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, analyzes decades of historical weather data to predict future conditions. In head-to-head tests over a one-year period, the AI model provided more accurate forecasts for over 90% of the globe, particularly excelling at predicting extreme weather events like hurricanes and heatwaves with greater lead time. The researchers note that while the AI model is computationally cheaper to run once trained, its “black box” nature presents challenges for meteorologists who rely on understanding the physical reasoning behind forecasts. The integration of AI techniques is poised to become a significant tool alongside established methods. Read the full article at https://sciencedaily.com/releases/2024/05/240509124123.htm.