With global warming, the number of extreme weather events will increase. This scenario, combined with accelerating urbanization, increases the likelihood of urban flooding. Therefore, it is necessary to predict the characteristics of flooded areas caused by rainstorms, especially the flood depth. We applied the Naive Bayes theory to construct a model (NB model) to predict urban flood depth here in Zhengzhou. The model used 11 factors that affect the extent of flooding—rainfall, duration of rainfall, peak rainfall, the proportion of roads, woodlands, grasslands, water bodies and building, permeability, catchment area, and slope. The forecast depth of flooding from the NB model under different rainfall conditions was used to draw an urban inundation map by ArcGIS software. The results show that the probability and degree of urban flooding in Zhengzhou increases significantly after a return period of once every two years, and the flooded areas mainly occurred in older urban areas. The average root mean square error of prediction results was 0.062, which verifies the applicability and validity of our model in the depth prediction of urban floods. Our findings suggest the NB model as a feasible approach to predict urban flood depth.

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.

Urban flooding has become a global problem, seriously threatening the healthy development of cities and the safety of people’s lives and property. Urban flood risk assessment can effectively identify potential hazardous areas and provide a basis for the development of targeted disaster prevention and mitigation strategies. However, the current urban flood risk assessment research is mainly based on the flood inundation or indicator evaluation system, the lack of inundation characteristic and hazard-bearing body socio-economic attributes of the comprehensive consideration, resulting in the assessment results and the actual flood risk there is a certain deviation. Therefore, this study integrated urban hydrological and hydrodynamic simulation technology and Fuzzy Matter-Element (FME) theory, proposed a comprehensive flood risk assessment method that takes flood inundation and socio-economic vulnerability into account, and quantitatively evaluates the flooding risk of Zhengzhou City under different rainfall return periods. The results indicate that low-risk zones are primarily located in the peripheral and fringe regions of Zhengzhou, whereas high and very-high risk zones are predominantly situated in the central urban area, particularly in the western Jinshui District, northeastern Erqi District, and northern Guancheng District. These areas are the old urban areas of Zhengzhou City which were constructed earlier, and are characterized by low drainage system construction standards, aging pipe networks, dense population and road networks, and high economic value. The results contribute methodological guidance and decision-making reference for urban flood management and control.

Deep learning models are widely used for urban flood prediction, but current research lacks a clear explanation of how indicator weight changes affect model accuracy. This study incorporated the attention mechanism between the convolutional and fully connected layers of the convolutional neural network (CNN) to enable the model to focus on critical flood-inducing factors, and employed the particle swarm optimization (PSO) to optimize the key hyperparameters (for example, the number of filters and learning rate). Furthermore, we employed Shapley additive explanation (SHAP) to analyze how flood-inducing indicator weight changes affect prediction accuracy. The model was tested on Haidian Island, China. The Nash-Sutcliffe efficiency (NSE) coefficient of the CNN model is 0.9287. After incorporating the attention mechanism into the CNN and optimizing the hyperparameters using PSO, the NSE is improved to 0.9503. The model demonstrates higher accuracy in predicting larger inundations, with the NSE for the 100-year return-period flood reaching 0.9535, compared to 0.8341 for the 5-year return period. Interpretability analysis shows that elevation is the most important flood-inducing factor, accounting for 44% of the total importance, followed by tidal levels, which account for 33%. The attention mechanism increases the weights of important flood-inducing factors (for example, elevation, tide level); after hyperparameter optimization, the model achieves more comprehensive learning, increasing the weights of the rainfall indicators that are neglected by the unoptimized model, and these weight changes improve the accuracy of the model. The research revealed the impacts of different flood-inducing factors on flooding and the influence of indicator weight changes on model accuracy.

Climate change and urbanization are altering urban flood pressure, raising questions about whether urban adaptive capacity can keep pace with these changes. This study examined flood pressure, adaptive capacity, and their coordination across 14 cities in the core development area of the Central Plains Urban Agglomeration, China, from 2016 to 2023. The entropy weight method, coupling coordination degree model, and four-quadrant classification were integrated to assess spatiotemporal patterns and transitions in pressure–adaptation combinations. The regional flood pressure index increased overall from 0.2549 in 2016 to 0.3028 in 2023, with fluctuations, while the adaptive capacity index rose steadily from 0.2730 to 0.5293. The regional mean coupling coordination degree increased from 0.5917 to 0.7626, and intercity differences narrowed. Pressure–adaptation combinations shifted from a predominance of low-adaptation types toward high-adaptation types: 13 of 14 cities were classified as low-adaptation types in 2016, whereas all 14 were in high-adaptation categories by 2023, including nine high-pressure–high-adaptation and five low-pressure–high-adaptation cities. These findings provide a scientific basis for differentiated urban flood management and adaptive capacity planning.