The collaboration is part of NASA's Open-Source Science Initiative and the 2023 Year of Open Science, a federal initiative promoting the open sharing of data and knowledge. IBM's model leverages its foundation model technology and is part of a larger effort to create and train AI models for different tasks. A commercial version of the geospatial model will be available through the IBM Environmental Intelligence Suite later this year.
Key takeaways:
- IBM and open-source AI platform Hugging Face have announced that IBM's geospatial foundation model, built from NASA's satellite data, will now be openly available on Hugging Face. This is the first-ever open-source AI foundation model built in collaboration with NASA.
- The model is aimed at democratizing access to AI for climate and Earth science research, as it can help overcome the challenges of analyzing large datasets from NASA.
- The model has been trained on Harmonized Landsat Sentinel-2 satellite data and has shown a 15 percent improvement over state-of-the-art techniques using half as much labeled data. It can be used for tasks like tracking deforestation, predicting crop yields, or detecting and monitoring greenhouse gasses.
- This collaboration is part of NASA's Open-Source Science Initiative and IBM's larger effort to create and train AI models that can be used for different tasks. A commercial version of the geospatial model will be available through the IBM Environmental Intelligence Suite later this year.