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 study published in Science, uses machine learning to analyze decades of historical weather data and current atmospheric conditions to generate forecasts up to 10 days in advance. In head-to-head comparisons with the European Centre for Medium-Range Weather Forecasts’ high-resolution system (HRES), GraphCast provided more accurate predictions for over 90% of 1,380 test variables, including critical measurements like atmospheric pressure, temperature, and wind speed. The AI system can generate a 10-day forecast in under one minute on a single Google TPU v4 machine, a significant efficiency gain over traditional methods that require hours of computation on supercomputers. Researchers emphasize that AI models like GraphCast are designed to complement, not replace, established numerical weather prediction systems, offering a powerful new tool for meteorologists. Read the full article at: https://sciencedaily.com/releases/2023/11/231114155020.htm