A new artificial intelligence weather forecasting model developed by researchers at the University of California, Berkeley, has demonstrated superior accuracy in global weather predictions compared to established numerical models. The system, named NeuralGCM, processes decades of historical atmospheric data to identify complex patterns, generating detailed forecasts for temperature, pressure, wind, and precipitation up to 15 days in advance. Initial tests show it matches or exceeds the performance of the European Centre for Medium-Range Weather Forecasts’ high-resolution model, which is considered the current global gold standard. The AI model operates significantly faster and at a lower computational cost once trained, potentially enabling more frequent updates and localized predictions. Researchers emphasize it is designed to complement, not replace, traditional physics-based models, offering a powerful new tool for meteorologists. Read the full article at https://technologyreview.com/2024/05/15/neuralgcm-ai-weather-model.