A DeepMind AI model got Hurricane Isaias' track right where classic models failed
During Hurricane Isaias, a DeepMind AI model placed landfall within a margin of a few hours more than three days out and came closest to the actual impact point, in Florida, while the traditional European and US systems drifted too far west. According to the National Hurricane Center's (NHC) 2025 report, the model beat its track forecast between 12 and 72 hours. The NHC keeps physical models, which are better on intensity.
In 40 seconds
- The DeepMind AI model was closest to Isaias' actual impact point in Florida, while the traditional European and US models drifted west.
- The NHC's 2025 report says the model beat its track forecast between 12 and 72 hours, with comparable skill on intensity.
- The NHC director said the official forecast had 20% to 40% more skill than the AI in predicting hurricane strength.
IASummary generated by artificial intelligence from a story by El Ecosistema Startup. It may contain errors: the original source prevails.




Comments
Be respectful. Comments reported by several people are hidden until a moderator reviews them.
You do not need an account to read, only to comment. Sign in with a code sent to your email or with your Google account. We only show the name you choose, never your email.