01/2024 – 06/2025

FAST-EO

The ESA-Project FAST-EO ("Fostering Advancements in Foundation Models via Unsupervised and Self-Supervised Learning for Downstream Tasks in Earth Observation"), led by IMF EO Data Science Department, explores the use of large multimodal foundation models for Earth Observation purposes. This initiative aims to enhance the inclusivity and versatility of these advanced AI systems through text-based and image-based querying capabilities in Earth Observation datasets.

FAST-EO High Level Architecture

The project will investigate the following use cases with the collaboration of four partners:

  1. Weather & Climate Disaster Analysis (IBM Zurich)
  2. Detection of Methane Leaks (KP Labs)
  3. Observation of Changes in Forest Above-Ground Biomass (DLR)
  4. Estimation of Soil Properties (KP Labs)
  5. Detection of Semantic Land Cover Changes (FZ Jülich)
  6. Monitoring Expansion of Mining Fields into Farmlands (DLR)