As climate change drives global temperatures to unprecedented highs, weather extremes are becoming more frequent. Traditional weather prediction methods demand substantial computing power, but a groundbreaking solution has emerged. Huawei's Pangu-Weather AI model, developed by Huawei Cloud, promises a remarkable 10,000-fold improvement in prediction speeds, enabling weather forecasts within seconds.
Pangu-Weather represents the first AI prediction model to surpass the precision of traditional numerical prediction techniques. Now, for the first time, it is being released to the public for free on the ECMWF website (European Centre for Medium-Range Weather Forecasts). This move empowers weather forecasters, meteorologists, enthusiasts and the general public with access to the Pangu Weather Model's 10-day global forecasts.
The ECMWF's release of Pangu-Weather aligns with their report, comparing its forecasts with those of the ECMWF IFS (a leading global NWP system) from April to July 2023. This report highlights the transformative potential of machine learning (ML) methods like Pangu-Weather, hailed as a "game-changer" for traditional numerical weather prediction (NWP) methods that have seen slow progress, improving by merely one day per decade, according to the World Meteorological Organization (WMO). The adoption of ML models can revolutionize weather forecasting, offering accurate forecasts with reduced computational costs.
Pangu-Weather's efficacy has been tested in extreme weather events such as Storm Eunice in February 2022 and the UK's record-breaking 40°C temperature in the summer of 2022. These examples illustrate the model's capability to forecast extreme weather and provide guidance for medium-range predictions.
The AI-powered Pangu-Weather prediction encompasses critical factors like geopotential, specific humidity, wind speed and temperature, playing a pivotal role in predicting weather system development, storm paths, air quality and weather patterns. Furthermore, the model demonstrated its prowess in predicting the trajectory of Typhoon Khanun, the sixth typhoon in 2023.
The ECMWF advocates for broader adoption of AI models within the global weather forecasting community, encouraging the exploration of their strengths and weaknesses to enhance weather management practices. As Pangu-Weather disrupts conventional weather prediction, it is set to reshape how we approach weather forecasting in the future.
Dr. Tian Qi, chief scientist of Huawei Cloud AI Field, an IEEE Fellow and academic at the International Eurasian Academy of Sciences, explained thus: "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. At present, Pangu-Weather mainly completes the work of the forecast system, and its main ability is to predict the evolution of atmospheric states. Our ultimate goal is to build a next-generation weather forecasting framework using AI technologies to strengthen the existing forecasting systems."