NeuralGCM, a new AI model combining traditional forecasting with machine learning, reduces computational power while maintaining accuracy for weather and climate predictions.

A new AI model, NeuralGCM, combines traditional weather and climate forecasting models with machine learning techniques, offering similar results to existing models while using less computer power. Developed by researchers from Google, MIT, Harvard, and the European Centre for Medium-Range Weather Forecasts, the model aims to enhance large-scale physical simulations essential for understanding and predicting Earth's system. The NeuralGCM model is part of a growing trend in research models using advances in machine learning to make weather and climate predictions faster and more cost-effective.

July 22, 2024
8 Articles