Google's new weather prediction model, NeuralGCM, combines machine learning and traditional physics-based techniques to enhance forecast accuracy while reducing computational costs. It leverages AI to improve predictions for smaller scales, such as cloud formations, which traditional models struggle with. The system produces fast, high-quality forecasts and shows promise for modeling large-scale climate events. NeuralGCM aims to support both short-term weather forecasts and long-term climate modeling, benefiting researchers and industries requiring precise weather predictions.

For more details, you can read the full article [here](https://www.technologyreview.com/2024/07/22/1095184/a-new-weather-prediction-model-from-google-combines-ai-with-traditional-physics/).