Global climate change and sea level rise have led to increased losses from flooding. Accurate prediction of floods is essential to mitigating flood losses in coastal cities. Physically based models cannot satisfy the demand for real-time prediction for urban flooding due to their computational complexity. In this study, we proposed a hybrid modeling approach for rapid prediction of urban floods, coupling the physically based model with the light gradient boosting machine (LightGBM) model. A hydrological–hydraulic model was used to provide sufficient data for the LightGBM model based on the personal computer storm water management model (PCSWMM). The variables related to rainfall, tide level, and the location of flood points were used as the input for the LightGBM model. To improve the prediction accuracy, the hyperparameters of the LightGBM model are optimized by grid search algorithm and K-fold cross-validation. Taking Haidian Island, Hainan Province, China as a case study, the optimum values of the learning rate, number of estimators, and number of leaves of the LightGBM model are 0.11, 450, and 12, respectively. The Nash-Sutcliffe efficiency coefficient (NSE) of the LightGBM model on the test set is 0.9896, indicating that the LightGBM model has reliable predictions and outperforms random forest (RF), extreme gradient boosting (XGBoost), and k-nearest neighbor (KNN). From the LightGBM model, the variables related to tide level were analyzed as the dominant variables for predicting the inundation depth based on the Gini index in the study area. The proposed LightGBM model provides a scientific reference for flood control in coastal cities considering its superior performance and computational efficiency.

Flood risk assessment is an important tool for disaster warning and prevention. In this study, an integrated approach based on a D-number-improved analytic hierarchy process (D-AHP) and a self-organizing map (SOM) clustering algorithm are proposed for urban flooding risk assessment. The urban flood inundation model and geographic information system (GIS) technology were used to quantify the assessment indices of urban flood risk. The D-AHP approach was adopted to determine the weights of the indices, which effectively makes up for the shortcomings of the AHP in dealing with uncertain evaluation information (such as fuzzy and incomplete information). In addition, the SOM clustering algorithm was applied to determine the flood risk level. It is a data-driven approach that avoids the subjective determination of a flood risk classification threshold. The proposed approach for flood risk assessment was implemented in Zhengzhou, China. The flood risk was classified into five levels: highest risk, higher risk, medium risk, lower risk, and the lowest risk. The proportion of the highest risk areas was 9.86%; such areas were mainly distributed in the central and eastern parts of the Jinshui District, the eastern part of the Huiji District, and the northeastern part of the Guancheng District, where there were low terrain and serious waterlogging. The higher risk areas accounted for 24.26% of the study area, and were mainly distributed in the western and southern parts of the Jinshui District, the southern part of the Huiji District, the middle and eastern parts of the Zhongyuan District, the northeastern part of the Erqi District, and the northwestern part of the Guancheng District, which consisted of economically developed areas of dense population and buildings, matching well with historical flooding events. To verify the effectiveness of the proposed approach, traditional approaches for risk assessment were compared. The comparison indicated that the proposed approach is more reasonable and accurate than the traditional approaches. This study showed the potential of a novel approach to flood risk assessment. The results can provide a reference for urban flood management and disaster reduction in the study area.

The USEPA (United States Environmental Protection Agency) Storm Water Management Model (SWMM) is one of the most extensively implemented numerical models for simulating urban runoff. Parameter optimization is essential for reliable SWMM model simulation results, which are heterogeneously sensitive to a variety of parameters, especially when involving complicated simulation conditions. This study proposed a Genetic Algorithm-based parameter optimization method that combines the Morris screening method with the generalized likelihood uncertainty estimation (GLUE) method. In this integrated methodology framework, the Morris screening method is used to determine the parameters for calibration, the GLUE method is employed to narrow down the range of parameter values, and the Genetic Algorithm is applied to further optimize the model parameters by considering objective constraints. The results show that the set of calibrated parameters, obtained by the integrated Morris and GLUE methods, can reduce the peak error by 9% for a simulation, and then the multi-objective constrained Genetic Algorithm reduces the model parameters’ peak error in the optimization process by up to 6%. During the validation process, the parameter set determined from the combination of both is used to obtain the optimal values of the parameters by the Genetic Algorithm. The proposed integrated method shows superior applicability for different rainfall intensities and rain-type events. These findings imply that the automated calibration of the SWMM model utilizing a Genetic Algorithm based on the combined parameter set of both has enhanced model simulation performance.

