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, outperformed the European Centre for Medium-Range Weather Forecasts’ high-resolution forecast (HRES) system in over 90% of 1,380 test metrics. The AI system generates 10-day forecasts in under one minute on a single Google TPU v4 cloud computer, significantly faster than traditional methods that require hours on supercomputers. Researchers note that while AI models show remarkable speed and accuracy advantages, they should complement rather than replace established physics-based systems due to different strengths and limitations. The development represents a significant advancement in computational meteorology and could improve severe weather prediction capabilities. Read the full article at https://sciencedaily.com/releases/2023/11/231114143522.htm