Studying the probability characteristics of meteorological drought transmission to hydrological drought can help alleviate drought and optimize the allocation of water resources. This study takes the Yiluo River as the research object, and Standardized Precipitation Index (SPI) and Standardized Streamflow Index (SSI) were used to represent meteorological and hydrological drought, respectively. First, the stability of the precipitation and stream flow sequence is tested by using the heuristic segmentation algorithm. The correlation between meteorological and hydrological watershed was analyzed using cross wavelet transform and lag correlation to study the transmission time of meteorological drought to hydrological drought. Second, the characteristics of drought such as drought duration, drought intensity, and drought intensity are discussed by using the run theory. Finally, the joint distribution of the SPI and SSI sequence is constructed using Copula function. From the perspective of conditional probability, the propagation probability and propagation threshold from different levels of meteorological drought to hydrological drought are calculated. A hydrological drought prediction model based on the SPI—P(SSI|SPI) relation curve is proposed. The model is also validated based on the historical data. The results show that the model is suitable for light and middle hydrological drought prediction.

Accurate prediction of urban floods is regarded as one of the critical means to prevent urban floods and reduce the losses caused by floods. In this study, a refined prediction and early warning method system for urban flood and waterlogging processes based on deep learning methods is proposed. The spatial autocorrelation of rain and ponding points is analyzed by Moran's I (a common used statistic for spatial autocorrelation). For each ponding point, the relationship model between the rainfall process and ponding process is constructed based on different deep learning methods, and the results are analyzed and verified by mean absolute error (MAE), root mean square error (RMSE), Nash efficiency coefficient (NSE) and correlation coefficient (CC). The results show that the gradient boosting decision tree algorithm has the highest accuracy and efficiency (with a 0.001 m RMSE of the predicted and measured ponding depth) for ponding process prediction and is regarded as the most suitable method for ponding process prediction. Finally, the real‐time prediction and early warning of urban floods and waterlogging processes driven by rainfall forecast data are realized, and the results are verified by the measured data. The research results can provide theoretical support for urban flood prevention and control.