training of machine learning algorithms that require EO and other geospatial data as input. The activity shall be performed in close collaboration with the EO user community, implementing representative use cases from the industry. The use cases to be selected for GPU implementation and the functionality to be developed are agreed with the ESA TO and validated against end-users in order to ensure end-user uptake. The EO use cases to be selected shall be based on machine learning algorithms that utilize EO data to extract information. Use cases are selected for optical and for SAR data usage. The use cases are analysed in order to select the ones that can clearly gain benefit from GPU acceleration – either for preparing data for training the AI/ML algorithms or applying the algorithms on a large amount of data in order to extract information. Based on the selected use cases, a toolbox allowing for these use cases to be implemented in a cloud environment is developed. The toolbox is based on open-source tools and maximizes re-use in context of existing software solutions for AI/ML algorithms development – assessing how these could be implemented on GPU infrastructures. Particular care is taken in order to guarantee the modularity and expandability of the developed toolbox, in order to allow addition of extra tools and deployment in various processing clusters (e.g. the DIAS-es and EO datacubes). A cloud infrastructure is selected and the toolbox is deployed in the environment in order to allow demonstration to expert and end users and collect feedback. The GPU processing results is analysed and compared to results obtained through baseline implementation (i.e. on CPU-s) of the same algorithms, both performance and accuracy-wise. Deliverables include the final tools developed, and a selection of ECSS documentation.

Located on the eastern shore of the Baltic Sea, the coastline of Latvia is about 500 km Ιong. Consisting mainly of low-lying sand beaches, it is highly susceptible to wave and wind-induced erosion. Future climate change projections from IPCC indicate an increase in mean Sea Surface Height and storm frequency in the Baltic Sea area. Therefore the need for reliable erosion assessment is of high importance. Gathering reliable monitoring data has been a complex challenge due to the sporadic nature and high costs of in-situ observations. Today the available remote sensing datasets and developments in data processing mechanisms enable new means to establish a consistent data flow for monitoring needs. The purpose of this R&D activity is to build a robust coastal monitoring system that uses remote sensing data as the input source. The processed data will provide means for analyzing and improving the understanding of coastline dynamics in Latvia. The comprehensive dataset will benefit public, governmental, and private sector stakeholders by providing open access to an operational dataset and the developed processing methodology. The resulting data will enable and improve efforts of sustainable environmental monitoring, spatial planning, climate change impact assessment, etc. The activity also fits within the national and EU-level framework efforts for achieving climate literacy and open data policy. Finally, an essential outcome of the activity is building capacity by increasing competence and processing capabilities in the Climate and Forecast department of the Latvian Environment, Geology, and Meteorology Center and strengthening cooperation with partners at the local and regional levels.

The proposed project would investigate the use of Graph Signal Processing (GSP) for remote sensing problems. Observations provided by different satellites are often packaged as separate products with different spatiotemporal resolutions and coverage. With existing technologies, these differences in resolution are significant obstacles to combining multi-sensor (e.g., radar, visible, short-wave infrared) observations from various satellites. Motivated by these considerations, we will explore a graph-based analysis and visualization method that integrates publicly available observations from geostationary (GEO) and low Earth orbiting (LEO) satellites. The aim is to produce actionable datasets for applications where remote sensing data provide significant added value. Our main goal is to explore a technology that enables the integration of satellite data with in-situ measurements), while using relevant ancillary data (terrain information, for example). We propose an alternative to existing merging methods based on graph signal interpolation. Graphs are a good fit for processing signals that: i) lie on irregular domains and ii) are the result of physical processes where observed correlations can be attributed to the effect of multiple variables. Our novel GSP approach estimates high-resolution observations using graph-based interpolation on a graph constructed with weights that are a function of ancillary data such as altitude and temperature at high resolution. The explored methodology will construct graphs that allow us to combine multiple observations (from different satellites and at different resolutions) with relevant geoinformation. In this formulation, coarse observations are considered graph signals at specific nodes. In contrast, graph edge weights are chosen as a function of terrain information (e.g., distance, differences in altitude or similarity between neighbouring observations from another instrument).

The GRD4ML Project (Geophysical Reference Data for Machine Learning) will create an Enhanced Environment to generate Reference Data for the Retrieval of Geophysical Parameters by Machine Learning, which will be referred to as the GRD4ML Environment or GRD4ML-E hereafter. This environment is composed of a set of integrated tools, procedures and best practices, suitable for integration into any cloud provider (e.g. a DIAS), which are available to scientists and application developers to easily create, enhance, utilise and manage comprehensive sets of reference data for geophysical applications using ML techniques. The project is based on a multi-disciplinary approach and leverage both scientific (such as machine learning techniques and geophysical models) and leading-edge technological aspects (e.g. cloud-based processing, horizontal and vertical scalability, data traceability, etc.) and comprises two demonstration cases, on ozone and soil moisture retrieval, that is used to proof the concept.

This is a delta request sponsorship for the GRD4ML project (ID 57460) which due to some delay risks to run out ICT resources before final presentation.

This project aims to address the Green transition needs by providing tools to key stakeholders to improve their understanding and provide them with evidence-based information to support the green transition. Furthermore, these tools will provide actionable information for citizens, policy-makers and stakeholders engaged in the green transition. In this project, large amounts of earth observation datasets will be used to derive relevant key indicators for different green transition domains, namely for the energy transition, mobility transition, sustainable cities, carbon accounting and earth observation adaptation services, each of which addresses several applications.

The study’s main objective is to obtain improved high-resolution maps of renewable energy sources (RES) potential for planning activities of the future Austrian power sector. The key RES of interest will be wind, solar and hydropower. Additional renewable energy resources are also relevant but have not been considered since their assessment either overlap with other GTIF-AT scenarios (biomass) or require fundamentally different approaches and highly specific local data (e.g. geothermal heat). Furthermore, the availability of RES is only relevant if this energy can be accessed and harnessed. Mapping RES potential, therefore, has to include two elements, i.e. the mapping of the availability of RES in time and space as well as their applicability, like estimating RES potential by also considering factors that either constrain or enable effective usage of the available RES.

The ESA Green Transition Information Factory (GTIF) allows users to interactively discover the underlying opportunities and complexities of transitioning to carbon neutrality by 2050 using the power of Earth Observation, cloud-computing and cutting edge analytics.

The main goal of the EO4MASRISK is to fully utilize Sentinel-1 data, evolving from periodically updated ground deformation maps to early mapping and monitoring of landslide activity to increase urban resilience. EO4MASRISK service will help stakeholders and end-users to easily identify landslide moving areas and related potential impacts on built-up areas. The EO4MASRISK service functionality will provide the following information: Ground deformation time series; Ground deformation yearly velocity map; Landslide activity map (three levels, e.g., low, medium, high); Map of vulnerable elements at risk, e.g. buildings and infrastructure (three levels, e.g. low, medium and high); Datasets of the economic value of a property (available only for stakeholders); Potential damage map (three levels, e.g., aesthetic, functional, structural); Economic impact of a landslide on a building or infrastructure (euros/m²).

Within this ESA Living Planet Fellowship, we mainly intend to analyse ground deformation hazards induced by meteorological changes and seismotectonic conditions in eastern Belgium, western Germany and the south-eastern Netherlands. Thus, its outcomes should also be interesting for the ongoing Interreg project Einstein Telescope EMR Site & Technology (E-TEST). The focus is on the differentiation of weather-induced and seismotectonically influenced Earth surface processes in the E-Test area, where human-induced groundwater level changes are observed. The regional aspect of ground deformation in the E-Test area would be approached by Differential Synthetic Aperture Radar Interferometry (DInSAR) processing. Detailed analyses will be performed along the numerous faults crossing the E-Test area. Differential ground deformation across fault structures should be relatively small, probably a few millimetres. Such small displacements require precise surveying using DInSAR studies supported by installing fixed corner reflectors. Also, repeated very high resolution (VHR) images and digital elevation model (DEM) will be collected using Unmanned Aerial Vehicles covering the whole potentially subsiding area.

Moreover, in parallel, geodetic monitoring will be collected using DGPS measurements on benchmarks and Essential Climate Variables (ECVs) monitoring to determine the meteorological conditions when ground deformation is increased. The project also aims to develop a permanent monitoring system which would last after the project’s duration. Finally, we will develop models allowing us to manage and visualise (also in Extended Reality environments) the slow ground movements measured by remote sensing.

Indeed, karst phenomena strongly control the extent of construction in the target area – at least in the limestone regions; therefore, a significant objective of this project is to detect limestone and related karstification, especially along faults.

In the framework of the Horizon 2020 e-SHAPE project, ISPRA, as a linked third-party of

Eurogeosurveys will analyze geohazards affecting the Como (Northern Italy) urban area.

In particular, the project aims at assessing the vulnerability to the subsidence of infrastructure and real

estate assets. The first data needed to conduct this analysis are Ground Motion data, as up-to-date as

possible. Therefore, the use of the P-SBAS DinSAR service to obtain deformation time series

and mean velocity maps from Sentinel-1 images would be of great support to the project.

This initiative, led by the Asian Institute of Technology {AIT), is a capacity-building project that aims to enhance the capabilities of the Asian Development Bank’s developing member countries (DMCs) in utilizing Earth Observation (EO) data for disaster risk reduction in coastal areas. The coastal regions of Georgia are experiencing increasing risks due to land subsidence, storms, and sea level rises, which can lead to increased coastal erosion, inundation of low-lying areas, and degradation of coastal ecosystems. Climate change is driving more extreme weather events, and urbanization is exacerbating vulnerabilities in coastal areas; therefore, utilizing advanced technologies such as remote sensing can improve our capacity to mitigate the potential impact of coastal risks. With this background, the objectives of this project are:

– Monitoring displacement and ground motion in Georgia’s coastal region,

– Monitoring coastal erosion,

– Area stability assessment in the coastal zones,

– Integrating remote sensing data with coastal modeling.

This project’s objective(s) is to link the in-situ data collected for groundwater extraction and the values of subsidence obtained from the analysis of the Sentinel-1 data. The output of the study will be of high importance to decision-makers to focus on areas not highly influenced by subsidence due to groundwater extraction and, hence, will be safe for future developments. The results will be available for published papers in highly ranked Q1 journals. The project’s output is expected to be replicated in other study areas in Egypt, such as Dakhla and Kharga Oasis in the Western Desert.

In this research project, we would like to explore areas of land subsidence with the P-SBAS on-demand processing service on the GEP. The objective is to obtain land displacement velocities for watersheds that are over-exploited and need modeling-based approaches to mitigate the risk of land subsidence. Land subsidence data obtained from the InSAR processing on the GEP is going to be used as calibration data for a geomechanical model, which will be coupled with a groundwater flow model. Therefore, the acquisition of P-SBAS processed InSAR data from the GEP is critical for our project. Foreseen results are as follows:

– Develop an innovative methodology for the hydrogeological characterization of large-scale aquifer systems using low-cost and nonintrusive data such as satellite-based Earth Observation (EO) techniques.

– Integrate advanced EO techniques into numerical groundwater flow and geomechanical models to improve the knowledge about the current capacity to store water and the future response of aquifer systems to natural and human-induced stresses.

– Enhance the knowledge about the impacts of agricultural and tourism activities on the water resources by quantifying the ground deformation during the monitored periods.

This initiative seeks the use of the Geohazard Exploitation Platform to provide training to scientists who want to access and process the open satellite data provided by the CEOS space agencies to the 14 Geohazard Supersites of the GEO-GSNL initiative (geo-gsnl.org). At the moment Sentinel 1, Pleiades and CSK data it is used, teaching the trainees how to process these data on the GEP.

The Geohazard Exploitation Platform is used to host Pleiades data for the 14 Geohazard Supersites of the GEO-GSNL initiative (geo-gsnl.org). The data are provided for free by CNES following agreements negotiated between the single Supersites and the CEOS Data Coordination Team. As per the agreement of GSNL, CNES, and the GEP managers, the Pleiades data acquired over each Supersite will be sent to the GEP after production. This process will be started after approval of the sponsorship. There are several tens of Pleiades images already available for upload, and about 50 were acquired for the various Supersites. The data is made discoverable and downloadable from the GEP for all authorised users. Authorization is granted by CNES following a request from the Supersite Coordinator. The authorised users need to have or obtain a GEP login. The Pleiades data are used for scientific research on earthquakes and volcanoes. The outcome of such research generates a few tens of publications in peer-reviewed journals each year.

The project aims at using the Geohazard TEP cloud processing service with Sentinel-1 data for InSAR processing. The subject of the study is the Gulf Coast Aquifer system subsidence. Land subsidence is a persistent worldwide problem that harmfully affects several regions and especially keeps the coastal communities at significant risk of multiple hazards. There are some well-known contributing factors behind this geological hazard. Recently, a combination of Global Navigation Satellite System (GNSS) and Interferometric Synthetic Aperture Radar (InSAR) have been used to monitor and quantify the subsidence rates. Unfortunately, it suffers from the lack of continuity over the spatial surfaces due to vegetation decorrelation, cultivation, and non-cultivation seasons, in the agricultural areas, and rough topography. However, the lack of continuity can be settled using artificial intelligence algorithms. The Gulf Coast in Texas, United States, has a prolonged history of land subsidence provoked by excessive groundwater and hydrocarbon extraction. The substantial withdrawal of groundwater in the drought period could affect the properties of the reservoir, which is often irreversible. In addition, the growth faults and presence of salt domes in this region are being evidenced to trigger land subsidence. This research focuses on the Gulf Coast of Texas, while the previous workers mainly focused on Harris and Galveston counties. I will use Geospatial analysis, InSAR data, Machine learning algorithms, Regression Analysis, LiDAR, GPR, EMP, and Seismic data for this work.

The population of howler monkeys at Hacienda La Pacifica, in the northwest province of Guanacaste, Costa Rica, has experienced a dramatic decline recently. We are investigating various factors that may be playing a role in this decline. We are in great need of mapping and vegetation data going back as early as possible. Howler monkeys have been quite resilient in the face of anthropogenic modification, that is, until recently. Anecdotally, we have heard of decreasing numbers of individuals throughout Central and South America. We conducted a census in 2017 and have comparable data from several censuses prior at this site. Mapping data is critical to publishing census results and documenting this recent trend in a peer-reviewed journal of our discipline, such as the International Journal of Primatology or Neotropical Primates. I will be working with these data alongside undergraduate STEM majors, many of whom are minority students who can benefit from learning how to conduct GIS analyses.

This project is planned to support the Ukrainian Government with information on harvest progress using Sentinel-1 coherence backscatter information and following the algorithms developed in the ESA project “Impact of Covid19 on Harvest of row crops (CovidHarvest)”. From optical data, the maturity of the fields can be monitored, and potential yield can be simulated. Furthermore, we will determine whether the actual harvest took place with this activity.

Within this project, it is planned to support the Ukrainian Government with information on seed bed preparation and harvest progress using Sentinel-1 coherence and backscatter information and based on the algorithms developed in the ESA project “Impact of Covid19 on Harvest of row crops (CovidHarvest)”. With this activity we will determine whether the actual seed bed preparation and harvest took place.

This project’s objective(s) is to evaluate the recovery of London’s night economy in central London (Westminster and City of London areas) to inform the local city council with data-driven research evidence. Postgraduate students will conduct the work upon completing their individual projects under the project coordinator’s supervision. The NDVI datasets and buildings data will be utilised to support data exploration on healthier and greener London towards the Net Zero goal in 2030 through multi-sourced data fusion and application. It will also support postgraduate students’ individual projects. It will be helpful to provide the students with real datasets, applying their taught Geospatial interpretation and analytical skills using Python towards real urban topics’ exploration and evidence generating.

The project’s objectives are:

1. To identify high conservation values existing in Mount Mantalingahan Protected Landscape, their locations and extent, and provide management recommendations and;

2. To capacitate and improve the partners’ skills in assessing High Conservation Value number 2 (landscape-level ecosystems and mosaics) and High Conservation Value number 3 (threatened and rare habitats and ecosystems) and utilize biodiversity data to inform management decisions.

For objective one, we shall identify the high conservation values (HCV) in two categories: HCV2 and HCV3. HCV2 pertains to landscape-level ecosystems and mosaics, while HCV3 refers to the presence of threatened and rare habitats and ecosystems. HCV2 will require developing a map of land cover with class categories based on the IPCC’s standard six land cover classes. HCV3 will require creating a change detection map to determine where and how much forest loss occurs.

Those who will benefit from the results are mainly the indigenous people’s communities residing in the protected landscape and also the wildlife and biodiversity therein. For the communities, the ecosystem services are also protected to provide continuous provisioning and to regulate services, considering that we will have information on the landscape and the threatened ecosystems and habitats. The regulating services should also consider protecting the remaining forest to help mitigate climate change effects. The geospatial information collected and derived from satellite imagery will be part of the data collection of the government body authorized to develop and protect the protected landscape.

The results can be made available with written permission from the project prime.

Digital surface and digital terrain models are critical in different industrial sectors. But there is a barrier towards getting these products: the high cost of very high-resolution data (30cm to 50cm). Our project aims to generate high-quality DSM and building height models using high-resolution data (1-3 meters) instead of VHRI by developing and applying state-of-the-art artificial intelligence algorithms. The beneficiaries of the project will be environmental managers and telecommunication specialists.

Our idea is to develop a system backed by a deep learning algorithm that produces high-quality elevation data based on its inputs, which are high-resolution stereo data. The central part is the algorithm covered by a system which makes it more usable. That system abstracts the complexities of the algorithm and makes it easier to use by specialists in other fields.

The project is focused on the creation of several functionalities that are useful in the agricultural sector. Specifically, these features will be useful in high-value crops like almonds, olive-grooves, pistachios and avocados, between others.

Giving to agronomists the information related to the canopy trees without the necessity of flying drones can make the change in the following years to better monitor these type of crops. The objectives are:

– To create an algorithm for automatic detection of canopy trees.

– To create an algorithm for automatic detection of vegetation covers.

– To give insights about the healthy of every tree in the crop.

– To create variable rate application maps for canopy tree crops.

The main beneficiaries of these functionalities are farmers, field technicians and agronomist engineers. Specifically, the technicians and the agronomist can improve their current work thanks to the insightful maps that could be created with the algorithms explained. Tasks like the irrigation or fertilization of the trees can be improved in order to produce more while reducing the use of natural and artificial resources. For example, knowing the exact healthy state of every tree we can create variable rate application maps so that the machinery can apply just the exact quantity of product that is needed. The agronomists and technicians can be single workers or they can make part of technical advisory services from cooperatives, fertilizer companies or agrotech companies which are already in the market. The maps will be consumed through a web application platform called Graniot where the beneficiaries can create their own insightful maps or ask for specific ones. The platform will facilitate the way beneficiaries access to the most innovative satellite technology: very high resolution images of 50x50cm and 30x30cm per pixel. The maps can also be consumed through an API for technological companies.

This project, anchored within Ovis Analytics GmbH, is non-commercial and aims to evaluate the feasibility and potential of utilizing deep learning techniques for forestry analysis through high-resolution satellite data, specifically Planet’s SkySat imagery. At Ovis Analytics, we want to make sustainable forest management possible by giving forest managers the tools needed to evaluate and manage forests sustainably at scale. Given the detailed analysis requirements and results from having tested various low-resolution solutions like Sentinel-2 and Landsat, we have a deep understanding of what’s needed to deliver these tools: a fusion of high-resolution satellite imagery and sophisticated deep learning algorithms. The rich, detailed data from SkySat imagery, coupled with the robust analytical power of deep learning, has the potential to unlock unprecedented insights into forest health, growth patterns, and responses to environmental stressors. Now, we want to verify this against ground-truth data. The core objectives include:

1) Framework Development: Developing a deep learning framework adept at extracting valuable forestry insights from SkySat imagery.

2) Scalability and Effectiveness Assessment: Assessing the framework’s scalability and effectiveness across diverse forest types and geographical regions.

3) Forest Ecosystem Understanding: Advancing the understanding of forest ecosystems to support sustainable management practices.

4) Stakeholder Engagement: Engaging with academic and industry stakeholders to foster knowledge exchange and further development of the framework.

5) Pre-commercial Feasibility Evaluation: This project is pre-commercial and focused on feasibility evaluation rather than revenue generation. The findings and methodologies will be used to determine a development roadmap, laying the groundwork for potential future commercial endeavors.

Established in 2019, Albo-Climate is combining geospatial modeling and AI expertise to provide state-of-the-art remote sensing solutions for carbon-stock and ecosystem monitoring across diverse ecosystems. Albo’s technology solves the manual, expensive, hardware-dependent in-field measurements common in the carbon-credit market. We are creating a new paradigm of transparency and scalability in Nature-Based Climate Projects, by mapping land-use and carbon-stock changes at high accuracy and on a per-pixel resolution. Our innovative solution has already received the Solar Impulse Prize and Official Concept Note Approval from Verra, the largest registry for voluntary carbon credits in the world.

Albo Climate’s cutting-edge, automatic, remote sensing platform allows landowners of any size – both public and private – to easily enter the carbon credit market and start selling credits from their land. Albo’s solution also enables project developers seeking to participate in the carbon credit market to easily and efficiently initiate a Nature-Based offset project and monitor their project development. Moreover, Albo’s technology allows project developers to detect major threats affecting the project site in near real-time such as deforestation, forest degradation, crop diseases, and flooding. By removing the main structural, technological and financial barriers, Albo aims to scale up the voluntary carbon credit market and unlock its full potential to mitigate climate change.

The European Ground Motion Service (EGMS) provides InSAR-based terrain motion measurements using Sentinel-1. This is an unprecedented opportunity to study geohazards and human-induced deformation, such as slow-moving landslides, subsidence due to groundwater exploitation or underground mining, volcanic unrest, etc. The EGMS also serves as a starting point for investigating ground motion affecting buildings and linear infrastructures. The EGMS distributes three levels of products updated annually.

The objective(s) of this project is to host on the GEP the complete L3 EGMS dataset over Europe and serve it to the community as a collection via the new Ground Motion Visualisation Service. The EGMS L3 collection will be offered in a dedicated workspace where users will be able to:

• Visualise the average velocity dynamically on the map

• Customise the data map rendering via layers selection and colour scale adjustment

• Filtering of points according to velocity thresholds

• Access the Time Series Viewer providing:

o Displacement TS for each measurement point (point selection)

o Area of Interest statistics (bbox selection)

o Profile analysis (line selection)

o Export of TS in CSV and CovJSON formats

The key project aim of this master thesis is to apply state-of-the-art deep learning methods on satellite

imagery to detect bi-temporal changes in land usage in Germany. Achieving this research aim serves

two purposes: firstly, it showcases how state-of-the-art deep learning techniques can be used to analyse

remote sensing data for a large geospatial region (the whole of Germany) that would not be possible to

analyse in a manual fashion, and secondly, it sheds light on the key research question addressed in this

work:

Research question: How did the land cover and land usage change due to human and non-human

influences between two points in time?

Three research objectives support the research aim and the key research question: i.)

Train a deep learning model to be able to classify satellite images into separate land-use classes with a

classification accuracy that is significantly above a naïve (baseline) classifier when evaluated on holdout test data. ii.) Acquire suitable satellite image(s) from Germany at two distinct points in time that

can be meaningfully compared (i.e., where the weather and cloud conditions are sufficiently similar to

warrant comparison) and pre-process the data to be handled by the trained deep learning model. iii.)

Classify the satellite image(s) at both points in time and compare the land-use classes, both in

aggregate and individual changes.

The HAACT is a free service to the humanitarian community which since 2021 has used innovative methodologies to share analyses that complement existing information mechanisms, particularly in hard-to-reach areas of the Central Sahel and since 2024 in Benin, Togo, Nigeria, Sudan and Yemen. Requested by UN agencies, decision-makers/donors, humanitarian coordination structures (RRM, Inter-Cluster, NGO Forum) and operational players, the HAACT is recognized for the reliability and independence of its analyses. A mechanism whose methodologies enable it to respond with agility to the various challenges faced by decision-makers and operational players. It produces humanitarian alerts as well as localized and contextualized needs assessments. The analyses produced are widely shared with the humanitarian players involved. The HAACT makes a wide range of contributions to operations, from contextual analysis to activity monitoring. Mobilizing a unique diversity of information sources and media (satellite imagery, photos/videos, key informants, civil society organizations, the web and social networks), the HAACT overcomes partners localized, siloed approaches (to promote holistic, territory wide approaches) and maximizes the reliability and neutrality of information (solid triangulation methodologies). The HAACT has demonstrated its complementarity with existing mechanisms and added value in the production of information and analysis on several types of crises- whether in hard-to-reach areas or those with a humanitarian presence. Whether on the scale of large or small population basins, the HAACT helps prioritize areas/needs, shares complementary and enlightening information on high-stakes issues (e.g. blockades), and contributes to the accountability of populations. Its services have already been called upon in response to shocks, on forgotten crisis situations, and as part of more thematic analyses in line with the priorities of the humanitarian community.

As a grassroots humanitarian cluster based in London, working in partnership with Ukrainian NGOs and volunteers (Odesa), mapping humanitarian needs, and conducting assessments on the ground are paramount for our long-term efforts and accurate reporting capabilities. Our extensive fieldwork in urban/rural areas across southern Ukraine (Mykolaiv, Odesa), as well as in de-occupied regions (Kherson), includes damage (i.e., such as schools, kindergartens, hospitals, etc.) and humanitarian assessments (at household level), upon which further procurement planning is based. In addition, we monitor last mile delivery to settlements/communities in most need through the Frontline platform. Therefore, applying for the ESA sponsorship would drive our project objectives in several ways:

1. Enhanced mapping and humanitarian assessment capabilities by integrating a remote analysis tool with high-resolution satellite imaging.

2. Enhanced geographical outreach and forward planning. Beneficiaries: local communities & administrations in hard-to-reach areas/ de-occupied regions of southern Ukraine who require continued humanitarian relief /reconstruction efforts.

3. Risk mitigation and improved situational awareness in a humanitarian context. At present, the assessments are conducted on the ground by affiliated volunteers and researchers, who document the extensive infrastructural damage, covering multiple localities (hundreds of sqm) and producing visual reports. However, access into remote areas, mainly rural, and across mined terrain is highly problematic, notwithstanding safety concerns. Therefore, the ability to conduct at least part of the analysis /interpretation remotely would reduce the presence on the ground and hence, unnecessary exposure to the threat environment.

4. Effective resource management: as Ukrainian charities struggle with manpower due to active/ongoing conscription and scarce resources (i.e., fuel) to conduct granular fieldwork, operational and logistical costs would be significantly reduced. Beneficiaries: humanitarian volunteers & (cluster) partner charities.

This study generally aims at investigating what are the most efficient IWRM and IRBM strategies to develop and implement that will ensure social and hydroecological resiliency of the Sanaga River Basin in the context of climate uncertainties? The overall purpose of this dissertation is to elaborate predictive hydrological machine learning models and roadmap schemes for decision makers that will enable them to enhance water security, water access and resilience in managing fisheries and energy resources of the Sanaga River Basin in the context of climate change and increasing water scarcity risks; and to propose adapted management strategies as mitigative solutions. Specifically, we will:

• Assess current Land Use and Land Cover of the Sanaga River Basin; describe how it has evolved during the last decades and predict future physiographical states from the climate trends according to the climate models scenarios RCP 6.5 and RCP 8.5;

• Investigate the hydrological response of the Sanaga River Basin and predict possible extreme hydrological events based on some IPCC, CMIP6 and CORDEX climate models;

• Determine the hydrological resiliency of the Sanaga River to sustain current and future National projects for hydroelectric development;

• Assess and model the ecohydrological response of the Sanaga River Basin, and predict future trends in hydrological and ecological indicators;

• Assess the Water Policies and Governance of the Sanaga River Basin in the new framework of decentralisation and regional competencies transfer; and propose an interregional Master Plan for IWRM in compliance with SDG 6 criteria and others real options criteria.

The objective of the project is to compare state-of-the-art and Hydrocoastal products in the Northern Adriatic Sea against in situ measurements.

The main objective of the project is to maximise exploitation of SAR and SARin altimeter measurements in the coastal zone and inland waters, by evaluating and implementing new approaches to process SAR and SARin data from CryoSat-2, and SAR altimeter data from Sentinel-3A and Sentinel-3B. There are specific objectives for each of the Coastal Zone and Inland Water domains, and particular Technical Challenges to be addressed. However, one of the key aims is to link together and better understand the interactions processes between river discharge and coastal sea level. Key outputs are global coastal zone and river discharge data sets, and assessments of these products in terms of their scientific impact. The aim of the project is to study new approaches for processing SAR and SARin data from Sentinel-3 in coastal zone and inland water. Various approaches are evaluated in selected test zones and the most promising processing schemes are identified. The chosen approach is then implemented to generate global coastal zone and discharge datasets and the scientific impact of these products is evaluated in few case studies.

The objective of this project is to develop a web-based tool for the validation of Sentinel-2 and Sentinel-3 derived bio-geophysical products against ICOS terrestrial ecosystems measurements. The Integrated Carbon Observation System, ICOS, is a pan‐European research infrastructure for observing and understanding the greenhouse gas (GHG) balance of Europe. The major mission of ICOS is to integrate highly standardized networks from multiple domains, such as the atmosphere, terrestrial ecosystems, and oceans, and collect and make available standardized open data from more than 140 measurement stations across 14 European countries. Besides, as a science-based infrastructure, ICOS has been developed by addressing the Essential Climate Variables (ECVs) and in the terrestrial ecosystem domain provides both observations towards the ECV anthropogenic GHG fluxes mainly related to land use and biophysical parameters such as land surface albedo, leaf area index, aboveground biomass, and soil carbon.

The aim of this study is firstly to demonstrate that ICOS terrestrial ecosystem sites can serve as a network for the validation of Earth Observation products and then enhance our ability to validate satellite EO data in terms of spatial and temporal coverage. To this end, focusing on the current ESA optical imaging sensors, namely Sentinel-2 and Sentinel-3, the WP aims to provide a web-based tool for the validation of satellite‐derived biophysical products against in situ data, by identifying ways how to properly scale and compare the ground-based measurements with satellite measurements: the objective is to ensure good representativeness of the validation dataset impacted both by an inner spatial heterogeneity and temporal variability of terrestrial surfaces and a different spatial and temporal sampling between the two dataset. In detail, the project will focus on the validation of a subset of radiation and vegetation parameters, including key terrestrial ECVs, namely: Surface Reflectance (SR), land Surface Albedo (SA), Land Surface Temperature (LST), Fraction of absorbed photosynthetically active radiation (FAPAR), Leaf Area Index (LAI), Chlorophyll Index (CI), Chlorophyll Content (ChlC). The Terrascope development environment has been selected to guarantee effective EO data access, good data completeness and easy interoperability. The tool has been developed and as a next step, it is planned to ingest data from ICOS specifically processed within the Grounded EO ESA activity.

Telespazio VEGA UK Ltd are the prime contractor for ESA’s “EO Exploitation Platforms Common Architecture (EOEPCA)”. EOEPCA aims to facilitate the adoption of a freely available common architecture that supports a paradigm shift from “bring the data to the user” (i.e. user downloads data locally) to “bring the user to the data” (i.e. move user exploitation to hosted environments with collocated computing and storage). This leads to a platform-based ecosystem that provides infrastructure, data, computing and software as a service. The resulting Exploitation Platform is where scientific and value-adding activities are conducted, to generate targeted outputs for end-users. The focus of the Common Architecture is to define an open architecture using open interfaces that facilitate the federation of services in the “EO Network of Resources”, and to develop a Reference Implementation of the architecture for deployment as an operational service. The project is at a stage where the architecture has been defined. The project team has been expanded with Domain Experts to refine the architecture and develop a reference Implementation based on the building blocks defined by the architecture. The current Phase 1 runs until the end of October 2020, with the possibility of an extension into Phase 2 to the end of 2021. Under the terms of the contract, ESA will sponsor the development of the Reference Implementation with the provision of ICT resources within the ‘Network of Resources’ to support the development, integration and test of the Common Architecture software components and their deployment as an integrated set of platform services.

EOEPCA aims to facilitate the adoption of a freely available common architecture that supports a paradigm shift from “bring the data to the user” (i.e. user downloads data locally) to “bring the user to the data” (i.e. move user exploitation to hosted environments with collocated computing and storage). This leads to a platform-based ecosystem that provides infrastructure, data, computing and software as a service. The resulting Exploitation Platform is where scientific and value-adding activities are conducted, to generate targeted outputs for end-users. The focus of the Common Architecture is to define an open architecture using open interfaces that facilitate the federation of services in the “EO Network of Resources”, and to develop a Reference Implementation of the architecture for deployment as an operational service. The project has now entered Phase 2. The project team has been expanded with Domain Experts to refine the architecture and develop a Reference Implementation based on the building blocks defined by the architecture produced during Phase 1. Phase 2 runs until the end of 2021. ESA sponsors the development of the Reference Implementation with the provision of ICT resources within the ‘Network of Resources’ to support the development, integration and test of the Common Architecture software components and their deployment as an integrated set of platform services. Phase 1 received sponsorship, but a large part of the credits were unused due to some initial billing problems that took several months to resolve and deterred use of the service for some time. In the later months of Phase 1, the usage was ramped up to expected levels and has proved an invaluable resource for the development team. The experience of Phase 1 has informed this request, along with a project requirement to target and demonstrate our work on more than one infrastructure platform. Thus, we are requesting ICT resources to support our development and demonstration activities on multiple Data and Information Access Services (DIAS):

 CREODIAS (Cloudferro)

 MUNDI Web Services (Open Telecom Cloud) The use of multiple DIAS is important to ensure that the Reference Implementation is not tied to a specific infrastructure provider – noting that the two DIAS selected are backed by different underlying cloud providers. This should help to ensure that the Reference Implementation is engineered generically.

The present initiative aims to explore the value of some cross-cutting technologies to develop innovative and interdisciplinary indicators from EO and geospatial data that provide new perspectives and relevant information on the complex societal challenges, by taking advantage of cloud-based EO platform capabilities, accessible data, computational resources, and analytical capabilities. The IDEAS project aims to develop five new indicators at a European/world level and their visualisation. Requested for Object storage is put in the number of months, but it will be used as 2TB for 12 months during a project duration.

The project objectives are:

1) Semantic mapping and normalization between CAPO crop codes and crop labels

2) Pilot application of Sen4CAP at the Cyprus level

3) Crop-type classification of non-eligible Sen4CAP parcels through the use of drones

4) Adoption of Sen4CAP for CAP monitoring in Cyprus

5) Κnowledge transfer of the use of Sen4CAP to the Cypriot Paying Agency

Existing methodologies for monitoring the temporal changes in forest areas have poor performances in high altitude and sloping areas such as Alp mountains or Iberian mountains. That is why, in such hilly regions, prediction of tree cover density or decision on forest existence and forest type are highly error prone, as already demonstrated by [Dostálová et al.] [Cremer et al.]. Thus, our aim in this research is to develop a robust tree cover density prediction algorithm by combining the earth observation data with topographic information and climate categories. Existing European wide forest change detection methodologies are mostly rely on classical statistical measurements and thresholding techniques, however in our research, we are aiming at using advanced machine learning techniques such as variants of UNet and Transformer architectures.