The public health risk caused by urban floods is a global concern. Flood risks are amplified by the interaction of rainfall and storm tides in coastal cities. In this study, we investigate the flood risks of rainfall and storm tides coupling statistical and hydrodynamic models and evaluate the influence of different parameter estimation methods and bivariate return periods (RPs) on flood risks in the coastal city. The statistical model is used to obtain the bivariate design of rainfall and storm tides with the integration of copula function, most-likely weight function and Monte Carlo simulation method. The bivariate designs are adopted as the input boundaries for the hydrodynamic model established by Personal Computer Storm Water Management Model (PCSWMM), and the flood risk is evaluated by the hydrodynamic model. Subsequently, the influence of different parameter estimation approaches (that is, parametric and non-parametric) and bivariate RPs (that is, co-occurrence RP, joint RP, and Kendall RP) on bivariate designs and flood risks are investigated. With Haikou coastal city in China as the case study, the results show that: (1) Gumbel copula is the best function to describe the correlation structure between rainfall and storm tides for the parametric and non-parametric approaches, and the non-parametric approach is a better fit for the observed data; (2) when the Kendall RP is large (more than 100 years), the flood risk is underestimated with an average of 17% by the non-parametric estimation, and the parametric estimation approach is recommended as it is considered the most unfavorable scenario; (3) the types of bivariate RP have the important impact on the flood risk. When there is no specific application need, the Kendall RP can be adopted as the bivariate design standard of flooding facilities since it can describe the dangerous areas more accurately for multivariate scenario. The results can provide references for reasonable flood risk assessment and flooding facility design in coastal cities.

Global climate change and accelerated urbanization have intensified extreme rainfall events, exacerbating urban flood risks. Although data-driven models have shown potential in urban flood prediction, the ability of single models to capture complex nonlinear relationships and their sensitivity to hyperparameters still limit prediction accuracy. To address these challenges, this study proposes an urban flood prediction model by integrating Transformer, Long Short-Term Memory (LSTM), and Sparrow Search Algorithm (SSA), combining Transformer’s global feature extraction with LSTM’s temporal modeling. The SSA was adopted to optimize hyperparameters for the Transformer-LSTM model. Dropout and early stopping techniques were adopted to mitigate overfitting. Applied to Zhengzhou city of Henan province, China, the model achieves a Nash-Sutcliffe Efficiency (NSE) of 0.971, indicating that the proposed model has high prediction performance for urban flooding. The experimental results demonstrate that the Transformer-LSTM-SSA model outperforms the standalone Transformer, LSTM, and Transformer-LSTM models by 12.9%, 10.1%, and 2.9% in NSE accuracy, respectively, while reducing MAE by 62.12%, 56.9%, and 34.21%, respectively, and MAPE by 21.69%, 22.2%, and 10.89%, respectively. Furthermore, the proposed model exhibits enhanced stability and superior generalization capability. The Transformer-LSTM-SSA model exhibits superior performance among the comparative methods, thereby demonstrating the model’s viability for providing a reliable solution for real-time flood prediction and early warning.

The uneven spatial and temporal distribution of water resources has consistently been one of the most significant limiting factors for social development in many regions. Furthermore, with the intensification of climate change, this inequality is progressively widening, posing a critical challenge to the sustainable development of human societies. The construction of large-scale water projects has become one of the crucial means to address the contradictions between water supply and demand. Thus, evaluating the functional aspects of water source network structures and systematically planning the layout of engineering measures in a scientifically reasonable manner are pressing issues that require urgent attention in current research efforts. Addressing this, our study takes the Erhai Lake basin and the surrounding areas in southwest China as the study area and combines landscape ecology and network analysis theory methods to propose a water supply network analysis method that takes into account both structure and node characteristics. Based on this methodology, we analyze the connectivity characteristics of water supply networks in the Erhai region under current (2020) and future (2035) planning scenarios. The results show that there were 215 nodes and 216 links in the water supply network of the Erhai Lake basin in 2020; with the implementation of a series of water conservancy projects, the planned 2035 water supply network will increase by 122 nodes and 163 links, and the connectivity of the regional water network will be significantly improved. Also, we identify some key nodes in the network, and the results show that the water supply network in 2035 will have obvious decentralization characteristics compared with that in 2020. And, based on the network degradation analysis, we find that with the implementation of engineering measures, the resilience of the water supply network will be significantly strengthened by 2035, with stronger risk tolerance. This study extends the quantitative representation of water source network characteristics, which can provide a useful reference for water network structure planning and optimization.