An AI model may not have seen a specific record-breaking hurricane before, but it has seen its components—intense wind, low pressure—in other storms globally. It predicts novel extreme events by composing these learned "local statistics" or "parts" into a new, plausible combination.

To generate a range of possible weather scenarios, DeepMind uses a novel technique called "functional generative networks." Instead of only adding noise to the input data, this method directly modifies the neural network's internal parameters (weights) for each simulation, creating a diverse set of potential outcomes.

Counter-intuitively, successful weather and climate AI models are not trained on long-term data. They are trained to predict only the next six hours autoregressively. This surprisingly generalizes to stable rollouts predicting weather patterns for hundreds or thousands of steps into the future, enabling long-term forecasting from short-term training.

AI's advantage is superior pattern recognition, not magic. Since the physical laws governing weather are constant, an AI trained on vast historical data can identify subtle, previously unnoticed relationships between past and future events, leading to more accurate predictions than traditional models.

Unlike traditional models that make localized predictions, AI models analyze the planet's entire weather state simultaneously. This allows them to learn from large-scale structures, like a whole hurricane, using context from one side of a storm to improve predictions for the other side.

Traditional weather forecasting requires massive supercomputers, limiting access to large agencies. New AI models are tens of thousands of times faster and can run on a single consumer-grade GPU. This democratizes high-fidelity weather modeling for smaller agencies and nations, especially in the global south.

Most AI weather models project the Earth onto a flat rectangle, causing simulations to become unstable and "blow up" over long periods. By incorporating the planet's spherical geometry using Fourier Neural Operators, models like ForecastNet remain stable for long-term climate rollouts, effectively becoming climate models.

The AI model confidently predicted Hurricane Melissa would become a Category 5 storm while it was still a tropical depression. This high confidence directly influenced the National Hurricane Center to issue their earliest-ever Category 5 forecast for such a low-intensity storm, providing crucial extra warning time.

Traditional physics-based simulations can "blow up" when small errors compound, leading to absurd forecasts. AI models have a safer failure mode: when encountering uncertainty, they "regress to the mean," predicting the historical average weather, which is a more stable and less misleading outcome.