Google DeepMind's AI Gave Jamaica an Extra Day to Prepare for a Category 5 Hurricane

Key points

• Google DeepMind's WeatherNext model predicted Hurricane Melissa would hit Jamaica as a Category 5 storm five days before landfall, with 80 percent confidence.
• On average, WeatherNext gives forecasters one full extra day of accurate warning compared with existing models, according to a paper published in Nature on Thursday.
• The model generated 1,000 possible storm scenarios at once, a volume traditional computing cannot match.
• DeepMind is releasing the WeatherNext models as open-source software so outside researchers can study and improve them.
• Even the model's own developers cannot fully explain how it achieves its accuracy using lower-quality input data than traditional forecasting requires.

In October 2025, a storm built quietly over the Caribbean. Traditional weather models disagreed on its trajectory: would it stay weak, or strengthen and turn toward Jamaica? WeatherNext, an AI forecasting system built by Google's DeepMind and Google Research divisions, sided firmly with the latter. Five days before the storm made landfall, it flagged an 80 percent chance of a Category 5 hurricane striking Jamaica.

It was right. Hurricane Melissa brought flooding and landslides across the island. But the early warning meant communities had more time to prepare. When we first covered WeatherNext on 6 August, the story was the model's ability to call Melissa's rapid intensification from Category 1 to Category 5, a call no previous tool had managed that far out.

What makes this different from regular weather forecasting?

WeatherNext buys forecasters roughly one extra day of reliable warning. Its three-day forecast is about as accurate as older models' two-day forecasts. Historically, the researchers say, gaining that single day would have taken a decade of incremental scientific work.

Mike Brennan, director of the US National Hurricane Center, said: "Time is really golden for those types of decisions, so the ability to push forecast accuracy out as much as a day beyond what we've previously been able to do is really valuable."

Organising evacuations and moving supplies are time-sensitive jobs. Getting them wrong costs lives.

Why are hurricanes so hard to predict in the first place?

Two things must be predicted at once, and they demand very different kinds of data. Tracking which direction a storm travels requires big-picture global weather data: cold front positions, wind patterns across whole ocean basins. Predicting intensity requires fine-grained local data about ocean temperature and the atmosphere directly above the storm. Earlier AI models handled track reasonably well. Intensity, says Kate Musgrave, tropical cyclone group lead at the Cooperative Institute for Research in the Atmosphere and a co-author on the paper, "they could not do well at all."

DeepMind's team addressed this by training WeatherNext on large volumes of general weather data alongside the far smaller set of historical cyclone records. Broad atmospheric patterns first, then storms.

The strangest part: WeatherNext uses lower-resolution input data than traditional models consider necessary for intensity forecasting, yet it still outperforms them. When the team shared this with other scientists, "they were shocked," says Ferran Alet, a research scientist at Google DeepMind and a lead author on the paper. Something in the coarser data carries more useful signal than anyone previously suspected. Nobody knows what.

"It's a black box," Alet acknowledges, "but that gives physicists a signal that something is happening that was not previously understood."

What happens next?

DeepMind is open-sourcing the WeatherNext models so independent researchers can probe them and perhaps figure out what the AI spotted that human physicists missed. The 1,000-scenario-per-storm output, up from 50 last year, helps capture butterfly-effect divergences that traditional numerical models simply cannot generate at that scale.

Brennan is clear-eyed about the limits. No single model is guaranteed to perform best in every future season. Human experts still translate raw forecasts into impact assessments. "A hurricane is not just a track or an intensity forecast," he says. "It requires experts to translate that into what the impacts are going to be, and it's the impacts that kill people."

The open-source release is the piece worth watching. If outside researchers can crack what the model is seeing in low-resolution data, the physics payoff could outlast the forecasting one.