As an output of our research, we will predict more robustly which parts of European forests are subjects to degradation and how severe those changes are. Thus, our contributions will help decision makers to take preventive measures for protecting the forest areas and recovering them in the long term.

Since 2004 Instituto Geográfico Nacional (IGN) has been in charge of volcano monitoring by law. A monitoring system has been developed to perform its duties, mainly focused on the Canary Islands, Spain’s most important volcanic region. According to its responsibilities, IGN successfully managed the La Palma eruption in 2021. One of the techniques applied was InSAR (Sentinel-1 mainly), thanks to an automatic system which generates interferograms, coherence and displacement maps very quickly as soon as images are available. These results are combined with other deformation data and derived geophysical information to produce hazard maps and forecasts. Several PSBAS processing were also performed during the La Palma eruption thanks to the ESA NoR funding. In addition, the GEP services improved the Volcanic Monitoring System at Instituto Geográfico Nacional (Spain). As a result, information was extremely useful in managing the emergency.

On the other hand, IGN is Copernicus Relay and National Land Reference Centre. Since 2017, IGN has been organizing training events related to Copernicus activities. During 2020- 2021 some courses focused on InSAR were partially funded using NoR “GEP services to improve the Volcanic Monitoring System at Instituto Geográfico Nacional”. We had a dedicated app in GEP where participants were guided to process some selected cases using mainly PSBAS service. These GEP sessions showed the potential of InSAR advanced techniques; some students show particular interest in including InSAR-GEP in its professional activities. IGN belongs to MITMA (Ministerio de Transportes, Movilidad y Agenda Urbana), which has duties on infrastructure maintenance (ports, roads, railways…). InSAR techniques are not well known, but we know they have a strong potential in infrastructure monitoring that we would like to show during the course. Moreover, through an organism called CNIG, we participate in EGMS validation consortium with our permanent GNSS network, so we are especially interested in disseminating InSAR and GNSS validation activities. Therefore, our project is focused on a specific training event from 3 to 14 October, where we would like to introduce the use of PBSAS service to 20 new students to process some dedicated use cases.

The project intends to bring information about new and current fly tipping and illegal landfills over the territories. We do that by combining very high-resolution optical images with state-of-the-art deep learning algorithms. We integrate the results of our analysis in a geographical database, and we build collaborative functions to help stakeholders coordinate their action to evacuate the waste and wipe the polluted sites. Our end users are public authorities that struggle to understand the phenomenon and the spatio-temporal patterns due to the lack of a platform centralizing all the location, date of images, approximated volume, growth over images acquisition and actions that have been undertaken on the locations.

The project implies to task AOI regarding the level of the customer (region, department), requiring between 8 and 12 images a year, depending on the feasibility, available bandwidth and cloud coverage.

The platform is available for end users without limitation of time or functionalities, and they are aware about the last date the predictions have been added to the platform. Which depends on the acquisition

process.

The Image Satellite Visualizer is an Android application developed to obtain satellite images and display them on a Liquid Galaxy system, a multi-screen and multi-device computer cluster capable of running an immersive panoramic experience. The Sentinel Hub OGC API images will be stored on the device and sent to Google Earth as a Ground Overlay. The project aims to show satellite images of respective areas to obtain a more complex layer of information. Results can be used to make Liquid Galaxy an alternative educational tool in classrooms, giving the power to teachers to display geographic info intuitively.

Project objectives: Scientific VM template to provide continuity after esa365 migration

The main goal of this research project is to make the most of the powerful Sentinel 1 Ground Range Detected (GRD), Sentinel 2 MultiSpectral Instrument (MSI), Sentinel 3 as well as Sentinel-5p TROPOspheric Monitoring Instrument (TROPOMI) data. Additionally, I want to use the GHS-BUILT-S R2023A – GHS built-up surface grid data ingested into Sentinel Hub to create an example Jupiter Notebook that demonstrates a use case for accessing and working with the data set. I will also use the data for my Master’s Thesis project about extreme events. This project aims to push the boundaries of Earth observation and geospatial analysis by combining cutting-edge satellite data, advanced processing techniques, and state-of-the-art cloud infrastructure. A crucial objective is to seamlessly integrate the processed GHS-BUILT-S R2023A data for usage in a Jupyter Notebook to evaluate the impacts of wildfire on populated areas on a European site. By using widely accepted data sharing and interoperability standards, I hope to encourage collaboration and allow different scientific fields to use these data products.

The project aims to generate an initial debate about IUU fishing in the South West Atlantic region and about the need for regional cooperation and strategic tools adaptation to combat it, exposing the threats that unreported and unregulated fishing implies to the regional marine ecosystem, national and regional economies, safety and geopolitical stability. The objectives are:

• Produce knowledge and information about IUU fishing oriented to politicians, legislators, NGO representatives, and decision-makers in Argentina and among other stakeholders of the region (South America)

• Spread quality information for regional and international media about IUU fishing in the South Atlantic Ocean and possible pathways to solutions.

• Introduce massive regional public in the debate about IUU fishing (beyond Argentina)

As a continuation of research regarding the development of regional correction models (Nadzir, 2017; Passaro, Nadzir, & Quartly, 2018) and to utilize many advancements achieved by various Coastal Altimetry datasets (Passaro, Cipollini, Vignudelli, Quartly, & Snaith, 2014; Birol, et al., 2021), a comprehensive evaluation of various retracker designed for coastal areas and development of regional correction model are planned to improve altimetry data around Indonesian seas further, in turn also improving the estimated marine geoid model. This topic is mainly divided into two parts: improving the altimetry dataset by comparing coastal datasets, developing regional correction models, and establishing a marine gravity model from the improved datasets. Five working packages (WPs) are dedicated to fulfilling this goal that will last for ~ 36 months. The first WP is working towards finding the most suitable coastal datasets (currently using five datasets: ALES (Passaro, Cipollini, Vignudelli, Quartly, & Snaith, 2014), X-TRACK/ALES (Birol, et al., 2021), TUDaBo (Fenoglio & Buchhaupt, 2018), STARS (Roscher, Uebbing, & Kusche, 2017) and SAMOSA++ (Dinardo, et al., 2020)). Then, the process will continue in the 2nd WP, which is concerned with formulating correction models, currently the sea-state bias model. After that, the improved altimetry datasets will be used to determine the marine gravity model of Indonesia, using either sea surface slope (SSS (Sandwell & Smith, 1997)) or sea surface height (SSH (Andersen, Knudsen, & Berry, 2010)). The results will be compared and validated in the 4th WP, similar to Zhang, Abulaitijiang, Andersen, Sandwell, & Beale, 2021. Moreover, in this WP, the marine geoid model will be compared with various global models such as XGM2019e (Zingerle, Pail, Gruber, & Iokonomidou, 2020) and EIGEN-6C4 (Förste, et al., 2014). Lastly, in the 5th WP, land data provided by the Indonesian Geospatial Agency (BIG) will be assimilated with the marine gravity model to obtain Indonesia’s most updated gravity model.

The objective of the project is to assess the health conditions of different crops such as coffee, cotton across various plantations in Africa, South America and Asia by using high resolution satellite images. The project aids the farmers by providing timely remedies to improve the yield. This helps the farmers to take rapid decisions on various remedies to be considered for effective yield. The solution will help upon the following functionalities:

– Crop Health Assessment for Various Farms: For precise and timely production forecast, crop health assessment is a vital component. Using a variety of image processing techniques, the health of the plants is determined from the satellite images. Plants are classified into healthy and unhealthy plants, and the farmer is informed of the health conditions of the crops across the farm.

– Remediation Steps to be taken by farmers: The agriculture industry faces numerous difficulties that needs timely resolution. The project proposes remedies for the identified health conditions. These remedies can be applied for improving the yield across the plantations

– Accessing Yield of various crops: From the satellite images captured from the plantations, the project can derive an approximate yield of various crops grown. This can help the farmers understand their overall productivity across farms. The predicted yield can help the farmers to make effective global decisions. The project utilizes high resolution satellite images to achieve these functionalities. The results of this research are used to make wise decisions in a timely manner to increase yields throughout the plantations across various geographic regions.

The artificial iNtelligence for Food sEcuRity- INFER- Project aims to foster the adoption of Al models for Earth Observation (EO) applications. Many initiatives have been recently launched by the ESA to augment the availability of training data, to support new ideas through the creation and management of challenges, and to incrementally adopt standards that facilitate the interchange and reuse of resources. This project has a focus on a more operational aspect, e.g. to enhance existing cloud-based processing-oriented platforms (e.g. TEPs, DIAS and other initiatives) by adding Al-specific capabilities.

“Floods are increasingly affecting many countries globally, and in particular, urban areas, over the past decades. In several Global South cities and particularly in Sub-Saharan Africa, they are the most frequent disaster. The gradual transformation of natural soils into impervious surfaces has led to a low infiltration capacity and a growing surface runoff volume. This change, which reflects urbanisation, has become uncontrolled due to poor control over land, rapid housing production, urban growth, and cities’ fragmentation legacy inherited from the colonial period. Over time, so-called “”informal”” settlements have been set up in spaces where the risk of flooding is high. This mechanism tends to weaken vulnerable populations, including the poor and people “”trapped”” in these areas. The adaptation measures adopted by both the population and other actors (governmental* and non-governmental) are often temporary and insufficient. Given the population growth projections for these cities, there is a risk that future urban expansion amplifies the exposure of vulnerable groups to flooding in the coming years.

The overarching question addressed in this research is: “How to foster the resilience of informal settlements located in flood-prone areas?” The objectives are (i) to develop simplified models of pluvial floods considering climate change, and applicable in data-poor environments such as Global South cities, (ii) to analyze the drivers and challenges of urban densification and expansion, and informal settlements development on the one hand and vulnerability to flooding on the other hand, and (iii) to develop a hydrosocial model dedicated to informal settlements in flood-prone areas. We will synthesize the research results in an integrated approach for the cumulative and long-term adaptation of informal settlements exposed to flood risks.”

The “Information Factory Pathfinder: Drought/Irrigation Indicators for Danube Region (Danube GTIF)” generally shall establish means to match better demand and supply regarding information products that can be derived from satellite Earth Observation (EO) by a combination of EO and non-EO geo-spatial | /environmental data, and be provided via services to customers (end-users) in government, commercial and scientific institutions in the Danube Region and beyond. To suppliers of those non-space data that may create an additional value for irrigation/drought applications fed by EO, Danube GTIF shall offer an attractive data-sharing environment. The bidder proposed three use cases in the project as demonstrators in three countries, with local integrators as initial use cases. One of them is Use-case 1.:Hungary, support software for agricultural consultancy. The scope of this use case is to demonstrate how the Information Factory can support many farming companies with services that promote sustainable development and operation both in environmental and economic terms. With the services offered by the Information Factory, we aim to create a targeted software solution that provides all relevant indicators for consultants and business owners and lets them run simulations for their farms to prepare for different scenarios under different (simulated) environmental and economic conditions. Lechner Non-profit Ltd. provides field monitoring services for drought risk and damage assessment. These services will be onboarded on the Information Factory and become the fundament of the resulting use case demonstrator. A module to support agricultural consultants will be implemented in the proposed demonstrator. Based on soil data, dynamic meteorological data, satellite imagery, and modeling components provided by the IF framework, predictions will be made available at the level of individual agricultural parcels (fields), including characteristics of interest such as yield and water demand. These data and predictions will be available dynamically, i.e., several scenarios and “what-if” modalities can be run and analyzed over the parcels of interest.

Agro Profi Ltd. is selected as a local integrator for this use case.

The uptake of local soil samples is an essential aspect of this use-case demonstrator. We need to develop a tool for uploading soil samples, which will be listed on the Marketplace as an API for all value-adders and local integrators. This can result in new intermediary information products that will also be shared on the Marketplace.

The overall project aim is to establish means to match better demand and supply regarding information products that can be derived from satellite Earth Observation (EO) by a combination of EO and non-EO geospatial/environmental data and be provided via services to customers (end-users) in government, commercial and scientific institutions in the Danube Region and beyond. The specific application for yield is one of the critical services for all agriculture-related services – monitoring the plant’s growth and growth condition over time to predict the current and potential yield accurately. Specifically, we will provide advanced Crop modeling for Insurance-related Crop Damage Assessment and loss adjustment, which is of central importance for insurance companies since payout from insurance is directly related to the relevant loss in the harvested yield of the specific crop.

The “Information Factory Pathfinder: Drought/Irrigation Indicators for Danube Region (Danube GTIF)” establishes means to better match demand and supply regarding information products that can be derived from satellite Earth Observation (EO), by a combination of EO and non-EO geo-spatial /environmental data, and be provided via services to customers (end-users) in government, commercial and scientific institutions in the Danube Region1 and beyond. To suppliers of those non-space data which may create an additional value for irrigation/drought applications fed by EO, Danube GTIF offers an attractive data-sharing environment. A win-win partnership model shall be offered by which these suppliers would maintain their own datasets inside the Danube GTIF and make them available either at commercial conditions or following open data policies. To suppliers of value-added information products which may be contributed as “applications” to the Danube GTIF either provided via an algorithmic workflow, combining existing data and information products, or via AI models and relevant AI training, Danube GTIF offers a hosting and Request ID: 4108vC Page 2 of 5 NoR Version: V4.5.1-4.5.6 1. 2. runtime environment. As well, a win- win partnership model shall be offered by which suppliers would make their application(s) consumable at commercial conditions to Danube GTIF customers.

The use case objective is the identification and mapping of potential irrigation sites to enhance the capacity for resilience against drought events.

The main technical objectives are to prototype an Information Factory that will enable data owners, analytics companies and end users to host, find and ingest EO data to get them parsed into analytics pipelines and make them available for direct integration.

The proposal is within the ESA PECS Programme for Bulgaria where we propose to develop a sediment deposition monitoring system with two applications:

1) the monitoring of the fairway of navigable rivers,

2) the monitoring of the live storage of reservoirs retained by dams.

The proposed system focuses on sediment deposition in the Bulgarian part of the Danube River and sediment deposition in the Arda River, more precisely concerning the dead storage of the three reservoirs on that river created by the three dams: Kyrdjali; Studen Kladenec; and Ivaylovgrad. This pretends to help the two public organizations: Executive Agency for Exploration; and Maintenance of Danube River and Dams and Cascades Enterprise, to better fulfil their responsibilities for the fairway and the water resources management, by adopting an innovative use of Earth Observation data, EO4AI, to build an AI solution that utilizes them in combination with in situ measurements and other contributing factors and derives forecasts of sediment deposition. The technical objectives of ISMoSeDe are:

1) to develop a method for predicting the sediment deposition, by exploring the variety of factors impacting this process (e.g. water turbidity, the river runoff, the velocity and direction of the flow, meteorological data, human activities influencing the discharge from hydro reservoirs and hydropower plants and by using in situ measurements and different categories of satellite data, most prominently water turbidity, but also precipitations, wind, vegetation, soil moisture, air temperature)

2) to create a linked data infrastructure, combining different types of heterogeneous data (e.g. in-situ measurements, satellite data, domain knowledge about sediment deposition)

3) to build an integrated system, where the GIS component will show the river catchments and the sediment deposition forecast, and the system will allow querying of historical and forecast data in an integrated manner with the GIS.

As a result, it provides an integrated information system for monitoring sediment deposition implementing a semantic information infrastructure with an AI component for predicting sediment transport and deposition, visualizing the forecasted changes in the river morphology, and enabling consultation, observation and query historical and forecast data. To obtain this, it is convenient to link data technologies and neural network architectures to create semantic information infrastructure with an intelligent layer where ontologies and logical reasoning interact with prediction models, derived from neural networks, and satellite data source – the ADAM platform that will provide direct access to the necessary satellite data and a GIS component to visualize the Basemaps for the territory of Bulgaria; Satellite imagery; Hydrographic data; Sediment in-situ measurements, and Sediment deposition forecasts from the intelligent component of the system. We started with CNNs and extended the models with generative adversarial network architectures and evolutionary algorithms that can deal with inconsistent data. Historic data from satellites and in-situ measurements about turbidity, surface reflectance, precipitations, snow cover, wind, vegetation index, solar irradiance, velocity, and direction of the river stream are used. A sedimentation monitoring domain ontology is designed, and situations that need logical reasoning to augment the neural network models are identified and implemented. The interaction and the data flow between the semantic infrastructure, the GIS component and the satellite data are designed to ensure the integrated system functions in a synchronized manner.

Satellite altimetry has been increasingly used for inland water monitoring. For instance, a plethron of studies investigated lake level variations across the globe to look into the responses of lakes to climate changes and human activities. Moreover, altimetry can establish so-called virtual hydrological stations and provide river water level time series. Thus, this information is used for hydrological studies, such as discharge estimation, hydrodynamic modelling, etc. However, operational applications are rare because altimetry-derived water level quality varies with certain conditions, especially the topography and surroundings. This issue has been reported frequently in the literature. The retrieval water level of narrow rivers is challenging. Indeed, this is a big challenge for the potential use of altimetry for hydrology, hydraulics, water resources management, etc. Our previous work has demonstrated the value of altimetry-derived water level data for hydrodynamic model simulation, especially the Cryosat-2 with dense ground coverage. Given the sparse gauging stations, altimetry-derived water levels can greatly facilitate flood modelling and forecasting. Current altimeters, such as Cryosat-2 and Sentinel-3, often offer pretty good data quality. However, whether accurate water levels can be retrieved depends on the algorithms. Exploring the capability of different altimeters for narrow river-level retrieval is a necessary step for improvement. This has not been widely studied, and the potentials are poorly understood. We ask whether it is feasible to use altimetry data to construct water level time series for narrow rivers. Therefore, we will develop algorithms to enhance water level retrieval in this project.

One of the selected projects from the OSIP campaign is the WASP project of the company Argans. The aim is to detect windrows as a proxy for marine litter monitoring from space. Litter windrows in the ocean are small-scale aggregations of floating litter, with lengths ranging from tens to hundreds of metres. They are generated by specific wind-triggered oceanic dynamics that create convergence zones. This study aims to construct a map of these windrows in the Mediterranean Sea, analyse their correlation to other drivers, and test the capability of the Copernicus Sentinel-2 satellite to anticipate areas for potential environmental monitoring and cleaning action. It additionally correlates the number of windrow pixels in an image to the meteorological parameters that preceded its formation. The project integrates data from Sentinel2 with data from climate reanalysis to investigate the predictability of formation of windrows, and as such, marine litter hotspots.

This use case belongs to a pilot project of the Space and Security Community Activity of the Group on Earth Observations (GEO), carried out in cooperation between EU SatCen, ESA, EuroGeoSurveys (in particular with the Instituto Geologico y Minero de España -IGME), the World Food Programme and the German Federal Agency for Cartography and Geodesy (BKG) and the IHE Delft Institute, on an in-kind basis. The pilot is coordinated by EU SatCen, while WFP acts as liaison with its field office in Pakistan and relevant Pakistani users. IGME is extrapolating previous algorithms and results to an Area of Interest (AoI) in Pakistan. In addition, ESA and BKG support analysing users’ needs and identifying synergies with available resources. Pakistan is now ranked as the world’s fifth-largest population. It is among South Asia’s most rapidly urbanising countries (annual rate of 3%). According to the United Nations Population Division, by 2025, nearly half of the country’s population will live in urban areas.

The increasing trend of urbanisation has significantly strained access to essential services. One of the biggest challenges faced by the country due to increased population is access to clean water and water management. The groundwater table in Pakistan is believed to drop a meter yearly due to over-exploitation for drinking and agricultural purposes. Pakistan has the world’s 4th largest groundwater aquifer. Still, at the same time, it is the 4th most significant groundwater withdrawing country, making the Indus Basin aquifer the second most overstressed groundwater basin globally. This deteriorating condition calls for groundwater resource management, which depends on effectively monitoring the water table. A specific technique in this regard is Synthetic Aperture Radar Differential Interferometry (DInSAR), using Sentinel-1 data, which is used to track land subsidence (that can be later analysed to find a correlation with groundwater extraction) and associated risks for population and infrastructure. The selected area is the twin cities of Islamabad and Rawalpindi, which is smaller than 50 x 50 km and has strong reasons to be identified as the best AoI for the study.

The Trans Adriatic Pipeline (TAP) is a pipeline that extends from the Turkey-Greece border, crosses the northern Greece mainland and southern Albania, and ends up in southern Italy through the Adriatic Sea. Along this pipeline, several areas of geohazards have been identified posing a threat to the integrity of the pipeline. These geohazards are related to slope failures i.e., landslides and rockfalls, liquefaction and subsidence. This project focus on landslides that represent the most significant hazard for TAP due to the fact that can induced severe damages to the pipeline in case of triggering of the mass movement. In particular, the goal of this project is twofold; application of the InSAR technique in order to identify areas of active slope failures along the TAP and monitoring them in order to evaluate the landslide displacement rates. Furthermore, the obtained results by the application of InSAR will be compared to an existing inventory of landslides along the TAP corridor and validated based on the outcome of inclinometer systems that have been installed within the landsliding mass in order to measure the displacement along the sliding surfaces.

ADM-Kenya aims to co-develop solutions for monitoring crop conditions and cropping systems using Earth Observation (EO) time-series observations. The goal is to derive evidence-based, quantitative estimates of vegetation conditions with improved spatial and temporal resolution. Additionally, we strive to develop innovative EO-based solutions for drought monitoring nationally in Kenya. The primary technical objective is to build cloud-based processing algorithms to enhance spatially explicit analysis of drought hazards and impacts. Furthermore, the project aims to create drought-relevant agricultural information. This encompasses high-resolution crop management information derived from multiple remote sensing data sources. These data include national-level irrigation maps and localized information on cropping practices (mono/mixed cropping) for pilot areas. For the process of contextualization and validation, we develop innovative data fusion approaches. These approaches will be based on field observations and very high-resolution satellite data.

This project is summarized in the following objectives: 1) To evaluate the variability in the spectral response of the TreeTalker (TT+) sensor to the transmission of sunlight for the monitoring of seasonal phenological dynamics at the level of forest species. 2) To evaluate the variability in the spectral response of the TT+ sensor to the transmission of sunlight. for the monitoring of seasonal phenological dynamics in different forest ecosystems of the TT+ network. 3) Expand the scale of evaluation of forest ecosystems by integrating the spectral information of the TT+ sensor with active, passive and hyperspectral sensors for seasonal phenological evaluation and ecophysiological parameters in the areas with TT+ network monitoring.

This thesis aims to study the new methodology of Interactive, Active Object Detection (IA-OD) in Remotely Sensed (RS) data. IA-OD is a computer vision task that combines machine learning-based object detection with interactive elements and active learning, allowing users to participate in the detection and training process. In this context, interactive refers to a system where a user can interact with the detection model to refine, guide, or query the detection process iteratively. While active refers to the process of active learning, where the model selects and queries the most informative data points to be labelled by an oracle, to improve its performance with a minimal amount of newly labelled examples.

This activity refers to the analysis of multi-sensor EO time series at various scales, to evaluate the impact of COVID-19 in selected Areas of Interest over Europe. The analysis aims to detect/discover changes in patterns of life indicating preparatory, response and recovery measures and activities.

Anecdotal evidence suggests that intertidal sediments in Southwest England estuaries appear to be undergoing a shift from smothering green macro-algae, to dense seagrass habitat. The causes and spatial extent of this change and the impacts on estuarine ecology are unknown. Furthermore, whilst much is known about subtidal seagrass and their high global conservation importance, little is known about intertidal species and the ecosystem services they provide. Therefore, this project seeks to evidence the recent ecological and spatial changes of intertidal seagrass in the South West, and to establish the ecological and socioeconomic value of intertidal seagrass. The project makes extensive use of Earth Observation (EO) data to develop a methodology that can efficiently and accurately map intertidal seagrass beds in Southwest England. The results of which, when coupled with in-situ ecological observations, have significant implications for national environmental policy makers, with potential for scalability to a global level. The project aims to:

1. Provide formal evidence for the change in intertidal vegetation.

2. Identify the regional and local drivers of apparent increases in intertidal seagrass meadows in SW England

3. Determine which factors can be managed to support seagrass restoration efforts elsewhere.

4. Provide understanding of the ecological consequences of this change for intertidal ecosystems

5. Consider what ecosystem services are supported by intertidal seagrass and what are the implications of seagrass recovery for natural capital.

The methodology applied is the following:

 Using empirical observations from the ground and aerial drone photography to train models that analyse EO data from satellites to identify intertidal seagrass. This analyses NDVI to track the extent of recent development of intertidal seagrass in SW England and other estuaries in the UK.

 Through case studies in SW England the project explores historical occurrence and possible causes of the development of meadows.

 Through field sampling in estuaries and laboratory analysis, the project examines the influence of seagrass on the underlying benthic fauna and its functions.

 The project then quantifies potential effects on the flows of ecosystem services, including carbon flows for climate regulation, finally considering the social and economic natural capital implications.

 During the project a programme for future monitoring of intertidal seagrass through citizen science projects with drones, is an area that could be developed.

The main objective of this research project, which is part of my Bachelor of Science Geology studies at the Open University, is to investigate ground displacements that occur before landslides in urban areas in Germany, with a particular focus on former coal mining areas that have been flooded and converted into swimming lakes. The reason for this focus is that landslides on the shores of these lakes can cause damage to buildings due to large waves (up to 1.5m) created as a result of the landslides. To achieve this objective, the study will utilize Sentinel-1 data and process Persistent Scatterer Interferometry (PSI) products with the SNAPPING service from Geohazard TEP to detect potential areas at risk of landslides on the shores of these lakes. The Sentinel-1 data will provide high-resolution radar images that can be used to detect ground displacements, and the SNAPPING service will process this data to extract relevant information for the study. The study will begin by investigating spots with known landslides and analyzing the horizontal and vertical ground motions before these events. This information will then be used to identify places where the risk of landslides is increasing. The study will focus on an area of approximately ten sqkm around each lake, considered an appropriate size. The results of this study will be shared with researchers, lecturers, and local administrations in the affected areas, as well as through local public media outlets.

We used the SBAS-InSAR service to process Sentinel-1 data to generate ground displacement time series and LOS deformation velocity over the Lagos metropolis. The SBAS-InSAR results produced subsidence maps for Lagos. In addition, geostatistical tools were applied to the LOS velocity to create a continuous subsidence field for the Lagos metropolis. The next phase of the study will focus on modeling land subsidence future scenarios from the most recent date viewpoint. The SBAS analysis and Persistent Scatterer analysis results will be contrasted and compared. In addition, landslides in part of southeast Nigeria will also be studied using InSAR data. The results of observation will then be used to predict future trends.

As a GEP Early Adopter, SBAS-InSAR service has been used to process Sentinel-1 data in order to generate ground displacement time series and LOS deformation velocity over the Lagos metropolis. With the SBAS-InSAR results, subsidence maps were produced for Lagos. In addition, geostatistical tools were applied to the LOS velocity to create a continuous subsidence field for the Lagos metropolis. The next phase of the study focuses on modelling land subsidence future scenarios from the most recent date viewpoint. The results of SBAS analysis and Persistent Scatterer analysis are contrasted and compared. Landslide in part of south-east Nigeria is also studied using InSAR data. The results of observation are then used to predict future trends.

Recent improvements, especially in the last decades, in the Earth Observation

field allow to measure the cumulative deformation occurred for example during

the seismic cycle or volcanic activities by means of remote sensing data with

high accuracy. The use of radar satellite data and the multi-temporal differential

interferometric techniques allow to obtain information concerning the

processes and phenomena relative to the cumulate and subsequent release of

the ground deformation related to the aforementioned phenomena. Hence by

now, it is of fundamental importance to have the availability of powerful

methods to achieve such goal and the SBAS approach for sure represents the

state-of-the-art among the possible methodologies. The proposed project

intends to provide mean ground velocity maps and the relative displacement

time series for the areas prone to be exposed to different types of hazards

worldwide but especially in the Italian territory.

Who will benefit from the project results: The outcomes from this project

will be of high importance for research aim providing a very important

input to the modelling algorithms other than a reliable information to be

integrated and merged for a deep investigation and knowledge of the

considered areas. Moreover, the Local Authorities and decision makers as

providing information to mitigate possible risks in several fields of

application thanks to the nowadays large availability of Earth Observation

data acquired with dense temporal and spatial sampling.

Bog Surface Oscillation (BSO) is a hydrological self-regulation mechanism that allows peat-rich bogs in temperate regions to swell during the wet season before shrinking in the dry season. Managers at Burns Bog in Delta, British Columbia, use BSO as a critical metric to understand the overall health of the bog because it can indicate the depth of the water table and the potential water storage capacity, reveal associated hydrological dynamics, and provide insights into the restoration progress in the bog (Howie and Hebda, 2018). The monitoring of BSO at Burns Bog has been a multi-decade project and is done using fixed piezometer sticks at 67+ monitoring sites throughout the nearly 2000-hectare bog (Hebda et al., 2000; Howie and Hebda, 2018). However, it is still challenging to understand the oscillation of the entire bog and visualize its spatial patterns and temporal changes. InSAR is an effective tool to address these challenges by mapping the surface line-of-site deformation for the coherent areas of the bog and thus visualizing the spatiotemporal variations. DInSAR has previously been used to monitor the changes in peatland surface deformation in a growing body of literature (Cigna et al. 2014; Alshammari et al. 2020). Sentinel-1 time series interferograms for this project will be generated for dates between 2014 and 2021. We intend to use the P-SBAS workflow for the interferogram generation process. The generated interferograms will be used to monitor the surface oscillation at Burns Bog, observe its spatial and temporal changes, and understand environmental factors’ impacts (e.g., precipitation and temperature). The data collected from the ongoing field monitoring program (e.g., elevations of bog surface) will be used to determine the accuracy of this integrated P-SBAS approach. Research results are expected to improve our understanding of surface elevation changes at Burns Bog and support better ecosystem management.

The objective of this project is to be able to determine whether the plant types, hydrophytes, mesophytes, xerophytes, and halophytes, in a coastal case study (lagoon/estuary), in this case, the Knysna Lagoon, can be remotely identified from satellite imagery and whether this can be used as additional information in determining the location of the High-Water Mark remotely. The project results will be if satellite images can be used to determine the High- Water Mark remotely and ensure that it conforms to the Integrated Coastal Management Act 2008 in the Western Cape, which will aid in reducing the time spent on surveying.

The aim of this project is to address the pressing issue of “Climate Change Action and Resilience” in the Northern Canadian Territories, with a specific focus on the vulnerability of infrastructure, particularly airports, to permafrost impacts. Climate shifts and human activities like construction have led to increased ground temperatures and deeper active layers in regions with frozen ground, resulting in issues such as sinking buildings and ground shifting. Adapting construction methods to manage freezing conditions is crucial to mitigate these risks. Monitoring ground surface deformations becomes vital for managing permafrost-related risks and supporting community planning. Interferometric Synthetic Aperture Radar (InSAR) techniques offer continuous and high-resolution spatial information, especially valuable in areas where collecting in situ data is challenging. The main goal is to focus on assessing permafrost’s impact on essential infrastructure, especially airports, which are critical for native communities.

The project aims to identify the nature and extent of illegal sand mining and subsequent impacts on societies and ecosystems in South-East Asia, particularly in the Mekong Delta area and the Ayeyarwady region. As urbanization and population growth drive the demand for construction materials worldwide, local riverine and ecosystems are under increasing stress due to the exponential growth of dredging activities. However, the official reports on mining are considered unreliable as they do not account for the illegal sources of sand. Illegal mining is estimated to constitute one-third of the total sand demand in South-East Asia. Therefore, international organizations like the UN and the WWF, among others, are calling for research into sand mining monitoring systems to identify illegal activity. Moreover, they want to inform regulations and policies to hinder indiscriminate mining that threatens severe environmental damage, ecosystem services, and people’s livelihoods.

Ice covers are common in cold regions, including Canada. Ice covers have been reported to be a significant factor in reducing the accuracy of lake water level retrieval using Sentinel-3 altimetry data. I request a temporary, continuous level-1B stack data in one winter to explore ice cover effects. This project will provide inputs and benefits for new retrackers development in EO science communities, water surface height data accuracy for hydrology research communities, and sustainable water resources management.

Given that the spread is through proximity to infected persons, there is no contribution that EO can credibly make to propagation analysis or forecasting. Therefore, the focus should be on mapping visible aspects of preparations, consequences and recovery. Within this context, the following analyses could be possible using a mix of EO and in-situ datasets:

• Change in situation at border check-points (both Intra-Schengen and Schengen External Borders)

• Change in situation for economic operators (factories, supermarkets, transport networks, oil refineries, commercial ports)

• Changes in human activity distribution (e.g. parked car distributions over urban areas, agriculture)

Investigations are performed with free Sentinel data but are complemented with Pleiades, Planet and Spot commercial data, accessible via the EuroDataCube.

In the wake of a forty-year tradition of research conducted by the University of Naples l’Orientale in the Arabian Peninsula, since 2009, the Italian Archaeological Mission in the Kingdom of Saudi Arabia has been carrying out research activities at the site of Dumat al-Jandal (ancient Adummatu) and in the North Arabian region of Jawf. The research, which initially focused on the ancient oasis and made it possible to rediscover the main cultural phases from the Assyrian era to the advent of Islam, is now articulated in a broader spectrum of contexts and disciplines. The archaeological excavations in the oasis are joined by the restoration and consolidation works (which have already contributed to the entry of Dumat al-Jandal in the UNESCO Tentative List); as well as remote geoarchaeological activities have been implemented, which have made it possible both to exponentially enrich the mapping of the cultural heritage of the region, identifying over 18,000 prehistoric sites, and contributing to the training of Italian and Saudi collaborators regarding the production of remote sensing archaeological maps based on the use of photo-interpretation and remote paleoenvironment recognition. In particular, the recognition and in­depth studies along Wadi As-Sirhan, which flows in an NW-SE direction in the wide valley of the Jawf at the center of the research concession of the Archaeological Mission itself, are promising.

This study shall utilize remotely sensed data, in particular high-resolution imagery, to implement the remote and field activities of the Project. Data imagery shall be addressed to collect and categorize archaeological evidence in the framework of the analyses in the al-Jawf northern Saudi Arabia region. The main focus will be the reconstruction of the palaeoenvironmental contexts from Prehistoric times (Late Pleistocene – Holocene) to Ιron Age along Wadi al-Sirhan, the main geoarchaeological feature of al-Jawf and to highlight – eventually – anthropic patterns through the analyzed areas under study.

Forests are the most actionable nature-based solution to remove CO2 from the atmosphere. However, forestry carbon fluxes vary based on management practices. We want to empower the forestry industry with diversity, biomass, and carbon data to grow forests and better fight climate change. Existing tools to inventory forests, assess their condition, and monitor changes are limited: they are expensive because they require sending experts on site and imprecise because they are based on statistical extrapolations. Using satellite data and artificial intelligence, we are developing kanop, an application to create forest digital twins. It will contain the same inventory (location of each tree, volume, species, etc.) and the indicators of its carbon sequestration performance (stocks, flows). Better monitored and therefore better managed, this forest will provide a more extensive and objective environmental service, essential for its long-term preservation.

