Today, the top international academic journal "Nature" published the research results of the Huawei Cloud Pangu large-scale model research and development team - "Accurate medium-range global weather forecasting with 3D neural networks". According to the data, this is the first paper in the regular issue of Nature published by a Chinese technology company as the sole author in recent years . The reviewer of "Nature" spoke highly of this achievement: "Huawei Cloud's Pangu meteorological model allows people to re-examine the future of weather forecasting models, and the openness of the model will promote the development of this field."
HUAWEI CLOUD Pangu meteorological large-scale model research results published in the regular issue of "Nature"
The HUAWEI CLOUD Pangu Meteorological Large Model is the first AI model with an accuracy exceeding that of traditional numerical forecasting methods, and its speed is more than 10,000 times faster than traditional numerical forecasting. At present, the Pangu Meteorological Large Model can provide global meteorological forecasts at the second level. Its meteorological forecast results include geopotential, humidity, wind speed, temperature, sea level pressure, etc., which can be directly applied to multiple meteorological research subdivision scenarios. The European Medium-range Forecast Center and the Central Meteorological Observatory have found the superiority of Pangu forecasts in actual measurements.
In May of this year, the direction of typhoon "Mawar" received widespread attention. The Central Meteorological Observatory stated that the Huawei Cloud Pangu large model performed well in the path forecast of "Mawa", and it predicted that it would turn to the east waters of Taiwan Island five days in advance. At the just-concluded 19th World Meteorological Congress, the European Center for Medium-Range Forecasting also pointed out that Huawei Cloud's Pangu meteorological model has an undeniable ability in accuracy, and the purely data-driven AI weather forecasting model has demonstrated forecasting capabilities comparable to numerical models.
The Huawei Cloud Pangu Large Model R&D team found that there are two main reasons for the lack of accuracy of the AI weather forecast model: first, the original AI weather forecast model is based on a 2D neural network, which cannot handle uneven 3D weather data well; second, the AI method lacks mathematical and physical mechanism constraints, so iteration errors will continue to accumulate during the iteration process. To this end, the team creatively proposed a three-dimensional neural network (3D Earth-Specific Transformer) adapted to the earth coordinate system to process complex uneven 3D meteorological data, and used a hierarchical time-domain aggregation strategy to reduce the number of forecast iterations, thereby reducing iteration errors. By training a deep neural network on 43 years of global weather data, the Pangea meteorological large model surpasses traditional numerical prediction methods in terms of accuracy and speed.
In the future, HUAWEI CLOUD will cooperate with global meteorological agencies to continue to explore and give full play to the application potential of AI in the meteorological field, and provide support for various industries such as agriculture, forestry, animal husbandry, fishery, aviation and navigation.
More scientific research hotspots are in " Eurasia Academic "~