While tech companies and meteorological offices around the world are already applying AI to the weather, the European Centre for Medium-range Weather Forecasts (ECMWF) said its operational model broke new ground by making global predictions freely available to everyone at any time.
This milestone will transform weather science and predictions, said Florence Rabier, director-general of ECMWF, an intergovernmental organisation.Making the AI Forecasting System operational produces the widest range of parameters using machine learning available to date.An experimental version tested over the past 18 months showed the system was about 20 per cent more accurate on key predictions than the best conventional methods, which feed millions of worldwide weather observations into supercomputers and crunch them with physics-based equations.
The new European system could predict the track of a tropical cyclone 12 hours further ahead, giving valuable extra warning time for severe events, said Florian Pappenberger, ECMWF director of forecasts.
Clive Cookson
Improved weather forecasting with better accuracy and predictions over longer timespans seems like a genuinely positive application of machine learning, unlike the multiple pitfalls of generative AI. Google’s DeepMind announced similar results from its GenCast AI model recently – which incidentally was trained on historical weather data from the same ECMWF. Turns out European AI models are not that far behind as many Americans insist on fearmongering.