A new study published in Science demonstrates that an artificial intelligence weather forecasting model has achieved superior accuracy compared to conventional physics-based models. The AI system, developed by researchers at a leading tech firm, was trained on decades of historical global weather data. In head-to-head tests over a one-year period, the AI model provided more accurate predictions for key atmospheric variables like temperature and humidity across multiple altitudes. The model’s speed is also a significant advantage, generating a 10-day forecast in under a minute on a single desktop computer, a task that typically requires hours of computation on supercomputers using traditional methods. While promising, the researchers note that further testing is needed for extreme weather events, and the system is intended to complement, not replace, existing forecasting infrastructure. Read the full article at https://sciencedaily.com/releases/2024/05/240509124558.htm.