The goal of the GEN4GEO project is to design a system that leverages generative artificial intelligence (GenAI) to enable the exploration and visualization of geospatial data through natural language interaction between users and systems. While foundation models are general-purpose and suitable for data exploration across various contexts, they have significant limitations in handling data — …
The AI4FLUM project will develop an AI model for classifying forest land use of special tree covered areas by training on FAO’s Forest Resource Assessment (FRA) data, interpretating in a compatible way with the FRA Remote Sensing Survey (RSS) process and provide a related module to be integrated into FAO’s SEPAL The model will be …
Trafficability of open terrain remains a key issue in national security applications, both in operational and strategic defence planning context. Whereas in a strategic context, the planning entities may rely on irregularly updated soil maps produced on a national level and lower resolution, in operational (tactical) context, for planning defensive routes or predicting opponent’s offence, …
The TRANSITION project aims to develop and implement advanced Web Services and Applications that integrate Earth Observation (EO) and non-EO data using a sophisticated Multilevel Agent-Based Modelling (ML-ABM) system. The primary goal is to support the EU Green Deal’s vision by simulating complex socio-environmental dynamics to inform policy-making and decision-making processes. Specifically, TRANSITION focuses on optimizing land …
This activity aims at developing an immersive visualization application associatedwith an EO use case. This implementation will benefit from and will allow the exploitation of some key techniques/technologies of Virtual and Augmented Reality and Artificial Intelligence. The project contributes to demonstrating how Digital Twins can serve Policy and Decision Makers in understanding the status of relevant environmental …
AI for satellite interferometry (InSAR) to simplify data exploitation and interpretation by adding a classification layer to large inSAR point cloud databases. Over the years, InSAR has become a common approach to map and monitor ground displacement at different scales, from local to regional and national. At large scales, InSAR provides such a volume of …
Introduction and Objectives The European Space Agency, ESA, is organising the EO Science for Society Info Day to present the 2024 workplan for FutureEO-1 Segment 2 Block 4 “EO Science for Society” and highlight opportunities for European entities to participate in these activities. The event will take place on 28 March 2024 and will be fully online. …
The instability of Antarctic ice shelves is one of the most critical open questions in polar science, due to its capacity to drive rapid sea level change at – and beyond – current high-end climate projections. Yet forecasting future instability is notoriously difficult because of the complex, non-linear forcing mechanisms controlling an ice shelf’s response, …
Fostering Advancements in Foundation Models via Unsupervised and Self-Supervised Learning for Downstream Tasks in Earth ObservationThe objectives will be achieved through the validation of the proposed FMs (Multimodal Foundation Models) on suitable downstream applications that address global societal challenges. More specifically, the validation of the proposed FM architectures will be conducted on six main use …
Summary The project “Foundation Models for Climate and Society” (FM4CS) seeks to leverage the breakthrough of Foundation Models (FMs) in shaping the future of Earth observation. During the last year, FMs have revolutionized the understanding and processing of data, in particular language data, paving the way for significant advancements in various fields. FM4CS aims to …
