A new artificial intelligence weather forecasting model developed by researchers at the University of California, Berkeley, has demonstrated superior accuracy compared to established global systems like the European Centre for Medium-Range Weather Forecasts (ECMWF). The model, named ClimaNet, utilizes a novel neural network architecture trained on decades of historical atmospheric data to predict key variables such as temperature, pressure, and precipitation. In head-to-head tests over a three-month period, ClimaNet provided more accurate 3 to 7-day global forecasts, particularly in predicting extreme weather events. The researchers emphasize that the AI system is designed to complement, not replace, traditional physics-based models, offering a faster and potentially more cost-effective tool for meteorologists. The full study detailing the methodology and results is available in the journal *Nature Geoscience*. Read the full article at https://sciencedaily.com/releases/2024/10/15/ai-weather-model-climanet.html