AI gains ground in weather forecasting: it nailed Hurricane Isaias' track when traditional models failed
Machine learning-based weather forecasting models are already operating in real time as support for meteorologists. During Hurricane Isaias, an AI model placed the landfall point in Florida with an error margin of a few hours at more than three days out and came closest, while the traditional European and US systems drifted too far west. The director of the US National Hurricane Center noted that its official forecast was 20% to 40% more skillful on intensity.
In 40 seconds
- An AI model nailed Hurricane Isaias' track and came closer than traditional models to the landfall point in Florida
- The NHC's official forecast was 20% to 40% more skillful than AI on intensity, according to its director
- The NHC incorporated AI models in real time in 2025 and DeepMind's model beat its track forecast between 12 and 72 hours
Read the full story at Xataka
IASummary generated by artificial intelligence from a story by Xataka. 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.