A new artificial intelligence weather forecasting model developed by Google DeepMind has demonstrated superior accuracy compared to the world’s leading conventional system in a comprehensive global evaluation. The model, named GraphCast, predicted weather conditions up to 10 days in advance more accurately than the European Centre for Medium-Range Weather Forecasts (ECMWF) high-resolution forecast (HRES) system across over 90% of 1,380 test variables. These variables included critical atmospheric measurements like temperature, pressure, wind speed, and humidity at various altitudes. The AI system operates by analyzing decades of historical weather data to learn underlying atmospheric physics, generating forecasts in under a minute on a single machine. While traditional numerical weather prediction relies on complex physics equations solved on supercomputers, the AI approach offers a significantly faster and computationally cheaper alternative. Researchers emphasize that AI models like GraphCast are not replacements but powerful complementary tools that could enhance the speed and detail of global weather forecasting. Read the full article at: https://technologyreview.com/2024/01/15/1086821/ai-weather-forecasting-model-graphcast-beats-traditional-methods/