The project objectives are to transform agriculture into a source of passive income for farmers and create an ecosystem based on AI using the Farming As A Service (FAAS) concept.

Farmers being part of this ecosystem will benefit from live customized agricultural plans and actions for their farms. The agricultural plan and actions modify according to crop evolution, the impact of agricultural technological activities, meteorological events, and pest/plant disease events. Starting with data gathering from satellites and interpretation from our agriculture specialists will offer farmers recommendations on what actions they need to take to protect their crop, what products they should use and in what quantity to maximize their yield and save money. This way, products will be applied rationally using Variable Rate Application, soil will be protected and regenerated by implementing agroforestry and carbon farming methods.

• Measure the performance of implementing agroforestry in conventional agriculture;

• Measure the performance of carbon farming methods;

• Study the overall temperature reduction of the crop by implementing agroforestry and carbon farming;

• Study the reduction of evapotranspiration of water from plants and soil by implementing agroforestry and carbon farming;

• Reduce the use of chemicals products for agriculture;

• Reduce overuse of water;

• Reduce labour with agricultural machines;

• Obtaining sustainable agriculture.

From the result of this study will benefit:

• Farmers, because they save money and resources;

• Consumers, by eating healthier food because the plants will be closer to natural development, with minimum intervention with chemicals;

• Overall population, because our actions will reduce the carbon footprint of businesses related to agriculture.

The results directly impact the economy, the population’s health and climate change, so that they will be available from day one of our launch on the market. The results will improve as our ecosystem improves.

We are a group of data science graduate students working on our final capstone project. We are working with researchers in Louisiana to develop a tool that will query historical air pollution data from the Sentinel-5p satellite for researchers to analyze disparities in air pollution exposure in the state.

The EPA has raised red flags about issues with environmental justice in the area, and this data is essential for providing researchers with the information they need to analyze these trends with air pollution specifically.

Additionally, we want to develop a prototype of a tool for the state that will propose an alternative to air pollution estimates using satellite data rather than their current sparse sensor data.

The primary goals focus on:

– Enhanced Agricultural Insight and Support: to analyze crop conditions throughout their growth cycles using multispectral imagery. This will help in assessing plant health, estimating biomass, and predicting yields, which are vital for supporting local farmers in maximizing their crop outputs and managing resources efficiently. Implement predictive analytics to forecast agricultural outputs and potential issues such as pest infestations or crop diseases. This proactive approach will enable farmers and agricultural boards to take timely action, thereby minimizing losses and optimizing production.

– Dynamic Urban and Environmental Monitoring: Utilize satellite data to monitor urban expansion and its impact on natural resources and surrounding land. This will assist urban planners and government bodies in making informed decisions regarding land development, infrastructure projects, and environmental conservation. Monitor environmental parameters such as land degradation, deforestation, and changes in water bodies, aiming to provide a sustainable model of monitoring that contributes to ecological conservation efforts.

– Data-Driven Decision Making for Policy Makers: Develop a reliable database of geographical and environmental data that policymakers can use to draft regulations and policies aimed at land use efficiency and sustainable development. Provide regularly updated data and trend analysis to government agencies and non-governmental organizations involved in land management, helping them to respond effectively to changes and plan future initiatives based on solid empirical evidence. Capacity Building and Technology Transfer: Establish a knowledge transfer framework whereby local analysts, technicians, and decision-makers are trained

in the use of satellite imagery and GIS tools. This capacity-building effort will ensure that the benefits of the project extend beyond its lifecycle and contribute to long-term improvements in local expertise. Engage with academic and research institutions to facilitate ongoing research into improved methods of satellite analysis, fostering an environment of innovation and continuous improvement.

We want to perform a first evaluation of as many as possible geohazards tep products and applications, exploring their use, their outcomes, as well as the usage of the interpreted data (after exporting from geohazards-tep) as input for geospatial analysis in our GIS Portal. The geohazards-tep data shall be processed in correlation with our power plants’ geographic database to identify the actual presence or possibility of land surface (or other) phenomena impacting our Assets. The added value of the geospatial results analysis would benefit all Operation & Maintenance areas/levels. It shall identify sensitive areas in our plants and trigger all relevant O&M activities.

The project aims to monitor the land use, animals, and grass savannahs. The system requirements are:

• Land identification.

• Biomass identification.

• Biomass estimation.

• Land usage reports over a couple of months (as much time as possible) to verify and validate results.

Outputs will be trained neural networks for land identification, biomass segmentation, and volume estimation (m^2) reports will be given to local/regional government bodies.

Objective of this project is to examine how the railroad system impacts the living environment in a certain region, by using artificial intelligence and land classification.

This project will focus on the field site of Bull Island, an island located within Dublin Port in North County Dublin, Ireland. Its creation began around 200 years ago, and now the island stretches approximately 5 km long and 1 km wide. It is home to St. Annes Golf Club and the Royal Dublin Golf Club. In 1964, the construction of a causeway connected the island to the mainland. The causeway also divided the island’s salt marshes into a north and south lagoon. Both lagoons have similar characteristics of being low-lying and sheltered behind a coastal spit, salt-tolerant grasses, Ιow energy, and fine­grained sediment.

This project aims to map, describe, and compare land cover change at Bull lsland in the past 100 years, from about 1809 to the present. Using historical maps from GeoHive, contemporary data from the ESA, and ArcGIS, this project will map environmental degradation, anthropogenic influence, and landscape and landform (dunes, sand bar, salt marshes, beach flat) development at Bull Island. The project will also map any impacts on carbon storage, location, and sequestration, one of the coastlines’ most vital and prominent processes. It is crucial to map and observe carbon storage at Bull Island, considering present and intensifying future climate change, sea-level rise, increased erosion, and extreme weather events that threaten coastlines and soil geography like Bull Island. Therefore, an essential objective of this project is to inform crucial coastal management plans to protect those living on the coast and important ecosystem services, biodiversity, and natural coastal processes.

Another important aim of this project is to fill a gap in the current literature and data surrounding Bull Island. Contemporary literature and data on Bull Island are limited, and its impacts and history are still debated. Considering the island’s proximity to Dublin city and ecosystem services, studying and gaining knowledge on its creation is vital.

The primary objectives of this project encompass the creation of a training dataset comprising pre- and post-landslide Sentinel-2 images and the exploration of deep-learning-based change detection models. The training dataset, spanning global coverage and featuring over two hundred landslides, will undergo processing to enable its integration into an innovative workflow. This workflow will incorporate both supervised and unsupervised deep learning-based change detection models designed to identify landslides using paired Sentinel-2 images. The ultimate goal is to assess the suitability of deploying this workflow in regions prone to landslides for emergency detection, rapid response to new incidents, and efficient damage assessment.

The project aims to analyze and monitor the landslides caused by wet microexplosions in Brazil using Sentinel Hub VAS – EDC. The primary focus is to detect and predict the occurrence of landslides and assess the extent of the damage caused by them. The project aims to provide valuable insights and information to various stakeholders, including government authorities, emergency services, and local communities, to enable them to take preventive measures and respond effectively during a landslide caused by a wet micro explosion. The project results will also be helpful for urban planners and developers to design and implement appropriate infrastructure and land use policies. The project’s beneficiaries are the residents on the oceanic Coast of South and Southeast Brazil, who will benefit from the increased safety and reduced risks of property damage and loss of life due to landslides.

Additionally, the government authorities and emergency services will benefit from the timely and accurate information to plan and execute effective response measures. The project will also utilize the Weather Research and Forecasting (WRF) model to generate weather forecasts/simulations that could trigger landslides. The WRF model will enable the project team to simulate and predict extreme weather events, such as heavy rainfall or thunderstorms, that could trigger landslides. This will allow the project team to issue early warnings and take preventive measures to reduce the risk of landslides and minimize their impact.

LAYERS is an AgTech platform currently being used by more than 3.000 users around the globe for all kinds of crops in four main products: SatTech2.0, SatPred, SoilTech and DroneTech. This platform evolved from drone-only to multi-input mainly for the operative costs and complications of the drone operations. However, drone are still being used in some “surgical crop-specific” use cases such as tree counting, weed or disease detection and monitoring.

SatTech2.0 and SatPred products use as spatial data Sentinel-2 and Sentinel-1 data accessed through SentinelHub.

The objective of “LAYERS HD Upgrade” is to explore, implement and test with real users higher resolution images in both intensive (e.g. orange trees) and extensive (e.g. sugarbeet, corn) crops.

PlanetScope HUM will be implemented in different crop types and both spatial and analytical results will be presented at least using NDVI but most probably other indexes such as NDRE. All these data will be available in LAYERS.

Rest of satellite sources will be explored in at least a fruit and an extensive field to evaluate the value that these products may have to the end-users. Imaging will be available in LAYERS.

All of these demonstrations will be offered to LAYERS users with no additional cost.

Corporations are facing growing pressure to decrease greenhouse emissions. For organisations, there are two ways to align with global climate strategies: cutting their own emissions and voluntary carbon offsetting. Voluntary carbon offsetting refers to paying another organisation for carbon removal by a third party. This method is associated with several well-known risks, including improper carbon accounting, re-release of stored carbon and negative unintended consequences on humans and ecosystems. Many carbon offsets involve methods with a high risk of being reversed over decades. In the case of physically storing carbon in a reservoir (e.g., forests or geological sink), the risk of the reversal must be acknowledged and accounted for. The above risks and their negative consequences can be accounted for if regular monitoring of carbon offsets is in place. In the case of agroforestry solutions (e.g., reforestation or improvement of agricultural practices to store more carbon) and organic soil carbon, such monitoring is required over vast territories. Therefore, companies employ artificial intelligence (AI) methods and satellite or aerial imagery to provide long-term monitoring. We propose a research project to explore how corporations monitor, account for and disclose their offsets, make decisions about the choice of these offsets, and how to choose AI methods for such monitoring. We will compare these methods and verify their performance on publicly available datasets. We will explore how these methods can be used in ESG reporting and what metrics can be derived from these methods.

SOWIT leverages all the power of Remote Sensing (drone & satellite), Agronomy and AI to provide decision support systems to African farmers. The information gap is filled allowing farmers to optimise inputs and improve their productivity, especially those facing huge instability related to global warming and extreme yield and input volatility. The solutions provide farmers with critical information such as water stress and nitrogen deficiency to better control their operations (sowing, fertilisation, harvesting). SOWIT was just selected in the last batch of the Copernicus Incubation program and won a grant to develop a remote sensing solution based on satellite imagery, to help the African farmers optimise their fodder quality. Harvesting fodder at the right time is vital for the farmer to get a product that is easily digestible by the cattle, and it has been observed throughout Africa that estimating the dry matter levels was not precise and needed to be streamlined. Furthermore, the farmer gets access to the heterogeneity of his plot, which in turn will allow him to plan his harvest, starting with the plots that have the highest levels of dry matter. The goal behind these solutions is to provide the smallholder farmer with all the tools necessary to help him/her increase his/her yields and face the challenge of the sustainable intensification of production. Getting access to the Sentinel Hub platform (Sentinel Playground & EOBrowser) alleviates all the complexities involved in fetching large amounts of satellite imagery from multiple providers, and all the preprocessing necessary to integrate this imagery into our processing chain. Getting access to multiple satellite constellations allows to explore other improvements that can be brought to the farmers, like using SWIR or radar data to estimate irrigation needs through soil moisture, humidity and surface temperature. It is possible then to extract multi-temporal imagery to build large databases that will feed our processing chain and algorithms participating in the improvement of the reliability of a developed model. This project combines agronomical models developed with the partnership of top-notch European research institutes and SOWIT’s knowledge in data science and image processing. It also involves a large part dedicated to ground truthing (mainly paid for by the grant from Copernicus), to collect data on Alfalfa crops at different growth stages, thus building a model that will estimate the dry matter levels with a margin of error of around 5%. This ground-truthing happens in Soudan, where there are partnerships with many smallholder farmers and a large corporation that will provide access to their fields. The results of this project are delivered as georeferenced maps through our web or mobile application, where the farmer sees the variability of his plots. In addition, the farmer gets push alerts to inform him when the dry matter is approaching critical levels so that he gets all the leverage needed to harvest at the right time and the right place.

The main objective of LIFE URBANGREEN is to optimize and demonstrate, in real-life, an innovative

technological platform to monitor ecosystem services of urban green areas and to improve their

management. During the project, the existing management platform R3 TREES will be integrated with 5

innovative management components aimed at:

• reducing water consumption, providing water only when and where needed

• reducing the carbon footprint of maintenance activities through a more efficient job planning

• quantifying ecosystem services provided by green areas

• monitoring health conditions of trees using remote sensing data

• increasing citizen participation in urban green management.

The expected result is a smart and integrated management system that monitors and governs all urban green areas management activities, maximizing ecological benefits.

LOGS project aims at investigating the past, recent, and future evolution of a hundred Local Glaciers (LG) near the Greenland settlement of Sisimiut. Greenland LGs, namely those glaciers not linked with the Greenland Ice Sheet (GrIS), are often overlooked by the research community in favour of GrIS, despite their higher sensitivity to climate change. LGs contribute for 15% of Greenland’s ice loss and have an important role in the local landscape providing hydropower, serving as recreational terrain and affecting local ecosystems. Understanding the past, recent and future evolution of such landforms is therefore not only fundamental to evaluate the cryosphere’s response to global and local warming, but also to inform the locals on the evolution of their natural landscapes and related practical effects.

Sea levels are rising due to global warming and the Philippines is expected to be negatively affected by this phenomenon. Located adjacent to Metropolitan Manila, Manila Bay not only provides resources and livelihood to surrounding communities but also poses a threat to nearby low-lying areas. Potential impacts of sea level rise include coastal recession, loss of coastal infrastructure, temporary or permanent inundation, and displacement of communities. In addition, it may also have negative consequences on the national and local economy. A comprehensive analysis is vital when tackling an issue such as sea level rise especially since regional sea level estimates vary from global rates. Remote sensing provides the technology to obtain and extract data over a large area through time. With the additional data obtained from in-situ measurements, will provide accurate estimates that will guide decision-makers in the effective planning and management of resources provided by Manila Bay. This also provides a baseline for future research on sea level rise in the country. The project aims to localize and quantify space-based measurements from satellite sensors through correlation with in-situ. Variables of interest include:

1) Sea surface temperature (SST),

2) Significant Wave Height (SWH),

3) sea surface height (SSH),

4) salinity,

5) wind speed, and

6) solar Irradiance.

These are extracted from remote sensing products such as Sentinel-3 (SRAL, WST), Landsat, and MODIS. Multiple in-situ instruments will also be deployed in different parts of Manila Bay to ensure that the entire bay is covered. -Who will benefit from the project results: Researchers and local communities.

The primary objective of this project is to identify and localize potential Roman settlements in the Amstetten district of Austria using high-resolution satellite imagery. We aim to create a comprehensive cartographic representation of these identified areas, which would serve as a valuable resource for future archaeological and historical studies. Furthermore, we seek to compare the newly discovered potential sites with existing archaeological findings in the region. This would not only validate our methodology but also potentially fill gaps in the current understanding of Roman activity in the area. Ultimately, the project strives to make a significant contribution to the archaeological knowledge base by employing cutting-edge technology in a scientifically rigorous manner.

The scope of the project is the determination of long-term post-seismic ground surface movements in L’Aquila (Italy) after the devastating earthquake of Mw 6.1, on April 6, 2009. This earthquake highlighted the incomplete understanding of the geology of the area, in particular the Quaternary continental deposits and active tectonics, which caused the Paganica fault system to be ignored by researchers. Coseismic seismological and geodetic data converge in modeling a NWstriking, SW-dipping, normal fault (length ranging between 12 and 19 km) as the causative fault of the 2009 earthquake (Chiaraluce, 2012 and references therein). Soon after the earthquake, a fault bounding to the east of the Middle Aterno Valley, along which primary coseismic ruptures, was interpreted as the surface expression of the modeled fault (Boncio et al., 2010; Emergeo Working Group, 2010; Falcucci et al., 2009; Galli, Giaccio, & Messina, 2010; Vittori et al., 2011). The scientific production concerning seismological, geodetic and geologic coseismic data is focused on the identification of the seismic sources. In particular, the geodetic data is focused only on co-seismic and immediate postearthquake. **The aim of our project is to investigate post-earthquake movements to understand the evolution of the fault system by using a novel approach derived by the calibration and integration of ESA Sentinel1 InSAR with GNSS and with high-resolution leveling networks measured in 2009 and 2018. **

The study area is characterized by vertical movements in both lowering and lifting that go from -2 mm /a up to 5 mm/a. The research will provide unique and important geophysical information concerning the dynamic of the fault system after the earthquake of 2009. At the same time, we will test a new method for the integration and calibration of InSAR with GNSS and with high-resolution leveling networks.

This project is part of a PhD on the topic of LULC Classification. The goal of this research is to characterise land degradation processes in the region of Ferizaj in Kosovo for the years 2000, 2004, 2010, 2018 and 2024 by using high-resolution satellite images. For this purpose, it is needed to:

– to address how land degradation affects agricultural productivity and what key factors contribute to these impacts,

– to spot the current spatial patterns and levels of land degradation

– to determine which early detection of land degradation techniques can be applied using remote sensing and GIS technologies to minimize impacts on agricultural land

– to predict the expected future land cover scenarios considering the current land cover trends of land degradation

– to estimate land surface temperature and correlate with land use to measure the impact of LULC change over land surface temperature.

– to identify groundwater potential zones using different variables along with land use to see the spatial correlation between groundwater and land use classes.

In 2020 Greenpeace Global Mapping Hub initiated the crowdsource project on wall-to-wall mapping of burned areas in Russia. Having manually-identified samples from this research, we aim to develop automatic fire detection methods using machine learning for consistent and permanent analysis. Start with one region as a test (Russian Far East) where we want to reach constant monitoring, and then we want to scale this approach for the whole country. We consider using Sentinel-2 images in a set of pre-trained models (ready to be used already) for getting the initial result, which will be checked with experts on a special internal platform and then (after approval) used in the final front-end digital product for users permanently. This project aims to help fire-fighting teams, researchers and NGOs in Russia get high-quality, up-to-date, consistent and user-friendly information on fires – location, area assessment, historical analyses, regional statistics etc. There are two peaks of fire activity in the country in spring (March-May) and summer (July-September), where we expect the highest satellite imagery usage for operational monitoring. In autumn and winter, data could be helpful for long-term analysis and preparation for the next fire season. It will not be a single-time analysis but a dataset derived on demand by the user with all programming parts at the backend. The reason for such a project is the lack of official data on burned areas in Russia, especially on non-forest lands (agriculture, bare, grasslands etc.) that play an essential role in GHG emissions.

With nearly half a billion people living in the close vicinity of active volcanoes around the world, the volcanic threat nowadays represents a major subject of global societal issues focusing on both the population protection / prevention and health. The diversity of acquisition systems, as well as the availability of large quantities of data, make the use of space imagery particularly suitable to meet the technical needs raised by the dynamic monitoring of continental surfaces.

Thanks to several decades of development, optimization and exploitation, the SAR interferometry has largely demonstrated its potential for excellence and today constitutes a proven, relevant and high-performance technique. This technique reveals in particular a significant potential in many fields of application addressing natural hazards as related to population prevention

(earthquakes, volcanic eruptions, landslides, floods, etc.), agriculture / forestry (deforestation, fires, phenological evolution, structural modifications and textures of the soil and plantations, etc.), geodynamics (phenomenon of subduction, subsidence, etc.) or questions relating to town planning (modification of the urban landscape, exodus, etc.).

For that reason, the primary objective of our project focuses on the assessment of the dynamical monitoring of explosive volcanoes based on an approach combining Machine Learning methods and Differential SAR Interferometry (DInSAR) products.

This is an ESA project through an Open Call application. The primary objective of our project focuses on the assessment of the dynamical monitoring of non-vegetated volcanoes based on an approach combining Machine / Deep Learning (ML / DL) methods and Persistent Scatterers Interferometry (PSI) products. Considering the growing popularity of Artificial Intelligence to process and promote Earth Observation data, the potentiality of SAR imagery can be greatly increased. More precisely, the task will be here to detect anomalies regarding the volcano activities through the development of a prototype software based on AI technologies allowing the detection of non-nominal behavior in temporal series of PSI products. For that purpose, our approach aims at first using the Surface motioN mAPPING (SNAPPING) service (Full Resolution mode) to generate relevant interferometric products dedicated to active and hazardous non-vegetated volcanoes. This will allow the creation of a relevant Training Database. It is important to understand that our intentions do not claim to replace the monitoring and forecasting equipment of well-known volcanoes (Etna, Vesuvius, La Soufriere, Piton de la Fournaise, Kilauea, La Palma…) which benefit from a whole range of advanced monitoring instruments (ground stations, inclinometers, extensometers, tide gauge, seismometers, gas emission detectors…). But precisely relying on these well-known candidates to constrain, assess and validate our Machine / Deep Learning approaches. These ML/DL implementations specifically aim at addressing the generalization of reliable monitoring of other hazardous volcanoes all around the world for which the monitoring services are much weaker, or even non-existent. The latter precisely constitute imminent threats for the surrounding populations and are, in particular, responsible for a large number of fatalities following sudden and sustained volcanic explosions. From the DInSAR and PSI side, based on the Sentinel-1 data temporal series, the ESA SNAPPING service will provide us with relevant information allowing monitoring and measuring volcanoes-related surface deformations (inflation/deflation, fault detection…). It’s important to keep in mind that we will first focus on non-vegetated volcanoes to allow better detection and estimates of surface displacements. By carrying out both temporal and dynamical monitoring, we would be able to detect tremors of the volcano’s surfaces, as well as figure out the progression of volcanic activity evoking an eruptive episode. On the THALES side, we will bring AI (ML / DL) skills to determine the relevant criteria indicating a resumption of volcanic activity through abnormal behavior detection. Schematically, anomaly detection consists in determining whether a given observation of a dataset is “significantly different” from the overall sample: outliers will then have to be spot on and labeled as anomalous. For that matter, we will first focus on 5 candidate volcanoes. The analysis of the time series of these reference volcanoes, for which we have their activity history and eruptive episodes, will aim at presenting an approach to study key parameters (early signs of eruption) qualifying a renewed volcanic activity, and the creation of a training database. The application of Machine / Deep Learning techniques on this database then targets the implementation of a Forecasting Tool Prototype showing warning indicators of volcanic unrest/activity resumption, and its generalization to other non-vegetated volcanoes. Note that this project is part of a process of continuity. Indeed, the first part here proposed aims at studying non-vegetated volcanic surfaces. The targeted prototype aims to be scalable by considering areas for improvement in terms of integration of simulated data or even multi-sensor data (integration of thermal infrared data…). To achieve this commitment, the development prospects are already under discussion with research laboratories (IPGP), for the proposal of an extension of our study through future OpenCall. In addition, the current subject is not devoid of interest in volcanoes, which today have a high level of measurement stations. Our recent exchanges with the IPGP effectively reveal the interest of the PSI technique for very well-monitored volcanoes insofar as the measurement stations, providing only local coverage, would benefit from spatial generalization over the entire surface of the volcano by the combined contribution of PSI data.

The goal is to create a model for land cover that will result in automatic detection of cover areas in selected locations/areas of interest using machine learning (AI). The results for part of Croatia will be freely available to governmental agencies interested in land cover changes, same as any individual interested in monitoring modifications over a specific period. Results will be freely available through the online viewer as an image.

This is joint initiative among the AI4Arctic project (ESA), the ExtremeEarth project (H2020), the Danish ASIP project, and the ESA Phi-lab. Within the polar context, the most promising application for Artificial Intelligence is the use of machine learning to automate sea ice classification and detection of icebergs. Progress in this area could transform how information is produced to ensure the safety of ships travelling in the North Atlantic, Arctic, and Antarctic regions. Currently, ice charts are created through the manual interpretation of satellite earth observation images (primarily SAR data, augmented by optical data in some situations). This process is slow and expensive, limiting the currency of information that is provided to ships and the extent of the area that can be analysed. The objective of this initiative is to improve automation in sea ice charting by bringing together domain experts within the sea ice and the AI communities to collaborate in the application of machine learning techniques applied to Sentinel-1 SAR data. Collaboration includes:

– Machine learning and AI techniques and architectures for improving automation of sea ice charting from EO data (SAR and microwave radiometer).

– Presentation and introduction of sea ice datasets for training and testing of AI/D models Presentation of existing architectures and results of automation.

– Preprocessing and de-noising to make Sentinel-1 data analysis-ready for Future developments and collaboration between AI and sea ice experts.

Two training datasets will be made available through the Polar-TEP website. These will serve as a common foundation for discussions, comparison of approaches, and future development within the community. Further, machine learning resources (data, tools, and compute) and a collaboration forum will be made available to the community on Polar TEP for the next year to enable continued research and communications. The machine learning resources include:

– Discourse Forum – a mailing list, discussion forum, and long-form chat room.

– Hopsworks – an open-source platform for the development and operation of machine learning pipelines at scale, including a feature store. It supports data exploration and model development in Python using Jupyter notebooks and conda to run production-quality end-to-end machine learning pipelines.

– Eo-learn – a collection of open-source Python packages that have been developed to seamlessly access and process spatio-temporal image sequences acquired by satellites in a timely and automatic manner. Eo-learn encourages collaboration by sharing and reusing specific tasks in typical EO-value-extraction workflows, such as masking, image co-registration, feature extraction, classification, etc.

The Norwegian Computing Center, the Danish Meteorological Institute (DMI), the Technical University of Denmark (DTU), Polar View, Nansen Environmental Remote Sensing Center (NERSC) and ESA (European Space Agency) have created a sea ice challenge, intending to bring together ΑΙ and Earth Observation players to address the challenge of “automated sea ice mapping” from Sentinel-1 SAR data.

Manual ice charting from multi-sensor satellite data analysis has been, for many years, the primary method at the National Ice Services for producing sea ice information for marine safety. Ice analysts primarily use satellite synthetic aperture radar (SAR) imagery due to the high spatial resolution and the capability to image the surface through clouds and in polar darkness, but also optical imagery in clear-sky and daylight conditions, thermal-infrared and microwave radiometer data from, e.g. AMSR2. Ice analysts mention the spatial resolution of microwave radiometers as the primary limitation of using data.

The traditional manual ice charting method is time-consuming and limited in spatial and temporal coverage. Further, it is challenged by an increasing amount of available satellite imagery, along with a growing number of users accessing wider parts of the Arctic due to the thinning of the Arctic sea ice.

Automating the time-consuming and labour-intensive sea ice charting process can provide users with near-real-time sea ice products of higher spatial resolution, larger spatial and temporal coverage, and increased consistency. Convolutional Neural Network (CNN) has excellent potential in automated sea ice prediction in satellite images. However, automating the process on SAR data alone is challenging. SAR images show patterns related to ice formations, but backscatter intensities can be ambiguous, complicating the discrimination between ice and open water, e.g. at high wind speeds. The training dataset made available in this challenge contains Sentinel-1 active microwave data and corresponding Microwave Radiometer (MWR) data from AMSR2 to enable challenge participants to exploit the advantages of both instruments. While SAR data has ambiguities, it has a high spatial resolution, whereas MWR data has good contrast between open water and ice. However, the coarse resolution of the AMSR2 MWR observations introduces a new set of obstacles, e.g. land spill-over, which can lead to erroneous sea ice predictions along the coastline adjacent to open water.

The objective of the AutoICE challenge is to advance the state of the art of sea ice parameter retrieval from SAR data resulting in an increased capacity to derive more robust and accurate automated sea ice maps. In this challenge, we aim to push forward the new capability to retrieve multiple parameters, specifically, sea ice concentration, stage-of-development and floe size (form).

This project aims to create a training dataset and train a machine learning model with the collected dataset to detect landslide events based on change detection using two images of areas affected by landslides: a pre-event image and a post-event image. Further objectives include testing one of the most advanced earth observation-specific collaborative platforms and seeing if there is enough support to conduct academic research, including training a machine learning model. Furthermore, the project aims to benefit the landslide inventory sources with a tool that can detect landslides automatically, thus making it easier to create a database with new events. It shall also benefit the academic field of research on landslide prevention and machine learning methods application. The case study will be developed within the joint project of the GIS GEOLab of Politecnico di Milano and the Hanoi University of Natural Resources and Environment in Vietnam -the ‘Geoinformtics and Earth Observation for Landslide Monitoring’. Lastly, the project shall also be beneficial to the openEO platform itself.

The MAFIS project is aimed at assessing the above-ground biomass (AGB) of forested areas and at detecting forest “disturbances” deriving from natural phenomena and man-made activities. MAFIS can provide regular, accurate and timely information, to Public Administration, for authorization and control of forest exploitation, and to forest owners/industry, for planning plantation and raw material purchase. Through a CCN proposed to ESA, the analysis should be extended to assess and monitor urban forests and green areas for providing information to the participating cities in Italy and Europe. OBJECTIVES: 1) Forestry-Tep – Onboarding of MAFIS workflow to perform second large area test (planned in MAFIS project) that will include countries candidate for membership of the EU (North Macedonia, Montenegro, etc.) as there is intertest from DG-ENV and EEA about illegal forestry practices; – Compare AGB results on MAFIS Veneto test area, using algorithms already developed by VTT and GMATICS; – Perform Forestry-Tep operational test in terms of performance/cost with respect to various platform resource configuration 2) Urban-Tep – Onboarding of MAFIS workflow for mapping and monitoring of urban forests and green areas to enrich the service portfolio of Urban-Tep and Ellip; – Test the integration of MAFIS produced information layers with Urban-Tep information layers and resource configurations to define possible harmonized products and evaluating performance/cost options for responding to different end-user requirements; – Develop cooperation and possible business agreement between GMATICS and Urban-Tep. 3) Data Cube over European cities – Setup the MAFIS for urban forest and green areas Data Cube (onboarding satellite, aerial and local data) based on EDC resources and services; – Run the MAFIS for urban forest and green area workflows on EDC; – Onboarding of MAFIS for urban forest and green area results (dataset derived from the satellite data) on the Data Cube in order to made available the fruition to external users (e.g. municipalities, public entities) METHODS: 1) Forestry-Tep – MAFIS forests in natural environment workflow based on Sentinel-1, Sentinel-2 and Landsat-8 data for detecting forest disturbances; – Forest AGB estimates in natural environment by using ALOS-2 data and a Random Forest trained with various field historical and recently acquired data. 2) Urban-Tep – End-to-end methodologies that will use different satellite, aerial orthophoto/LiDAR and in-situ data, providing information suitable for design, planning, monitoring and maintaining urban forests and green areas; – The methodologies will be based on AI algorithms and various consolidated methods such phenological analysis by fusing the results derived from different satellite data. 3) Data Cube over European cities – Implementation of Data Cube over ten European cities by using EDC services, including local data and satellite data (VHR and Hyperspectral for mapping and Sentinel-1/2 and Planetscope for monitoring); – Implementation of catalogue for project partners (access and processing of original data) and final users (visualization of data and produce results). The deliverables are:

1) Forestry-Tep – Forest disturbances in MAFIS second large test areas (EU candidate countries); – Forest AGB estimation over Veneto test site using VTT and GMATICS algorithms; – Performance/cost analysis results with MAFIS workflows over large areas.

2) Urban-Tep – Urban forest and green areas monitored by MAFIS urban workflow through Urban-Tep.

3) Data Cube over European cities – Data Cube including local, aerial and satellite data plus information results produced by MAFIS urban workflows. Access and processing of data for project partners; data and results visualization for final users. The MAFIS project is co-founded by ESA through an EOEP5 contract and additional CCN.

Adaptation of water and land management is essential in the Mediterranean basin, which is already facing overexploitation of water/soil resources and will experience significant hazards due to changes in climate forcing. Meeting the growing demand for food and water requires rationales for designing innovative solutions in agricultural land use planning and practices so that stakeholders (e.g., public authorities including water and agricultural managers, farmer or water user associations) can setup trade-offs between various needs at different levels (e.g., agriculture versus other uses, farmers versus farmers). In the context of rainfed and irrigated agriculture, innovative solutions must aim to collect better, store, distribute and use water resources to manage current situations and design possible evolution pathways. Therefore, water resource managers are looking for decision support system (DSS) tools based on the modulation of spatial structures and connectivities induced by hydro-agricultural practices (e.g., land use, inter-cropping, irrigation techniques) and infrastructures (e.g., reservoirs like dams, benches). Existing integrated water management frameworks include, among other things, integrated modelling schemes to simulate evolution impacts in terms of matter fluxes and stakeholder knowledge to design possible evolutions and quantify their impacts. However, these integrated frameworks do not explicitly account for spatial structures and connectivities concerning hydro-agricultural practices and infrastructures.

Meanwhile, significant progress in the last decade regarding spatial structures and connectivities was made. Nowadays, it is necessary to sustain efforts on these progresses and to capitalize on recent advances by designing (1) new monitoring and modelling tools, (2) integrating new models within integrated schemes, (3) simulating processes with calibration procedures devoted to integrated modelling schemes, and (4) analyzing the impacts of modulation scenarios on matter fluxes and storages, in the light of convergent/divergent stakeholder viewpoints. Therefore, we propose a new approach based on interferometric products to be considered for building and implementing these innovative means.

The northern Brazilian coast has one of the largest continuous mangrove areas on Earth, with the mangroves from the Bragança Peninsula in eastern Amazonia, a global hotspot of intensive changes in mangrove coverage. Degraded mangrove areas are found close to the centre of the Bragança Peninsula, on the highest tidal flats. They may be related to the building of the road Bragança-Ajuruteua during the 70ths decade. Throughout the last decades, several authors noticed Avicennia trees’ colonization of once-degraded areas. This research aims to assess the mangrove dynamics from a perspective of the degradation, regeneration and changes in mangrove structure over the last four decades (1986-2019) based on optical and radar imagery, photogrammetry techniques, topographic data, and surface models. The research will be divided into two phases:

• Multitemporal spatial analysis using GEOBIA land cover land use techniques on high-resolution spatial imagery will not only provide the changes in mangrove areas but also give us regeneration rates and regrowth dynamics.

• Validation of the models obtained in the first phase using topographic data from fieldwork and Digital Surface/Vegetation models obtained through photogrammetric techniques using drone imagery.

The project uses remote sensing data to identify and map biodiversity hotspots in a specific area. This project also uses remote sensing data to assess the threats to biodiversity hotspots, such as deforestation, land use change, and climate change. This project seeks to identify areas of high conservation priority by analyzing the relationship between biodiversity hotspots and threats. Additionally, the project aims to develop a methodology for monitoring changes in biodiversity hotspots and threats using remote sensing data over time. Finally, a comprehensive report will be generated highlighting the study’s findings and providing recommendations for biodiversity conservation and management. Overall, this project aims to raise awareness about the importance of biodiversity conservation and the role of remote sensing data in monitoring and managing biodiversity.

