During hurricane season, meteorologists rely on a variety of different forecast models. As this season comes to an end, experts are taking stock of which ones performed well and which ones didn’t, and Google’s rookie model has left them absolutely gobsmacked.
Though Google DeepMind’s Weather Lab only began releasing forecasts in June, it was by far the best model for predicting hurricane track and intensity this season, according to a preliminary analysis by Brian McNoldy, a meteorologist and senior researcher at the University of Miami. Meanwhile, America’s flagship weather model—the Global Forecast System—was the worst performing.
The National Hurricane Center will release official data on each model’s performance in a few months, but this initial assessment foreshadows a turning point in hurricane forecasting. With the incredible superiority of AI-based models becoming blatantly apparent, it may be time to start phasing out traditional, physics-based models.
“Going forward, it is safe to say that we will rely heavily on Google and other AI weather models, which are likely to improve in the coming years, as they are relatively new and have room for improvement,” Houston-based meteorologist and space reporter Eric Berger wrote for Ars Technica.
The rise of AI forecasting has begun
McNoldy’s analysis includes two charts: one comparing track forecast accuracy for all 13 named storms in the Atlantic Basin this season, and one comparing the intensity forecast accuracy for all 13 storms. The different colored lines represent different forecast models, denoted by the legend on the right-hand margin. The lower a line is, the better that model performed.
This chart shows the track forecast accuracy for all 13 named storms in the Atlantic Basin in 2025 © Brian McNoldy via Bluesky This chart shows the intensity forecast accuracy for all 13 named storms in the Atlantic Basin in 2025 © Brian McNoldy via Bluesky
The GFS—referred to as AVNI in this instance—is displayed in orange all the way up at the top of the charts. NOAA developed this model in the early 1980s, and the National Weather Service still uses an updated version as its primary forecast system today.
“The GFS was especially awful in its forecast for Melissa, with an average 5-day track error ballooning to over 500 miles [800 kilometers], insisting on a turn out to sea that never transpired,” Miami-based meteorologist and hurricane specialist Michael Lowry wrote in a recent blog post.
Unlike Google’s forecast model, the GFS is based on traditional physics and advanced supercomputers. The difference between them clearly stands out on these charts. Google’s model is all the way at the bottom, indicating superior performance to all other evaluated models—especially the GFS.
“The beauty of DeepMind and other similar data-driven, AI-based weather models is how much more quickly they produce a forecast compared to their traditional physics-based counterparts that require some of the most expensive and advanced supercomputers in the world,” Lowry wrote. “Beyond that, these “smart” models with their neural network architectures have the ability to learn from their mistakes and correct on-the-fly.”
An urgent need for better forecasts
Hurricane Melissa—which ravaged the Caribbean last week—is just one example of how rising sea surface temperatures are supercharging storms. As climate change causes hurricanes to become deadlier and more damaging, it’s essential that forecasters have the best possible tools to predict their paths and intensities.
AI-based models could help forecasters adapt to a warming world. DeepMind’s stunning debut has certainly caught their attention and may mark the beginning of a new era in hurricane prediction.
