Huawei’s Pangu-Weather AI model that can predict weather events in seconds has been released to the public for free.

The climate is warming and, as a result, the likelihood of extreme weather events is increasing. Traditional weather prediction requires huge amounts of computing power to work. Now, an AI-powered weather model is being released to the public that transforms the way weather is predicted.

Pangu-Weather, an AI model for weather prediction developed by Huawei Cloud, enables more accurate weather forecasts to be made with a 10,000 times improvement in prediction speeds, reducing global weather prediction times to just seconds. This facilitates the early prediction and preparation of extreme weather. These results were published in Nature last month.

Pangu-Weather has higher precision than traditional numerical weather prediction (NWP) methods and is being released to the public for the first time, for free on the ECMWF (European Centre for Medium-Range Weather Forecasts) web site. This provides global weather forecasters, meteorologists, weather enthusiasts and the general public with a platform to view Pangu Weather Model’s ten-day global weather forecasts.

In addition to making ten-day weather forecasts available, the ECMWF has also released a report comparing the forecasts made by Pangu-Weather and the ECMWF IFS – a global NWP system – from April to July 2023.

According to the report, the uptake of machine learning (ML) methods such as Pangu-Weather could be “a game-changer for the incremental and rather slow progress of traditional NWP methods” whose forecast skill has been increasing by about one day per decade, according to the World Meteorological Organisation (WMO). This can be attributed to the high computational cost of running a forecast with standard NWP systems. ML models are poised to change weather forecasting with forecasts that require much lower computational costs and are highly-competitive in terms of accuracy.

“Weather forecasting is one of the most important scenarios in the field of scientific computing because meteorological prediction is a very complex system, yet it is difficult to cover all aspects of mathematical and physical knowledge,” said Tian Qi, chief scientist of Huawei Cloud. “At present, Pangu-Weather mainly completes the work of the forecast system, and its main ability is to predict the evolution of atmospheric states.”

Pangu-Weather model’s prediction capabilities have been tested in extreme situations such as Storm Eunice, which hit north-western Europe in February 2022, and the first time the UK hit +40˚C in summer 2022. These two examples show that data-driven models are capable of forecasting extreme weather situations and of providing guidance for medium-range forecasting.

The Pangu-Weather prediction covers geopotential, specific humidity, wind speed and temperature. All this information is critical to predicting the development of weather systems, storm trajectories, air quality and weather patterns. Pangu-Weather has also been used in predicting the trajectory of Typhoon Khanun, the sixth typhoon this year.

The ECMWF has long called for more efforts from the global weather forecasting community to use AI models as additional components of their forecasting and to explore the strengths and weaknesses of such models to assist management of weather.

“Our ultimate goal is to build next-generation weather forecasting framework using AI technologies to strengthen the existing forecasting systems,” said Tian Qi.