This project aims to test the ability of remote sensing to produce biodiversity statistics for a dairy supply chain in southwest Ireland. Under the Corporate Sustainability Reporting Directive and other voluntary reporting standards such as Science-based Targets for Nature, companies must report on the biodiversity in their upstream supply chain, so-called scope three biodiversity. Key metrics are the extent/quantity and condition/quality of habitat in the supply chain and whether these measures change over time.

The FarmZeroC project, a Science Foundation Ireland-funded research project aiming to demonstrate a sustainable dairy farm business model, has developed a proof of concept remote sensing workflow to measure the quantity and quality of habitat on Irish dairy farms using very high-resolution Pleiades imagery and Sentinel 1 and 2 time series. Having demonstrated that measuring extent and condition is possible on ten dairy farms, the aim is to test scaling out this system to a whole dairy supply chain. This project aims to test how scalable the proof of concept remote sensing workflow is, with key performance indicators being the availability of cloud-free Pleiades imagery across a whole supply chain, the accuracy of habitat classification across a supply chain, the cost of imagery, and the cost of computing.

More extreme, prolonged, and widespread droughts are accelerating tree mortality across biomes. Our ability to mitigate these changes depends on our ability to predict when and where mortality events are most likely to occur. This is complicated by the fact that, even within the same species, genetic variation drives phenotypic differences in ecophysiology, which result in populations having differential mortality risks under similar conditions. Thus, forecasting a species’ probability of mortality under drought can be improved by understanding its genetic and phenotypic variation across landscapes. Unfortunately, resource-intensive methods requiring field campaigns and laboratory analyses have historically prevented scientists from gathering spatially explicit datasets describing genetic variation at large scales. However, remote sensing and machine learning present the opportunity to efficiently generate continuous, high-resolution maps of genetic variation across landscapes. Early efforts to map intraspecific genetic variation using remote sensing have yielded promising results but have focused on small areas using hyperspectral and high spatial resolution imagery from drones and aircraft. Scaling up the mapping of intraspecific genetic variation to broader spatial and temporal coverage will depend on multispectral satellite data. In this study, I will map intraspecific variation in ploidy level (number of chromosome copies) in quaking aspen (Populus tremuloides) across the western United States by combing remote sensing and machine learning methods with existing genetic datasets. Quaking aspen (Populus tremuloides) is a model tree species for understanding genetic drivers of climate-induced mortality. The species has seen significant mortality across its range linked to drought. Within-species variation in lack in recent years, mortality risk has been linked to polyploidy (higher numbers of chromosome copies). I will ask: (1) Can moderate-resolution multispectral satellite imagery classify ploidy level in quaking aspen? (2) At what spatial and temporal extents are spectral signals of ploidy level in aspen consistent? If successful, I will use the resulting maps to (3) test the hypothesis that drought mortality risk in the species is a function of ploidy level.

More extreme, prolonged, and widespread droughts are accelerating tree mortality across biomes. Our ability to mitigate these changes depends on our ability to predict when and where mortality events are most likely to occur. This is complicated by the fact that, even within the same species, genetic variation drives phenotypic differences in ecophysiology, which result in populations having differential mortality risk under similar conditions. Thus, forecasting a species’ probability of mortality under drought can be improved by understanding its genetic and phenotypic variation across landscapes.

Resource-intensive methods requiring field campaigns and laboratory analyses have historically prevented scientists from gathering spatially explicit datasets describing genetic variation at large scales. Remote sensing and machine learning, however, present the opportunity to efficiently generate continuous, high-resolution maps of genetic variation across landscapes. Early efforts to map intraspecific genetic variation using remote sensing have yielded promising results, but have focused on small areas using hyperspectral and high spatial resolution imagery from drones and aircraft. At the current moment, scaling up mapping of intraspecific genetic variation to broader spatial and temporal coverage will depend on multispectral satellite data.

The output of this study will be the largest continuous map of aspen ploidy to date, enabling consideration of ploidy in a macroecological context. If predictions have low accuracy at the extent of the entire state, I will be able to instead determine the spatial scales at which spectral signals of ploidy level are consistent. Even at smaller scales, e.g. national forests, findings would have useful ecological and land management applications. I will ultimately use the output map to test the hypothesis that ploidy level predicts mortality following drought. If true, we will identify areas that may be important seed sources for climate-resilient restoration efforts, as well as high-risk areas that should be prioritized for future management.

The main objective of the study is to use non-parametric machine learning classifiers to map informal settlements of Old Naledi from Sentinel-2 data and Google Earth data. To achieve the main objective, the study will implement the following specific objectives: Extract buildings from European Space Imaging/Maxar WorldView and Google Earth data features using CNN and RF. Examine the significance of GLCM texture in the extraction of buildings in informal settlements. Determine the accuracy of extracting informal buildings from European Space Imaging/Maxar WorldView, and Google Earth using ground-truth data

As part of the non-competitive ESA EXPRO activity MAPTCHA after initial tests we want to establish EDC/OpenEO platform as data backend for these and potential further activities. Thus, the present request for a single license to continue testing at the remaining first phase and the project, and possibly the coming ones.

The objective of this project is to assess the applicability of remote sensing in obtaining data on hydroelectricity production. In particular, the aim is to analyse how the water levels of hydroelectricity plant reservoirs can be estimated using satellite imagery over time and how this data can be used to analyse competition and the use of market power in the market for electricity in the Nordic countries. The data collecting objective is to collect biweekly data on reservoir water levels of 400 reservoirs over four years (2020-2023) in Norway. Remote sensing data can potentially be a valuable source of information about the market power (the capacity to produce at a given time) of individual hydroelectricity producers, and this data can prove to be especially important in regions and countries where data about reservoir water levels is unavailable or difficult to access for researchers. The project uses the remote sensing data together with other data in a wider analysis of imperfect competition and the use of market power in the Nordic market for electricity, Nord Pool.

“The Wild Intelligence Lab project was launched in January 2021. Since then, we have been able to recruit 40 qualified students, doctoral candidates, and postdocs from the fields of computer science, engineering, and physics for our project. Wild Intelligence Lab enables objective decision-making in the sustainable development of conservation driven by data. We work on solutions for the protection of threatened ecosystems. We count animals and plants on drone images. Using artificial intelligence, the software recognizes giraffes, rhinos, and antelopes, records animal populations, and calculates the amount of food available. Using satellite imagery, we evaluate the health of trees. By analyzing this data, our work can be used to develop strategies to protect threatened ecosystems. Currently, we are developing our software in close collaboration with the nature reserve Kuzikus in Namibia. Doing so, we can start with a minimal viable product and continuously add software features, tailored to the needs of conservation experts. For us, scalability is key. Thanks to our software architecture, we only need new data from unknown wildlife to train our algorithms for quantifying animals and vegetation, providing wildlife experts with transparency and protecting endangered plant and animal species in the long run. In addition, Dr. Friedrich Reinhard and Berend Reinhard, head of the Kuzikus nature reserve in Namibia, are founding members. Our members are involved voluntarily and some of them are writing theses in the form of master’s theses about the project. Currently, we are working closely together with our partners Kuzikus, Drone Adventures, LiveEO and SAVMAP. We want to use the high-resolution satellite data from Pleiades to calibrate our model and make the algorithms more robust for new areas. In the future, we aim to use the model for new projects, such as the Black Rhino Habitat Suitability Analysis. This is intended to identify new, suitable and safe habitats for black rhinos in Namibia. This should enable the breeding programme for this endangered species to continue. Further information is available at the following link:

https://wildintelligencelab.com/black-rhino-habitat-use/”

The goal of my master’s thesis is to analyze the environmental impact of earthquakes using Sentinel-2 satellite data via the openEO platform. This study will focus on changes in land cover and vegetation health, providing crucial insights for environmental scientists, urban planners, and disaster response teams.By employing geospatial data analysis and computing indices like NDVI, NDWI, and NDBI, the project aims to offer a quantifiable understanding of post-earthquake environmental changes. The findings are intended to enhance disaster management strategies and environmental recovery efforts.The results will be shared with the academic community and stakeholders in a publicly accessible format, contributing to wider knowledge in disaster response and environmental monitoring. This research will also be published on EO4Society and the NoR Portal to ensure broad dissemination and application.Request ID

I am analyzing and comparing methods for detecting forest changes using Sentinel-1 and Sentinel-2 time series. The goal is to find a time series change detection method that is robust in detecting different forest changes (wind throw, bark beetle-induced damages and drought stress) at an early stage in “near-real-time”. The combination of optical Sentinel-2 data and radar Sentinel-1 data is promising for near-real-time detection of forest damages as the additional radar data provides essential insights during cloudy or fogged weather conditions, whilst the capacity of Sentinel-2 imagery is limited due to cloud cover. This is especially important for detecting changes due to storm or heavy wind events, in which Sentinel-2 data has been proven insufficient for near-real-time detection. Furthermore, current methodologies mainly focus on optical Sentinel or Landsat data. Thus there is a need for additionally utilizing available radar data. The outcome of this study is a robust time series change detection method which can be applied to newly acquired data in a near-real-time scenario. This time series change detection method may help foresters detect forest changes early and take targeted action to protect their forest from damage such as insect infestations.

This project aims to build a global wildfire burn mask dataset for 2018-2020 at a 10m resolution for Class E fires (300 acres) or greater. Burn masks are regularly used for wildfire prediction, and wildfire spread prediction. As global conditions continue to worsen due to Climate Change, we must work to minimize the effects of wildfires through artificial intelligence. This dataset is created to provide viable information for neural networks in wildfire prediction. The methodology used to create this dataset is based on the European Forest Fire Information System’s (EFFIS) Burnt Area product and the Global Wildfire Information System’s (GWIS) GlobFire Database. This dataset is necessary as it enhances both of these datasets. While EFFIS already produces a well-respected burnt areas dataset, its resolution is 250m and is only for the EU and surrounding EU countries. The GlobFire dataset is also well respected, though its resolution is 500m. This dataset would be the first of its kind, as its both global and at a resolution of 10m. The results of this project will include three different burn masks for each fire utilizing the dNBR, RdNBR, and RBR (additional information below). Masks will be made publicly available as image files and ESRI Shapefiles. The python script will also be publicly available and include a user guide detailing how it can be used and updated.

Vegetated coastal environments account for a significant proportion of global ‘blue carbon’ sinks, as well as providing recreational opportunities and buffering against climate-change-related flood and erosion hazards. Saltmarshes are key contributors to global carbon reduction goals (over 50 times more efficient at trapping carbon than rainforests) and to nature-based coastal protection. They are, however, intrinsically dynamic systems and are suffering global degradation resulting from reclamation, sea level rise, eutrophication and other indirect human impacts. Ever-higher resolution remote sensing options offer exciting opportunities to track, assess, manage and preserve the benefits these habitats provide both locally, nationally, and internationally. This research project will use satellite imagery from Sentinel-2 to capture seasonal and inter-annual change on a selection of Irish east coast marshes (particularly those in Malahide and Bull Island) and restored saltmarshes along the southeast coast of Ireland. For that purpose, we follow the next steps:

– Use satellite imagery of Irish east coast saltmarshes (natural and restored) to capture seasonal and inter-annual change in saltmarsh ecosystems, specifically in saltmarsh vegetation and geomorphology

– Use ArcGIS for mapping the bio-geomorphological evolution of saltmarshes using satellite images of the various natural and restored saltmarshes along the Irish east coast

– Compare and contrast natural saltmarshes with restored saltmarshes to assess changes in bio-geomorphological evolution

– Gather insight into whether restored saltmarshes evolve similarly or not to natural saltmarshes on a seasonal and inter-annual time scale, assess the integrity of saltmarsh ecosystems in both scenarios

– Conclude implications for future saltmarsh ecosystems (natural and restored) with global degradation occurring from reclamation, sea-level rise, eutrophication, and other human impacts

The methodology followed involves:

– Collecting Sentinel-2 imagery of Irish east coast saltmarshes

– Mapping Sentinel-2 images in ArcGIS- using various tools to map bio-geomorphological features and map their evolution on a seasonal and inter-annual time scale

– Using previous research literature to support my claims on various topics (climate change, blue-carbon, coastal ecosystems, saltmarshes and saltmarsh evolution, remote sensing as a tool to track changes in saltmarsh evolution)

– Field work for ground referencing saltmarshes, comparing these findings from satellite imagery to those in the field sites

We will use SAMOSA and ALES+ waveform retracking methodologies for our research. Our approach involves a comprehensive evaluation, comparing high-precision tide gauge data from observation stations to the satellite altimetry waveform retracking process. This evaluation is crucial to ensure the accuracy and reliability of the satellite altimetry data in our analysis, especially in the critical geographical region of the Chinese waters and high-latitude areas. China’s maritime territory and high-latitude regions hold unique significance due to their vulnerability to the impacts of climate change and sea level rise. Understanding these areas’ dynamics is paramount for scientific research and addressing environmental challenges. These regions experience complex interactions between oceanic and atmospheric processes and are often subject to extreme weather conditions.

The project aims to establish how much air pollution has been avoided in Seville due to the pandemic and its consequences during the most significant impact, studying the primary polluting particles and

gases emitted. Estimate the origin of said emissions obtained to determine those not emitted due to the pandemic.

MedEOS is a research project that aims to develop, implement and/or generalize methodologies using Earth Observation (EO) to acquire coastal water quality information about nondirectly remotely measurable parameters. It is part of the ESA Mediterranean Sea Regional Initiative within FutureEO-Segment1 ESA programmatic line (2020-2022) and aims to develop and produce high-resolution, gap-free maps of experimental EO water quality products by employing data fusion techniques to combine the high temporal resolution of S3-OLCI and high spatial resolution of S2-MSI data. Moreover, MedEOS will develop, implement and demonstrate a methodology to produce an

extensive tracking of river plumes in Mediterranean coastal waters with the use of EO products.

We aim to develop an algorithm that automatically and periodically tracks and predicts the Mediterranean coast-line and near-shore bathymetry using Sentinel public information. The main objective is to create a tool that will allow us to predict if the sand amount in the Mediterranean beaches is being depleted or not, at which rates, and in which zones are the most affected. Also, this tool will provide information on the aftermath of any climatic adverse event (hurricane, tsunami, storm, etc.). More information will help stakeholders and decision-makers create new policies that may help preserve the coast-line by directing specific actions. Also, the objective is to replace the yearly campaign using an aeroplane to take orthographic photos of the coast-line, with a product that can weekly monitor the status and evolution of the coast-line. The final project, which is our objective, aims to be user-centric, allowing anybody to use it easily. Finally, different ML and AI algorithms will be implemented so that not only any user can assess what has happened over the years in a specific region. They also can accurately predict the evolution of the coast-line and near-shore bathymetry over the upcoming months.

The main objective of this research project is to determine the Mekong River’s (MR) water level and validation with in-situ data. Το guides the policymakers, i.e., the Mekong River Commission (MRC), to resolve the transboundary Mekong River water management issues. Water level (WL) and water volume (WV) are among the most crucial physical quantities for water resources management, and also are indicators of the impact of climate change. The traditional and straightforward approach to monitoring WL is using local in situ gauges or stage stations. They would provide continuous and reliable WL measurements at locations along the river. However, primarily due to the length and remoteness of the MR, it would not be easy to install and maintain adequate gauge stations to monitor the entire river. More importantly, other issues associated with economic/political restrictions/data latency would also result in data inaccessibility in different countries. The feasibility of obtaining timely and continuous observations at multiple sections along the river remains a challenge. To monitor such an important yet poorly understood watershed, this study proposes to use timely satellite measurements at low cost with reliable data quality. Recent advances in geodetic satellite technology allow spaceborne sensors to be a feasible means to retrieve inland WL for adequately wide rivers. So the main objective of this study is to monitor Mekong River flow by accessing the following river parameters.

1. Το determine the water levels for the Mekong River and its validation with in-situ data.

2. Το estimate the time-series water levels for the spatiotemporal variation in the Mekong River flows.

The objectives of this project are:

1. To evaluate the effectiveness of utilizing Machine Learning (ML) in developing an early warning system that integrates climate and health data in two diverse regions worldwide. These regions encompass both higher and lower/middle-income areas, providing insight into global variations in data availability and quality.

2. To identify the most relevant health measures for investigating physical and mental health emergencies linked to methane and ozone concentrations in both regions (higher and lower/middle-income areas) and assess the feasibility of using ML to predict the incidence rates of emergencies associated with air quality.

3. To determine user functions that enhance the visibility of climate change impacts and evaluate their deliverability considering data availability and quality in the regions.

The results of the project can benefit various stakeholders including communities, healthcare professionals, policymakers, and the public. Communities in both regions can gain access to early warning systems, enhancing their ability to prepare for and respond to climate-related health emergencies. Healthcare professionals can benefit from improved understanding of relevant health measures, enabling better management of health crises. Policymakers can have access to data-driven insights to inform policy decisions aimed at mitigating the impacts of climate change on public health. The public can benefit from increased awareness and understanding of climate change impacts. The project results are available to beneficiaries through various channels, including research publications, reports, and online platforms. Access to these results will be provided under open-access conditions, ensuring that stakeholders can freely utilize and build upon the findings. Interactive tools and user-friendly interfaces are developed to facilitate easy interpretation and utilization of the data by diverse audiences.

The objectives of the project are: estimate which bands from the selected satellites have good correlation to methane fluxes recorded, and model spatially and temporally changing methane fluxes. The expected results are to identify which satellites, what resolution and bands showed good correlation to ground recorded methane fluxes, as well as modelling the changing variability in methane fluxes monthly, seasonally and spatially varying within the focusing area.

It is a first of a kind study that compares multiple high-resolution satellites with good temporal coverage to methane fluxes in Arctic. The results are meant for the research conducted by IUSS Pavia, Insubria University, University of Alaska Fairbanks, Toolik Field Station. The results are maps available in the form of images representing seasonally and spatially varying fluxes.

Using satellite data, the Chasing Methane Super Emitter dashboard aims to track and identify methane super-emission events from oil and gas facilities in India. It focuses on detecting high-leak events or “super emitters” that contribute significantly to total methane emissions. Methane super-emitters are a small percentage (approximately 5%) of leaks from oil and natural gas systems that account for a disproportionate amount (over 60%) of total methane emissions (https://pubs.acs.org/doi/full/10.1021/acs.est.6b04303). These leaks are typically associated with high-pressure devices like high-bleed pneumatic air pumps and compressors. Oil and gas operations are significant (~30%) sources of human methane emissions due to the extraction, production, and distribution processes involved. We can address a major contributor to overall methane emissions by targeting methane leaks from these systems.

Sound evidence exists that recent, human-induced climate changes significantly influence population processes and parameters of migratory species. Migration patterns change and species relax their migration habits, influencing survival probability. In others, new migration routes are being established, new stopover sites are explored, and new wintering areas are occupied. ΑΙΙ to match the population’s demands for resources and conditions with the environment. White Stork is well-studied model species of a long-range migrant where all listed changes were described. However, their scale and underlying mechanisms remain unknown. Most dramatic changes are evident in juvenile birds, who tend to start migrating in their pre-reproductive period in contrast to their sedentary behavior at the wintering grounds until sexual maturity. Therefore, we decided to focus our study on the juvenile individuals. Between 2015 and 2021, ten juvenile individuals were equipped with GPS/GSM telemetry devices and tracked during the entire migration route at stopover sites and wintering grounds. Our main objectives in the study are (1) to analyze in detail migration parameters, speed, length, and height, (2) to recognize the most important stopover sites and to analyze habitat use there, (3) to recognize the most important wintering grounds for the White stork, determine their habitat use and potential threats. With the results, we can demonstrate the priority stopover areas during the migration. Moreover, we would like to describe which habitats the species prefer – both during the migration and at the wintering grounds. The results are essential for any future conservation-oriented activities for the species.

On August 7, 2020, the Mila region was hit by a moderate earthquake which caused a huge

landslide that swept away 1/4 of the city of Mila and caused the distruction of buildings and important

infrastructure. With the evolution of the space technology, this geological event can be measured with

precision, and it is possible to determine the boundaries of the affected areas while calculating the slip displacement using only two high resolution images (before and after the event). The obtained results (displacement maps) will contribute to the the understanding of the damage caused and will be used to compare radar and optic data.

The project aims to highlight the implications of mining and quarrying activities on the biophysical environment. This will entail spatial mapping, Land Use Land Cover analysis of satellite images to detect changes on land structure and vegetation communities. Impacts of these changes will be analyzed on the hydrology and water resources because the ecosystems in which large scale exploration activities are occurring have water channels passing nearby.

The results will be spatial maps of the extent of all mining and quarrying activities, change detection maps dating back to years before extraction activities began and 3D earth terrain models to translate changes in land structure and vegetation communities on the hydrological system. Mapping of the spatial extent and nature of mining and quarrying activities will be done through digitization of satellite images and verified though field surveys. Detection of landscape structure will be done through classification of satellite images (supervised classification and change detection algorithms). NDVI algorithm on the other hand will come in handy in detecting changes in vegetation communities. Satellite images furthermore can be helpful to detect physical changes in water sources such as water quality parameters of suspended solid matter. This will be supported by lab analysis data by the water authority in Kenya. The research will inform the government, exploration companies, and the communities on the implications of mineral and stone exploration activities in the County. In addition to adding to the knowledge in the use of satellite images for monitoring man’s activities in the environment.

The Łukasiewicz Research Network – Institute of Aviation (precisely the Remote Sensing Department) is implementing a project aimed at creating a Soil Mapping System for Cultivated Plants. Below is the justification of what the system is: Mobile Soil Mapping System for Crops is an automatic mobile robotic platform enabling the study of soil structure and properties, at the same time, determining the biochemical features of vegetation. This allows to define relationship between irrigation and yield quantity and quality. Currently, polish agriculture is witnessing the implementation of the latest technological advances, which allow for counteracting adverse environmental conditions, especially cyclically repetitive drought. Drought occurrence and other adverse environmental conditions can lead to water deficit, plant stress and, as a result, crop losses. Soil moisture deficiency is one of the most important factors limiting sufficient crop yield. Both the lack and excess of water are harmful to soil and crops. Precise monitoring (soil map production) of soil, i.e. determination of texture (granulometric composition), humidity, temperature, organic matter content, roughness and richness in elements (such as macroelements) and heavy metal contamination, in a precisely defined location, is necessary to maximize yields. Łukasiewicz Research Network – Institute of Aviation offers a Mobile Soil Mapping System for Crops to meet the expectations of the nowadays agricultural market. A system that allows to measure soil conditions in the field and to track its variability, which are linked to crop yields. Mobile Soil Mapping System for Crops is a prototype solution that is operated automatically. The platform itself is equipped with an independent electric 4-wheel drive. The ROVER type robot platform has dimensions of about 0.8 by 0.8 m and a load capacity of 100 kg, which allows it to equip it with numerous sensors. The use of 16-inch wheels with agricultural tyres allows for effortless movement in difficult terrain, including plowed field. The operating time of the platform on one charge is about 1 hour. Additionally, thanks to the use of satellite data – especially high-resolution data (PLANET and SPOT), it will be possible to verify the conducted research using a mapping system. Thanks to the high-resolution satellite data, it will also be possible to research an attempt to extrapolate the measurement results over a larger area.

Air pollution is caused by a combination of ~78% nitrogen, ~21% oxygen, ~0.9% argon and the remaining elements include carbon dioxide, methane, water vapour, hydrogen, and other trace elements emitted from factories and motor vehicles that burn fuel. The atmosphere is a delicate balance of these gaseous

elements and particles. Any imbalance, even in little extent can be inconvenient to living life forms including animals and crops.

There are different tools and techniques to study the air pollution problem. Remote sensing has been widely used for air quality studies since sum of the effects from the ground and atmosphere signal can be observed by the satellite sensors. Researchers have been using PM2.5 and PM10 to analyse the air

pollution situation using remote sensing for different countries. Our objective is to study the airpollution problem at delhi city and other metropolitan cities:

1. Modelling of PM2.5 and PM10 using Earth observation datasets

2. Fire detection model using Satellite imagery for agriculture problems

3. Development of an algorithm using an open source software interface R

4. Identification of lockdown effect during Covid-19 on atmosphere condition in Capital city of India.

We have been doing the basic analysis using ground observation datasets on cities of India. 22 of the 30 most polluted cities in the world are in India, and almost 99 percent of Indians breathe air that is above the WHO’s defined safety limits. According to the past analysis 76% of Indians live in places that do not

meet national air quality standards. In 2017 one in eight deaths in India was attributable to air pollution additionally average life expectancy of a child is reduced by at least 2.6 year.

Rewilding is a relatively new conservation technique gaining momentum rapidly and heralded as an essential tool in reversing global biodiversity decline. By the nature and scale of rewilding, there are likely to be considerable alterations to elements of the water cycle that are currently understudied. These changes generate the potential to help alleviate flood and drought (low flow) issues exacerbated by human management and climate change, specifically through the benefit of retaining water in the landscape. As such, this project’s aims are twofold: 1) to quantify the impact that rewilding has on surface soil moisture (SSM) contents across spatial and temporal scales, and 2) to relate any potential changes in SSM to differences in the discharge of nearby streams and rivers (where gauged), thus correlating SSM to flood and drought flow conditions. The primary aim will compare rewilded and agricultural land (‘control impact (CI) design) and examine the change in SSM through time and, where possible, before and after rewilding began (‘before-after (BA) design). The outputs will comprise a high resolution (10m) SSM dataset for rewilding sites on Rewilding Britain’s Network, dating from 2016 to present, derived using Sentinel-1 and Sentinel-2. These data will enable a detailed comparison of SSM between rewilded and managed landscapes, across the UK, at scales not previously investigated, along with the timescale of potential change (from 2016) and impact on nearby river flows. This work hopes to address how rewilding impacts SSM and the consequent impact on river flow during flood and drought. In addition, the dataset will be helpful to landowners considering rewilding and rewilding practitioners aiming to understand and quantify the broader impact that changes in land management strategy may have.

Two projects are involved in this research:

• MODREC project: after the massive flood of July 2021, Wallonia decided to fund research to improve the understanding of the hydrology of the Vesdre catchment. I’m doing physically based hydro modelling of the catchment. One of my model’s modules implies finely describing vegetation’s photosynthetic activities in space and time. I want to use OpenEO capabilities regarding data access and processing capabilities for this concern.

• Lifewatch: an EU initiative. I’m working in one of the Belgian teams supporting this international initiative. I’m thinking about openEO to perform various types of ecological modelling tasks, specifically the building of habitat maps.

Along Chile’s entire ~4000 km coastline, oceanic tectonic plates (the Nazca and Antarctic plates) subduct under the South American continent, repeatedly causing great to large earthquakes. Chile is thus a natural laboratory to better understand the processes related to large earthquakes. The PRECURSOR project is an initiative funded by the Chilean Ministry of Science to investigate the mechanics of slow earthquakes and their relation to precursory signals. For this purpose, we use deployed a pioneering experiment in Chile with a dense distribution of continuous 30 GNSS and 80 seismological stations (https://www.precursor.cl). Our project seeks to improve the detection of interrelated mechanisms controlling the failure of faults, to resolve spatiotemporal relationships between frequent small earthquakes and transient deformation, and provide new insights into the genesis of earthquakes.

With the projected recurrence of severe weather events and possibly the accompanying flooding from intense precipitation, an approach that outlines the susceptibility of recurrently impacted inland and coastal areas to future flood hazards would be beneficial. This is undertaken by assessing the impacts of past occurrences and integrating the findings with factors that constrain the distribution and intensity of the flood hazards. This assessment is particularly useful in the densely-populated coastal parts of the United States (such as the proposed study area). Anthropogenic-led land surface alterations and extreme resource utilization in most areas have led to processes that alter the surface cover and morphology. These changes, in combination with the climate change-induced sea-level rise (SLR), are further increasing the susceptibility of communities and resources to the impacts of flooding resulting from hurricane- and cyclone-induced storm surges. A three-fold approach is proposed in this study to investigate this effect:

(a) map inland and coastal areas that experienced recurrent (past) major flooding from periods of severe weather-induced heavy rainfall over the study area using a novel Synthetic Aperture Radar (SAR) data-based approach. Other approaches (e.g. unsupervised classification of L-band data from the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) data) and ancillary datasets are combined with the C-band SAR flood mapping to validate the result and reduce false detections;

(b) assess the possible role of anthropogenic alterations to the environment, principally surface deformation and land use/land cover changes, in exacerbating the impact of flood hazards. Surface deformation rates across the study area will be quantified using Envisat, ERS-2, and Sentinel-1 datasets and Interferometric Synthetic Aperture Radar (InSAR) techniques and calibrated by ground-based geodetic measurements;

(c) for coastal areas, a model will be developed that simulates the future inland progression of floodwaters from storm surges following possible severe weather-induced flood events by integrating impact analysis from past events, current and projected SLR rates, and land surface changes.

The project’s overall objective is to develop a model that provides accurate and real-time rainfall predictions, which can be used for various applications like agriculture, water resource management, and disaster prevention, by using the integration of multiple data sources, including weather stations, satellites, and radar.

This research seeks support from the European Space Agency (ESA) through the Network of Resources and is part of the PhD project at the University of Siena (Italy) focused on coastal erosion analysis. Coastal erosion causes a loss of shorelines worldwide and is mainly accelerated by climate change. The study of erosion is crucial to mitigate its impact on the environment and develop effective and preventive coastal management strategies. The Ombrone Delta on the Tyrrhenian coast (Tuscany, Italy) undergoes significant sediment loss, which poses a dramatic environmental issue. This research aims to understand the recent shoreline evolution using a multi-disciplinary approach combining sedimentology, remote sensing, and statistical analysis and to identify possible early proxies indicating shoreline’ evolutive trends.

The United Arab Emirates (UAE) are located on the southern side of the Arabian Gulf, at the north-eastern edge of the Arabian Plate. The bedrock geology is well exposed in the Hajar Mountains and the Musandam Peninsula of the eastern UAE, and along the southern side of the Arabian Gulf west of Abu Dhabi. The tectonic history of the UAE include the opening of the Red Sea by the Middle to Late Eocene, culminated the start of the NE tilting. The movement of the Arabian crust under the Iranian crust (Subduction Zone) is about 3 cm/year. Thus, the broader area of UAE is considered relatively active and the need to address various geohazards is necessary. The availability of satellite-based techniques, an specifically InSAR, offer the opportunity to measure surface displacements relevant to geohazards, being essential for improving our understanding of the phenomena related to both natural (subsidence, landslides, etc.) and anthropogenic hazards. The significance of these phenomena in terms of risks – to both people and infrastructures – is considerable; the resulting surface displacements must therefore be surveyed in order to prevent potential damages (in the case of anthropogenic hazards, surveillance may even be required by the regulations in force). The main objective of the current work is to address relative sea level changes and coastal vulnerability over entire UAE territory. A precise (millimetric precision) and comprehensive measurement of the ground motion along the coast is therefore required to fully characterize the sea level rise. For this purpose InSAR appears as the most effective tool to link the sea level estimates at global and regional scales to the local scale.

As Federal Attorney for Environmental Protection (PROFEPA), the Institution in Mexico in charge of monitoring forest losses, it is necessary to have instruments and technologies that allow real-time monitoring, especially when a Work is about to be developed that will pass through one of the Natural Reserves of international interest that has the recognition as Mixed Heritage granted by UNESCO. The expected results of the project are to detect illegal deforestation in time and to avoid more significant environmental damage during the execution of the project.

We intend to monitor past (i.e. over recent years) changes in glacier velocity, to establish whether glacier velocity increases prior to volcanic eruptions. The results will be of interest to the scientific community, but might also help improve volcano monitoring and associated hazard prediction.

The aim of this research project is to use the MPIC-OPT-ICE tool to monitor the surface velocity of glaciers that occupy active volcanoes with a particular focus on Mount Wrangell (Alaska), Mount Veniaminof (Alaska) and Volcan Peteroa (Chile). Preliminary results are planned to be made available by June 2022.

The primary objective of the proposal is to continue the monitoring using GEP in several areas of Granada and Málaga provinces, both in Southern Spain. Currently, the research team is working with its own InSAR results obtained using the software of the Catalan Telecommunications Technology Centre (CTTC) and the data provided by GEP in success processing jobs during the Early Adopters Programme. Now, we need to run new jobs in GEP to complete displacement series and to try to analyse some places in detail. In these new processing jobs, different combinations of SAR images are performed, excluding those taken in winter or selecting them according to different time ranges. There are defined different reference points to know the sensitivity of the analyses according to this parameter. To do so, the following GEP services are of great interest: SBAS Stripmap, SBAS-InSAR S-1 TOPS and FASTVEL S-1, being Granada province the first objective. During the last years, the work has pursued the detection of active landslides mainly in locations where landslide activity may imply an important hazard related to critical infrastructures and resorts. Monitoring such activity is crucial to know about the nature of the surface displacement or slope instability and thus, to prevent for further damages. Some of the examples during this work that are going to continue are the following:

(1) The Rules Reservoir. The slopes of this reservoir are affected by active landslides, implying an important hazard for the reservoir itself as well as for two roads and a viaduct that cross the reservoir.

(2) The Granada Tropical Coast. Several urban resorts of this touristic well-known coast are built on unstable slopes, where constant damages in houses and roads are affecting population safety and generating heavy economic losses.

(3) Sierra Nevada National Park and La Alpujarra historical region. Both areas are mountainous areas that are affected by large-scale landslides, mainly due to the high topographic gradients.

The tourism and the value of the national heritage itself of both places justify the importance of monitoring landslide activity for the related hazard assessment for roads, villages and hiking trails. Málaga province is the second objective. The aim is to monitor and further define some areas that showed ground displacement of unknown nature, like the case of Zafarraya area, with special interest in monitoring some mountainous ranges and towns of the province to detect unstable slopes. This is the first InSAR study focused on landslide detection in this region up to date.

The primary objective of this study is to detect active landslides within landslide susceptible areas in Alberta, Canada. InSAR derivatives will be used as one of the inputs to improve the 2016 landslide susceptibility map. For 2020-2021, one of the study areas for landslide is Swan Hills region in Alberta. Within this region, InSAR analysis will be represent one data input. Although InSAR will not yield coherent results that directly relate to slope movement over all the Swan Hills due to vegetation cover, the InSAR displacement map can be examined at specific locations (e.g. on a subset of bare slopes) where the movement likely relates to landslide movement, and this will potentially provide valuable training data for the susceptibility model. We will also examine the InSAR results specifically at rights-of-way in river crossings. The secondary objective of this study is to monitor subsidence over abandoned coal mines in Alberta that might pose environmental and public safety. For 2020-2021, the goal is to monitor ground deformation in the Smoky River coal mine, where the fieldwork and recent studies indicate the presence of ongoing subsidence in certain areas of this abandoned mine. ESA’s Geohzards TEP services provide a unique opportunity to utilize huge Sentinel-1 archive for time-series surface displacement detection over very large areas that has significant operational value to assist efficient decision-making to ensure public and environmental safety. SBAS Ground Motion Services is very useful for landslide monitoring and coal mine subsidence detection, which is used for these various study areas in Alberta, Sentinel-1 InSAR analysis will be performed. Although InSAR does not yield coherent results that directly relate to slope movement overall due to vegetation cover, the InSAR displacement map can be examined at specific locations (e.g. on a subset of bare slopes) where the movement likely relates to landslide movement, and this potentially provides valuable training data for the landslide susceptibility model. It is also examined the InSAR results specifically, at pipeline rights-of-way. The results include time-series displacement and mean velocity (cm/year) over the abandoned coal mining site that would help inform potential environmental and public safety issues for efficient decision-making. InSAR displacement map for the Swan Hills area are used to support landslide susceptibility modelling, but also to be potentially used for other investigations on rights-of-way etc.

