AI Sharpens Hurricane Forecasts With Extra Day of Accuracy, but Humans Still Call the Shots

Google DeepMind's AI Model Transforms Hurricane Forecasting

The National Hurricane Center began using Google DeepMind's AI model in late June of 2025, marking a shift in how meteorologists approach hurricane forecasts.1

1

The collaboration intensified in 2026 when the model was added to some of NHC's track and intensity consensus aids, coming to the fore as an intense El Niño weather pattern led to a record number of hurricanes in the Pacific.2

2

When Hurricane Isaias struck the southeastern United States last month as a major storm, AI sharpens hurricane forecasts demonstrated its value in real-world conditions.

Ferran Alet, a DeepMind research scientist who leads its cyclone work, explained that Google doesn't have a hurricane-specific model. Instead, it's the same model used for everyday weather, pushed to its limits. "We see extreme weather as almost like something we should strive for because it's the most challenging thing for us and then everything will follow," he told AFP.1

1

Improving Hurricane Forecasting Accuracy With Extra Lead Time

A DeepMind paper published in Nature in August found the model gave forecasters on average an extra day's worth of predictive accuracy, with three-day forecasts as good as what earlier models could provide for only the next two days.1

1

This improvement in predictive accuracy represents a breakthrough for meteorologists tracking tropical cyclones, which are notoriously complex to predict and pose a growing threat in a warming world.

For Isaias specifically, Google DeepMind's AI model recognized it could become a tropical cyclone a full week before it formed.2

2

The model can generate 1,000 possible scenarios for each cyclone and forecast rainfall alongside the storm track and intensity, meaning the path it will follow and how strong it will get. Dan Brown, NHC Operations Division Chief, confirmed that "during Isaias, the AI models performed quite well for track," adding that "AI models appear to be good at quickly predicting shifts in complex steering patterns."1

1

How AI Models Differ From Traditional Forecasting Methods

Prior to AI, the National Hurricane Center used several kinds of models to forecast tropical cyclones. Dynamical models use supercomputers to solve the equations of fluid motion and thermodynamics that govern the atmosphere. Statistical models rely on historical relationships between storm behavior and variables such as location and date, and hybrids combine physics and statistics.1

1

AI models, on the other hand, learn from large datasets, like statistical models, but on a vastly bigger scale and with the ability to pick up far more complicated patterns.2

2

The NHC also uses AI models from the European Centre for Medium-Range Weather Forecasts and the National Weather Service, and has an agreement with Google to work on developing its models. Brown singled out DeepMind and the NHC's own model, called HCCA, as two of the best-performing track and intensity aids.1

1

Why Humans Still Call the Shots Despite AI Advances

The technology isn't without limitations. Brown said that individual models can "wildly flip their tracks or intensity projections from cycle to cycle," leaving hurricane specialists to use their experience and human judgment to decide which models best capture a given storm, and to blend them.1

1

He also noted that physics-based models built the baseline on which the AI models were trained.

"As for the hurricane specialist? The specialist becomes more important than ever. An algorithm can show a track probability, but it doesn't look at live aircraft and satellite data to determine the current structure of the storm," said Brown.2

2

This underscores why humans still call the shots in final forecasting decisions, despite AI's ability to process vast amounts of data and identify complex patterns.

The Climate Change Paradox of AI Forecasting

The gains in forecasting precision are taking place as the U.S. data center buildout is rapidly changing the composition of the electric grid. Planned newer data centers are set to be largely powered by natural gas, according to an analysis by Cleanview, increasing the United States' carbon footprint and worsening climate change.1

1

AI is often criticized for the energy its data centers consume, which is driving more fossil fuel use and contributing to climate change.

Climate change in turn is causing hurricanes to become more powerful, carry more rainfall, and move more slowly, thus worsening impacts.2

2

This creates a complex situation where AI helps forecast the very weather events that climate change—partly driven by AI's energy consumption—is making more severe. As hurricane seasons grow more intense, the extra day of predictive accuracy provided by AI could prove critical for evacuation planning and emergency response, even as the technology's environmental footprint raises questions about long-term sustainability.