Nvidia has released three open-source AI models aimed at helping create better weather forecasts, faster.
The models, which the AI chip firm announced at the American Meteorological Society’s annual meeting in Houston in the US, are part of a broader push by the company to provide open-source software, powered by its chips, for everything from chatbots to self-driving vehicles.
In the case of weather forecasting, Nvidia is aiming to replace expensive and time-consuming conventional weather simulations with AI-driven versions that the company said can rival or exceed the accuracy of older methods. The AI models, once trained, are also faster and cost less to run.
Mike Pritchard, the director of climate simulation research for Nvidia and a professor of earth system sciences at the University of California, Irvine, said that one of the practical business applications of the new weather models will be in the insurance industry. Insurance companies often want to understand extreme outlier events, such as massive floods or hurricanes.
But predicting such events in detail has historically been expensive, because weather forecasting is performed in “ensembles”, or groups of individual “member” predictions about how a weather event might play out from a given starting point. To find possible outlier events, the ensembles must contain many members, but calculating each one in precise detail to see whether a particular property might flood is slow.
‘Earth-2’
“The tension is gone, because once trained, AI is a thousand times faster,” Pritchard said in an interview. “So you’re free to run massive ensembles. And insurance companies are running, like, 10 000-member ensembles.”
Read: Nvidia’s next AI chips are in full production
Nvidia’s “Earth-2” models introduced on Monday include one aimed at making 15-day weather forecasts, one that specialises in forecasts of up to six hours for severe storms over the US, and one that can be used to integrate disparate data streams from a variety of weather sensors to make them a more useful starting point for other forecasting technology. — (c) 2026 Reuters
Get breaking news from TechCentral on WhatsApp. Sign up here.