Google DeepMind's AI Hurricane Model Beats Forecasts by Over a Day, Study Finds
Source The New York Times
At a glance
A Google DeepMind AI model predicted typhoons more accurately than existing forecasting models by more than a day, according to a study published in the journal Nature. The study analyzed hundreds of typhoon forecasts made from 2023 to 2025.
Key points
The U.S. National Hurricane Center used the AI approach last year during Hurricane Melissa and correctly predicted sudden changes in its strength in advance.
The research team says the AI model clearly outperformed other widely used forecasting models.
Outside experts called AI forecasting an important advance, saying it could give people more time to evacuate and help protect lives and property.
Emanuel, an MIT professor emeritus, said humans must still make the final decisions and that AI will be just one source of information to consider, like satellite images.
Why it matters
If typhoon forecasts come a day earlier, residents get more time to evacuate and prepare, which can directly help reduce loss of life and property.
Original article
A.I. Brings Big Gains to Hurricane Forecasts, Google Researchers Say
The New York Times · Aug 28, 2026, 6:02 PM GMT+9 · nytimes.com
Read on The New York TimesAI read the original article and summarized it in plain language. It may contain mistakes, so please check the original for accuracy. The article's copyright belongs to The New York Times.