NASA Fine-Tunes Climate Predictions With New AI Model

NASA has teamed up with Oak Ridge National Laboratory and IBM’s research and development arm to create an artificial intelligence-powered weather and climate model. The Prithvi-weather-climate foundational system leverages 44 years of meteorological, Earth surface, solar radiation, and atmospheric data to offer a high-resolution view of current and future climate patterns. The hope is that the model will facilitate speedier and more accurate local, regional, and wide-scale weather forecasts.
Most modern weather predictions are taken from coarse-resolution climate models, which become less precise as you look at smaller geographical swaths. This tends to be fine when forecasting the climate for a general area—say, the Caribbean or the midwestern United States—but gets tricky when you need fast and accurate predictions for a specific place. MIT recently built an algorithm to close that gap, but it’s tailored for extreme weather, particularly in the face of human-exacerbated climate change.
Built on NASA’s Modern-Era Retrospective analysis for Research and Applications (MERRA-2) dataset, the Prithvi-weather-climate model uses AI to identify historical patterns and apply them to hypothetical and real weather scenarios. Although the model could be used to anticipate extreme weather events, including natural disasters, it also has a future in localized weather forecasts and predictions related to climate change. For example, the Prithvi-weather-climate model could look at large-scale climate change phenomena and predict how a particular community might be impacted. 
“The rapid changes we’re witnessing on our home planet demand this strategy to meet the urgency of the moment,” Karen St. Germain, director of the Earth Science Division of NASA’s Science Mission Directorate, said. “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.”
The Prithvi-weather-climate model joins a family of Prithvi systems, named after the Sanskrit word for “Earth.” Among these are NASA’s Goddard Earth Observing System (GEOS), which consists of two Earth system models, and Global Modeling and Assimilation Office (GMAO), a duo of seasonal and atmospheric forecasting models. Following in these systems’ footsteps, the Prithvi-weather-climate model will be made open-source later this year on Hugging Face in accordance with NASA’s open science principles.
ExtremeTech supports Group Black and its mission to increase greater diversity in media voices and media ownerships.
© 2001-2024 Ziff Davis, LLC., a Ziff Davis company. All Rights Reserved.
ExtremeTech is a federally registered trademark of Ziff Davis, LLC and may not be used by third parties without explicit permission. The display of third-party trademarks and trade names on this site does not necessarily indicate any affiliation or the endorsement of ExtremeTech. If you click an affiliate link and buy a product or service, we may be paid a fee by that merchant.

source