Artificial intelligence is increasingly being used to address the growing threat of extreme weather events such as heavy rain, hail and storms, according to groundbreaking innovations recently unveiled by the China Meteorological Administration.
The administration presented 16 innovations in urban weather at a conference in Beijing on Monday, part of 103 research advances in AI applications, radar networks and short-term heavy precipitation forecasting. term.
These achievements were made through the Urban Weather Science and Technology Alliance, launched last year by the Beijing Meteorological Department and comprising meteorological departments of 38 major cities.
Beijing’s Leadsee-Precip, a global deep learning model designed to generate precipitation forecasts from weather circulation fields, is one of the domestically developed AI-based forecasting systems that excels in forecasting the distribution and intensity of precipitation.
Feng Jin, head of the Leadsee development team and a researcher at the Institute of Urban Meteorology, said deep learning weather forecasting models have outperformed traditional numerical models in terms of accuracy and efficiency.
AI-driven global circulation models or GCMs, which integrate traditional numerical weather prediction techniques with machine learning, can provide forecasts in up to one minute – a dramatic improvement over the 30-minute processing time required by conventional models, Feng said.
However, current GCMs lack detailed atmospheric and precipitation data, which Leadsee compensates for by focusing on precipitation forecasting, he added.
“Leadsee fills critical gaps in AI-based global circulation models, especially in forecasting extreme precipitation,” Feng said, adding that the model ensures accuracy even with unbalanced precipitation data.
During Typhoon Gaemi, which made landfall in Fujian province and Taiwan in July, Leadsee successfully predicted a change in precipitation patterns over Beijing, allowing local authorities to effectively adjust their flood prevention strategies.
The Beijing Meteorological Department conducted a comprehensive assessment based on references provided by Leadsee, concluding that Gaemi’s impact on the Beijing area would significantly weaken, Feng said.
Additionally, model evaluations during this year’s flood season demonstrated a 20 percent improvement in forecast accuracy for heavy precipitation compared to traditional models.
Beyond Beijing, the Shenzhen Meteorological Bureau in Guangdong Province has developed an AI-based system for heavy precipitation nowcasting, and the effective heavy precipitation nowcasting time has been extended by an hour to two hours. Leveraging high-resolution data sets from radars, satellites and weather stations, the system has already outperformed traditional methods, according to the office.
Technological innovation has proven vital for disaster response and event planning during major events, such as the 40th anniversary celebrations of the Shenzhen Special Economic Zone in 2020 and the 25th anniversary of Hong’s return Kong to China in 2022, the office added.
Chen Zhenlin, director of CMA, said Leadsee is an example of provincial meteorological departments actively exploring the field of artificial intelligence.
“These innovations provide strong technological support to further improve urban weather services,” Chen said.
zhaoyimeng@chinadaily.com.cn