Lakes are an essential part of global water resources. Their changes are important indicators of regional and global climate change and critical parameters for water resource evaluation and water balance analysis in river basins. The Qinghai-Tibet Plateau is known as the “Asian Water Tower” and is called the “third pole” of the earth, with thousands of lakes. The dynamic monitoring and investigation of the water levels of these lakes is helpful to the research on global climate change and will also provide dynamic monitoring information for the research on lake ecological maintenance, water resource utilization, water cycle and ecological environment process. Satellite altimetry is one of the most important means to obtain changes in lake water levels. After more than 20 years of development, a series of monitoring data of lake water level changes on the Qinghai-Tibet Plateau has been obtained, and the long-term monitoring results of water level changes in some lakes on the Qinghai-Tibet Plateau from 1972 to 2021 have been formed. For example, Hwang et al. used T/P series data to monitor the water level changes of 23 lakes on the Qinghai-Tibet Plateau from 1993 to 2014, and the smallest, frog lake, was about 25 km2; Gao et al. integrated Envisat, Cryosat-2, Jason-1 and Jason-2 Data, obtained the water level changes of 51 lakes on the Qinghai-Tibet Plateau from 2002 to 2012, and analyzed the impact of permafrost on them; Song et al. used ICESat satellite data to obtain the water level changes of 105 lakes on the Qinghai-Tibet Plateau from 2003 to 2009, and analyzed the water level changes. Its relationship with climate change; Chen et al. integrated the data of Jason-2, Jason-3, CryoSat-2, and Sentinel-3A and obtained the water level changes of 261 lakes on the Qinghai-Tibet Plateau with an area greater than 10 km2 from 2016 to 2019. Most lakes are on the rise. The plateau mentioned above lake water level monitoring is limited by the size of the ground footprint and the distance interval of the satellite altimetry points. The altimetry point coverage is mainly concentrated in large and medium-sized lakes with a water surface area greater than 10 km2. Less work has been carried out on a relatively large number of small lakes. Sentinel-3 data makes it possible to monitor the water level of small lakes.

The Einstein Telescope (ET) is a proposed underground infrastructure to host a third-generation gravitational-wave observatory. There are currently two candidate sites to host it: one is located in Sardinia, in a favourable geological context, and the other is in the Meuse-Rhine Euregion. Site-characterization studies are underway towards the site selection, which is expected in 2024. The research aims to evaluate the sardinian candidate site by integrating remote sensing techniques with geological and geophysical data. In this framework, a fascinating aspect relates to surface deformation evaluation through the PSI technique with SAR data. Recent years’ Sentinel-1 data from the Copernicus program represents a good opportunity to check recent crustal movements: they are supposed to be very little accordingly with a particular Sardinian geological asset. A first analysis has been performed locally at my university workstation with Snap2Stamps methodology: the next step is to expand time series observations and to fix a “zero” for further investigation. Unfortunately, SAR data processing is very expensive in terms of time and resource consumption, so the possibility of using the SNAPPING service is an excellent opportunity to achieve my research scope. My research result will be published in dedicated scientific publications in an open-access format to be directly available to project developers and the scientific community. The impact estimation is very high due to the substantial interest in this strategic project.

To address increasing water demands in expanding metropolises, groundwater resources stored in many aquifers are overexploited. This process is further exacerbated by climate change and its impacts on the availability of resources. Land subsidence due to aquifer depletion often combines with ground faulting /fracturing and damage to private and public urban infrastructure, including housing, service buildings and transport networks. This project will use long time series of satellite SAR data and advanced multi-temporal InSAR methods to retrieve land subsidence patterns and rates from space, with centimetre to millimetre accuracy. Satellite observations will be combined with ground truth and information on infrastructure and population that could be impacted to estimate the risk posed by differential deformation of the ground surface. The primary source of SAR data will be Sentinel-1, providing weekly temporal coverage since the end of 2014. The processing method will be based on the conventional SBAS InSAR technique by CNR-IREA, parallelised and already integrated into GEP. Integration of the latter with traditional two-pass analysis with SNAP and its derived services SNAC and COIN would also be considered further to enhance the knowledge of the observed ground processes. The main area of interest will encompass major cities of central Mexico (e.g. Mexico City, Aguascalientes, Morelia, Queretaro) and the capital city Rome in Italy.

Land subsidence, caused by factors such as groundwater extraction, tectonic activity, and human interventions, poses a significant threat to archaeological sites. By monitoring and analyzing subsidence patterns, we can better understand the risks to these sites and develop targeted preservation measures. This research project aims to implement a comprehensive land subsidence monitoring program for selected archaeological sites in Egypt. The primary objectives are to assist in exploration operations and develop effective protection strategies for these invaluable cultural heritage locations. By providing a detailed understanding of land subsidence dynamics at archaeological sites, this research contributes significantly to the preservation of Egypt’s cultural heritage and enhance the efficiency and safety of future archaeological explorations.

The project aims to elaborate on specific products, live NDVI curves, and images of Sentinel images of each parcel managed within the Common Agricultural Policy (CAP) in Catalonia. The geographical scope is Catalonia (about 34.000 km2). The project will allow for improving the management of CAP’s grants in Catalonia and the optimization of public resources, and therefore it has a public interest. The results will be used for inspectors (civil servants) to conclude the eligibility of the parcels. They will also be used to inform the CAP beneficiaries about their fields’ conditions.

The main objective of this research project is to develop innovative solutions to monitor the structural integrity of existing critical linear infrastructure in northern Canada built on areas with a prominent presence of permafrost. Using satellite data captured over multiple years, we aim to track the localisation of such critical structures over time to estimate their displacement. This information will then be combined with geomechanical models to predict the effects of degrading permafrost. Our chief regions of interest are northern Manitoba and NorthWest Territories because they display a mix of continuous, discontinuous and sporadic permafrost. The first goal is to develop a deep learning-based algorithm for accurately detecting and localising structures such as roads and railway lines from high-resolution optical imagery. Then, based on these detections from historical imagery data, we would quantify the displacements of the structures with the aid of radar imaging, which allows us to measure surface deformations through interferometry techniques such as Interferometric Synthetic Aperture Radar (InSAR). The second goal is to develop a prediction model for estimating permafrost degradation due to the correlation between the estimated structure deformation and a geo-mechanical and hydrological model. The proposed research is expected to significantly impact the lives of the aboriginal and northern communities by making them less vulnerable to the harmful effects of climate change. These effects include public health risks, lack of access to transportation infrastructure, housing affectation, diminished food security, and threats of community disruption such as relocation. In addition, the academic community could benefit from the outcome of the algorithms and analytical pipelines developed as part of this research, along with curated data which will be made publicly available to help advance AI research for battling climate change.

The objective(s) of this project is/are to:

• Monitor coastal turbidity in land reclamation sites around Singapore for Environmental Monitoring and Management Planning (EMMP), which is one of the measures to protect the coastal environment from the destructive actions of land reclamation operations.

• Create a coastal turbidity model to predict coastal turbidity from imagery using in-situ turbidity data and high-resolution PlanetScope imagery.

• Share the results with our stakeholders, the Maritime Ports Authority of Singapore (MPA), to better help with decision-making, ensure turbidity concentrations are within permissible limits, and avoid transboundary pollution.

The objective is to monitor different hazards and environmental impact due to human activities and natural phenomena by means of remote sensing data. The proposed project aims to carry out an extensive exploitation of available remote sensing data and methods to evaluate for various geohazards, with emphasis to landslide, coastal erosion, subsidence phenomena, volcano and earthquake hazard, risk management and disaster prevention. The methodology to achieve the above objectives is the analysis of multi-source EO data, mainly by means of InSAR time-series analysis, optical data, seismic, and causative sources modelling. A fundamental role in such studies is provided by surface displacement time series obtained by Advanced InSAR (A-InSAR) analysis that analyze the spatial and temporal deformation over areas affected by such various phenomena. In fact, Advanced InSAR (A-InSAR) approach has been demonstrated to be the only remote sensing technology to monitor deformation from space with millimeter accuracy. The focus is on the use of multitemporal InSAR services such as SBAS (Small Baseline Subset) and/or PS (Persistent Scatterers) already available on the ESA Geohazard Exploitation Platform (P-SBAS and Fastvel tools). It is also used the SNAP InSAR and the DIAPASON tools in case of seismic or eruptive event. Moreover, using both the ascending and descending orbit, allows to decompose the LoS deformation into the Up and E-W directions to better image the ground deformation field. The retrieved deformation patterns are validated with external data (i.e. leveling and geodetic data) where available. The retrieved ground velocities are used as input for the inversion algorithms adopted to model the different possible sources. The research team at INGV has significant expertise in hazard analysis, evaluation, modeling and assessment using in situ and remote sensing data since decades. The proposed project has the following main innovative items.

• A full analysis and models of complex geological processes having impact on populated areas by merging multi-source remote sensing data with geological and geophysical data from surface and subsurface monitoring activity.

• The use of remote sensing data and geological/ geophysical information to provide hazard scenario models and identify unstable areas related to surface dynamics due to a variety of ground processes. • The proposal aims to establish a possible procedure for the long-term monitoring of hazardous phenomena related to human activities and natural processes. This project aims to delimit hazardous areas and manage the crisis for the Authorities in charge. Objectives

• The process of Copernicus Sentinels data, especially referred to the Sentinel1-A/B SAR acquisitions, by means of multi-temporal InSAR (A-InSAR) methodologies. It shows that this kind of data is now essential to evaluate hazards such as those affecting the selected study areas.

• The retrieved results will be shown at international Symposia and Conferences and, where relevant, proposed to the interested Authorities.

• The project stimulates cooperative scientific research between researchers in the field of geological disasters monitoring, emergency management and remote sensing. In fact, the obtained outcomes will be used and shared in the framework of already active national and international projects (among them for example the ESA ‘Dragon-5’ and European Union Civil Protection and Humanitarian Aid ‘SaveMedcoasts2’ projects). The deliverables consists on mean ground velocity maps and the relative displacement time series. Possible hazard scenarios (i.e. future flooding affected areas) could also be provided by means of post-processing analysis performed in a GIS environment.

Ground mass movements are one of the natural hazards that heavily impact our society, and this is particularly true in the Lisbon urban area, primarily due to its topography. The current landslide risk assessment provides only a qualitative picture of the exposure because they rely on indirect susceptibility and triggering factors. Kinematic parameters can be an extraordinary advancement, as they directly monitor the state of the mass movement. Multitemporal Interferometric Techniques are well-established for very slow movements (mm/year). Still, the constellation of the Sentinel-1 mission, with images available every 6 to 12 days, allows determining movements in the mm/week range compatible with landslides and retaining wall movements. The main objective of this project is to detect landslide-prone areas in the Lisbon area using ground displacement and velocity time series, to have early interventions and prevent landslide hazards. To accomplish this objective, five steps will be taken:

1. The use of landslide forecasting methods that use kinematic parameters on previous landslide events in Lisbon using ground displacement and velocity time series obtained by Persistent Scatterer Interferometry (PSI).

2. Comparing the effectiveness of the landslide forecasting methods of the different case studies.

3. Establishing a method of landslide forecasting.

4. Applying the method established in the Lisbon area.

5. Determining the landslide-prone areas.

Salt dissolution and flow are causing the development of active sinkholes that are subsiding at rates of 4-20 cm/yr, significant to giant landslides (1 km3 to 100 km3). In addition, salt flow is causing diapir growth and the breakage of the caprock. This research belongs to a national project and a proposal for a future European project (POCTEFA call) that involved the Universities of Zaragoza, Barcelona, and Girona in Spain, The Geological Survey of France, and the University of Pau in France, the University of Florida in the USA and the Geological Survey of Israel. The main results of interest for the Geohazards TEP community are the analysis and assessment of InSAR-web tools in (1) the detection of sinkholes in agricultural lands and industrial areas, (2) the calculus of moving rates of slow-moving and giant landslides able to cause significant damage and (3) the study of salt flow trends and fault displacement related to salt flow rates. All these geologic processes are being monitored with geodetic and remote techniques (airborne and terrestrial LiDAR, differential GPS, precise leveling, and photogrammetry). In addition, the deformation rates will be compared with ESA InSAR Web-tools data (SBAS and Fastvel Sentinel approach).

A few decades ago, the subsidence phenomena were detected in several cities in Mexico (Mexico City, Aguascalientes, Celaya, Morelia, Querétaro, San Luis Potosí, etcetera). Since 2016, INEGI has been carrying out a project of subsidence detection using Sentinel-1 data and applying PSI methods with SNAP and StaMPS free software. More than 30 subsidence areas have been detected, for which subsidence models were produced applying a procedure based on the experience acquired using the cited software and techniques. Some studied cases have shown time variations in sinking rates and require continuous monitoring. The objective of using Geohazard TEP processing services is to enhance the products of subsidence deformation rates in areas already studied and to detect possible new regions affected by subsidence. The overall objectives of the project are:

• To enhance our current procedures at INEGI for subsidence detection and vertical displacement rates quantifying;

• To get improved accuracies of subsidence rates in subsidence products;

• To improve coverages (avoid gaps) of subsidence in deformation products for areas already studied by INEGI and to detect possible new regions affected by subsidence.

The improved products would be freely available and updated subsidence models for all the detected subsidence regions, presented as raster images (GeoTIFF) with a 1-arcsecond resolution, providing subsidence rates in millimetre units.

Some of the produced subsidence models are already used by geologists as auxiliary data to detect subsidence structures (faults), civil engineering studies, and risk disaster management. Still, more products have been publicly available recently, and we expect more users to exploit the information for diverse purposes.

Due to the water monitoring problems in Brazil, there is a demand for tools to automate this process. With all the facilities generated from images obtained by satellite, a system that uses computational intelligence techniques to indicate the water quality of the water resources would be of great value to the public or even private entities. Given this scenario, this research aims to develop a model of water quality monitoring through satellite imagery using deep learning, which can be applied in reservoirs and other aquatic environments.

The main objective of this research project is to analyse the ecological rehabilitation progress in a disturbed area by extractive industries using remote-sensing imagery. This result is expected to give evidence to decision-makers about how vegetation cover develops over time. Since multiple sites were seeded in the area at different years, this study hopes to quantify the trajectory of recovery of these different patches to see the differences between those that achieved a good level of ecological healing and those that faced problems to achieve successful ecological rehabilitation. As a secondary objective, the research pretends to identify with more detail the observable differences between a successful and no successful rehabilitation in the areas seeded with native and grazing vegetation. Given the spectral heterogeneity of ecological components making up the different sites, this goal will provide insights into how high-resolution imagery could be employed to detect metrics such as tree and shrub cover, bare area, grass biomass, and landform design which cannot be detected with low-resolution imagery. Ultimately, this procedure using high-resolution imagery is expected to be used for long-term periods (decadal), reducing the necessity of using the field-based monitoring approach to assess rehabilitation’s success.

The study area is located in the northeastern Nile Delta. It covers 1047 km2 and contains thirty-three archaeological sites spanning the Prehistoric (5500-3100 BC) to Byzantine (395-638 AD) periods. Previous studies have highlighted the vulnerability of the north Nile Delta aquifer to seawater intrusion due to excessive groundwater extraction and rising sea levels without considering land subsidence contributions. Additionally, the impact of seawater intrusion on archaeological sites has not received due consideration. Therefore, this research aims to complement previous studies by examining the extent to which archaeological sites in the northeastern Nile Delta are exposed to deterioration resulting from the contamination of shallow groundwater by seawater. It also considers the contribution of land subsidence in exacerbating the problem.

The Nile Delta was formed by the progression of a complex system of deltaic fans throughout the Pleistocene, with the Modern Delta being formed from sediments supplied by at least ten distinct distributaries throughout the Holocene. With an average elevation of approximately 1 m above sea level within 30 km of the coast and a predicted rise in sea level ranges from 1.8 –5.9 mm/yr, the northern Delta’s subsidence has become a significant concern to the Egyptian population and government. The major problems in the Nile Delta vary from 1 mm to 8.4 mm/year according to the locational position. Maximum estimated land subsidence levels are in the eastern part of the Nile Delta, exceeding 8.4 mm per year. Hence it creates a significant impact on the infrastructure and development in the area.

Moreover, it worsens the impact of sea level rise due to climate change; the cumulative subsidence and the scenarios of sea level rise will double the flooded area. Recently, the excessive exploration and production of oil and gas in the region accelerated the subsidence and might create a high risk for the Nile Delta and the local community. No real-time tool could monitor or/and forecast the land subsidence. However, precise measurements of land subsidence could be achieved by core samples and C14 analysis, which could be simulated to provide a more comprehensive picture of the geographical extent of the Delta. Given the lack of response to such risk, this method is costly and time-consuming. InSAR technology of remotely sensed data could solve this problem and provide an operational tool to estimate the land subsidence to a millimetre level on extensive coverage of the Nile Delta.

Moreover, it could be used frequently to keep monitoring and validate the subsidence. The challenge of this technology is the agriculture coverage that disturbs the backscatter of the RADAR signal. Further improvements in the models and techniques introduced the differential InSAR that calculates the phase shift due to surface elevation changes. Such technology needs in-depth study on the Nile Delta to understand the land subsidence and be a tool for supporting the local community. This research explores the potentiality of InSAR and DInSAR techniques and data models to estimate the land subsidence in the Nile Delta and correlate the highest subsidence levels with the geographical location and proposed drivers. Develop the capacity of young researchers at the national authority for Remote Sensing and Space Sciences in this field and provide an interface that might support local beneficiaries and government from the risk of land subsidence.

The Junior Academy of Sciences of Ukraine is a state-funded extracurricular educational system that develops and implements methods of science education. the Junior Academy of Sciences of Ukraine received the status of Category 2 Science Education Center under the auspices of UNESCO and joined the network of Copernicus Academies. In 2012, a new section, Geographic Information Systems (GIS) and Remote Sensing of the Earth (RS), was established at the Kyiv branch of the JASU, which is supervised by the GIS and RS Laboratory. Today in Ukraine there is a delicate civil and governmental situation, and high-precision satellite images are important data for monitoring and assessing its status. We are already using Copernicus data that is publicly available, but high-precision satellite imagery will increase the amount of information for students and teachers for identifying the state of civil infrastructure. We have experience in conducting both national and international educational events for students and teachers. We will use this experience for the organization of international webinars.

Currently, around 1.5 billion people live in semi-arid areas and this number is expected to increase due to shifts in climate zones. In order to ensure their food security and counteract the impending water shortage, measures are necessary on different spatial and temporal scales. A comparatively simple and cost-effective method is the construction of dams along the flow cross-section of seasonal rivers. These act as natural barriers and within a few years fill up with sediment, in which the water collects and is protected from evaporation and too rapid runoff. The project presented aims to qualitatively and quantitatively determine the effect of sand dams in selected regions of Africa through time series analyses of satellite images. In this way, it brings together remote sensing to support humanitarian work, satellite-based environmental monitoring as well as semantic earth observation data cubes and time series analyses. Who will benefit from the project results: In preparatory discussions with non-governmental organizations that have already implemented sand dams in various regions of the world (International Aid Services and Sand Dams World Wide), it became clear that sand dams are an effective means of combating water shortages, but are not very well known. Scientific monitoring of the implemented projects has not yet taken place but could help the idea to become more popular. The scientific questions and objectives of the project outline are therefore geared to the actual needs of the humanitarian aid actors. In concrete terms, they are based on the hypothesis that sand dams have a positive effect on their environment, but that this effect varies depending on the climate zone and landscape.

The study will use Sentinel-6 and Sentinel-3 FFSAR data to detect changes in water levels in the Yangtze River (2019.1-2023.3). The accuracy of the two data types in the Yangtze River will be evaluated through measured water level data and compared with other satellite monitoring water level data. The study will focus on analyzing the transit points’ waveform characteristics and interference factors based on the topographical features of the Yangtze River’s transit points. The causes of changes in the Yangtze River’s water level will be analyzed with climate data.

Beginning in March 2023, and with increased intensity starting in June, Canada has been affected by unprecedented wildfire season with hundreds of wildfires. As the worst wildfire season in recorded Canadian and North American history, eleven provinces and territories have been affected, with large fires in Alberta, Nova Scotia and Ontario and Quebec. The goal of this pilot workspace is to assess with NRCan and CSA if mCube can be used as an operational tool to support wildfire management using EO. Wildfires have large extent, are in multiple areas, widespread over the territory and this requires a continuous monitoring service with synoptic, objective and timely observations in particular hot spot mapping and burned area mapping. As an alternative to data download and stand-alone processing to retrieve burned area maps it is suggested to consider on-line mapping. At this aim Terradue was requested by ESA to provide a tailored processing environment (mCube) derived from the Charter Mapper to support CSA and NRCan in the context of the wildfires affecting Canada. The goal of this pilot workspace is to assess with NRCan and CSA if mCube can be used as an operational tool to support wildfire management using EO.

The Massive Open Online Course – Earth Observation Open Data Science (MOOC EOODS) teaches the concepts of data cubes, cloud platforms and open science in the context of earth observation. Ιt targets Earth Science students and researchers who want to increase their technical capabilities onto the newest standards in ΕΟ computing, as well as Data Scientists who want to dive into the world of ΕΟ and apply their technical background to a new field. Before starting, prerequisites are general knowledge of ΕΟ and python programming. Then, the course explains the concepts of data cubes, ΕΟ cloud platforms and open science by applying them to a typical ΕΟ workflow from data discovery and data processing up to sharing the results in an open and FAIR (Findable, Accessible, Interoperable, Reusable) way. An engaging mixture of videos, animated content, lectures, hands-on exercises and quizzes transmits the content. After finishing, the participant will understand the theoretical concepts of cloud-native ΕΟ processing and have gained practical experience by conducting an end-to-end ΕΟ workflow. As a result, the participant will be capable of independently using cloud platforms to approach ΕΟ related research questions and be confident in sharing research by adhering to the concepts of open science.

Forests can play a critical role in mitigating climate change (CC). Still, at the same time, CC and the increasing frequency of natural/climate-related disasters are threatening their health and condition. In several Swiss regions, forests protect humans and infrastructures against natural hazards. However, forests need to be climate resilient to be effective for both risk protection and CC adaptation services. Thus, a comprehensive harmonized framework and action plans based on adaptation and not only reaction are required.

For this reason, the objectives of this project are to: 1) collect, harmonize and share atlases and data on Alpine past climate-related disasters; 2) quantify the past evolution trends of Swiss forests for evaluating the future ones according to IPCC scenarios; 3) integrate effects of climate compound events on trees/forests in natural risk models; and 4) raise the awareness of practitioners, decision-makers and the public for CC impacts on protective forests.

As a start, a comprehensive workflow has to be developed by including forest characteristics trends from field measurements from national forest inventory and satellite imagery technology.

This project seeks to assess how high-resolution multi-spectral satellite imagery can aid local governments in their battle against diseases caused by arboviruses, especially Dengue fever. The desired outcome is to benefit the local population and create awareness about what conditions favor mosquito breeding and best practices to mitigate the chances of a local outbreak. Dengue fever originally does not occur in South America and has arrived strain by strain over the last decades. With 4 of 5 strains present in Brazil, the risk of Dengue hemorrhagic infections is high, putting at risk all age groups, particularly kids and the elderly. Medium-sized cities count on professionals who eradicate mosquito breeding sites in public and private spaces. Fighting surges in mosquito populations is an unfair race, particularly after intense summer rains, requiring an agile reaction from the authorities. The idea is to use information derived from remote sensing data (detecting unmanaged swimming pools, puddles, ponds, water tanks, as well as dense vegetation) to identify points of concern that need urgent attention of the health surveillance authorities, thus making sure that the likeliest mosquito breeding sites are neutralized promptly.

The recent up-listing of leopard status from “Near Threatened” to “Vulnerable” on the IUCN Red List underscores the urgency of understanding and mitigating the threats faced by leopards. In Namibia, where leopards reside within a diverse array of protected regions, they encounter various challenges. A concerning proportion of farmers admit to shooting leopards on sight after livestock depredation, revealing the complexities of human-leopard interactions in this landscape (Portas et al., 2022). This study focuses on the natural habitat use and activity levels of leopards in anthropogenic landscapes in Namibia. This is done by using GPS radio-data of collared leopards living around human infrastructure on farmland. The main aspects to explore are:

– whether different types of anthropogenic infrastructure affect the natural habitat of the leopards, and

– whether human activities influence the animal’s diurnal and nocturnal movement. In addition,

– important movement corridors or pathways used by the animal between fragmented habitats in the area are identified.

Farmers can utilize this knowledge to create more efficient methods to protect their livestock from leopard predation through understanding when leopards are most active and probable to hunt and, consequently, when they will attack livestock. These objectives seek to safeguard the well-being of wildlife through conservation research. In essence, this study pursues to further the objectives of the Naankuse Foundation, centred on safeguarding Namibia’s wildlife, preserving its landscapes, and improving the livelihood of people they work with. The initiative endeavours to work towards fostering an indispensable coexistence between humans and wildlife, allowing all species to survive and thrive together, seamlessly aligning with the foundation’s overall purpose.

The objective of this project is to develop water quality soft sensors in Finnish lakes, utilizing multi- and hyper-spectral imagery and in-situ lake measurements, with case studies on two Finnish lakes. For this application, Sentinel 2 L2A data is utilized together with public TARKKA+ water quality information, (a) to generate soft-sensor maps of water quality as a result (b) to compare the indicator maps generated with different satellites (c) to propose pre-processing procedures and optimal kernel parameters for water quality models. The results are made available in an open-access form as an original article.

Wetlands represent an ecosystem type with an importance for biodiversity which is disproportionally high in relation to the area they cover at the global level. Knowledge about wetlands and their conservation status is thus of utmost relevance for attaining the sustainable development goals, particularly those relating to clean water and biodiversity. Characteristics of wetland inundation extent and seasonality are important for their ecological functions. Quantifying the impacts of human activity on wetlands requires monitoring of both wetland extent and dynamics, on the one hand, and human activities, such as those connected to urbanisation, on the other hand. Earth observation (EO) using satellites can support the management of impacts of climate and land-use change on wetland ecosystems by facilitating monitoring of wetland water extent and seasonality in an economically and ecologically efficient manner especially if integrating all available resources (e.g., EO programmes). While European EO research and monitoring efforts have mainly focused on the European Copernicus programme, the Chinese space programmes are rapidly developing. Numerous EO missions have been launched or are in planning, especially targeted at applications for monitoring natural hazards, effects of climate change and influence of human activities. The MARSHES project, funded by the Austrian Research Promotion Agency (FFG), aims at the joint exploitation of European and Chinese EO data for wetland ecosystem monitoring to make best use of the available complementary features of both EO programmes.

The overall aim of this project is to investigate the role that Antarctic sea ice plays in stabilizing marine ice cliffs. The initial focus will be to develop a robust Antarctic sea ice thickness product by utilizing data from CryoSat-2 and Sentinel-3. At present, accurately estimating sea ice thickness from satellite radar altimetry is hamstrung by a lack of knowledge about the penetration of the Ku-band radar pulse in the Southern Ocean snow layer. This has precluded an analysis of decadal trends in Antarctic sea ice thickness and volume and an assessment of the drivers of Antarctic sea ice variability. Correctly identifying where the radar return originates is critical for accurately converting sea ice freeboard to sea ice thickness using the buoyancy equation. The general assumption is that the dominant radar scattering horizon is located at the snow /ice interface, based on laboratory experiments conducted on a cold, dry snowpack, and is widely adopted in Arctic sea ice thickness retrievals. There is much less certainty surrounding Antarctic Ku-band snow penetration owing to i) a more complicated snow stratigraphy involving thicker and older snow, ii) widespread flooding and brine-wicking of the snowpack, iii) the occurrence of melt and re-freeze events capable of shifting the scattering horizon and iv) limited in-situ data for analysis/validation. One dedicated field survey found that volume scattering within the Antarctic snowpack was prevalent and estimated the main scattering horizon to be around halfway between the air/snow and snow/ice interfaces. Α lack of understanding about radar penetration poses a significant hurdle to multi-frequency approaches for snow depth estimation and accurate conversion of satellite-estimated sea ice freeboard to sea ice thickness. Ι propose a research strategy to measure the radar penetration and snow depth on Antarctic sea ice using data from the ESA CryoSat-2 and Sentiniel-3 radar altimeters, detailed below in the “implementation methodology” section.

The water ecological status of the reservoirs of the province of Córdoba, contemplates a high impact on the social and environmental levels. Due to anthropogenic events, there has been an excessive proliferation of algae or eutrophication in the main reservoirs that provide this vital importance resource. Remote sensing images have the potential to offer a synoptic, objective and continuous view of some water ecological status key variables. Since 2011 the use of Landsat sensors for the monitoring of San Roque Lake has been explored. However, since 2015, with the advent of the Copernicus ESA’s (European Space Agency) program the interest parameters retrieval faces a new paradigm. The combined use of both satellites (S2 – S3 Synergy) will allow us to obtain weekly frequency images of the province of Córdoba, to derive detailed maps of the variables related to the reservoir’s water quality. Sentinel images can be complemented with NASA’s (National Aeronautics and Space Administration) Landsat-8 data, in orbit since 2013. The main objective of this project is to develop a software platform for processing spatial and temporal distribution maps of the key water biophysical variables, such as the chlorophyll-a concentration (indicator of phytoplankton biomass), the water transparency, the particles in suspension concentration and the dissolved organic matter content, from the fusion of satellite images. The biophysical variables retrieval models are calibrated and validated with water ground truth data obtained in a set of specific measurement campaigns. In a complementary way, the water ecological status is correlated with epidemiological data of non-specific diarrhea. This project continues a job developed in UBP (Blas Pascal University) in collaboration whit the MAIE (Master’s Degree in Spatial Information Applications) of the Gulich Institute and the Secretaría de Recursos Hídricos of Córdoba province Government. The project also has the support of the IPL (Image Processing Laboratory) of the University of Valencia – Spain with vast experience in the subject.

The study aims to build and test novel approaches for detecting, analysing, and visualising acoustic data by focusing on both temporal and spatial information in the soundscape. Combinations of acoustic indices and geographical variables (i.e. climate, vegetation, remotely sensed data) will be used in several Australian ecosystems to describe acoustic elements, including biodiversity, across short (24-hour) and long (1-year) recording periods and spatial scales and identify environmental drivers of acoustic variability. I intend to have a good overview of how sounds are related to the landscape and which landscape features are more critical in driving the soundscape – mainly animal sounds.

I’ll look into soundscapes and how they relate to wildlife, validating the method for ecological monitoring and conservation purposes. The remote sensing data will help me to relate the sounds collected to the environment. I will be making comparisons between ecosystems. Having the images to calculate landscape metrics and include land-use and cover in my models would be very beneficial. Also, I’ll be analysing one year of soundscape, and it would be excellent to have satellite images over the time I’ll be analysing so I can compare how the vegetation changes over seasons and how this is reflected in the sounds and biodiversity.

A major challenge faced by the world in the near future is to ensure food security. Sharp growth in population and increased food demand have already pushed the existing practices in agriculture to their limit for better and healthier crops. But with the advent of deep learning techniques and the availability of high-resolution RGB, Infrared, Near-infrared, Hyperspectral and Multispectral satellite imagery has opened new avenues for Precision Agriculture to meet always increasing demands for food. This study aims to contribute to the cause by making use of satellite imagery for land use classification. The yield prediction will be made based on the evaluation of multi-temporal crop data and vegetation indices computed from the electromagnetic bands of the satellite imagery. This advanced information regarding cultivated crops and yield prediction will make the authorities take timely interventions to ensure that consistent and sufficient food is available to everyone.

My project takes multispectral drone data over a diversity of sites of known burials in several climates and terrains to determine the strengths and limitations of this technology in detecting ground disturbances related to forensic science (homicide burials, weapons or drug hides, buried evidence, etc.). By capturing one moment at a time, this multispectral data needs to be compared with past satellite imagery to assess how ground disturbances age by establishing past baselines for known buried objects (e.g., a 2012 known burial should be compared with 2012 undisturbed ground). Satellite images with high-resolution multispectral data are critical for my work to see how these known burials age, how vegetation re-populates, how it responds to a different nutritional profile with a buried object present, and for how long the response to disturbances lasts and the site heals over.

The objective is to perform a Multispectral Image processing to boost crop health and Aerial crop analysis. Analyzing the ground area for crops to get the maximum out of the crop-grown area. Using the images and then analyzing them in different areas. Develop a tool that users can input data requests into Sentinel Hub through the platform API to acquire data. The tool can have options like geographical AOI sensors and platforms temporal windows pre-processing levels conversion to Sentinel Hub evalscript manual based AOI on screen (possibility) Then the tool must also integrate with the preceding software modules in different platforms around data download, metadata reading and download.

The National Geographic Okavango Wilderness Project (NGOWP) collaborates with the National Geographic Society and its implementing partner, the Wild Bird Trust. We are working across the Όkavango-Zambezi Water Tower Project Area’ in the Angolan highlands and the Okavango River Basin and catchments of the Kwando River extending across Namibia and into northern Botswana. In addition, we work with local communities to monitor the wetland health of the Okavango Delta World Heritage Site in Botswana. Since 2015 the National Geographic Okavango Wilderness Project has systematically explored the major rivers that sustain the Okavango delta: Cuito, Cuanavale, Cubango and Cuando. This entailed land-based expeditions to rediscover the river sources in the highlands of Angola, followed by mekoro (traditional dugout canoes) expeditions all the way to the rivers’ ends whilst recording data on biodiversity, ecosystem health and socioeconomics. The team soon recognised the importance of what has now been termed the Okavango-Zambezi Water Tower. Founding principles include upholding traditional knowledge systems and land rights, optimising sustainable traditional and alternative livelihoods, and gathering detailed baseline ecological, biodiversity and socio-economic data to inform conservation decision-making within the Project Area. Our mission is to support the development of a vibrant conservation economy by establishing a network of conservation areas within the Project landscape, including the Okavango-Zambezi Water Tower, which connects the headwaters and source lakes of four major rivers in Angola with the Okavango Delta and the Zambezi River. Intended outcomes include delivering water security, socio-economic development, biodiversity conservation and enhanced climate change resilience.

The implementation of this project aims to conduct rapid assessments of natural disasters in urban areas in Taiwan, Asia, or other regions, such as landslides, debris flows, and floods caused by typhoons and heavy rainfall, ground subsidence and soil liquefaction caused by earthquakes, and ground displacement caused by active faults. The evaluation results will serve as public resources to provide a fundamental understanding of the causes of disasters and aid in disaster relief efforts. The analysis results of this project will be provided free of charge for use by government agencies and civilian rescue units. The evaluated data will be provided in geographic information system format or image files.

