-Huawei's Pangu-Weather AI model can predict weather events in seconds - just released to the public for free
SHENZHEN, China, Aug. 4, 2023 /PRNewswire/ -- July 2023 is likely to mark the warmest month on record and possibly the warmest in 120,000 years. The climate is warming, and as a result, the probability of extreme weather events is increasing. Traditional weather forecasting requires huge amounts of computing power to work. Now a new AI-powered weather model is being released to the public that transforms the way weather is predicted.
Pangu-Weather, an artificial intelligence model for weather forecasting developed by HUAWEI CLOUD, enables more accurate weather forecasts with 10,000 times improvement in forecast speeds, reducing global weather forecast times to just a few seconds. This facilitates early forecasting and preparation for extreme weather conditions. These results were published in the peer-reviewed scientific journal Nature on July 5, 2023.
Pangu-Weather is the first AI forecast model with higher accuracy than traditional numerical forecasting methods and is released to the public for the first time, free of charge on the ECMWF (European Center for Medium-Range Weather Forecasts) website. This provides global weather forecasters, meteorologists, weather enthusiasts and the general public with a platform to view Pangu Weather Model's 10-day global weather forecasts.
A "game changer" for traditional weather forecasting
In addition to making 10-day weather forecasts available, the ECMWF has also released a report comparing forecasts made by Pangu-Weather and ECMWF IFS (a world leading NWP system) from April to July 2023.
According to the report, the adoption of machine learning (ML) methods such as Pangu-Weather could be "a game changer for the incremental and rather slow progress of traditional Numerical Weather Prediction (NWP) methods" whose forecasting ability has increased by about one day per decade (according to the World Meteorological Organization, WMO). This can be attributed to the high computational cost of running a forecast with standard NWP systems. ML models are poised to revolutionize weather forecasting with forecasts that require much lower computational costs and are highly competitive in terms of accuracy.
Dr. Tian Qi, Chief Scientist of HUAWEI CLOUD AI Field, IEEE Member and Scholar of the International Eurasian Academy of Sciences, explained: "Weather forecasting is one of the most important scenarios in the field of scientific computing because weather forecasting is a complex system, however, it is difficult to cover all aspects of mathematical and physical knowledge.At present, Pangu-Weather mainly completes the work of the forecast system, and its main ability is to predict the evolution of states atmospheric."
Proven high accuracy in forecasting extreme weather conditions
The forecasting capabilities of the Pangu-Weather model have been tested in extreme situations, such as Storm Eunice that hit north-west 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 events and providing guidance for medium-range forecasts.
The Pangu-Weather forecast covers geopotential, specific humidity, wind speed and temperature. All of this information is essential for predicting the development of weather systems, storm tracks, air quality, and weather patterns. Pangu-Weather has also been used to predict the track 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 its forecast systems and to further explore the strengths and weaknesses of such models to aid climate management. .
Dr. Tian Qi said, "Our ultimate goal is to build a next-generation weather forecast framework using AI technologies to strengthen existing forecast systems."
Photo - https://mma.prnewswire.com/media/2169705...
View original content: https://www.prnewswire.com/news-releases/el-modelo-pangu-weather-ai-de-huawei-puede-predecir-eventos-meteorologicos-en-segundos-301893803.html