A new study demonstrates that artificial intelligence models can produce weather forecasts with accuracy comparable to traditional physics-based systems, but in a fraction of the time. The research, led by scientists at a major tech firm, tested an AI model that was trained on decades of historical weather data. The system generated a 10-day global …
A new study demonstrates that artificial intelligence models can produce weather forecasts with accuracy comparable to traditional physics-based systems, but in a fraction of the time. The research, led by scientists at a major tech firm, tested an AI model that was trained on decades of historical weather data. The system generated a 10-day global weather forecast in under a minute on a single desktop computer, a task that typically requires hours of computation on a supercomputer for conventional models. While the AI forecasts matched the skill of the leading numerical prediction models for mid-latitude weather patterns, researchers noted that the AI system currently struggles with predicting extreme weather events and has limitations in regions with less training data. The findings suggest AI could become a powerful tool for providing rapid, lower-cost forecasts, potentially augmenting existing methods. For the full details, read the complete article at https://technologyreview.com/2024/05/15/ai-weather-forecasting-study.
Join the Club
Like this story? You’ll love our Bi-Weekly Newsletter



