GenCast predicts weather and the risks of extreme conditions with state-of-the-art accuracy
Google DeepMind's GenCast just beat physics-based models at weather prediction. Here's why that matters for your infrastructure.
Why it matters
DeepMind released GenCast, a generative AI model that delivers state-of-the-art weather forecasting accuracy up to 15 days ahead, demonstrating a major capability breakthrough in applying deep learning to complex physical systems—relevant for infrastructure planning, insurance, and climate-risk modeling decisions.
The key facts
5 to knowGenCast model achieves state-of-the-art accuracy in weather prediction
Forecasts extend up to 15 days ahead
Model addresses uncertainty and extreme weather risk prediction
Published by Google DeepMind on Dec 4, 2024
Represents shift from traditional physics-based to generative AI approaches in meteorology
Go to the source
Google DeepMind Blogdeepmind.google
Publisher excerpt: New AI model advances the prediction of weather uncertainties and risks, delivering faster, more accurate forecasts up to 15 days ahead