Google’s AI model just nailed the forecast for the strongest Atlantic storm this year

ARS TECHNICA

In terms of track, Google's model not only beat the "official" track forecast from the National Hurricane Center but also bested a number of physics-based models that make global forecasts as well as hurricane-specific models.

A physics-based model is a traditional forecast model based on complex equations. Also called numerical weather prediction, such models take initial atmospheric conditions and then crunch through calculations to determine how the atmosphere will change over time.

This process requires intensive computational power but has historically served meteorology well. Error trends in hurricane track forecasts have dropped significantly over the last quarter of a century as computer hardware has improved and our ability to gather and input real-time atmospheric conditions has strengthened.

Similarly to track forecasts, Google's model also outperformed other models for the first 72 hours when it came to intensity forecasts. Its performance at two days is particularly striking.

Read more | ARS TECHNICA

---