NASA, IBM Research Release New AI Model to Improve Weather Forecasting

NASA and IBM Research have introduced the Privthi-weather-climate foundational model, an artificial intelligence-powered tool that improves regional and local weather and climate models.

Trained on NASA’s Modern-Era Retrospective analysis for Research and Applications, the NASA-IBM Research model uses AI learning abilities to apply patterns taken from initial data to a wide range of different scenarios.

Oak Ridge National Laboratory and NASA’s Interagency Implementation and Advanced Concepts Team at Marshall Space Flight Center also contributed to developing the weather-climate model, NASA .gov reported.

Kevin Murphy, NASA’s chief science data officer for the Science Mission Directorate at NASA Headquarters, said the new model encourages the international community to explore and use capabilities developed by the U.S. space agency, ensuring that it benefits all mankind.

NASA has been testing various possible applications for AI. In August, Edward McLarney, the digital transformation lead for AI and machine learning at NASA, confirmed that the agency is assessing the viability of using OpenAI’s generative AI solution to help with code-writing, research summarization and other uses.