Accelerating Climate Modeling with Generative AI

A climate model combining generative AI and physics data is 25 times faster than the state of the art
Dec 2, 2024
From left: Rose Yu, a faculty member in the UC San Diego Department of Computer Science and Engineering, and Ph.D. student Salva Ruhling Cachay examine data. Photo: David Baillot/UC San Diego Jacobs School of Engineering

The algorithms behind generative AI tools like DallE, when combined with physics-based data, can be used to develop better ways to model the Earth’s climate. Computer scientists in Seattle and San Diego have now used this combination to create a model that is capable of predicting climate patterns over 100 years 25 times faster than the state of the art.