A new artificial intelligence weather forecasting model, developed by researchers at the University of California, has demonstrated superior accuracy compared to conventional physics-based models in a comprehensive global assessment. The AI system, trained on decades of historical weather data, can generate high-resolution forecasts for temperature, precipitation, and wind patterns in minutes, a task that typically requires hours of supercomputer calculations. Initial results show a 15-20% improvement in predicting extreme weather events like hurricanes and heatwaves over a 10-day period. While promising, meteorologists caution that further testing is needed during rare or unprecedented weather scenarios not represented in the training data. The research team plans to make the model open-source to encourage broader validation and development within the scientific community. Read the full article at https://sciencedaily.com/releases/2024/10/240415120543.htm