IBM NASA Geospatial

Enterprise
community

AI & ML interests

Geospatial foundation models using HLS2 data

NASA and IBM have teamed up to create an AI Foundation Model for Earth Observations, using large-scale satellite and remote sensing data, including the Harmonized Landsat and Sentinel-2 (HLS) data. By embracing the principles of open AI and open science, both organizations are actively contributing to the global mission of promoting knowledge sharing and accelerating innovations in addressing critical environmental challenges. With Hugging Face's platform, they simplify geospatial model training and deployment, making it accessible for open science users, startups, and enterprises on multi-cloud AI platforms like watsonx. Additionally, Hugging Face enables easy sharing of the pipelines of the model family, which our team calls Prithvi, within the community, fostering global collaboration and engagement. More details on Prithvi can be found in the joint IBM NASA technical paper. For more enterprise-ready finetuned versions of the Prithvi model, please visit the IBM Granite Hugging Face page.

Watch Prithvi end to end demo
Watch Prithvi end to end demo

More information: NASA Blog post, NASA Veda system, IBM Press/Blog post, EIS, Code