WASHINGTON DC — The National Oceanic and Atmospheric Administration launched a suite of artificial intelligence–powered global weather forecast models late last year to improve speed, efficiency, and accuracy. The rollout has coincided with a Trump administration budget proposal this year that called for a modest increase for the National Weather Service and a 40% cut to NOAA overall.

In March, an agency official said the new forecast models are being trained with centuries of weather data. NOAA has not wholly switched to AI forecasting and is employing artificial intelligence in its ensemble models, which blend multiple techniques to produce a range of probable outcomes.

"NOAA's new AI-powered model suite is an addition to our stable of weather models, not a replacement, and was built on data from the agency's flagship physics-based Global Forecast System model," said National Weather Service spokesperson Erica Grow Cei. Addressing observations data, she said, "Despite the misinformation circulating about missing weather and climate data, there is, in fact, a wealth of weather data collected each day, from satellites in space, to a network of weather balloons, to buoys in the ocean, and land-based sensors."

For decades, scientists used traditional physics-based models to predict future weather conditions using complex mathematical equations. Artificial intelligence–based models instead identify patterns in decades of historical data to forecast weather outcomes, use less computing power than traditional models, and have been found to outperform traditional models for some aspects of weather forecasting. An April study published in Science Advances found that AI-based models underperform in predicting extreme weather events and tend to predict weather similar to historical events, while traditional physics-based models, which assess and predict outcomes based on physical conditions, do not have that underperformance problem.

Forensic meteorologist Chris Gloninger said conventional models outperformed AI-based ones when forecasting a historic February 2026 blizzard in the northeastern US. "The AI weather models were trained on a climate that no longer exists," he said. Gloninger said that if the government scales up reliance on AI-powered models while reducing the amount of data that powers them, it could compromise federal forecasts. "You have infrastructure systems in this country that are built on having a steady or static climate, and we know that that's not the case as extremes are increasing," he said.

"Under Trump, climate and weather data collection has declined," said Monica Medina, who served as NOAA's principal deputy undersecretary of commerce for oceans and atmosphere from 2009 to 2012. The National Weather Service faced decades of understaffing prior to 2021, and recent cuts have exacerbated understaffing at the agency.

NOAA will issue its outlook for the 2026 Atlantic hurricane season on Thursday.