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, detailed in a Science journal publication, uses machine learning to analyze decades of historical weather data and identify complex atmospheric patterns. In head-to-head comparisons with the European Centre for Medium-Range Weather Forecasts’ high-resolution forecasting system (HRES), GraphCast provided more accurate predictions for over 90% of 1,380 test variables, including temperature, pressure, wind speed, and humidity at multiple atmospheric levels. The AI system can generate a 10-day forecast in under one minute on a single Google TPU v4 machine, significantly faster than traditional methods that require hours on supercomputers. While promising for improving extreme weather event predictions, researchers note that AI models like GraphCast still rely on traditional systems for initial conditions and require further testing for operational reliability. Read the full article at https://sciencedaily.com/releases/2023/11/231114143522.htm