Projects

Project Title	Topic	Collaborators	GitHub Repo	Publications
Air Quality Platform data processing	IoTSentinel-5p DataAir Quality	Valeria Pia Vevoto
Giga Connectivity	Connectivity DataSatellite Data AnalysisAI - Machine & Deep Learning	Kelsey Doerksen		AI-POWERED SCHOOL MAPPING AND CONNECTIVITY STATUS PREDICTION USING EARTH OBSERVATION
Onboard real-time segmentation	Satellite Onboarding AISemantic SegmentationAI - Machine & Deep LearningSentinel SAR Data	Cristopher Traba Castro	github.com
Distributed Ledger Technologies for Satellite-based Emergency Mapping	Federated LearningBlockchain & Web3Decentralized & DistributedSentinel SAR Data	Robert Cowlishaw
Air pollution, meteorological conditions and COVID-19 incidence	Remote Sensing DataCopernicus DataAir Quality	Leona Hoffmann
Creating terrains using generative modelling and satellite images	Computer VisionAI - Machine & Deep LearningRemote Sensing DataHigh-performance Computing	Paul Borne Pons
Implicit neural representation for 3D lidar point clouds processing	3D LidarAI - Machine & Deep Learning	Mathilde Letard
QUAI4EO 1 — Quantum Machine Learning for Image Analysis
QUAI4EO 2 — Dynamic Systems and Generative Models
Modelling, Generation and Mitigation of Striping Noise in the ESA MetOp-SG Microwave Imager - Satellite Destriping Scientific Challenge Preparation		Monica Beghini
Automated Detection of Water-Area Dynamics in Small Agricultural Reservoirs from COSMO-SkyMed		Noemi Mannucci
A Systematic Comparison of TerraMind and THOR: Downstream Deployment Architecture Outweighs Model Choice in Geospatial Foundation Model Performance		Frederik Schindlegger
Unlocking the Potential of Quantum Machine Learning Algorithms for Earth Observation
Making GeoFMs Sensor-Aware for On-board Earth Observation		Elouann Lucas
Learning Semantic Information from Level-0 SAR for Onboard Land-Cover Classification		Pretha Sur
Cognitive Cloud Computing in Space for Earth Observation (3CS4EO)
HYPER-EDGE — Hyperdimensional Computing for On-board Wildfire Detection and Air Quality Assessment
Hyperspectral Imagers with High Spatial Resolution (PINEAPPLE)
Bád - EO Foresight Cognisat-6 In Orbit Demonstration
NEURO-RESPOND
Gaussian Boson Sampling for Earth Observation (GBS4EO)
Quantum computing for ground motion measurements		Giuseppe Buono
SpinQC4EO
Diffusion-based anomaly segmentation of Sentinel-3 data		Andrianirina Rakotoharisoa
TerraVerse — Multimodal Generative Models for Earth Observation Simulation and Analysis
Immersive Visualization Metaverse (IMMERSIVE EO)
FAST-EO — Fostering Advancements in Foundation Models via Unsupervised and Self-supervised Learning for Downstream Tasks in Earth Observation		German Aerospace Center (DLR) – Remote Sensing Technology Institute IBM Research Europe KP Labs sp. z o. o.
