A new artificial intelligence weather forecasting model developed by Google’s DeepMind has demonstrated superior accuracy compared to the world’s leading traditional system in a comprehensive global evaluation. The GraphCast model, which uses machine learning to analyze decades of historical weather data, outperformed the European Centre for Medium-Range Weather Forecasts’ high-resolution forecast system in over 90% of 1,380 test variables. Researchers found the AI system was particularly adept at predicting extreme weather events and atmospheric conditions at higher altitudes. The study, published in Science, suggests AI could significantly improve weather prediction while reducing computational costs, though experts note traditional models remain crucial for understanding atmospheric physics. Read the full article at: https://sciencedaily.com/releases/2023/11/231114143522.htm