It's surprising that AI models trained on general data can accurately predict rare events like hurricanes. The reason is that the physical world is "forgiving"; extreme phenomena are governed by strong physical structures and signatures that AI can learn effectively, even from a limited number of examples.

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.

Unlike traditional neural networks which require fixed-resolution inputs (e.g., pixels), neural operators model data as continuous functions. This allows them to "zoom in" and make predictions at resolutions higher than the training data, a crucial capability for multi-scale physical phenomena like weather patterns.

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.

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's ability to handle novel situations isn't just an emergent property of scale. Waive actively trains "world models," which are internal generative simulators. This enables the AI to reason about what might happen next, leading to sophisticated behaviors like nudging into intersections or slowing in fog.

Instead of a single prediction, advanced weather models generate a range of possible scenarios. This probabilistic approach, which explicitly represents uncertainty by creating an "ensemble" of forecasts, leads to more robust and accurate overall predictions, which is a counterintuitive result.