Jane Edwards
IBM Research and NASA have developed an artificial intelligence model that could help detect and predict natural disasters and severe weather patterns, improve spatial resolution on global climate simulations and create targeted forecasts using localized observations, among other applications.
NASA said Wednesday the AI model, called the Privthi-weather-climate foundational model, will be unveiled later this year on the machine learning and data science platform Hugging Face.
“The NASA foundation model will help us produce a tool that people can use: weather, seasonal and climate projections to help inform decisions on how to prepare, respond and mitigate,” Karen St. Germain, director of the Earth Science Division at NASA’s Science Mission Directorate.
The foundational AI model, which was trained on the space agency’s Modern-Era Retrospective analysis for Research and Applications or MERRA-2 data, can scale to regional and global areas without compromising resolutions.
IBM Research and NASA developed the Privthi-weather-climate model with Oak Ridge National Laboratory, Stanford University, Colorado State University, University of Alabama in Huntsville and other offices within the space agency.
