The AI models, developed under an initiative called Project Eagle, promise to deliver better forecasts using less computational power, providing extended lead times for high-impact weather events. Darryl Kleist, Deputy Director of NOAA's Environmental Modeling Center, explained the motivation behind the new AI models.

NOAA is using those traditional forecasting models as frameworks for its new AI forecasting systems. The agency has estimated that the AI programs will require between 91% and 99% less computing resources than traditional models, while at the same time extending the life of a particular forecast, potentially by as much as 18 or 24 hours.