Short-duration heavy rainfall (SDHR) refers to rainfall events with 1-h accumulated rainfall of no less than 20 mm, characterized by sudden onset, rapid development and strong destructive potential. Accurate forecasting of SDHR remains a global challenge. Data-driven artificial intelligence (AI) techniques provide new avenues for SDHR forecasting. However, high-quality training datasets needed by the AI techniques are still lacking. Based on the data from multiple sources, including observations from 158 radar stations, 48,000 rain gauges, and 3-km China Meteorological Administration (CMA) regional reanalysis product, the National Meteorological Information Centre (NMIC) of CMA has developed a large-volume, well-labeled AI training dataset for SDHR (AIDA-SDHR), with minute-level temporal resolution and kilometer-level spatial resolution. Data processing techniques such as data cleansing based on multi-source data cross-validation, sample labeling via segmented inverse distance-weighted interpolation, and targeted feature extraction, were employed. The AIDA-SDHR dataset covers 14,392 SDHR events that occurred in central–eastern China since 2016, with a total of 1,181,308 samples. Each sample is annotated with a 6-min accumulated rainfall intensity label and supplemented with 10 radar-derived features as well as 30 atmospheric state variables, enabling direct deployment for training of AI models. Evaluations show that based on the AIDA-SDHR dataset, quantitative precipitation estimation by an AI model (AI-QPE) outperforms the algorithm of the radar reflectivity–rainfall (Z–R) in capturing the spatial distribution and intensity of rainfall, reducing the root-mean-square error (RMSE) by 12.19%. Furthermore, integrating more samples from AIDA-SDHR into the Yushi AI forecasting model improves its performance, with increases of 4.68% and 15.69% in the threat score (TS) for composite reflectivity and extreme composite reflectivity (≥ 50 dBZ) forecasts at 0–60-min lead time. Overall, the AIDA-SDHR dataset paves the way for development of AI-based monitoring and forecasting of SDHR in China. Moreover, it also holds substantial potential for a deeper understanding of the formation and evolution of SDHR.

Accurate forecasting of heavy precipitation in central China is still a challenge, within which a key issue is our still incomplete understanding of the convective systems (CSs) responsible for such events. In this study, through use of an iterative rain-cell tracking algorithm, the macroscale characteristics (scale, intensity, duration, etc.) of the CSs that produced 595 short-term heavy precipitation events in Hunan Province, central China, are quantitatively analyzed, based on radar reflectivity, echo top, and rainfall observations at 1-km and 6-min intervals in April–September of 2016–2018. The results show that CSs present significant seasonal and diurnal features. Spring CSs usually cover a larger echo area with stronger convective cores and thus generate more precipitation than summer CSs, though summer CSs develop more vigorously and frequently. CSs initiated at 1400–1600 local time are characterized by the strongest convection and a smaller spatiotemporal scale, causing violent and transient showers with typical areal precipitation of 0.5–1 mm km⁻², but less total precipitation. Further analyses of the relationships among the scale, intensity, duration, and total precipitation of CSs reveal that the convective intensity is linearly correlated to the spatiotemporal scale of CSs, with the duration increasing on average by 0.0372 h dBZ⁻¹; the echo area is significantly correlated to the total precipitation, and the duration and rainfall amount are connected with the area expansion rate (AER) of CSs: when the AER exceeds 50%, CSs expand rapidly with increasing total precipitation, but the duration is shorter. These findings provide a helpful reference for the forecasting of short-term heavy precipitation induced by CSs in central China.