Due to the complex interaction of urban and mountainous floods, assessing flood susceptibility in mountainous urban areas presents a challenging task in environmental research and risk analysis. Data-driven machine learning methods can evaluate flood susceptibility in mountainous urban areas lacking essential hydrological data, utilizing remote sensing data and limited historical inundation records. In this study, two ensemble learning algorithms, Random Forest (RF) and XGBoost, were adopted to assess the flood susceptibility of Kunming, a typical mountainous urban area prone to severe flood disasters. A flood inventory was created using flood observations from 2018 to 2022. The spatial database included 10 explanatory factors, encompassing climatic, geomorphic, and anthropogenic factors. Artificial Neural Network (ANN) and Support Vector Machine (SVM) were selected for model comparison. To minimize the influence of expert opinions on model training, this study employed a strategy of uniformly random sampling in historically non-flooded areas for negative sample selection. The results demonstrated that (1) ensemble learning algorithms offer higher accuracy than other machine learning methods, with RF achieving the highest accuracy, evidenced by an area under the curve (AUC) of 0.87, followed by XGBoost at 0.84, surpassing both ANN (0.83) and SVM (0.82); (2) the interpretability of ensemble learning highlighted the differences in the potential distribution of the training data’s positive and negative samples. Feature importance in ensemble learning can be utilized to minimize human bias in the collection of flooded-site samples, more targeted flood susceptibility maps of the study area’s road network were obtained; and (3) ensemble learning algorithms exhibited greater stability and robustness in datasets with varied negative samples, as evidenced by their performance in F1-Score, Kappa, and AUC metrics. This paper further substantiates the superiority of ensemble learning in flood susceptibility assessment tasks from the perspectives of accuracy, interpretability, and robustness, enhances the understanding of the impact of negative samples on such assessments, and optimizes the specific process for urban flood susceptibility assessment using data-driven methods.

Urban flooding can be predicted by using different modeling approaches. This study considered different methods of modeling the dynamic flow interactions between pipe systems and surface flooding in urban areas. These approaches can be divided into two categories based on surface runoff collection units. This paper introduces a new hydrodynamic model that couples the storm water management model and the 2D overland model. The model’s efficiency was validated based on the aforementioned experimental dataset; agreement was verified by correlation values above 0.6. Additionally, this study used different approaches and compared their accuracy in predicting flooding patterns. The results show that the use of sub-catchments to model the collection of surface runoff was not predictive of the inundation process, indicating a lower goodness of fit with the recorded values than that of adopting cells. Moreover, to determine which method of adopting cells to collect runoff could better predict rainstorm-induced inundation, an error and correlation analysis was conducted. The analysis found low error and high correlation, suggesting that inundation can be effectively predicted by the new approaches. Ultimately, this study contributes to existing work on numerical analysis of the interaction methods of urban flooding.

Due to the existence of drainage networks, urban areas have formed their own hydrological mechanism. The pretreatment of complex and elaborate drainage network data has become a challenging step in building an urban hydrological model. This study proposes a network-combing method based on the potential outfall mechanism for an urban drainage system, analyzes the topological structure of the underground network, and generates a subcatchment based on the potential outfall (SBPO). Two hydrological methods are constructed for a typical region in Kunming, Yunnan Province, China. The results show that: The network-combing method of potential outfall mechanisms can well complete the sorting work of a drainage network system and can clarify the relative independent relationship. The SBPO method basically agrees with the SWMM constructed with a high-resolution network in terms of runoff volume, the peak value and the duration of the outflow process at the outfall. However, the subcatchment by the potential outfall mechanism can help to understand the service partition, and the calculation cost is greatly reduced. The method emphasizes the importance of the influence of a drainage system on water confluence, which can help to better understand the process of runoff in urban areas.

Identifying the patterns of rainstorms is essential for improving the precision and accuracy of flood forecasts and constructing flood disaster prevention systems. In this study, we used a manifold learning algorithm method of machine learning to analyze rainstorm patterns. We analyzed the spatial–temporal characteristics of heavy rain in Beijing and Shenzhen. The results showed a strong correlation between the spatial–temporal pattern of rainstorms and underlying topography in Beijing. However, in Shenzhen, the spatial–temporal distribution characteristics of rainstorms were more closely related to the source of water vapor causing the rainfall, and the variation in characteristics was more complex and diverse. This method may be used to quantitatively describe the development and dynamic spatial–temporal patterns of rainfall. In this study, we found that spatial–temporal rainfall distribution characteristics, extracted by machine learning technology could be explained by physical mechanisms consistent with the climatic characteristics and topographic conditions of the region.

Small reservoirs in hilly areas serve as critical water conservancy infrastructure, playing an essential role in flood control, irrigation, and regional water security. However, dam-break events pose significant risks to downstream urban areas, threatening the sustainability and resilience of cities. This study takes Guangyuan City as a case study and employs numerical simulation methods—including dam-break modeling, hydrological modeling, and hydrodynamic modeling—to analyze the impact of dam-break floods on downstream urban regions. The results reveal that dam failure in small reservoirs can cause peak flood velocities exceeding 15 m/s, severely endangering urban infrastructure, ecosystems, and public safety. Additionally, for reservoirs with large catchment areas, dam-break floods combined with rainfall-induced flash floods may create compound disaster effects, intensifying urban flood risks. These findings underscore the importance of sustainable reservoir management and integrated flood risk strategies to enhance urban resilience and reduce disaster vulnerability. This research contributes to sustainable development by providing scientific insights and practical support for flood risk mitigation and resilient infrastructure planning in mountainous regions.

Cities along rivers are threatened by floods and waterlogging, and the relationship between rainstorms and floods is complex. The temporal and spatial distributions of rainstorms directly affect flood characteristics. The location of the rainstorm center determines the flood peaks, volumes, and processes. In this study, machine learning algorithms were introduced to analyze the rain–flood relationship in Luzhou City, Sichuan Province, China. The spatial and temporal patterns of rainstorms in the region were classified and extracted, and flood characteristics generated by various types of rainstorms were analyzed. In the first type, the center of the rainstorm was in the upper reaches of the Tuojiang River, and the resulting flood caused negligible damage to Luzhou. In the second type, the center of the rainstorm occurred in the Yangtze River Basin. Continuously high water levels in the Yangtze River, combined with local rainfall, supported urban drainage. In the third type, the rainstorm center occurred in the upper reaches of the Yangtze and Tuojiang rivers. During the flooding, rainfall from Yangtze River and Tuojiang River moved towards Luzhou together. The movement of the rainstorm center was consistent with the flood routing direction of the Yangtze and Tuojiang rivers, both of which continued to have high water levels. The flood risk is extremely high in this case, making it the riskiest rainfall process requiring prevention.