The main objective is to analyze environmental changes in buffer zones of Protected Natural Areas. The years of interest include the last decade, the territorial scope of the province of Misiones (Argentina), and its limits with Paraguay and Brazil. Since this is non-commercial research oriented to education and environmental awareness, the main beneficiaries will be citizens and public institutions committed to environmental conservation. The formats of the results will be academic articles and presentations under open access license.

A key challenge faced by the African continent is the rapid population growth and urban development, which have led to increased pressure on water resources, encroachment on wildlife habitats, and elevated vulnerability to climate change impacts. This project aims to map wetlands and land cover changes in rapidly growing African cities to support the development of nature-based solutions for climate resilience. The project will leverage analysis enabled by the Digital Earth Africa (DE Africa) platform and develop additional insights using complementary Earth observation (EO) datasets from the Copernicus program. The project aims to demonstrate how EO data can be used to support better development decisions and promote its wider adoption on the continent.

Transport Canada’s Navigation Protection Program (NPP) is responsible for keeping Canada’s navigable waters open for transport and recreation. NPP relies on information from public servants, industry and the public to identify and monitor obstructions to navigation (e.g. unauthorized construction activities and wrecked vessels). Major challenges for NPP inspectors include travel, access to sites, systems integration, mapping inspections, and workload. The objectives of the National Research Council’s (NRC) Navigation Protection Program (NPP) Automated Scanning Tool (NAST) – Phase 1 project was to:

• Evaluate the utility of earth observation to detect and identify obstructions in Canada’s waterways in support of the NPP;

• Understand NPP processes and information requirements;

• Identify suitable satellite imagery and coincident reference and ground truth;

• Examine the extent to which potential navigation hazards can be identified from suitable satellite imagery;

• Provide recommendations for follow-on work to develop and implement a stand-alone decision-support tool NAST Phase 1 confirmed that satellite remote sensing technologies have the potential to aid the NPP in the execution of its mandate. Moreover, the use of satellite imagery in combination with automated analysis procedures for the rapid scanning of large areas promises to enhance the ability to detect and manage obstacles to navigation in a timely fashion.

The objectives of the current Phase 2 project are to demonstrate the rapid, cost-effective assessment of large areas with respect to potential navigation hazards and to provide intuitive decision support in the shape of an easy-to-use dashboard containing target detections and ancillary information to facilitate the efficient assessment of potential threats by NPP inspectors.

One of the Phase 2 work packages is to develop AI/ML-based models, including designing and developing training and validation datasets and Initial classification to detect small vessels using a convolutional neural network (CNN) classifier. As part of that work, ML platform options will be evaluated. One of those platforms will be Polar TEP.

The use of NDVI values from Sentinel Hub helps to assess habitat quality, more specifically to determine when crops are collected. This data will be useful to understand the movements of bird species in the area, especially those that feed on grain.

The project’s primary goal is to develop a prototype application to monitor changes in the coastal area that primarily involve the illegal construction of buildings and other infrastructure (beaches, dams, piers, bridges, etc.). Also, as part of the project, changes in the quality of the sea near the coast will be monitored, which can indicate the possible devastation of the coast itself. The lack of a comprehensive system for tracking the state of the maritime domain is a significant environmental problem for sustainable coastal environmental management. The technological answer to this problem is possible through innovative machine learning methods and available Earth observation data. Combined, these technologies can be used to develop an automated “cloud” system for monitoring and classifying spatial changes in the coastal area. Unlike the current model requiring third-party notification, automatic monitoring would be possible in near real-time (3- 5 days). The main scope of the proposal is detecting unauthorized and illegal build-up of buildings and other infrastructures (illegal beaches, dams, docks, bridges) in coastal areas. Sea incidents that we know and are frequent (grounding of ships or accidents on crude oil tankers and cargo ships etc.) will not be included in the project scope at this stage. The only “sea incidents” that will be included in our project are incidents/changes connected with the quality of the seawater near the coast that indicate possible coastal devastation. Before the development of the application, it is necessary to conduct comprehensive analyzes and tests to determine the feasibility of such a system and its accuracy. Establishing an innovative software solution for automated monitoring and classification of environmental changes based on space technology products would reduce the level of anthropogenic devastation of maritime assets, resulting in a more efficient coastal environment management model.

The central goal of this project is to create an open data platform that allows the creation, visualization, and download of scalable earth observation models based on spatial indexes. This platform will provide researchers and analysts with a no-code/low-code tool to perform analytics using multiple big datasets, either from raster (e.g., sentinel-2 10 m resolution) or vector (e.g., world population sociodemographic variables), at scale (e.g., at country level) and extract insights easily and intuitively. This will involve a series of partial objectives:

• The definition and implementation of a data warehouse designed for time and spatial big datasets with ML capabilities.

• The design and development API for visualizing and extracting the results.

• The implementation and testing of the platform in a use-case of detection of burned areas within Spain.

The project aims at:

• Processing and making available ten years of Geophysical Doppler shift from Envisat ASAR to the oceanographic community.

• Establishing routines to enable future exploitation of SAR Doppler from Sentinel-1.

• Establishing a time series of SAR Doppler from 2002 onwards.

• Investigating the possibility of, and the effect of, assimilation of SAR Doppler shift into METs ocean model.

• Delivering a new high-resolution dataset of the inter-annual, seasonal and monthly mean ocean circulation in the Nordic Seas that will: Advance the understanding of the relationship between the surface circulation and the magnitude of ocean volume transport, in particular for dominant current systems and across straights and gaps.

• Providing new insight οn the energy content and exchanges between the mean and varying ocean circulation

• Accessing the new EarthConsole service, integrating the GSAR processor (used in RSS), and processing the years 2002-2007 from WS level-0 data.

• Finalising the implementation of the calibration routines described in the Prodex ISAR final report at METs infrastructure.

• Evaluating the possibility of assimilation of the SAR Doppler shift in a ROMS framework used at the ΜΕΤ Norway for Ocean Modeling.

• Taking advantage of new and historic high-resolution satellite remote sensing datasets (i.e., synthetic aperture radar, altimetry, gravimetry, SST, ocean colour) and ocean models to study the upper ocean circulation in the Nordic Seas.

Like most arboviruses, RVF is driven by a complex interaction of mosquito vector populations and vertebrate hosts in different habitat types under varying environmental conditions. During previous outbreaks, primary key vectors of

the RVF virus were identified, but the limited understanding of their ecology in diverse ecological zones and the interplay with the nomadic pastoral systems along the major livestock movement routes are unknown. For these reasons, this study seeks to analyze cattle movement routes to understand resource utilization, i.e., where they spend a lot of time grazing and how they often utilize that area, water points, and distance moved between forages. This will provide new insights on the exposure of cattle to mosquito biting. Analyses of cattle movement pathways (trajectories) also integrate each cattle location into the larger context of the spatial distribution of the population and changing environmental conditions. A perspective that has not yet been used in understanding RVF outbreaks, so the information obtained from this research will be valuable to the science community and fill a research gap on the role of cattle movement in the spread and maintenance of RVFV.

It is also envisaged that tracking animal movement will permit the identification of areas where the introduction or amplification of the disease could potentially occur due to a high density of RVF vector populations. This will contribute to the understanding of RVF epidemiology and present opportunities for strategic disease prevention.

Resources are needed for the CI/CD of the NoR Search and Discovery component of the NoR portal.

During the last four decades, about 100 people have lost their lives each year in the European Alps. Worldwide, there are roughly 250 avalanche fatalities each year. Annual financial losses from road closures and infrastructure damages are estimated to be in more than one billion euros in Europe. Despite a nearly two-fold increase in winter backcountry usage, avalanche fatalities have remained stable. This is likely due to improved avalanche forecasting as well as increasing public awareness. Conventional avalanche forecasting is carried out by human experts who use empirical knowledge to arrive at a regional-scale avalanche danger rating. The experts rely on diverse, incomplete data, especially on avalanche activity, which is rarely available at a scale relevant for the entire forecast domain. While the majority of avalanche fatalities stem from winter backcountry recreation, periodically, catastrophic avalanche events with several hundred fatalities take place, mostly in developing countries. Over the last five years, we have developed an operational processing chain that automatically outputs avalanche detections from Sentinel-1 data. The avalanche detection algorithm has an acceptable probability of detection (POD) for medium sized avalanches (can bury a car) and a very good POD for large avalanches. In recent projects, the focus has been on three different types of services:

1) The processing system has been pre-operationally tested in selected regions in Norway and is now operationally used by the Norwegian Avalanche Centre in daily avalanche forecasting from winter 2019/2020. This service delivers systematic avalanche detections over entire winters in several test areas worldwide in the recently finished AVAMAP project (ESA EO Science for Society). It has been shown that large avalanches are detectable with a POD of around 80 %. Consistent monitoring of avalanche activity requires a region of interest to be in Europe. Only in Europe, enough spatio-temporal coverage of Sentinel-1 is ensured. Other mountain worldwide regions suffer from either long repeat frequency of 12 days or lack coverage by multiple geometries (ascending/descending) or tracks.

2) Batch processing of all available Sentinel-1 data over an area of interest for avalanche hazard mapping. Users are public road authorities and local communities that assess the risk of avalanches hitting infrastructure.

3) On-demand processing of Sentinel-1 data after a major avalanche cycle or catastrophic avalanche event. Several worldwide cases have been processed in recent years and the followed method is considered highly feasible on a global scale.

Data extraction results will be regularly be posted by our association on our website (currently under development), our Instagram and on our university’s private network, and we plan to collaborate with at least another Engineering school to implement our data into AI algorithms to accurately predict natural phenomena. We plan on developing our very own meteorological station based on the data we will extract. Finally, we plan on participating on SentinelHub’s custom script competitions and on those of many other institutions. We believe this makes us a research and educational project which has the potential to reach a large number of beneficiaries.

This request serves to support the prize giving of the OEMC Hackathon organized by Opengeohub, namely through a yearly basic openEO Platform license for Hayri Latif Yılmaz (hayrilatif@gmail.com) and a yearly research institute openEO Platform license for Mohammad (MohammadHussein.Alasawedah@eurac.edu) & Suriyah (Suriyah.Dhinakaran@eurac.edu), both working at EURAC. These users were the hackathon winners of, respectively, the Global FAPAR Modeling challenge (https://www.kaggle.com/competitions/oemc-hackathon-global-fapar-modeling/leaderboard) and the EU Land Cover Classification challenge (https://www.kaggle.com/competitions/oemc-hackathon-eu-land-cover-classification/leaderboard).

The objective of this project is to detect surface signatures of Offshore Wind Farm (OWF) up-/downwelling dipoles in the German Bight, North Sea. OWFs generate hydrodynamic processes, which have the potential to significantly impact coastal marine ecosystems.When the wind is stronger than ca. 5 m/s, Offshore Wind Farms create upwelling and downwelling cells in the water column (Floeter et al., 2022), which bring new nutrients to the sunlight zones in the upper water column, fueling algae blooms.It is still unclear, if these processes create detectable cold-high chlorophyll (upwelling) – warm-low chlorophyll (downwelling) dipole signatures at the sea surface. In case it is possible, seasonal quantification of OWF induced new primary production would be possible using satellite data.Request ID

The OGEOREP project aims at:

– meeting specific operational requirements of a group of industry organisations, and

– establishing generic EO capabilities available to the concerned target demand sector to help showcase the capabilities of newly available EO missions (e.g. Sentinels etc.) and the European EO service industry it will be done with OSRL as stakeholder user representative.

The project’s main objective is to maximise the exploitation of SAR and SARin altimeter measurements in the coastal zone and inland waters by evaluating and implementing new approaches to process SAR and SARin data from CryoSat-2 and SAR altimeter data from Sentinel-3A and Sentinel-38. Specific objectives for each Coastal Zone and Inland Water domain and particular Technical Challenges must be addressed. However, one of the objectives is to link together and better understand the interaction processes between river discharge and coastal sea level. Key outputs are global coastal zone and river discharge datasets and assessments of these products regarding their scientific impact. The first part of the project, which included the definition of the products and assessment of different algorithms, has been performed in-house. For the upcoming phase, the computing resources required for generating and distributing the Global validated Coastal Zone dataset, and Global validated River Discharge data sets that shall be built could benefit from using EarthConsole.

“The Open-Earth-Monitor Cyberinfrastructure (OEMC) project will increase European capability to generate timely, accurate, disaggregated, people-centered, accessible (GSM-compatible) and user-friendly environmental information based on Earth Observation (EO) data. We will achieve this by building a cyberinfrastructure anchored in FAIR data principles, leveraging and improving our existing platforms OpenEO.org, Geopedia.world, GlobalEarthMonitor.eu, EarthSystemDataLab.net, OpenLandMap.org, EcoDataCube.eu, LifeWatch.eu, XCUBE and EuroDataCube.com. We will implement OEMC infrastructure in 3 phases:implementation of the computing engine and in-situ O&M data services;direct application of the Open-Earth-Monitor to support EU Green Deal and other strategic actions;dissemination and engagement of stakeholders & target users through a series of open workshops, then revise the tools and adjust them to better fit their objectives and limitations.

Miscellaneous

“

On behalf of the German Federal Ministry for Economic Cooperation and Development (BMZ), GIZ implements the project of “FAIR Forward – Artificial Intelligence for all”. FAIR Forward strives for an open, inclusive and sustainable approach to AI on an international level. The project’s objective is to augment the prerequisites necessary for local AI development and use across its six partner countries (Rwanda, South Africa, Uganda, Ghana, Kenya and India). As part of the area of capacity development and removing entry barriers to AI, FAIR Forward has partnered with the Rwanda Space Agency (RSA) and the German Aerospace Center (DLR) to sustainably enhance capacity building efforts on Machine Learning for Earth observation (ML4EO) for Rwandan practitioners and support innovative ML4EO applications to address development challenges. Thereby, the program aims to lay the foundations of a prospering ML4EO ecosystem in Rwanda.

This project aims to support local and regional decision-making towards water security and the adaptation to hydro-climatic extremes in Southern Spain. It develops high-resolution and geospatial data products to feed into site-specific water security information and design site-specific climate adaptation measures. The project follows a multi-scale approach to increase the transferability of the results and to link local, provincial and national stakeholders in the agricultural sector, specifically for permaculture farming and related activities. Therefore, part of the project’s best interest is to assess to what extent some of the available high-resolution Earth Observation datasets for optical and radar sensors can be incorporated into the current methodology. The reason is not only to have more clarity on possible data uses for decision-making but also to get the research team in contact with these technologies as a reference for application in other projects. We plan to show the local stakeholders some of the possibilities of remote sensing within integrated water resources management, monitoring and evaluating current and future implementation measures.

This project aims to support local and regional decision-making toward water security and adapting to Southern Africa’s hydro-climatic extremes. It develops high-resolution and geospatial data products to feed into site-specific water security information and design site-specific climate adaptation measures. The OWASA project follows a multi-scale approach to increase the transferability of the results and to link local, provincial, and national stakeholders and African universities with the international research community.

It is, therefore, part of the project’s best interest to assess to what extent some of the available high-resolution Earth Observation datasets for both optical and radar sensors can be incorporated into the current methodology. With this, not only to have more clarity on possible data uses for decision making but also to get the research team in contact with these technologies as a reference for application in other projects as well, just the same as it will show the local stakeholders some of the possibilities of remote sensing within integrated water resources management.

openEO platform unites: i) the Proba-V exploitation platform, one of the first EO-focused private clouds in Europe, ii) Sentinel Hub, the most advanced on-the-fly satellite data processing engine handling more than one hundred million requests every month, and its future evolution, iii) Data Cube Facility Services, and iv) EODCs cloud infrastructure and HPC experience, integrating all of these with the openEO API openEO Platform will build a new European platform based on EOSC, five DIASes, and commercial clouds, VITO’s Mission Exploration platform and EODC, by using the unified openEO API to connect these platforms and make them usable with client software. In addition, the ESA data cube project and the national Austrian Data Cube (ACube) activity will be linked to the openEO Platform. The openEO Platform ensures federated data access, federated computing environments, flexible clients, and powerful interfaces. Large-scale use cases from different application areas will demonstrate its feasibility and success. openEO Platform will serve different user groups by providing clients and interfaces tailored to their needs: remote sensing researchers can use a front-end where JupyterLab is being proposed as its primary data science front-end. R users can use the openEO R client and develop workflows in RStudio using R-Markdown. Users accustomed to building workflows interactively can use the openEO web client for graphically creating workflows, exploring results, and managing jobs. Software developers can work in their programming IDE to integrate services into larger or dedicated applications. All interfaces share the openEO client-side libraries to minimize complexity. These libraries are already available for Python, R, and JavaScript, significantly reducing the learning curve for these services. For well-known services such as viewing, OGC services are exposed to ensure interoperability with other existing tools. The thriving open development model adopted by openEO will be continued while developing the openEO Platform to make it an inclusive community project.

The goal of the openEO platform project is to develop a cloud-based system for large-scale analysis of Earth observation data via easy-to-use programming libraries (Pyhton, JavaScript) and clients familiar to data scientists (Jupyter Notebooks, R, WebEditor). The project builds on the heritage of the H2020

project openEO and is now moving to an operational platform offering openEO as a service, embedded in a unique federated European architecture.

The development of the platform is driven by different use cases, all aiming at extending the capabilities of the platform through additional functionality linked to real-world examples. As foreseen in the project tender, part of the data access costs (in this case the requested commercial data) should be covered by additional funding.

Commercial data part:

The requested commercial data is used for a use case to determine fractional canopy cover (FCC). This parameter is important for monitoring changes in forested areas and is a key input parameter for many environmental and ecological models. In this use case, we foresee the prediction of FCC for a 900.000 km2 area in central Europe. The prediction will be based on Sentinel-1 and Sentinel-2 features such as polarization maps, individual bands or vegetation indices. The role of the Very High Resolution (VHR) data will be the delineation of forest and non-forested land cover at the pixel level in several

test sites.

The added value of the VHR data is the very high spatial resolution, which allows a detailed distinction of forested and non-forested areas in detail in many pixels at a small scale. Based on the FCC obtained for VHR pixels the FCC percentage is spatially scaled up to individual pixels of medium resolution sensors. In the use-case, the binary forest information is applied to a 20×20 m Sentinel-2 grid. Another valuable piece of information for FCC prediction over a large area is temporal resolution. Differences in phenology, forest cover density, and tree species benefit from multiple images or time series over the same site throughout the year. This strengthens the prediction of forest presence within each VHR pixel and increases the data density for the regression model and/or allows modelling of seasonal behaviour.

This project is part of a Ph.D., where I am researching the potential for using Sentinel-2 data to conduct systematic surveys of Norway, to improve landslide data for the Landslide Early Warning System. In my previous work, I tested a method using dNDVI to detect new landslides. This has been documented in two journal articles that are currently under review.

The objectives of my upcoming research include the following:

1. Expand the study to conduct a systematic regional survey of the Trondelag municipality in Norway. Use deep learning on these data to differentiate between negative dNDVI signals (vegetation loss) caused by landslides and other processes such as forestry, agriculture, construction, river erosion and deposition, and snow or cloud cover.

2. Show the potential of this method to detect landslides using international case studies with different environmental and vegetation conditions.

3. Use the landslides detected with satellite images to create a critical slope angle range for landslide initiation that can be used to inform landslide susceptibility maps.

This research will explore the effectiveness of various AI technologies and decision management algorithms to develop an Image Processing Tool for real-time cloud detection during an EO mission. Working on the captured satellite images that are publicly available, the project will develop DL-based algorithms for cloud detection. A model will be developed to analyse the cloud coverage to automatically identify the correct data to be collected (retained) and transmitted (sold) back to users on Earth for varying applications. Depending on their acceptable cloud cover requirements, it may include agriculture, forestry and wildfire applications, mining, water management, and astronomy.

Optimization of agricultural technologies in agriculture is necessary to preserve freshwater reserves and reduce the load on environmental water bodies. The search for optimal irrigation strategies and the use of water resources is important for improving the efficiency of water use in agriculture. Still, many solutions in the optimization of agricultural technologies maximize crop yields or the enterprise’s total revenue but do not consider the environmental impact. It is worth noting that a high level of water migration from the root zone can lead to the seepage of mineral fertilizers into the groundwater, which causes eutrophication and additional load on water systems. Conducting field experiments to find the best agricultural technologies can be time-consuming since it requires evaluating all possible combinations. Yield simulation models are widely used for planning agricultural practices, such as planting and harvesting, fertilizing and watering. We propose a method for optimizing agricultural technologies based on the use of the WOFOST yield simulation model, as well as the use of Sentinel-2 satellite images to improve the accuracy of the yield forecast. The use of multi-criteria optimization based on the NSGA-II genetic algorithm allows you to find the dates and volume of water for irrigation, maximize the yield and reduce the total water consumption.

This year, ESA’s next-generation #-sat-2 satellite will deliver a platform for the in-flight uploading, deployment and updating of third-party AI models. In parallel, Microsoft and Thales Alenia Space will demonstrate and validate in-orbit computing technologies and potentialities onboard the International Space Station (ISS) for the mission named IMAGIN-e (ISS Mounted Accessible Global Imaging Nod-e).

ESA’s vision for edge computing in space is to foster an ecosystem of Earth Observation applications. This challenge is designed to align with this goal and is open to a global audience of space, EO, and AI enthusiasts. It’s an opportunity for the global community to explore the potential of in-orbit data processing and contribute to the advancement of earth sustainability.

AI and Earth observation players, researchers, experts, and scientists from all around the world can participate in any of these two tracks: ESA #-sat-2 track: 6-U CubeSat orbiting Earth at 500 km with a multispectral camera in a sun-synchronous orbit IMAGIN-e track (ISS Mounted Accessible Global Imaging Nod-e, in collaboration with Microsoft and Thales Alenia Space): Hyperspectral camera on the ISS.

This open challenge will start Mid February until the end of June. Resources and toolkits will be provided at the start of the registration campaign to assist all participants during the challenge. In addition, a simulator for the IMAGIN-e & #-sat-2 optical payloads will be provided to participants as input to build their applications empowered by AI. The challenge will be accessible to all EO or AI practitioners, from students and early professionals to researchers, engineers and experts in the field.

The objectives of this project are to:

– Develop and validate an AI-Driven Orchard Monitoring System in a Pre-Commercial Setting: Leverage PlanetScope’s high-resolution satellite imagery to validate Orchard Mate’s AI algorithms in real-world conditions. This enables precise monitoring of individual olive trees, identifying issues such as irrigation leaks, pest infestations, and nutrient deficiencies in real-time.

– Demonstrate the efficacy of Satellite-Based Orchard Management Solutions: conduct pre-commercial trials to showcase the capabilities of Orchard Mate in improving orchard management. This involves detailed tracking of tree health, resource use, and yield outcomes across multiple orchards.

ORCS is an application based on Artificial Intelligence aimed to detect features like ships and airplanes over EO optical currently supporting RACE Project (https://race.esa.int/), a joint initiative between ESA and European Commission for the provisioning of several economic indicators. It has been employed a Faster RCNN architecture due to its capability to provide fast and reliable results in the object and features detection. The activity, started as internal prototype at the very beginning of the 2020 pandemic situation, it has been piloted as in-kind contribution to ESA and since September 2020 it is into operations running within the EDC platform and supporting indeed RACE project.

ORCS is an application based on Artificial Intelligence aimed to detect features like ships and aeroplanes over EO optical currently supporting RACE Project (https://race.esa.int/), a joint initiative between ESA and the European Commission for the provisioning of several economic indicators. It has employed a Faster RCNN architecture because it can provide fast and reliable results in object and feature detection. The activity started as an internal prototype at the very beginning of the 2020 pandemic situation, and it has been piloted as an in-kind contribution to ESA. Since September 2020, it has been running operations within the EDC platform and supporting the RACE project.

Dramatically rising temperatures in the Arctic and the consequent thaw of permafrost soils lead to a growing exposure of organic matter (OM) and its carbon (OC) to the hydrological cycle and increasing fluxes from rivers to the Arctic Ocean. Declining sea ice extent and shorter ice-cover periods open new pathways for OC transport that may boost climate change positive feedback mechanisms. For example, increasing OM in surface water enhances radiative warming, which accelerates sea ice melt, which, in turn, opens new pathways for OC transport. OC, mobilized from thawing permafrost, affects the global carbon cycle at an unquantified level. We propose to use a number of CCI Essential Climate Variables (ECV) to quantify and monitor changes in OM and OC runoff and identify its controlling mechanisms. CCI Ocean Colour products will be used to quantify total riverine OC flux to the Arctic Ocean and monitor its pathways and fate. These data will be used to predict future trends in land-ocean OC transport. Ocean Colour Remote Sensing algorithms for the retrieval of OC concentration were recently evaluated in the Mackenzie and Lena River mouth regions (Juhls et al., 2019; Juhls et al, in prep.). They will be merged with ongoing in situ sampling of Arctic rivers (e.g. Juhls et al., 2020) to provide the first pan-Arctic long-term estimates of particulate and dissolved OC flux into the Arctic Ocean. Permafrost distribution and its thermal state (CCI Permafrost), snow cover (CCI Snow Cover), and land surface temperature (CCI Land Surface Temperature) will reveal terrestrial drivers for long-term flux trends and their inter-annual variations over the same period. Sea surface temperature and salinity (CCI SST and CCI Sea Surface Salinity) and sea ice concentration (CCI Sea Ice) will reveal implications for the Arctic Ocean. This project will bring together multiple CCI data across the coastal divide to show linkages between land and marine responses to climate change. Complementary ongoing projects, such as the EU H2020 project Nunataryuk will stimulate and promote this proposed project. The Host Institute, the Alfred Wegener Institute, is an ideal platform to successfully carry out this project due to its deep and broad knowledge and world leadership in Arctic research. This project is co-funded by ESA as one of the ESA CCI postdoc fellowship projects.

In the ‘OSINT’ or Open Source Intelligence field, one of the main obstacles for researchers is the need to perform manual actions, specificallyinformation searches of different types repeatedly. Our proposal aims to automate and simplify one of these types of searches: monitoring areas of interest, primarily maritime ones. We will investigate the feasibility of a series of OSINT experiences, including vessel detection and oil spill monitoring. For this, we will use as open sources the public data of the AIS (Automatic Identification System) network and the imagery provided by the Sentinel-1 and Sentinel-2 satellite constellations of the ESA. Our objective is to detect and, as far as possible, identify the vessels present in a specific area, storing the information associated with these contacts.

Earth Observation missions generate a large amount and variety of satellite data, treasure troves waiting to be fully exploited but currently underused because their data format, volume and complex geometry constitute a barrier for many users. To help remove this barrier and foster data synergy exploitation, open tools such as the Ocean Virtual Laboratory were developed with ESA support, making data discovery, access and analysis a rather easy task for science users. The aim of the OVL-NG study is to: Evolve, maintain, operate the ESA Ocean Virtual Laboratory Next Generation according to User needs.

The main technical objectives of this project are to prolong the ESA/Copernicus data visualisation and promotion activities started in OVL and S3VIEW for 24 months, to improve tools and services based on user feedback and to explore ways for improving the sustainability of these services in the long term.

Major changes are required in the core of the SEAScope application to allow it to stream data from a remote source, such as a Cloud, a DIAS or a datacenter. These developments are mandatory to facilitate the visualisation of large quantities of EO data and to make the application more attractive for users who need to explore and analyse these data without downloading full data sets. Design and implementation of user-requested features will be intertwined with the development of these core evolutions to achieve the most satisfactory outcome. The sustainability of existing and upcoming services can be improved by reducing the amount of time required to operate them and by optimising both usage and cost of the infrastructure resources. A panel of clouds and DIASes will be studied to get a clear view of the offers available to host services similar to OVL-NG. The processing system that feeds the online portals will be optimised to consume as little resources as possible, to perform more monitoring tasks and to handle minor issues autonomously so that operating the backend of OVL-NG involves less human interventions.

Earth Observation missions generate a large amount and variety of satellite data, treasure troves waiting to be fully exploited but currently underused because their data format, volume and complex geometry constitute a barrier for many users. To help remove this barrier and foster data synergy exploitation, open tools such as the Ocean Virtual Laboratory were developed with ESA support, making data discovery, access and analysis a relatively easy task for science users. The OVL-NG study aims to evolve, maintain and operate the ESA Ocean Virtual Laboratory Next Generation according to user needs. The main technical objectives of this project are to prolong the ESA/Copernicus data visualisation and promotion activities started in OVL and S3VIEW, to improve tools and services based on user feedback and explore ways to enhance the sustainability of these services in the long term. In addition, significant changes are required in the core of the SEAScope application to allow it to stream data from a remote source, such as a Cloud, a DIAS or a data centre. These developments are mandatory to facilitate the visualisation of large quantities of EO data and to make the application more attractive for users who need to explore and analyse these data without downloading complete data sets.

The design and implementation of user-requested features will be intertwined with developing these core evolutions to achieve the most satisfactory outcome. The sustainability of existing and upcoming services can be improved by reducing the time required to operate them and optimising both the usage and cost of the infrastructure resources. A panel of clouds and DIASes will be studied to get a clear view of the offers available to host services similar to OVL-NG. The processing system that feeds the online portals will be optimised to consume as few resources as possible, perform more monitoring tasks, and handle minor issues autonomously so that operating the backend of OVL-NG involves fewer human interventions.

Earth Observation missions generate a large amount and variety of satellite data, treasure troves waiting to be fully exploited but currently underused because their data format, volume and complex geometry constitute a barrier for many users. To help remove this barrier and foster data synergy exploitation, open tools such as the Ocean Virtual Laboratory were developed with ESA support, making data discovery, access and analysis a relatively easy task for science users. The OVL-NG study aims to evolve, maintain and operate the ESA Ocean Virtual Laboratory Next Generation according to user needs. The main technical objectives of this project are to prolong the ESA/Copernicus data visualisation and promotion activities started in OVL, improve tools and services based on user feedback, and explore ways to enhance the sustainability of these services in the long term. Significant changes are required in the core of the SEAScope application to allow it to stream data from a remote source, such as a Cloud, a DIAS or a data centre. These developments are mandatory to facilitate the visualisation of large quantities of EO data and to make the application more attractive for users who need to explore and analyse these data without downloading complete data sets. The design and implementation of user-requested features will be intertwined with developing these core evolutions to achieve the most satisfactory outcome. The sustainability of existing and upcoming services can be improved by reducing the time required to operate them and by optimising both the usage and cost of the infrastructure resources. A panel of clouds and DIASes will be studied to get a clear view of the offers to host services similar to OVL-NG. The processing system that feeds the online portals will be optimised to consume as few resources as possible, perform more monitoring tasks, and handle minor issues autonomously so that operating the backend of OVL-NG involves fewer human interventions.

The WFP Innovation Accelerator was launched in 2016 to identify, nurture and scale bold solutions to end hunger globally. The Accelerator supports globally WFP internal teams, entrepreneurs, start-ups and NGOs from its base in Munich, Germany, through funding, hands-on support and access to WFP global operations and expert networks. EO & AI for SDGs Innovation Programme enables entrepreneurs and organizations to utilize Earth Observation technologies and Artificial Intelligence to achieve Sustainable Development Goals while striking for financial sustainability, growth, and industry leadership. The pilot project’s goals are twofold; first, the development of a novel hydrological drought index, and second, its comparison to and complementarity with a conventional meteorological drought index for the purposes of anticipatory action in Zimbabwe and Mozambique. The hydrological drought index (HDI) will comprise surface water availability, precipitation, and soil moisture measurements, including near-real-time historical measurements and predictions facilitated by rainfall forecasts. The HDI will be compared to meteorological drought indices (MDI) in the target geographies of Zimbabwe and Mozambique. The HDI and MDI will be compared for their predictive power of food and hunger proxies: zonal NDVI statistics (10m from Sentinel-2), food market prices, and other food production and security data available from the WFP. The final goal of the pilot project is to develop the market viability of the new HDI.

The Pacific Crest Trail Association (PCTA) is dedicated to preserving and promoting the iconic Pacific Crest National Scenic Trail (PCT), spanning from Mexico to Canada. The PCTA Interactive Map is a valuable resource for hikers, researchers, and outdoor enthusiasts, providing essential information about the trail’s condition, amenities, and surrounding environment. To enhance the map’s functionality and visual appeal, this project aims to acquire Sentinel-2 satellite imagery from Sentinel Hub and integrate it into the PCTA Interactive Map.

The acquired Sentinel-2 imagery will provide valuable insights into the trail’s surrounding landscapes, including vegetation cover, water bodies, topography, and current snow conditions. This information can assist hikers in understanding the terrain, identifying potential water sources, and planning their routes more safely and effectively. Moreover, the general public can utilize the imagery to understand environmental changes better, monitor vegetation health, and assess the impact of climate-related factors on the PCT ecosystem.

By incorporating Sentinel-2 imagery from Sentinel Hub into the PCTA Interactive Map, this project will significantly enhance the functionality of the map, benefitting the many hikers, researchers, and trail enthusiasts that utilize the map daily. The project will empower users to make informed decisions, promote environmental awareness, and contribute to preserving and enjoying the Pacific Crest Trail.

The objective(s) of this project is to classify paddy fields and non-paddy fields with remote sensing data using deep learning in Indonesia. We want to produce the best model and best data to detect where the paddy fields are in Indonesia. In the next step, we want to classify the paddy growth phase using data from monthly paddy growth monitoring in Indonesia and remote sensing data from Sentinel Hub. In this phase, we will have a model to estimate the monthly harvest area. Lastly, using the result from the previous phase we want to train a model to estimate total paddy production in Indonesia combining survey data and big data with deep learning and mass imputation.

Massive and secure insertion of photovoltaic energy on the electricity grid requires precise monitoring of weather-induced power fluctuations. This monitoring requires a perfect knowledge of the location and power capacity of the solar plants. In addition, an accurate and up-to-date database of solar plants can help monitor the relevancy of incentive policies aiming to support solar energy adoption. Unfortunately, there is currently no such comprehensive database. Existing databases are often limited geographically, present data at a low resolution (statistics at the level of a town or department), or have a low refresh rate, making them quickly obsolete. Reuniwatt has developed an innovative and patented technology to identify solar installations from the sky: PARCS or Photovoltaic Atlas Remotely Captured from the sky. For now, PARCS relies on an Artificial Intelligence (Deep Learning) model and airborne images with a resolution of 25/20 cm. The disadvantage of our current data source is that it is limited to the French territory and has a refresh rate of 3 years. We aim to evaluate the benefit of low-elevation orbit satellite imagery to improve the coverage and update the frequency of PARCS.CNES supports this ambition. We believe that Pleiades and Pleiades Neo images, which have respectively 50cm and 30cm resolution, are a promising alternative to our current data source. Still, the portability of our algorithm on those images is yet to be demonstrated. The NoR sponsorship would allow us to experiment at low risk.