Agentic AI for Earth Observation: Evaluation and Benchmarking of LLMs		Kaushik Pillalamarri
Optimizing Onboard Earth observation AI for robustness against Sensor Degradations		Ivar van der Spoel
Innovative Earth Observation and Artificial Intelligence Solutions for Water Resources Management and Risk Assessment		Celina Anael Farias
Onboard-Constrained Geospatial Foundation Models: Pretraining, Domain Adaptation, and Distillation for Φsat-2		Clément Gilli
Getting the most out of image-level labels: weakly supervised learning for hyperspectral image analysis		KP Labs sp. z o. o.		A. M. Wijata, L. Tulczyjew, P. Naylor, B. Le Saux, N. Longépé and J. Nalepa, "Getting the Most Out of the Image-Level Labels: (Un)Supervised Learning for Extracting Soil Parameters From Hyperspectral Images," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 19, pp. 7401-7418, 2026, doi: 10.1109/JSTARS.2026.3660363, https://ieeexplore.ieee.org/abstract/document/11370490 B. Grabowski, A. M. Wijata, L. Tulczyjew, B. Le Saux and J. Nalepa, "Soil Analysis with Very Few Labels Using Semi-Supervised Hyperspectral Image Classification," IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 407-411, doi: 10.1109/IGARSS53475.2024.10642465, https://ieeexplore.ieee.org/document/10642465 A. M. Wijata, P. Naylor, and J. Nalepa, " Learning from Image-Level Labels: Where Unsupervised and Supervised AI Algorithms Come Together," Living Planet Symposium 2025, Vienna, Austria, https://lps25.esa.int/programme/programme-session/?id=5345408F-6932-4CBD-8587-1F8BB229ADD6&presentationId=0C312308-4D8D-454B-9ABF-2585620E1D45
Geospatial Foundation Models for Archaeological Prospection Tasks		Elena Chiricallo
Physics-informed deep learning for subsurface reconstruction of essential ocean variables		Bruna Strack Candido
Raw-to-Processed in Orbit: Fast Onboard Image Reconstruction for EO	in-orbitSatellite Onboarding AISatellite Data AnalysisComputer Vision	Gabriele Inzerillo		Raw-to-Processed in Orbit: Fast Onboard Image Reconstruction for EO. Authors: Gabriele Inzerillo, Lorenzo Papa, Gabriele Meoni, Diego Valsesia, and Enrico Magli. Manuscript developed from the collaboration with ESA Φ-lab; Published at CVPR Workshop AI4Space.
L0-L1 PhiSat-2 Processing with Deep Learning	Deep Learningin-orbitSatellite Data Analysis	Gabriele Inzerillo
DepthDif: Conditional Diffusion for Densifying Sparse Ocean Temperature Observations	Diffusion ModelsComputer Vision	Simon Donike
Sub-aperture SAR processing and self-supervised enhancement of Sentinel-1 imagery for AI-ready Earth Observation datasets	Sentinel SAR DataAI - Machine & Deep LearningSatellite Data Analysis	Juan Francisco Amieva		Juan Francisco Amieva et al., "Self-supervised enhancement of Sentinel-1 Stripmap imagery exploiting full-aperture/sub-aperture pairs", AI4Space Workshop, CVPR 2026.
PyNASDet: Neural Architecture Search for Resource Constrained Satellite Object Detection	Remote Sensing DataSatellite Data Analysis	Valeria Biscardi
Finding DEM0: A Zero-Shot Depth Maps Calibration Framework for Generating Digital Elevation Models	Foundation ModelsCopernicus Data	Riccardo Contu
Hidden Markov Models for Desertification Assessment in Mediterranean Karst Ecosystems		Filippo Gregori
Towards Explainable AI: Application to Trustworthy Super-Resolution “OpenSR — Robust, accountable super-resolution for Sentinel-2 and beyond”	AI - Machine & Deep LearningAI Sentinel-2Satellite Data Analysis	No access
Generative AI for SAR Duty Cycle Reduction	AI - Machine & Deep LearningSentinel SAR Data	Lennart van der Peet	github.com
Generative AI for Earth System Science	AI - Machine & Deep LearningRiver Hydrometry	Gabriele Bertoli
Beyond Conditional Diffusion: A Physics-Guided Diffusion Framework for Joint Forecasting of Physical Drivers and Multispectral Satellite Data	Diffusion ModelsAI - Machine & Deep LearningAI Sentinel-2	Francesca De Falco
Automatic detection of Small Agricultural Reservoirs from Sentinel-1 SAR imagery using U-Net segmentation	AI Sentinel-1Sentinel SAR DataSemantic SegmentationAI - Machine & Deep Learning	Noemi Mannucci
Exploring Destination Earth to Leverage AI and Enhance End-User Accessibility to Earth Observation Data	Digital TwinFoundation Models	Emanuel Goulart
AI4EO and PINNs4EO	AI - Machine & Deep LearningPhysics-Informed Neural NetworksIce Monitoring	Peter Naylor
IC-EO: Interpretable Code-based assistant for Earth Observation	LLMCode AssistantFoundation ModelsSoftware Library	No accessNo access
Deep Learning for Efficient Onboard SAR Processing	AI - Machine & Deep LearningSatellite Onboarding AI	Gabriele Daga