A new artificial intelligence weather forecasting model, developed by researchers at a leading tech company, has demonstrated superior accuracy compared to conventional physics-based models in global medium-range weather predictions. The AI system, trained on decades of historical weather data, can generate a 10-day forecast in under a minute on a single machine, a task that typically requires hours of computation on supercomputers using traditional numerical weather prediction methods. Initial tests show the model provides more accurate predictions for key atmospheric variables, including pressure and humidity, over several days. While promising, experts note that further testing is required to assess its performance in predicting extreme weather events and its long-term reliability. The development signals a potential shift in how weather forecasts are generated, offering faster and potentially more accessible predictions. For the full details, read the complete article at the provided source.