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, was trained on over 40 years of global atmospheric data and can generate a 10-day forecast in under one minute on a standard computer cluster, a task that typically takes hours for conventional physics-based models. Researchers report that ClimaNet showed a 15% improvement in predicting key variables such as atmospheric pressure and precipitation patterns over a three-month testing period. The AI system uses a novel neural architecture that identifies complex, non-linear patterns in historical weather data that are difficult for traditional equations to capture. While promising, the developers note that further testing is needed for extreme weather events, and the model is intended to complement rather than replace existing physics-based approaches. The full research paper has been published in the journal *Nature*. Read the full article at https://sciencedaily.com/releases/2024/05/240521123456.htm