A Florida Congressman applauded the launch of AI-driven weather forecasting models.
U.S. Representative Scott Franklin welcomed the National Oceanic and Atmospheric Administration’s (NOAA) recent announcement of a new suite of operational, artificial intelligence-driven global weather forecasting models, calling the move an important step toward faster, more accurate forecasts and improved preparedness for extreme weather.
“Integrating artificial intelligence into weather forecasting has the potential to significantly improve the speed and accuracy of forecasts relied upon by states like Florida and the nation as a whole,” Republican Florida Congressman Scott Franklin said. “NOAA’s launch of these AI-driven models represents meaningful progress in modernizing forecasting capabilities and equipping forecasters and emergency managers with better tools to prepare for severe weather and wildfire risks. I’ve long supported responsibly incorporating AI into NOAA’s work, including through my TAME Extreme Weather Act and provisions advanced in the Weather Act, and I encourage the House to pass the Weather Act to continue this momentum.”
NOAA recently announced the rollout of a new suite of AI-driven global weather prediction models designed to improve forecast speed, efficiency, and accuracy while using fewer computational resources.
The models will operate alongside NOAA’s existing forecasting systems and include AI-based global and ensemble models, as well as a first-of-its-kind hybrid system that combines artificial intelligence with traditional physical forecasting models.
The new suite of AI weather models includes three distinct applications:
- AIGFS (Artificial Intelligence Global Forecast System): A weather forecast model that implements AI to deliver improved weather forecasts more quickly and efficiently (using up to 99.7% less computing resources) than its traditional counterpart.
- AIGEFS (Artificial Intelligence Global Ensemble Forecast System): An AI-based ensemble system that provides a range of probable forecast outcomes to meteorologists and decision-makers. Early results show improved performance over the traditional GEFS, extending forecast skill by an additional 18 to 24 hours.
- HGEFS (Hybrid-GEFS): A pioneering, hybrid “grand ensemble” that combines the new AI-based AIGEFS (above) with NOAA’s flagship ensemble model, the Global Ensemble Forecast System. Initial testing shows that this model, a first-of-its kind approach for an operational weather center, consistently outperforms both the AI-only and physics-only ensemble systems.
“NOAA’s strategic application of AI is a significant leap forward in American weather model innovation,” said Neil Jacobs, Ph.D., NOAA administrator. “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.”
This initial model suite is an outgrowth of Project EAGLE, a joint initiative between NOAA’s National Weather Service, Oceanic and Atmospheric Research labs, the Environmental Modeling Center in NOAA’s National Centers for Environmental Prediction, and the Earth Prediction Innovation Center. The team leveraged Google DeepMind’s GraphCast model as an initial foundation and fine-tuned the model using NOAA’s own Global Data Assimilation System analyses. This additional training with NOAA data improved the Google model’s performance, particularly when using GFS-based initial conditions.
Rep. Franklin is the author of the TAME Extreme Weather Act, legislation he introduced in multiple Congresses to direct NOAA to develop domestic datasets for AI forecasting, partner with private industry and academia, and integrate AI-based models into operational forecasts for weather and wildfires. During committee consideration of the Weather Act previously, Rep. Franklin also advanced these priorities through an amendment encouraging NOAA’s use of AI forecasting tools, which was included in the committee-passed bill.