PASS–SWIO is a 12-month capacity-building project that aims to establish a sea level monitoring system for Madagascar based on the installation and deployment of a low-cost relocatable tide gauge (Portagauge), which uses Global Navigation Satellite System interferometric reflectometry (GNSS-IR) technology, combined with the analysis of satellite altimeter sea level data to provide validation and more exhaustive scale knowledge on sea-level variability. Madagascar currently has limited tidal prediction capability (based primarily on model data) and no national sea level monitoring capability. There is only one functioning tide gauge station, whilst an earlier tide gauge was swept away several years ago in the cyclone-prone north of the island. The project partners will work closely with the national Madagascar Meteorological Agency (DGM – Direction Générale de la Météorologie) who will take responsibility for the local maintenance and operation of the Portagauge, and who will be trained to carry out the data processing and analysis (for tide gauge and satellite altimeter data). Discussions will be held with key stakeholders to review the project and agree on a Road Map for the sustainable long-term implementation of a national sea-level monitoring system for Madagascar, which can serve as a model for other island states and coastal countries in the South West Indian Ocean (SWIO) region and beyond. Sentinel 3 SAR Altimeter data, processed with the SAMOSA+ coastal processor, are needed to support validation of the tide gauge measurements at Toamasina, on the NE coast of Madagascar.

I am an investigative reporter with Noteworthy.ie in Ireland and I am currently carrying out an investigation into unlicensed peatland extraction in Ireland. Our investigations are published on our website and simultaneously on TheJournal.ie, the largest native Irish online news outlet with 550,000+ average daily users, aged largely between 24-55, with a 50/50 gender split. As we publish in the English language, we additionally attract a small audience from the US, the UK and beyond who have an interest in Irish and European issues. The main objective of this investigation is to outline the extent of unlicensed peat extraction across the country (historic and present) and key to the investigation is using satellite imagery to visualise/map the changes to peatlands over a series of time.

Unfortunately, the quality of publicly available satellite imagery for the land parcels in Ireland that I am examining is very poor and not up to publication standards.

In this light, I would like to ask if it would be possible to discuss our project with your team with a view to accessing the required satellite imagery to help tell this important story.

This project will be prepared as a part of a dissertation at the University of Edinburgh Earth Observation and Geoinformation Management department. The goal is to explore the aspects of InSAR usability for peatland subsidence detection and comprehensively analyse the subject matter. Peatlands are wetland ecosystems with low oxygen levels and limited nutrients. They comprise 3% of the world’s land surface, approximately 4 million square kilometres. Peatlands are crucial for several reasons. They serve as excellent carbon sinks, holding 1/3 of the world’s soil carbon, which is twice as much as all the forests in the world combined. Peatlands are currently facing several issues. Firstly, 12% of peatlands have been degraded. Secondly, climate change is exacerbating these issues. Thirdly, long-term subsidence is causing harm. Lastly, this harm can result in CO2 emissions. Thus, continuously monitoring the peatlands’ subsidence over space and time is essential.

Several studies have indicated that Synthetic Aperture Radar Interferometry (InSAR) is a promising method for monitoring land subsidence. InSAR has several key benefits, including high spatial and temporal coverage and the ability to detect vertical changes with precision as small as millimetres. Additionally, SAR data is often available at no cost. The main goal of this project is to determine if InSAR can effectively detect subsidence in peatland areas. Essentially, the project aims to find a low-cost, high-precision method that can monitor peatland subsidence while providing broad spatial and temporal coverage.

The Ecosystem Accounting project (PEOPLE-EA) will study the relevance of Earth Observation for ecosystem accounts in terrestrial and freshwater ecosystems, and develop, validate and showcase a number of advanced ΕΟ solutions to produce ecosystem accounts, in physical terms, on ecosystem extent, condition and services. The project will contribute to the international collaborative efforts to advance the use of Earth Observation in Ecosystem Accounting (GEO ΕΟ4ΕΑ) and support countries developing their national ecosystem accounting. The team will first comprehensively review the opportunities and challenges to integrating Earth Observation in SEEA compliant national accounting.

The project “Development of potentials in peri-urban spaces as sponge territories for climate adaptation and mitigation”, short PeriSponge, aims to develop a toolbox for the identification of urban and peri-urban problem areas in regards to green infrastructure (Stockholm system, sponge city, SUDs, LIDs, etc. ). Green infrastructure serves many goals: Flood prevention, climate adaptation, and mitigation, as recreational areas and the overall quality of urban living. Το construct green infrastructure at the most effective places, a spatial evaluation of all the mentioned attributes across the urban area is necessary. As a multidisciplinary team comprised of urban planners, civil engineers, landscape architects, and traffic planners, we will develop a comprehensive, openly available toolbox that allows municipalities, planners, and other stakeholders to evaluate urban areas based on their potential regarding green infrastructure. Part of the toolbox is a spatial analysis approach comprising several thematic layers and a public participation program. The methodology will be applied and tested in the Austrian Cities Feldbach, Feldkirch, and Wels. The city of Feldbach has also agreed to construct a pilot project after identifying a suitable location. The pilot project will be accompanied by continuously monitoring microclimatic and hydraulic conditions. The developed methodology will be transformed into an open guideline. This guideline will benefit all parties involved in the urban planning process. It will offer a generalized approach to prioritize green infrastructure projects and help guide investments and funds where they will be most fruitful. The guideline will be distributed through federal and state-level channels, scientific publications and conferences.

The aim of this PhD is to study how geography teachers in secondary school in France are using satellite images in their lessons (if they do so). In France, the Ministry of Education tried to support the use of such media in the class in the mid-1980’s but the result of the action was not as successful as hoped. Finally, it looks like today most teachers turn to Google Earth for basic needs, but satellite images are not much used as part of pedagogic approach. The French Ministry of Education and the French Space Agency (CNES) still put action to emphasis the benefit of satellite pictures in geography class, but it seems to have a limited effect for many reasons. Recruited as a geography teacher in French Guyana myself while working on my PhD, part of my study is to try to figure out what are the best options to make the use of satellite images in geography class easy and efficient for teachers who are, in France, mainly history teachers and sometimes lack of technical background. To do so, I build school activities linked with the official programs and focused on satellite images that I use and test in my classes. Some of them have been published on the CNES website “Geoimage”. I mainly use Sentinel-2 images for an obvious reason: easy access. I sometimes use “raw images” in QGIS as part of “Digital projects” with high-school students but also to build cartography activities. The possibility of accessing very high-resolution images would help to work on some part of the programs that needs to focus on urbanism, social inequality in the cities organization (slums), infrastructures (ports, airports) connected to globalization, migration and if possible, to geopolitical aspects (as part of the new specialization in high school called HGGSP). The results of my project should benefit to teachers and first of all to students at secondary school. I would publish the results in my PhD dissertation to be used by teachers for their class.

In Kosovo, land movement activities have never been analyzed comprehensively. Remote observations data such as Sentinel-1 have led me to approach and do research on this topic, and in particular, how stable the surface of the territory is and where the most significant surface subsidences in the last 3-4 years have occurred using InSAR StaMPS/ΜΤI, respectively application of DinSAR PS techniques and SBAS analysis to derive time series of deformation assessment.

The CreoDIAS platform provides development and testing environments for all the Phi Lab stakeholders who are allowed to get resources for their research purposes. Platforms are made of virtual machines or dedicated servers, access to EO data, virtual hard drives, and backup space/service; light customisation can be added to provide additional services. The named account recharge should be performed to keep the availability of the platform for all the Phi Lab fellows/PIs.

This research is to be completed as part of the ESA Pioneer Earth Observation Applications for the Environment (PEOPLE) Ecosystem Restoration initiative. The overall technical objective of the project is to develop methods and tools using EO data to support ER efforts based on the needs, opportunities, and challenges, including in disturbed and degraded natural and semi-natural terrestrial and freshwater ecosystems in Europe and internationally. Bringing the user to the data is essential to EO application development initiatives, especially those addressing large areas, extensive time periods, and multi-EO datasets. Furthermore, by using the F-TEP, we are ensuring that algorithms can be accessed and used by Early Adopters – e.g. non-government organizations – and we will demonstrate the value of cloud platforms.

Plastics pollution in aquatic environment is an emerging challenge (Rochman et al.,2013). The most visible and disturbing impacts of this plastic pollution are the ingestion, suffocation and entanglement of hundreds of marine species. It is projected that plastic use will increase, with a concomitant increase in post-consumer plastic. Most plastics originate from land and are transported through rivers into the world’s oceans. Accurate estimations of plastic mass stocks and fluxes on land, rivers, and the ocean are crucial to optimise prevention, mitigation and reduction strategies. According to (Lebreton, et al., 2019) Vietnam appears to be a major producer of mismanaged plastic waste with an estimated emission of 1.63 Mt y-1. Rivers are the main source of marine plastic pollution (Schmidt, 2017). Current estimates of plastic emissions in the ocean are uncertain due to a lack of observations. Data collection needs to be scaled up in time and space and remote sensing could offer a solution to this problem. Plastic debris is generally assessed according to size: 1) macroplastics. i.e. plastic items superior to 5 mm, and 2) microplastics, i.e. plastic items inferior to 5 mm (Arthur et al., 2008). With regards to microplastic, it is widely considered that 80% of marine debris is from land-based sources (Allsopp et al., 2006). Therefore, the microplastic assessments from in situ sampling aim to quantify floating debris (Morrit et al., 2014) and estimate the riverine plastic fluxes or plastic exported to oceans (Estahbanati and Fahrenfeld, 2016; Lahens, 2018). Most riverine macroplastic items are between 1 cm and 1 m in size and cannot directly be detected from space depending on spatial resolution of satellite images used. However, recent data from the Saigon River (Vietnam) showed a relationship between vegetation patches and river plastic (van Emmerik, et al., 2019). Water Hyacinths function as accumulation zones, entangling plastic items. Preliminary analysis has demonstrated that such patches can be detected using images from ESA Sentinel-2 satellites and potentially be ‘unmixed’ to determine if patches are dominated by vegetation, plastic or non-plant debris. In the proposed research, we further explore opportunities for plastic monitoring by using aquatic vegetation as a proxy. Vegetation in rivers is detected and analysed using available Sentinel-2 images for 2018. The focus is on the Sai Gon River which flows from Dầu Tiếnglake and ends up in the Dong Nai River next to Ho Chi Minh City. The seasonal variation in vegetation patches and the estimation of plastic transport are compared with the in-situ measurements.

Delineation of agricultural fields is desirable for the operational monitoring of agricultural production and is essential to support food security. However, automated field delineation remains challenging due to the large within-class variance of pixel values and small inter-class differences. Analyzing high spatial resolution Remote Sensing data permits the delineation of farm boundaries. Accurate delineation of farm boundaries is essential for planning and decision-making actions. First, it enables a better estimation of cropland areas, which is critical information for farmers and agricultural managers (e.g., ministries and private sector players). Farmers often use traditional measurement approaches to estimate the area of their farms, which sometimes leads to high under- or over-estimation. Accurate knowledge of farm boundaries (and, therefore, cropland area) will lead to efficient use of farm inputs such as seeds, fertilizers and pesticides. They may also help to optimize harvest logistics. Second, accurate information on farm boundaries can facilitate land registration and subsequent acquisition of land use rights for smallholder farmers (through a land tenure information system). Farmers, communities and the private sector are mostly deterred from investing in land resources due to unclear land use rights in rural areas. Developing an accurate parcel system through high spatial resolution remote sensing data is an essential first step towards creating a land tenure information system and, potentially, a land taxation scheme. Such a system will reduce land-related conflicts and encourage increased investment in agriculture. It can also improve farmer access to inputs and credits. Third, delineating farm field boundaries can improve crop type classification using object-based image analysis (OBIA) procedures.

HYDROCOASTAL is an ESA project to maximise the exploitation of SAR and SARIn altimeter measurements in the coastal zone and inland waters by evaluating and implementing new approaches to process data from CryoSat-2 and Sentinel-3. In addition, optical data from Sentinel-2 MSI and Sentinel-3 OLCI instruments will also be used in generating River discharge products. The region of interest of this project is the northern Adriatic Sea, especially the drainage basin of the Po river and its coastal zone. During the 2022 spring and summer and the preceding winter, unusual climatic conditions caused a deep river drought, with saltwater intrusion up to 40 km from the mouth of the river. This situation caused significant fish mortality, and, in addition, it is seriously damaging the agricultural economy and daily life of a large part of the country. In this context, the current project addresses the need to obtain a “reference” satellite altimetry dataset produced with advanced algorithm standards (SAMOSA+ IWHR), against which the project results will be compared. Moreover, such a database will supply a sea/inland surface level height database with unprecedented details owing to the high-frequency sampling (80Hz) of inland water at the ESA Altimetry Virtual Lab operated by the EarthConsole.

The implementation methodology is focused on creating a reference database of S-3A&B and CS-2 high-frequency sea/inland water level anomalies in the AOIs. The geographic areas are several lagoons in the northern Adriatic Sea, along with the surrounding coastal zones and drainage basins, especially the Po river.

Cryo-TEMPO is a project bringing together teams of radar altimetry scientific experts and software engineers to generate agile and state-of-the-art Thematic Data Products, which aim to open CryoSat-2 datasets to new sectors and user groups not being Altimetry experts. This data will go into the Polar Ocean Theme and contribute and improve data from both hemispheres.

CryoSat+ Antarctica aims to study CryoSat-2 measurements for the Southern Ocean and find novel processing algorithms and methods. Furthermore, the project explores the connection between the Antarctic sea ice and sea level. inter­compare and validate multiple approaches to sea surface height and sea ice thickness retrieval on Antarctic sea ice. The mechanism of the Southern Ocean is far from understood, and we need the best data processing to study these mechanisms.

GPOD data is currently used in the ALBATROS project, where its high signal-to­noise ratio makes it useful in tidal analysis. The objective is to foster collaborative research and interdisciplinary networking actions. Improve knowledge about bathymetry and ocean tides in the Southern Ocean. The knowledge about ocean tides is at the crossroads of many scientific fields, especially in the Polar regions, as it has a significant impact on ocean circulation modeling and the understanding of the coupled dynamical response of the ocean, sea ice, and ice shelves system, the quality and accuracy of sea surface height and sea ice parameter estimates from satellite altimetry, or the understanding of ice-shelf dynamics, for example.

Urban lakes, especially in developing nations like India, are polluted by civic sewerage lines and local municipal body garbage dumping. This is a considerable threat to the population’s health as a large population density around the polluted water body leads to diseases, infection, and the groundwater table as the pollutants percolate into the water table. In addition, these lakes are the catchment areas for tributaries of minor rivers used in agricultural activities. Our project aims to detect polluted lake bodies and their tributaries by analyzing high-resolution satellite imagery. The goal is to identify indicators of pollutants and trace the aftected bodies such as major rivers and agricultural lands aftected by this pollution. We plan to use Pleiades’ high-resolution imagery (50cm and 30cm) to identify en-masse:

1. Masks for Water bodies in urban areas such as lakes (including water filtration plant ponds) and open sewerage streams.

2. Urban agricultural bodies lying in the pathways of these streams/lakes.

3. Debris accumulates on water bodies due to illegal garbage dumping.

4. Identification of sources of pollutants adjoining the streams and lakes (such as waste segregation units, waste landfills, etc.).

This analysis can be helpful for civic bodies in curtailing pollution of potable water bodies and would encourage contracts with the provider for continually analyzed feeds. For example, the city of Bangalore has over 150 lakes which have recently become sewage infested and are affecting not just aesthetics but also polluting the groundwater table and agriculture of surrounding areas. Therefore, identifying the source of pollutants is essential in bringing public awareness and alerting the ciνic bodies in taking detrimental action towards keeping these water bodies clean.

The project uses Sentinel-1, 2, and Planetscope data to map the location of schools. Ιt maps the population in the catchment area along with the road network. This is done to assist the UNICEF GIGA project to determine which schools to roll out electricification and internet connectivity. The data is needed to identify areas and do a cost/benefit analysis.

SICE is delivering an automated open-source processing chain using Sentinel-3 OLCI and SLSTR data to determine a dry/wet snow and clean/polluted bare ice spectral and broadband optical albedo 1 km daily product for land ice (glaciers, ice caps, ice sheet). Land ice mass loss is the largest source of global sea level rise. Since 1992, two thirds of sea level contribution from land ice comes from the Arctic. Roughly half of the Greenland ice sheet mass loss is from increased surface melting. The fraction from surface melting is even higher for smaller Arctic ice masses. The dominant energy source for melt is absorbed sunlight controlled by surface albedo. Bare ice and snow impurities, including biological effects, present strong melt amplifiers through surface albedo. NASA MODIS sensors provide a climate data record (CDR) of snow extent and ice albedo since 2000 with the hosting Terra and Aqua missions now several years beyond their design lifetime. The NOAA VIIRS sensor bridges the need for a satellite-derived albedo. However, Copernicus Sentinel-3 also fulfils the WMO essential climate variable mandate, with the following advantages over VIIRS and MODIS:

 The Sentinel-3 OLCI instrument offers higher (300 m) finest spatial resolution (SR). The finest SR for MODIS is 500 m. For VIIRS, the finest SR is 750m.

 Sentinel-3 OLCI and SLSTR instruments offer more spectral coverage than MODIS or VIIRS, with the OLCI channel 21 of great value being located in the part of the spectrum most sensitive to snow grain size. Neither MODIS nor VIIRS measure in this spectral channel.

 The recently completed Scientific Exploitation of Operational Missions (SEOM) Sentinel-3 for Science (S34Sci) Land Study 1: Snow (S3 Snow) albedo algorithm outperforms the NASA MODIS MOD10A1 product for dry clean snow.

The main objectives of the work are:

1. Deliver an automated open-source processing chain using Sentinel-3 OLCI and SLSTR sensors to determine a dry/wet snow and clean/polluted bare ice spectral and broadband optical albedo 1 km daily product for land ice (glaciers, ice caps, ice sheet).

2. Determine an optimal cloud clearing process for cryospheric application leveraging cloud ID insight from SEOM Sentinel-3 for Science, Land Study 1: Snow

3. Test the above for application to sea ice (as opposed to land ice).

4. Implement terrain correction for slopes under 4 degrees typical of more than 90% of land ice. Terrain slope and azimuth have a strong impact on snow and ice anisotropic reflectance in optical wavelengths. Above 4 degrees remains in development elsewhere and does not comprise a significant portion of the ice sheet.

5. Validate the algorithms using field data.

6. Deliver daily 15 March – 30 September 1km pan-Arctic glacierized region albedo products for years 2017 onward via the PROMICE.org web portal.

7. Demonstrate a pre-operational near-real-time (under 6 hours latency) capability for Sentinel-3A and Sentinel-3B for delivering spectral and broadband albedo.

Provide cocoa and sugar cane farmers in Latin America with a precision farming platform that allows them to monitor their crops, detect any affectation in time, and apply best managing sustainable practices to protect the plantation, but also the soil, water, and biodiversity, all of them today in risk. AgroCognitive is a triple impact purpose startup, and our dream is food production that is sustainable, plenty, and profitable for everyone. In addition, we will conduct research for these crops, becoming a complete affordable management tool that significantly benefits our farmers’ communities and ecosystem.

The main objective of the project is to optimize water consumption for crop irrigation with a specific focus on addressing the local water scarcity context in Spain. The aim is to achieve optimal crop results through the efficient utilization of water and other resources. The primary field of application encompasses open fields and water-dependent crops such as algae aquaculture. This optimization will be facilitated by the utilization of Sentinel 2 images and associated indexes, such as NDVI, NDMI, SWIR and NDWI. By leveraging these indexes, the project aims to provide farmers and engineers with valuable insights into the physiological state of vegetation. This information enables a nuanced understanding of crop health, growth patterns, and water requirements and mitigates issues related to both overwatering and insufficient irrigation during essential periods while achieving the best results related to crop quality. By integrating high-resolution Sentinel image indexes with weather measurements and their water consumption data, agronomists will be empowered to make informed decisions, fostering an efficient and sustainable use of available resources.

The objective of this study will be to train and compare the performance ofmachine learning algorithms which we design in order to learn and predictchanges in winter wheat production in fields from the southwest of Sweden.The study will use available Sentinel-1 polarimetry radar data, field topography,Sentinel-2 multi-spectral data, and local weather data over four years as inputs.It aims to demonstrate the effectiveness of Sentinel-1 data in predicting winterwheat yield, emphasizing the necessity of pixel transformation and despecklingtreatment towards accurate predictions. The ultimate goal is to establish amethod that can reliably predict agricultural yields using Sentinel-1 data alone.Although at this stage this is only a research project the end beneficiary shouldbe farmers not only in Sweden but also world wide. The results and algorithms(not the data) will be published and be made available online via github.

Official statistics are hard to get in many lowest-income countries, such as North Korea and Myanmar. Nevertheless, without data, researchers and policymakers cannot systematically investigate regional events or policies. For example, the Sustainable Development Goals by the United Nations picks ‘No Poverty’ as Goal 1. Without reliable data on poverty, it will be tough to assess any progress made by countries. Our research objective is to use satellite images (Sentinel and Landsat) to predict grid-level economic statistics, including poverty and income. We plan to use a semi-supervised machine learning algorithm to generate annual grid-level poverty and urbanization measures in Asia, Africa, and Latin America. Ground truth data will consist of large-scale survey data, including the Demographic and Health Surveys by the USAID, Afrobarometer, and census data from various countries. The ultimate goal of this project is to provide readily usable grid-level economic statistics, allowing researchers to investigate multiple sub-national changes in economic statistics. We will provide data as raster data (e.g., GeoTIFF data). This way, researchers can flexibly use the data. For example, if one wants to use data at the town level, one can aggregate grids over administrative boundaries from a GIS vector shapefile. We will release these measures and codes publicly so that other interested researchers and policymakers can easily use them.

The objectives are:

1. To determine how landscape structure affects the structure of the bird community based on data from 2010 – 2023 from Slovakia and Croatia.

2. Prepare baseline 2020 landscape structure for monitoring effects on landscapes of the re-parcelling process planned in the region.

3. Based on results of 1) to predict the most probable influence on specific bird species as well as on bird guilds and conservation status.

The result of the project will be the preparation of various landscape metric variables to put as a starting pool for the selection of the most influential ones linked with an overall number of bird species. We will test linear but also other types of connections between variables of interest (number of species – number of species in guild-diversity or conservation value based on SPEC status) and different subsets of landscape metrics that can serve as predictors that describe overall bird communities, especially Passerine bird communities. Landscape metrics are measures and quantification of landscape structures and are extremely important for describing spatial patterns of bird populations, and landscape heterogeneity is probably the most determining factor. Since Croatia does not have an adequate way of collecting data on the biological elements of terrestrial ecosystems, we will use, besides some Croatian data, data from Slovenia.

Ornithology, ecology and conservation biology experts will benefit from the project results. Especially, managers who should give recommendations for upcoming re-parcelling of agricultural land planned to start soon in Croatia. The project is a non-commercial research project for the moment but the possibility to use results as some kind of web application (Shiny app) for landscape managers and Ministries responsible for CAP greening and Green Deal implementation.

This proposed feasibility study aims to identify areas where satellite technology can bring a new dimension to detect and prevent fraud in the food sector. The objectives of the study include:

• To develop services using viable satellite technology from a business perspective.

• To maximize the usage of available space assets, including ESA and other space technology.

• To develop services involving stakeholders from the food sector, focusing on certification processes and supply chain integrity.

The project result beneficiaries are Organic farmers, Organic food consumers, and Organic certification agencies. A demo service will be designed and developed using satellite imagery to collect and follow up on the feedback from different organic stakeholders during the project.

The using of InSAR data is very important due to their feasibility and capability of observing the patterns of ground deformation and infrastructure displacements. The objectives of this project are: First: Developing a methodology that can automatically analyze Sentinel-1 data packets (or TerraSAR-X if possible) depending on smart algorithms (Deep Convolutional Neural Networks DCNN as a preliminary choice) to identify the areas in which linear infrastructures are at risk of displacements due to landslides in the studied area. Second: Establish a predictive model for infrastructure displacements in the studied area, based on the methodology that we will try to develop and use a time series model of Artificial Neural Networks ANN as a preliminary choice. Third: Develop a GIS toolbox to integrate the final results within a GIS environment (using Python). To accomplish our project, we need to collect a large number of Sentinel1 images (or TerraSAR-X if possible) for the studied area and create a repetitive network of interferograms. Additionally, we are going to separate the distortion signals from the related sources of errors to achieve millimeter accuracy in detecting infrastructure displacements that could happen in areas of high sensitivity to landslides. Separating the distortion signal from the atmospheric error is one of the most difficult challenges we will face, thus we suggest using a high pass filter and a low pass filter to eliminate this error. Infrastructure displacements will be detected based on smart technology methods. We suggest developing a new methodology for monitoring infrastructure displacements based on deep learning algorithms. In particular, we propose using Deep Convolutional Neural Network DCNN algorithms to develop a monitoring methodology that takes into account the atmospheric corrections, and we propose using the Backpropagation algorithm or the Artificial Neural Network ANN algorithms to create the predictive model. Finally, we will integrate the research results within a Geographic Information Systems GIS environment and develop a GIS smart tool. We recommend the use of Python (the most widely adopted programming language in the fields of GIS and AI) in developing the proposed tool. The expected outcomes are represented in getting a functioning software code to implement as a GIS toolbox in:

1. Obtaining periodically updated measurements of displacements (every 6 months) over the studied area and similar areas with an accuracy of one centimeter per year.

2. Determining the level of catastrophic risk in potentially unstable locations. We are planning to get five levels of risk (very low, low, moderate, high, very high). The risk levels will be represented in polygons or dense points. Such results will serve local, regional and national authorities. The project is expected to be kindly funded by ESA NoR Sponsorship.

The project aims at processing multi-temporal images from Sentinel-1 using P-SBAS or other related methods. We want to investigate the deformation rate and pattern of Abuja, the study area, to know if there is an imminent geohazard problem. We wish to carry out a multi-temporal analysis of the site’s images from 2016 to 2020. This will give insight into the deformation pattern of the area.

We aim to support the Production Centre of the GEP dedicated to the CNR IREA Sentinel-1 P-SBAS service for P-SBAS stands for Parallel Small Baseline Subset and it is an advanced DInSAR processing chain for the generation of mean velocity maps and corresponding deformation time series from stacks of Copernicus Sentinel-1 SLC data. The employed interferometric technique produces not only the maps of ground deformation measured along the line of sight of the sensor but also takes advantage of a series of images (instead of only two as conventional DInSAR) acquired over time, allowing monitoring the temporal evolution of deformation. The service is now operated on the GEP, supporting up to 500 Copernicus Sentinel-1 images per run. Starting from the end of June 2019 it has been already open to 50+ users from 40 user organizations worldwide. It will be used also to support activities of the ESA EO4Alps Landslides project.

The requested resources are aimed at supporting the Production Centre of the GEP dedicated to the CNR IREA Sentinel-1 P-SBAS service. P-SBAS stands for Parallel Small BAseline Subset, and it is an advanced DInSAR processing chain for the generation of mean velocity maps and corresponding deformation time series from stacks of Copernicus Sentinel-1 SLC data. The employed interferometric technique produces not only the maps of ground deformation measured along the line of sight of the sensor but, taking advantage of a series of images (instead of only two as conventional DInSAR) acquired over time, allows monitoring the temporal evolution of deformation. The service is now operated on the GEP, supporting up to 500 Copernicus Sentinel-1 images per run.

The project provides empirical evidence from two case studies where it is possible to contrast the premise recurrently mentioned in the literature on the subject in the sense that the agroecological transition process contributes to improving the living conditions of the peasant population. Promoting demonstration plots is expected to generate agroecological learning processes by the farmers in the study area and strengthen the farmer schools’ scheme by developing baseline indicators and the agroecological transition process. Strengthening existing plots will also prevent new areas from being opened to agricultural cultivation. The knowledge derived from the project will support studies on agroecological transition and food sovereignty. From the above, it is necessary to determine and analyze the schemes under which peasant families in two regions of Chiapas sustain their agricultural production. As well as to identify the mechanisms that allow them to transition to an agroecological production scheme that contributes to achieving food sovereignty and reducing poverty in the territory. The project is carried out in the Highlands and Border regions of Chiapas. It is part of the Conacyt 2022(2) Cali for Postdoctoral Stays in Mexico for the Training and Consolidation of Researchers for Mexico, issued by the National Council of Science and Technology (CONACYT).

The project’s main results will demonstrate that it is possible to monitor electricity transmission infrastructures on a large scale, thanks to satellite images. More specifically, we will try to detect anomalies in the position or movement of electric transmission towers, using a range of satellite images showing the exact location but separated in time and point of view. Our research will be based on Pleiade Neo image archives.

The main results of this proof of concept may be made public with the agreement of our partners. If this leads to an industrial application project, the French public energy transport service will be the primary beneficiary.

Copernicus’ Sentinel-1 is the first operational mission that systematically acquires SAR data globally. The open and free data policy led to a massive rise of interest beyond traditional SAR experts and calls for easy-to-use tools that accelerate the uptake of this valuable data source. The Open SAR Toolkit (OST) aims to do so by bundling the full workflow for the generation of Analysis-Ready-Data (ARD) from Sentinel-1 for land in a single high-level Python package. The concept of ARD is driven by the need to let the user focus on the actual information extraction, thus providing ready-made data that does not need further pre-processing. OST can be considered as an end-to-end data preparation package that includes functionality for data inventory and advanced sorting as well as massive concurrent downloads from various data mirrors. The pre-processing routines are almost entirely based on ESA’s Sentinel-1 toolbox and wrapped into a single function for fully automated batch processing. Since at the moment there is no unique consensus on the specification of ARD products for SAR and the respective pre-processing steps involved, different types of ARD templates can be selected and customised. OST does include advanced types of ARD such as the combined production of calibrated backscatter, interferometric coherence and the dual-polarimetric H A-Alpha decomposition. Time-series and multi-temporal statistics (i.e. time scans) can be produced for each of these layers. The generation of seamless large-scale mosaics over time is possible, too. Jupyter notebooks are the main way to interact with OST and tutorial notebooks are available to get started. This project aims to further develop the toolkit and showcase advanced application possibilities through the use of fully automated ARD data.

Our overall objective is to implement digital and precision agriculture services for farmers to make data-driven smart farming decisions from sowing to harvesting. The followings are sub-objectives of the project.

• Integrating crop management, Sentinel data, weather data and AI to generate outputs that can monitor crop stresses owing to weeds, insects, lack of fertilizer etc.

• Enable users to identify hotspots for field scouting.

• Enable users to practice spot applications of inputs to save the cost of operation and environment.

• Predict crop yield at farm and regional scales.

• Enable policy users to know what is grown, where, and how it is performing.

Poor water and sanitation cost the global economy $225bn per year. Return on sanitation investment is difficult to quantify, yet 827k people die yearly due to poor water, sanitation and hygiene. The “Space for Sanitation” project aims to provide a complete sanitation waste treatment solution with smart management platform that will deliver safe and effective sanitation waste treatment with resource recovery and actionable insights relating to the broader sanitation ecosystem. The project will use pyrolysis to treat human waste at the source, neutralising harmful sanitation-related pathogens and recovering valuable byproducts, including thermal and electrical energy and biochar. The smart sanitation management platform harnesses the latest Internet of Things (IoT) and Artificial Intelligence (AI) technologies. It incorporates space-based technologies that deliver earth observation, satellite communications, and Global Navigation Satellite System (GNSS) capabilities. The platform will facilitate linking environmental data derived from terrestrial and space-based sensing capabilities to sanitation-related pathogens in waterways and disease incidence in communities. The fundamental goal of the activity is to create value from waste processes and sanitation management data, including the provision of predictive health analytics as the basis of an early warning system for the risk of disease.

The project focuses on polar and coastal altimetry estimating snow depth from the CRYO2ICE opportunity. The purpose is to improve Sea Ice Thickness measurements from altimetric satellites. The altimetry community and ESA will benefit from the results of this work. In addition, the output of the requested processing will be made publicly available in netCDF format.

Quantifying and identifying CH4 emissions precisely, especially for high emitters, (such as the Permian Basin in the United States, the Fresh Kills Landfill in New York, etc.) is key to effectively decreasing the emissions. However, these objectives are challenging, due to the diversity and wide distribution of methane sources. Livestock, fossil fuels, landfills, wetlands and biomass burning have been studied as major contributions of methane emissions, so detecting specific methane sinks to repair is demanding on a large global scale. In addition, the discharge of methane exhibits significant stochasticity both in time and space. Methane sinks present high-intensity and short-term intermittent emissions, or long-lasting continuous exhaustion, thus frequent and long-term monitoring is requisite to the accurate estimation of CH4 emissions. Meanwhile, due to the site-specificity and dynamic changes in terrain features of source sectors, methane emissions are extremely variable in duration, rate and flux across individual sites. Therefore, point-sources methane emissions quantification over large-scale (continental to global) and long-term (years to decades) is arduous but critical to curb global warming and estimate the forthcoming climate change. How to utilize remote sensing data, integrating satellites with aircraft, to precisely quantify point-sources methane emissions in North America is the focus of this research.

With glacier retreat and climate change, high mountain geohazards, including catastrophic landslides and glacial outburst floods, are becoming more common in many mountain ranges around the world. While some of these occur in remote valleys with little downstream impacts, others can be disastrous if they intersect human settlements or infrastructure such as roads or pipelines. For example, in February 2021, a large rock and ice avalanche descended the Ronti Gad and Rishiganga valleys in Uttarakhand, India, destroying two power plants and leaving 200 people dead or missing. I led a large international effort of geoscientists, hazards professionals, remote sensing experts, and social scientists, to understand the geophysical causes of the disaster, and we relied heavily on rapidacquisition, very high-resolution stereo imagery from WorldView, Pleiades, and SkySat to quantify the geomorphic changes caused by the landslide and ensuing debris flow and flood, and to serve as a terrain model on which we ran numerical simulations of the runout. Our first paper (Shugar et al., 2021) was published in Science about five months after the disaster. Similarly, high-resolution topographic data, generated by satellite DEMs or lidar, has been instrumental in understanding other high mountain geohazards. I am involved in other geohazards projects where we are making use of very high-resolution satellite imagery and lidar to quantify massive geomorphic changes. For example, I am building high-resolution DEMs from stereo SkySat and historic air photos to quantify any precursory motion for a landslide onto Canoe Glacier in coastal British Columbia, Canada. The landslide did not kill anyone or destroy infrastructure, but is considered a near-miss, as there is an air strip and access road for a nearby mine, downstream. Like with the Uttarakhand disaster, we are using the DEMs as an input for numerical modeling to determine what might have happened if the landslide was 10% larger, or occurred slightly farther down the valley. In other words, very high-resolution, rapidly acquired satellite data has become a critical part of modern geohazards work. So this proposal requests the ability to acquire high-resolution stereo imagery of geohazards as they develop, and so I cannot provide a specific location of interest. Each disaster is unique, as is the response of governments and international agencies to the event. In some cases, the international scientific community is called on to deliver timely assessments of the ongoing risks, as was the case following Nepal’s Gorkha earthquake, where I was part of a large team delivering evaluations of landslide risk from satellite imagery to agencies including NASA, and the Nepali Army. Aside from reports to organizations such as these, results from the proposed satellite analysis will be as peer-reviewed journal articles.

