The U.S. National Oceanic and Atmospheric Administration (NOAA) has launched a new suite of operational, AI-driven global weather prediction models, representing a major leap in forecast speed, efficiency, and accuracy. 

According to NOAA, the models deliver faster, more precise guidance while using significantly fewer computational resources.

The new AI weather model suite includes three applications: 

• AIGFS (Artificial Intelligence Global Forecast System), delivering faster, more efficient forecasts using up to 99.7% less computing power; 
• AIGEFS (Artificial Intelligence Global Ensemble Forecast System), an AI-driven ensemble extending forecast skill by 18–24 hours; and 
• HGEFS (Hybrid-GEFS), a “grand ensemble” combining AI and traditional models that consistently outperforms both approaches in testing.

“These AI models reflect a new paradigm for NOAA in providing improved accuracy for large-scale weather and tropical tracks, and faster delivery of forecast products to meteorologists and the public at a lower cost through drastically reduced computational expenses,” said NOAA administrator Neil Jacobs.

The initial model suite grew out of Project EAGLE, a collaborative effort involving NOAA’s National Weather Service, Oceanic and Atmospheric Research labs, the Environmental Modeling Center within the National Centers for Environmental Prediction, and the Earth Prediction Innovation Center.