News

IBM has announced that its geospatial foundation model watsonx.ai, developed using NASA’s satellite data, will now be openly available on the AI platform Hugging Face. This collaboration between IBM and NASA has resulted in the largest geospatial foundation model on Hugging Face and the first-ever open-source AI model built in partnership with NASA.

The model, trained on Harmonized Landsat Sentinel-2 satellite data (HLS), provides valuable insights such as flood and burn scar mapping. Furthermore, it can be adapted for various other applications including deforestation tracking, crop yield prediction, and greenhouse gas detection and monitoring.

By making the geospatial foundation model available on Hugging Face, NASA and IBM aim to democratize access to this technology and drive innovation in climate and Earth science. This initiative follows a new agreement between NASA and IBM to develop an AI model specifically for geospatial data.

Sriram Raghavan, Vice President of IBM Research AI, emphasizes the importance of open-source technologies in accelerating critical areas of discovery, particularly in relation to climate change. He explains that the collaboration between IBM’s foundation model efforts and NASA’s extensive repository of Earth satellite data, now accessible on Hugging Face, will facilitate faster and more impactful solutions to improve the planet.

The availability of IBM’s geospatial foundation model on Hugging Face will empower researchers, scientists, and developers to harness its capabilities and develop new applications to address pressing environmental challenges. This open-source approach showcases the power of collaboration in driving positive change and fostering a deeper understanding of our planet.

The post IBM and NASA Collaborate to Make Geospatial Foundation Model Open Source appeared first on satProviders.