The aim of this project is to develop two machine learning processes, which require VHR data:

– super-resolution method, trying to enhance Sentinel-2 resolution to 2.5 meters (14.000 sq. km of SPOT data is required for this purpose)

-multi-resolution building detection, based on Sentinel-2, SPOT and Pleiades data (800 sq. km of Pleiades data and 1.000 sq. km of SPOT data are required for this purpose).

This project will develop, test, and demonstrate software integrating the data science language R with the openEO software ecosystem. This involves developing an R client, integrating openEO software components in R integrated development environments (RStudio, Project Jupyter), and R user-defined functions that directly operate on data cubes and their interaction with the openEO back-end drivers. Selected use cases will demonstrate the usability of the developed components. The objectives are to install and maintain R, alongside Python, as a first-class data science language for analyzing Earth observation datacubes using the openEO software ecosystem and to develop it further to encourage cross-language inspiration and competition. This will be achieved by developing R software components on both the client and back-end sides, testing this software, and demonstrating it in full-fledged use cases. Client-side development will address expectations R users have and include availability from standard repositories (CRAN), integration with IDEs (RStudio, Project Jupyter), integration with modern data science approaches (tidyverse), integration with current r-spatial packages (sf, stars). Α further objective is to make it easy for users to compare local computations with those carried out on the cloud platform. This involves the ability to obtain (download) small data cubes, e.g., for a single pixel or a small region to analyze locally, and the ability to use identical R functions and data structures on the client and the cloud side, by using R UDFs (user-defined functions: the ability of the openEO ΑΡΙ to allow arbitrary, user-defined code on the cloud side in a constrained environment).

The Rapid Action on coronavirus and EO dashboard is a platform that demonstrates how the use of Earth observation data can help shed new light on societal and economic changes currently taking place owing to the coronavirus pandemic. Across all European countries and ESA Member States, the dashboard showcases examples of how different analyses over a wide range of Earth observation data coming from the Copernicus Sentinels and Third Party Missions, as well as groundbased observations and advanced numerical models via the Copernicus Services can illustrate these socio-economic and environmental changes. The dashboard not only captures the effects of the lockdown, but also shows how Europe is beginning its recovery and is relaunching a number of activities. In this framework PLES is in charge of keeping coordinate and consolidate the data indicators of the Dashboard and in this activity the Truck Detection indicator need to be updated to allow a more complete and explanantory effect of the pandemic impact on the commercial activities thought the monitoring of trucks traffic and made avaialbe on the dashboard the most recent and complete information regardig this indicator.

The recent global pandemic crisis (COVID-19) is posing strong pressure on national health organizations; moreover, changes in the economic models are expected during and after the crisis, concerning the pre-crisis structures and fluxes. The use of earth observation (HR and VHR satellite data) merged with population movement information (from mobile devices) and geostatistical administrative information (e.g. number of working permits to foreign citizens) can be used to assess the economic impact of the pandemic for international logistic hubs and agriculture management (workload, productivity). The use of machine learning (ML) / Artificial Intelligence (AI) tools allows for identifying correlations and extracting trends.

The objective is to provide the most critical drought indicators for agricultural decision-making at the regional level (NUTS3-NUTS5) and enable what-if scenarios for “average,” “best,” and “worst” case outcomes. The indicators to be provided are yield and water demand for the most important crop types: wheat, corn, sunflower, and soybean. The covered geography is Austria, Hungary and Romania.

The project aims to develop a robust and accurate rainfall prediction model using multiple data sources, including weather stations, satellites, and radar. The research question is: Can the integration of multiple data sources improve the accuracy of rainfall predictions? The project’s overall objective is to develop a model that provides accurate and real-time rainfall predictions, which can be used for various applications like agriculture, water resource management, and disaster prevention.

This research is to be completed as part of the ESA-funded Global Mangrove Watch: Radar Alerts for Mangrove Monitoring (RAMM) system that exploits the full Sentinel-1 time series to provide timely monthly mangrove forest change alerts to support end users in mangrove protection, conservation, restoration, and management. RAMM will be developed, demonstrated, and evaluated in a collaborative effort by Hatfield (a company with extensive mangrove monitoring and assessment experience), Aberystwyth University (a technical lead for Global Mangrove Watch (GMW) product development), and Wetlands International (one of five international NGOs coordinating the Global Mangrove Alliance). The technical objectives of the RAMM project are:

1. Benchmark candidate change detection algorithms using S-1 time series data for delivery of monthly mangrove change alerts.

2. Implement the best-performing algorithm in the C-DAS using open, cloud-native standards to enable the scalability of the RAMM system to global alerts.

3. Validate the performance of the RAMM system using a GMW validation dataset and evaluate the impact on end-users.

4. Develop a roadmap for operating RAMM across priority mangrove ecosystems globally.

The RAMM system seeks to enhance the information provided annually by GMW and monthly for selected regions based on the analysis of Sentinel-2 imagery. This addresses the need for more timely alerts of mangrove losses for the ongoing protection of mangroves and interventions to prevent and minimize losses. Providing a change alert system for mangroves using S-1 this activity will have the societal impact of providing more up-to-date alerts of changes across these landscapes, therefore allowing conservation organizations, governments, international organizations, and companies to better monitor the impact of our efforts to restore and protect these important ecosystems. RAMM will directly support Sustainable Development Goals (SDGs) and other international policies, e.g., Ramsar, Paris Agreement, and Convention on Biodiversity (CBD). The RAMM system co-locates compute resources with data from the EOData collections available within CREODIAS to minimise network cost and latency on analyses. Due to the massive size of EO Data, running EO pipelines with this approach enables green-software initiatives; especially when operating at regional/country scale analyses across a distributed compute cluster. We will be producing detailed performance analyses of our approach along with our objective goal to produce point/polygon alert statistics detailing changes for mangrove forest health. These results will be utilised by GMW to enhance their Mangrove Monitoring platform available online for the public. The algorithms will also be made Open Source to foster scientific and software advancement in Earth Observation analyses, pipelines, and community.

The objective(s) of this project is to test the Sentinel Hub batch processing API for processing large areas (> 500,000 ha) of rangeland in Sub-Saharan Africa. The work involves the monitoring of rangelands using EO and AI to assess the density and height of the grass. The outputs allow for targeted grazing by pastoralists across various RGU’s which ensures a sustainable supply of fresh grass for the heard while also ensuring this ecosystem is adversely damages by overgrazing. Information of the location of “optimum” RGU’s for grazing is delivered through an app that is made available to pastoralists.

The project’s primary objective is to develop and implement a prototype for an EO-based rangeland monitoring system at a continental scale for Africa. It will be based on the synergetic utilization of Sentinel-1 SAR, Sentinel-2, and Sentinel-3 multi-spectral data and shall cover the entire continent at 10m spatial resolution. This EO-based rangeland monitoring system aims to implement tailored algorithms within an end-to-end analysis and production workflow (ranging from data access and analysis to product generation, validation, and dissemination) that facilitates the routine (i.e., annual/seasonal/monthly), synoptic (i.e., a continental scale for Africa) and high-resolution (i.e., 10m) EO-based monitoring of rangeland systems. In addition, this project aims to develop and generate a suite of dedicated higher-level information products such as the spatial and temporal extent of rangeland and relevant land cover types, herbaceous biomass availability, carrying capacity, etc. Furthermore, the rangeland monitoring system is exceptionally user-driven, with priority given to direct response to the requirements and information needs of the key users. It builds upon and exploits the current observational capacity offered by the Copernicus Sentinel missions and will develop innovative and scientifically accurate products directly relevant to rangeland monitoring. The products will enable further application and services to build on top of them that can be utilized by a broad range of actors who expresses an interest in rangelands, from continental to local scales. The project further focuses on capacity development and knowledge transfer to organizations and actors in Africa to enable the operational production of the developed products after the completion of the project activity.

The coronavirus Covid-19 pandemic has virtually paralyzed daily life as we know it. Even when the spread of this highly infectious disease has been halted, the world will face huge challenges getting back to ‘normal’. European Space Agency (ESA), in coordination with the European Commission, is launching a special edition of the Custom Script Contest, focused on the support of space assets during the COVID-19 crisis, managed by Euro Data Cube group. Following a similar format, but further to looking for new algorithms, we are in the quest for ideas on how satellite data could help monitor and mitigate the situation for the upcoming months, while the world will organize to get back to business and will need to adapt from this crisis.

FOCUS CATEGORIES

– Economic operators’ activity (e.g. factories, supermarkets, transport networks, oil refineries, commercial ports), -human activity distribution (e.g. parked car distributions over urban areas, social distancing estimations),

– Agriculture activity (e.g. unattended fields and crops, disruptions due to supply chain issues, things that may contribute to mitigation of problems appearing 6 months from now).

TOOLS

To support you the Euro Data Cube team has specially prepared an environment where you will find:

– High-Resolution data sources in addition to our standard EO missions’ data offer. In partnership with Airbus and Planet we have made available Pleiades and PlanetScope data over several locations to support e.g. urban monitoring.

– A plethora of Euro Data Cube Tools ready to be used for this purpose – starting from EO Browser, Sentinel Hub and xcube services, eo-learn, Jupyter Notebooks, EOxHub hosted JupyterLab and more, something for any skill level and every analysis.

– You can use Custom scripts to visualize satellite data. To get started, visit the beginner tutorial on basic custom scripts or visit our Evalscript documentation for more complex scripting options, such as multitemporal scripting. You can find many custom scripts ready to be used instantly on our custom script repository.

CONTRIBUTION

How can you contribute?

– If you are a self-taught remote sensing enthusiast, check the data, play with it, come up with the idea, compile a presentation and send it through. Note that there does not necessarily need to be a script itself. A simple description of the idea supported by slides and exported images is sufficient.

– Earth Observation experts can perform a detailed analysis, using various tools, demonstrating the patterns.

– Machine learning experts can model agriculture activities and identify potentially abandoned areas, resulting in reduced yields in the harvest seasons.

-Satellite data providers, do contribute additional data so that people can perform even more interesting analyses.

DELIVERABLES

Results are submitted as soon as they are available, composed of:

– PowerPoint presentation with images and the resulting analysis (mandatory)

– Custom scripts/source code (desired) -Sample of the results (desired)

– All results containing satellite data are appropriately credited: “Contains modified data processed by Euro Data Cube”

The objective is to study the earthquakes in the Aegean & East Mediterranean area, and other seismically active areas worldwide. For that, we will produce co-seismic interferograms using Sentinel-1 data for crustal fault displacement, fault rupture & earthquake environmental effects. Products will include phase interferograms, unwrapped interferograms (LOS displacement), interferometric coherence maps, optical correlation displacement maps). There is an additional processing (SAR or optical data) for detailed surface displacement mapping, landslides and liquefaction effects. GEP cloud processing can facilitate rapid processing (InSAR and optical tools like SNAP, MPIC-OPT etc) for response and analysis in the case of earthquake or other significant geohazard events. The on-the-fly availability of the core data (Sentinel 1/2 & ESA legacy SAR) further reduces preparation and processing time. Results will be focused on displacement maps (InSAR or optical) produced by the relevant GEP services & supported data sources (Copernicus Sentinel satellites or other sources provided by the GEP Platform).

Products and derivatives will be used to a) delineate linear or diffuse surface displacement features or zones, b) map broad crustal displacement in kilometric scale, c) results and data will be used in scientific publications about active tectonics and seismicity. Some key event response rapid data will be shared to the scientific community through the GEP platform or open data repositories (e.g. Zenodo).

Results of processing for contemporary events (e.g. significant earthquakes) can be shared through social media platforms (Twitter) or accompanying news articles.

This project aims to create a viable methodology for rapidly mapping damage to civilian structures using object-based image analysis (OBIA), a technically sophisticated approach for semi-automated, supervised classification of higher-resolution imagery. Preliminary work for this project was already underway in February 2022, looking at a different area of interest. It is well documented that remote sensing can play a vital role in making damages visible to the world and helping government and non-government organizations develop effective plans for damage mitigation and reconstruction. However, documenting and analyzing damage using traditional remote sensing and image interpretation methods would be extremely time-consuming and highly resource intensive. Therefore, we propose a rapid, semi-automated approach to civilian damage analysis using object-based image interpretation (OBIA) to produce viable results quickly. The results will be in the form of sample damage classification maps and will be presented in the form of a working paper.

The current estimations of glacier mass loss at the sub-regional scale continue to be a challenge, largely because glacier estimates draw from a variety of observations and models. The inherent limitations of observation techniques and methods, as well as disparities in temporal and spatial coverage, often lead to significant differences and uncertainties that cannot be ignored among the estimates. In studies, Greenland’s peripheral glaciers (GPGs) have either been omitted or integrated with the Greenland ice sheet. Consequently, there is not only a lack of a quantitative estimation of the contribution of GPGs to the Greenland mass loss but also a gap in our qualitative comprehension of the relative processes influencing regional sea level change. This project aims to enhance the glacier mass loss estimations and decipher the intricate mechanisms that govern the response of glaciers, particularly in Greenland, to the dual forces of climate and oceanic warming. By refining these estimations, this study provides more accurate insights into the fingerprint of Greenland’s ice melt and strengthens existing models of Greenland mass balance. A hybrid model-data product will have great potential in improving estimations of GPGs mass balance, both rate and magnitude, derived from single mission and RCMs. This combination of high-spatial and temporal sampling we present allows us to examine the complex evolving regional variations in glacier mass loss, driven by both surface mass balance and ice dynamics. Meanwhile, new observational constraints bolster existing models of Greenland ice mass balance and lead to more accurate predictions of mass balance.

The goal is to update the regional glacier register of Valle d’Aosta (Italy) by re-measuring the surface of the glaciers at the end of the ablation season of the year 2019. The analysis is manually carried out in the GIS environment and merged into the GLIMS.

The project focuses on sustainable development goals and climate action. The project’s primary focus is on SDG 13, which focuses on climate action. With the global temperatures rising and changing climate cryosphere is one of the severely affected ecosystems. The Permafrost layer is one such feature within the cryosphere that hardly reacts to climate change, releasing greenhouse gases such as methane and carbon dioxide. The part of the permafrost layer that freezes and thaws is called the active layer. The project focuses on the depth of the active layer and GHG emissions from it. The project will focus on how the active layer thickness in permafrost varies with temperature increase and, the variables affecting the rapid growth in thickness and estimating greenhouse gases emitted from this layer, what environmental and climatic variables affect these emissions. Initially, all the parameters affecting the increase in depth of the active layer will be generated or gathered as a first product of satellite imagery or as an end product. Then, the most influential factors within these variables will be estimated using their relationships. Finally, sensitivity analysis will be run with these significant parameters to capture the actual change in active layer thickness. The results will be seasonal dynamic layer maps depicting their changing depths with temperature changes and factors affecting them. Secondly, capturing the changes in methane and carbon-dioxide emissions with the varying thawing depth of active layer thickness along with organic matter content, type of litter, vegetation and microbes type. This project will help understand the contributing factors affecting the deepening of the active layer in permafrost and the abrupt emissions of greenhouse gases.

The main objective of this project is to apply multi-temporal techniques processing of satellite radar interferometry with available radar images to monitor the ground deformation of different regions in Colombia affected by landslides, subsidences for Groundwater withdrawal, and deformation of volcanoes, among others. Most have been documented, and others have not. With these techniques, the average deformation velocity map for the most recent period will be obtained using Sentinel-1 data and a time series analysis with the spatiotemporal evolution in all the analysis zones. Unfortunately, as of today, there is not much information in Colombia documenting the new techniques for monitoring natural disaster risks. Moreover, for anyone wishing to carry out scientific research, the existing data is not easily accessible.

The project also aims to show the results to the university students’ community to enhance a new perspective on technological progress. Furthermore, the idea is to encourage future generations about the importance of scientific careers and their impact on society and show the importance of investment in this kind of technology.

The primary focus of this project is to utilize earth observation data to detect and analyze terrestrial mode transportation to conduct an economic analysis. The utilization of earth observation data offers valuable insights into the movement of goods and people across different regions. It provides an opportunity to explore the impact of transportation on economic activities. It is crucial to emphasize that the data collected and analyzed in this project will be strictly employed for academic and research purposes and will not be utilized for commercial or profit-driven objectives. This ensures that the findings and conclusions drawn from the study are meant to contribute to advancing knowledge and understanding in the field of transportation and its relationship with economic indicators. As part of the project’s objectives, the researchers seek to identify alternative indicators to assess the financial performance of regions or countries, moving away from relying solely on traditional metrics like Gross Domestic Product. (GDP). While GDP has been conventionally used as a measure of economic activity, it may not fully capture the complexities and nuances of economic development brought about by the transportation sector. Hence, by exploring alternative indicators, such as earth observation data related to terrestrial transportation, the project aims to provide a more comprehensive and nuanced understanding of the economic landscape.

Objectives of the project:

• Remote sensing system for opencast mines that analyzes the environmental impact of the mine on the surroundings and, through AI algorithms, propose actions to reduce negative impact and enforce positive impact.

• Remote sensing system for planning new mines.

• Remote sensing system for monitoring of recultivation of the mine area.

• Remote sensing system for monitoring production bottlenecks.

The quality of the satellite images is compromised by the atmospheric signal attenuation due to aerosols (i.e., aerosol optical depth and atmospheric water content) and clouds. Several approaches exist for the correction of atmospheric effects and to mask cloudy pixels. However, the effectiveness of various atmospheric correction approaches for reducing atmospheric signal attenuation and improving image quality has been limitedly explored. Moreover, the effect of residual errors emanating from the aerosols and clouds on biophysical parameters used in precision agriculture, i.e., leaf area index (LAI), canopy chlorophyll content, and N content, are rarely investigated. The advent of new generation sensors such as Sentinel-2 Multi-Spectral Imager and state-of-the-art machine learning algorithms provide prospects for improving the LAI, CCC, and N content. The contribution of this study is to improve the accuracy of biophysical parameters used for precision agriculture using a new generation sensor, i.e., Sentinel-2 MSI, and state-of-the-art machine learning algorithms. Specifically, the study will address a range of challenges limiting the applicability of Remote sensing for precision agriculture such as:

1. unfavourable atmospheric conditions such as aerosol optical depth and cloud cover,

2. radiometric accuracy and consistency effects on biophysical parameters,

3. infrequent observations due to reliance on one sensor, and inherent trade-offs between spatial and temporal resolutions,

4. optimal stage for modelling yield.

The goal of precision agriculture is to optimise agricultural inputs, management decisions, and production. Therefore, the knowledge of the optimal growth stage for modelling yield is still missing in the literature. Such information should inform the effectiveness of precision inputs and management principles. The overarching aim of the study is to assess the effect of atmospheric conditions on image quality for modelling LAI, CCC, and N content. The objectives of the study are:

1. To evaluate the performance of the atmospheric correction approaches for improving the radiometric integrity and consistency of Sentinel-2 MSI images in agricultural landscapes:

i. by assessing the residual errors in surface reflectance (SR) after atmospheric correction and

ii. the temporal consistency of derived SR under partially cloudy conditions.

2. To evaluate the effect of atmospheric correction residual errors on the prediction accuracy of leaf area index (LAI), canopy chlorophyll content and N content by:

i. evaluating the predictive capabilities of machine learning algorithms and

ii. their ability to find critical variables from corrected and uncorrected Sentinel-2 MSI and fused datasets.

3. To characterise the field variability in the biophysical and chemical composition of crops (Chlorophyll content, Catenoids, N content) through proximally sensed spectrometric data and optimised spectral variables under different indiscernible atmospheric conditions (i.e., AOD and water vapour); and

4. To determine the optimal crop growth stage for modelling crop yield using Convolutional Neural Networks (CNN). The requested commercial data will be used for data fusion with Sentinel-2 and prescription maps (to support Variable Rate Application Technologies) based on developed biophysical parameters in this study. The data will also allow inter-comparison and validation of Sentinel-2 results. The following deliverables are anticipated:

i. research publication;

ii. super-resolution biophysical parameters at the canopy level) to support precision agriculture and improve food production in Africa.

iii. prescription map to support variable rate application technologies in precision farming; and

iv. yield prediction model. Currently, the research is funded by Wits University, and Supported by the South African National Space Agency (SANSA) and H2020 AfriCultuReS project.

Accurate and frequent measurement of river flow rate is crucial for many Earth science applications, including flood prediction and monitoring, agricultural applications, hydrodynamic power management, and watershed modelling. However, comprehensive in situ monitoring of rivers worldwide is not feasible given their dynamic nature and vast number. We propose to use data from the NASA Cyclone Global Navigation Satellite System (CYGNSS) mission to develop a methodology for estimating the flow rates of rivers. We will build on previous work, using CYGNSS Level 1 raw, intermediate frequency (IF) data to demonstrate the ability to correlate CYGNSS data with streamflow on the Pascagoula River in Mississippi. We will expand our previous methodology by implementing a model for the sensor response that allows for the representation of complex river scenes that include nearby water bodies, varied river morphology, and surrounding terrain. We hypothesize that using the forward model to represent confounding factors affecting the CYGNSS raw IF signal, we will extend our existing methodology to remotely estimate river streamflow over a much more comprehensive range of river settings on a global scale. The proposed algorithm can also determine the width of other water bodies, such as wetlands and flood zones, at fine spatial scales (100 m or less), providing a valuable up-to-date water body extent dataset. The unique sampling and coverage properties of the CYGNSS constellation are crucial in developing this methodology. CYGNSS’s high revisit rate (on the order of hours) allows for near-continuous updates to river widths over the +/- 38-degree latitude coverage range, enables detection of rapid river responses to extreme precipitation events to support flash-flood monitoring and prediction, and provides critical data needed to constrain hydrology models and characterize large-scale water cycle processes.

This project aims to atmospherically correct Level 1C imagery using ACOLITE and to make these data publicly available for use in Aquatic Remote Sensing Science. Aquatic reflectance values are a primary dataset not currently available at large scales, meaning that most planetary-scale analyses of the aquatic environment use surface reflectance, which is not well suited for aquatic applications. Producing these data will allow fundamental science to advance using a standard data set for aquatic applications of earth observation science. The products, once created, will be combined with in-situ water quality observations to generate spectral models for retrieving water quality (cdom, turbidity, and chlorophyll) from aquatic reflectances.

The USGS NGWOS Remote Sensing of Water-Quality Research and Development (R&D) Project will:

• Evaluate existing relationships between satellite-based remotely sensed spectral data and in-situ water quality measurement as part of USGS historical monitoring programs and

• Evaluate and develop, where necessary, processing methods and IT infrastructure to process and disseminate water quality estimates from remote sensing platforms at a national scale.

The goal of this project is to understand the social and economic impacts of artisanal mines in Africa on the local population.

The methods and deliverables: machine learning (convolutional neural network) methods to detect the location of artisanal mines from processed sentinel-2 tiles. We are going to merge the localization data with other heterogeneous data to find the causality effects of these artisanal mines. The deliverable will be a paper. Here is an example of a previous paper from Mathieu Couttenier on the subject.

Project AEDES aims to aid in dengue response by detecting mosquito hotspots from FAPAR and NDWI readings. GIDEON aims to benchmark COVID-19 recovery by looking at night lights and NO2 readings. Prototype applications are provided for being used by national and local health agencies that aim to integrate socio-economic variables with GIS and satellite data applications.

ESA EOP-S has been solicited to provide at the beginning of October 2020 a training focusing on cloud computing for Agriculture to key African institutions. The needed resources in terms of infrastructure and trainers can be accessed through the EOCARE service, which is an adaptation of the RUS service (funded by EC) allowing to serve also non-European users. The training makes use of 30 VMs pre-installed and configured with Sen2Agri and SNAP, the VMs remains accessible to users for 2 months (beginning October – end November).

The S3 data in the middle and lower reaches of the Yangtze River are retrained and supplemented with other error corrections to obtain the observed water level along the track, construct the river water level change time series, summarize the changing trend of river water level in the middle and lower reaches of the Yangtze River, and analyze the various characteristics of water level. The new radar altimeter can monitor inland water bodies such as lakes and rivers. However, affected by the topographic features around the river and the land echo signal, the waveform data of the transit river is seriously polluted. At the same time, the wave peaks of the waveform data of these new radar altimeters have a fast decay rate, resulting in multiple wave peaks in different forms. Therefore, the previous retraining algorithm can not obtain effective tracking points. Therefore, based on the waveform analysis, combined with the existing physical model and empirical model, this paper intends to use the basis weight tracking algorithm to accurately extract the prominent wave crest to more effectively retrace the waveform data of the rivers in the middle and lower reaches of the Yangtze River, and improve the accuracy of single point observation water level as much as possible, to obtain a better water level time series. The above research method is applied to the middle and lower reaches of the Yangtze River in China to monitor the changes in river water levels in the middle and lower reaches of the Yangtze River from 2016 to 2021.

Objectives of the project include evaluating the efficacy of process-based stream restoration strategies in severely channelized streams to reconnect streams to their floodplains, slow the conveyance of water, increase stream structure complexity, increase water storage higher in watersheds, increase riparian and wetland habitat quantity and quality, decrease transport of sediment and nutrients, increase resilience of streams and watersheds to future disturbances including wildfire, drought, flooding, and general climate change.

The ESA River Discharge Climate Change Initiative project is a precursor study. It aims to derive long-term climate data records (at least over 20 years) of river discharge for some selected river basins (and some locations in the river network) using satellite remote sensing observations (altimetry and multispectral images) and ancillary data. It aims to provide a proof-of-concept for the feasibility of a potential River Discharge ECV product to meet the Global Climate Observing System requirements.

RoadSense is an AI-based solution enabling safer mobility by providing drivers with real-time safety-relevant data. Drivers get near real-time alerts for hazardous scenarios like accidents, aquaplaning, sudden brakes/stopping of vehicles ahead, airbag opening and other safety-relevant events. At the same time, each driver automatically shares vehicle data to inform other drivers about potentially dangerous situations. The in situ data is further enhanced by state-of-the-art machine learning models that analyse space images of the road infrastructure and provide critical road quality information and potentially dangerous road areas. The models are the key feature distinguishing our product from other traffic applications – they are the only way to perform on-demand road quality analysis automatically.

RoadSense builds its comprehensive knowledge about the Bulgarian roads infrastructure by combining Earth Observation, Vehicle, Weather, Governmental and Social data. The unique combination of data sources considers most of the factors that influence the safety of vehicles. This provides road users with a comprehensive picture of the current and upcoming road environment, based on which they can be aware, react and appropriately adapt their road behaviour before they reach the hazard.

Apart from alerting about dangerous situations and providing a detailed road quality status, RoadSense also awards drivers with points based on the anonymised data they share through the application. The points can be exchanged for purchases or discounts at partnering businesses or participate in large-scale mobility loyalty programs. At the same time, RoadSense provides businesses with intelligence and smart analysis of the roads infrastructure, vehicles usage and user behaviour. Leveraging this knowledge, companies will provide more reliable transport services, safer employer branding and sophisticated business decisions.

The objective of this project is to investigate various robust deep-learning techniques in the context of remote sensing. We look at the relationship between satellite data and different label sources from the perspective of misalignment-induced noise as well as the number of labels needed. We will investigate the role of self-supervised learning about various robust learning techniques. The study focuses on agricultural and biodiversity applications with a limited amount of training labels. The results of the project benefit the community by providing insights into robust deep learning specific for remote sensing applications.

This project aims at helping remote rural residents to plan their regional development. In addition, the idea is to provide them with auxiliary and comparison data as per their problems and resources.

The Axon Protocol project aims to enhance transparency along the life cycle of European forest management planning. The project aims to use remote sensing technologies to provide near real-time monitoring of natural assets, therefore increasing confidence in the impact of more sustainably managed forests by monitoring the evolution and performance of a European forest on critical variables, which include carbon sequestration, harvested levels, biodiversity state, and more. This will enable forest managers to unlock the necessary capital to implement a management strategy that will make forests more climate-resilient and maintain the carbon sink capacity of forests among various storage pools.

Chile hosts the largest glacial surface in the southern hemisphere outside Antarctica, adding to 23.641 km2 (Segovia & Videla, 2017). This glacier abundance brings essential benefits to Chile, such as water reserves, reducing the severity of seasonal flooding and droughts, and tourism value. However, glaciers also bring significant challenges, mainly due to their widespread retreat and increased landslides and floods (Harrison et al., 2018). As glaciers retreat, they leave behind unsupported valley walls prone to landslides. Additionally, this retreat gives rise to new lakes dammed by unconsolidated glacier deposits (moraines) or ice. Floods associated with the failure of these natural dams are known as Glacial Lake Outburst Floods (GLOF). GLOFs have killed more than 5,700 people over the past century along the Andes Range (Carrivick & Tweed, 2016).

Further, glacial lakes are becoming more numerous and extensive (Shugar et al. 2020), and their floods are expected to increase in frequency due to climate change (Harrison et al. 2018). The main objective of this project is to develop and deploy a prototype of SAGAZ, an alert and early warning system for glacial outburst floods (GLOF) in Chilean Patagonia. The risk assessment will be based on modeled future lake levels. The system will use field data from a network of lake monitoring stations and forecast meteorology to feed an integrated glacial-hydrological model capable of predicting future lake levels. Using this information and historical records at each lake, the system will compute and report a qualitative alert level (e.g., green, red) to inform authorities and the population about safe periods and warn about upcoming periods of a high probability of GLOF. If a GLOF is detected from an abnormal lowering of the lake level, a GLOF early warning will be issued and delivered automatically to the interested people and institutions. Το calibrate and test the model, time series of lake level and drainage events will be reconstructed using satellite imagery. Direct short-term beneficiaries are all the people living in areas at risk of GLOF. If the system proves helpful, it could also benefit people in Peru, Nepal, and several other countries with populations living in GLOF-threatened areas.

The project consists of developing automatic management tools for agriculture based on satellite information. More particularly create the detection of anomalies, the debinding of fields, the detection of crop types, the phenological changes of the crop under inspection (growth, flowering, senescence, harvest), and predicting yield. This data will be used to improve the financial companies’ risk management with the various producers. For FinTechs, using AI and satellite imagery aims to help banks and insurers improve their lending decisions and reduce the risk of default. By leveraging these technologies, banks can provide farmers with better access to finance and help support the growth of the agricultural sector. Using AI and satellite imagery aims to help farmers optimize their farming practices, improve yield and profitability, reduce operating and irrigation costs, and mitigate risks. These technologies offer an exciting opportunity to develop a more sustainable and efficient agricultural sector.

Sand Mining Watch is a global sand mining and sand resource monitoring platform. This project’s immediate goal is to add to India Sand Watch (ISW) Al-based sand mine detection tools that make it possible to produce high-resolution, real-time maps of sand mining activity in river basins across India. These tools and data can catalyse policy action, improve the monitoring and regulation of illegal mining activity, and improve the understanding of the socio-economic and environmental impacts of sand mining. The objectives are:

1. Build an Al-based sand mine detection tool that can accurately identify sand mines (in real-time) from a combination of freely available and commercial very high resolution (VHR) satellite imagery

2. Validate the performance of this tool through human review of VHR satellite images.

3. Generate a policy-based analysis:

a. Characterize the scope and scale of sand mining in India

b. Assess sand mining activity in restricted zones/near critical infrastructure

c. Evaluate current national and state regulations

d. 4. Socio-economic impacts

4. Test, validate and improve the system through collaborations with researchers, journalists, civil society members, affected communities and policymakers.

Background: Sustainable sand mining is one of the most pressing ecological challenges currently facing the planet. After water, sand is the world’s most valuable natural resource – over 50 billion tons of construction-grade sand and gravel were mined globally from rivers and beaches in 2027. As the major ingredient of concrete and asphalt, sand is vital to economic growth, especially in the Global South. Unfortunately, sand is being extracted from rivers at an unsustainable rate with severe environmental and socio-economic consequences. These challenges are particularly salient in India, where the growing demand for sand has led to a huge increase in illegal and excessive mining.

In a previous phase of the Sentinel-6 L1 Ground Prototype Processor contract, it has been developed a SAR back projection fully focused processor for altimetry (Sentinel-6). A major limitation of this processor is the run-time performance, which makes it unusable for operational purposes. To overcome this limitation, the strategy was twofold:

1. Implementation of some algorithm optimizations and

2. Writing a software which makes use of GPUs.

This optimized processor has been developed, and the first version has been accepted in November 2023. Preliminary testing has been done on the contractor infrastructure. This showed already very promising results, showing that the processor running on GPUs has a run-time performance improvement of over 50 times with respect to the one running on CPUs. Final acceptance requires a thorough assessment of both the scientific and the run-time performance of the processor. This needs to be performed on a dedicated machine with an agreed configuration. The virtual machine provided by Earth Console can fulfill this purpose. S6, CRISTAL and S3NG-T projects benefit from the project results. The current plan is to finalize the software on the target virtual machine and run some tests using Sentinel-6 data for the verification activities. This should cover a couple of months. The remaining period will be used to run an entire cycle (70 days) of S6 data with multiple configurations, optimized for different surface types. The generated data will be then analyzed and assessed in comparison with the existing operational data. Finally, this acquired knowledge will be necessary for future missions, such as CRISTAL and S3NG-T, for which this kind of processing is part of the mission requirements.

The urban environment is defined as the specific characteristics or features of cities. To be more concrete, the urban environment can be described by the urban physical environment, which is related to the built environment, geological, and local climate conditions. Recently, hazards in urban areas, especially anthropogenic subsidence, directly caused damage to the built environment. Such anthropogenic subsidence is often in response to human activities like groundwater extraction, geothermal fluids, oil, gas, coal and other solids through mining. The subsidence has a potential risk to the people’s property. It can cause damage to urban infrastructures, e.g., buildings, highways, airports, subways, and other ground facilities. The interferometric synthetic aperture radar (InSAR) technique is an efficient way to monitor the kinematic evolution of ground surface at millimetre precision. It is proved to be successful through a mass of subsidence monitoring case studies. However, how to systematically monitor the deformation in the urban environment is still on the way. This work attempts to seek for optimal and pragmatic solutions to overcome the current limitations addressed as follows. First, even with abundant SAR images, the development of automatic deformation detection methods in urban environments is still at an early stage. We plan to use SAR images in large numbers to detect the deformation automatically. Secondly, the urban interior spatial structure and utilization type can facilitate classifying the city into different risk levels under subsidence hazard. We then plan to explore its use in SAR method development maximally. Thirdly, as for the high-rise building area, irregular changes per individual building may lead to severe structural health problems. However, current SAR methods with a single viewing geometry can not suffice the need to obtain reliable measurements over the high-rise building area. Therefore, we resort to TomoSAR and develop a method to integrate InSAR and TomoSAR. Fourthly, when having information on local deformations and the associated damages, we need to focus on restoring and recovering the urban environment. But how to analyze urban resilience based on InSAR time series measurements is inadequate. Then, we plan to utilize the damage level table to transform quantitative InSAR measurement results into qualitative urban resilience analysis.