A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior accuracy compared to conventional physics-based systems in global medium-range weather predictions. The GraphCast model, described in a recent Science publication, leverages machine learning trained on decades of historical weather data to predict hundreds of weather variables up to 10 days in advance. In head-to-head comparisons with the European Centre for Medium-Range Weather Forecasts’ high-resolution forecast (HRES), GraphCast provided more accurate predictions for over 90% of 1,380 test variables. The AI system significantly outperformed HRES on key metrics, particularly in predicting extreme weather events like tropical cyclones and atmospheric rivers. Researchers note that while AI models like GraphCast offer remarkable speed and efficiency advantages, they are designed to complement rather than replace traditional numerical weather prediction systems, which remain crucial for data assimilation and model interpretability. The development marks a significant step toward hybrid forecasting systems that combine the strengths of both approaches. For the full details, read the complete article at: https://sciencedaily.com/releases/2023/11/231114155539.htm