AI-powered weather forecasting systems are revolutionizing the way we predict and prepare for extreme weather events.

The China Meteorological Administration (CMA) recently showcased 16 innovations in urban meteorological science, including AI-powered forecasting systems that excel in predicting rainfall distribution and intensity. These advancements are part of 103 research breakthroughs in AI applications, radar networking, and short-term heavy rainfall forecasting.

One of the domestically developed AI-powered forecasting systems is Beijing's Leadsee-Precip, a global deep-learning model designed to generate precipitation forecasts from meteorological circulation fields. This model has surpassed traditional numerical models in both accuracy and efficiency.

AI-driven global circulation models (GCMs) integrate traditional numerical weather prediction techniques with machine learning, delivering forecasts in minutes compared to the 30-minute processing time required by conventional models. However, current GCMs lack detailed atmospheric and precipitation data. Leadsee compensates for this by focusing on rainfall prediction.

During Typhoon Gaemi, Leadsee successfully forecasted a shift in rainfall patterns over Beijing, enabling local authorities to adjust flood prevention strategies effectively. Evaluations of the model during this year's flood season demonstrated a 20 percent improvement in forecasting accuracy for heavy rainfall compared to mainstream models.

Beyond Beijing, the Shenzhen Meteorological Bureau in Guangdong province has developed an AI-based system for heavy rainfall nowcasting, extending the effective lead time from one hour to two hours. This system has already surpassed traditional methods, proving vital for disaster response and event planning during major events.

These innovations highlight the potential of AI in improving urban meteorological services and enhancing our ability to predict and prepare for extreme weather events.