NoR sponsored projects

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 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 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.

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.

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.

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.

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.

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 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.

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?

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.

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.

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 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.

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.

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 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 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.

“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.”

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 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.

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.

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.

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.

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.

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.

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.

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’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.

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.

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.

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.

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.

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.

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 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).

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.

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 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.

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.

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.

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.

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.

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.

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).

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.

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 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.

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.

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 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

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

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

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).

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.

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.

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.

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.

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.

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.

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 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.

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.

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.

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.

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.

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 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.

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.

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).

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.

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.

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.

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 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.

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.

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 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.

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.

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 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.

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 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).

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 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.

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.

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 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.

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 objectiv eof 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.

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.

Project objectives: Scientific VM template to provide continuity after esa365 migration

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.

“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.”

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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

“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/”

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.

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.

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 non-directly remotely measurable parameters. It is part of the ESA Mediterranean Sea Regional Initiative within FutureEOSegment1 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.

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 non-directly remotely measurable parameters. It is part of the ESA Mediterranean Sea Regional Initiative within the FutureEO-Segment1 ESA programmatic line (2020-2022). It 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 the high spatial resolution of S2-MSI data. Moreover, MedEOS will develop, implement and demonstrate a methodology to extensively track river plumes in Mediterranean coastal waters using 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.

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.

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.

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 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.

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.

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.

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.

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.

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.

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 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.

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.

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.

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.

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.

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.

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.

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.

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 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.

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.

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 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, 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.

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.

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.

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.

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.

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’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.

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.

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.