BCG-USRA-NASA GAIA FM project

BCG X AI Science Institute, USRA’s Research Institute for Advanced Computer Science (RIACS), and NASA’s Ames Research Center have joined forces to advance science and engineering through several collaborative initiatives.

A major focus of this partnership is harnessing generative AI (GenAI) to improve the analysis and practical use of satellite data.

By combining expertise from industry, government, and academia, the team developed the GAIA Foundation Model (Geospatial Artificial Intelligence for Atmospheres)—a groundbreaking model trained and tested on 25 years of global satellite data. This dataset includes observations from a constellation of satellites such as Geostationary Operational Environmental Satellites (GOES), Europe’s Meteosat (EUMETSAT), and Japan’s Himawari.

Continuous and reliable Earth observation is critical for real-world systems like hurricane forecasting and wildfire detection. GAIA demonstrates promising capabilities, both in filling large gaps in satellite records and converting satellite imagery into precipitation estimates.

GAIA represents a new class of geospatial AI models with the potential to create significant impact across sectors—from more accurate weather forecasting to applications in insurance, power utilities, aviation, and agriculture.

Technical paper on the GAIA Foundation Model can be found [here]