The prediction of monthly rainfall is greatly beneficial for water resources management and flood control projects. Machine learning (ML) techniques, as an increasingly popular approach, have been applied in diverse climatic regions, showing their respective superiority. On top of that, the ensemble learning model that synthesizes the advantages of different ML models deserves more attention. In this study, an ensemble learning model based on stacking approach was proposed. Four prevalent ML models, namely k-nearest neighbors (KNN), extreme gradient boosting (XGB), support vector regression (SVR), and artificial neural networks (ANN) are taken as base models. To combine the outputs from the base models, the weighting algorithm is used as second-layer learner to generate predictions. Large-scale climate indices, large-scale atmospheric variables, and local meteorological variables were used as predictors. R², RMSE and MAE, were used as evaluation metrics. The results show that the performance of base models varied among the nine stations in the Taihu Basin, while the stacking approach generally performed better than the four base models. The stacking model showed better performance in spring and winter than in summer and autumn. During wet months, the accuracy of model prediction varied more significantly. On the whole, based on performance evaluation measures, it is concluded that the proposed stacking ensemble multi-ML model can provide a flexible and reasonable prediction framework applicable to other regions.

We examine urban flood response through data‐driven analyses for a diverse sample of “small” watersheds (basin scale ranging from 7.0 to 111.1 km²) in the Charlotte Metropolitan region. These watersheds have experienced extensive urbanization and suburban development since the 1960s. The objective of this study is to develop a broad characterization of land surface and hydrometeorological controls of urban flood hydrology. Our analyses are based on peaks‐over‐threshold flood data developed from USGS streamflow observations and are motivated by problems of flood hazard characterization for urban regions. We examine flood‐producing rainfall using high‐resolution (1 km²spatial resolution and 15 min time resolution), bias‐corrected radar rainfall fields that are developed through the Hydro‐NEXRAD system. The analyses focus on the 2001–2015 period. The results highlight the complexities of urban flood response. There are striking spatial heterogeneities in flood peak magnitudes, response times, and runoff ratios across the study region. These spatial heterogeneities are mainly linked to watershed scale, the distribution of impervious cover, and storm water management. Contrasting land surface properties also determine the mixture of flood‐generating mechanisms for a particular watershed. Warm‐season thunderstorm systems and tropical cyclones are main flood agents in Charlotte, with winter/spring storms playing a role in less‐urbanized watersheds. The mixture of flood agents exerts a strong impact on the upper tail of flood frequency distributions. Antecedent watershed wetness plays a minor role in urban flood response, compared with less‐urbanized watersheds. Implications for flood hazard characterization in urban watersheds and for advances in flood science are discussed.

The role of rainfall space–time structure, as well as its complex interactions with land surface properties, in flood response remains an open research issue. This study contributes to this understanding, specifically for small (<15 km²) urban watersheds. Using a flood frequency analysis framework that combines stochastic storm transposition (SST)-based rainfall scenarios with the physically based distributed Gridded Surface Subsurface Hydrologic Analysis (GSSHA) model, we examine the role of rainfall spatial and temporal variability in flood frequency across drainage basin scales in the highly urbanized Dead Run watershed (14.3 km²), Maryland, USA. The results show the complexities of flood response within several subwatersheds for both short (<50 years) and long (>100 years) rainfall return periods. The impact of impervious area on flood response decreases with increasing rainfall return period. For extreme storms, the maximum discharge is closely linked to the spatial structure of rainfall, especially storm core spatial coverage. The spatial heterogeneity of rainfall increases flood peak magnitudes by 50 % on average at the watershed outlet and its subwatersheds for both small and large return periods. The framework of SST–GSSHA-coupled frequency analysis also highlights the fact that spatially distributed rainfall scenarios are needed in quick-response flood frequency, even for relatively small basin scales.

The impact of spatial and temporal variability of rainfall on hydrological response remains poorly understood, in particular in urban catchments due to their strong variability in land use, a high degree of imperviousness and the presence of stormwater infrastructure. In this study, we analyze the effect of storm scale, position and movement in relation to basin scale and flow-path network structure on urban hydrological response. A catalog of 279 peak events was extracted from a high-quality observational dataset covering 15 years of flow observations and radar rainfall data for five (semi)urbanized basins ranging from 7.0 to 111.1 km² in size. Results showed that the largest peak flows in the event catalog were associated with storm core scales exceeding basin scale, for all except the largest basin. Spatial scale of flood-producing storm events in the smaller basins fell into two groups: storms of large spatial scales exceeding basin size or small, concentrated events, with storm core much smaller than basin size. For the majority of events, spatial rainfall variability was strongly smoothed by the flow-path network, increasingly so for larger basin size. Correlation analysis showed that position of the storm in relation to the flow-path network was significantly correlated with peak flow in the smallest and in the two more urbanized basins. Analysis of storm movement relative to the flow-path network showed that direction of storm movement, upstream or downstream relative to the flow-path network, had little influence on hydrological response. Slow-moving storms tend to be associated with higher peak flows and longer lag times. Unexpectedly, position of the storm relative to impervious cover within the basins had little effect on flow peaks. These findings show the importance of observation-based analysis in validating and improving our understanding of interactions between the spatial distribution of rainfall and catchment variability.

Shanghai is the economic center of China, but is vulnerable to threats from natural hazards. Along with climate change and fast urbanization, flood is the inevitable deterrent to the city’s development. Flood hazard mitigation is considered as a critical work for the city government to ensure safety, maintain sustainable development, and reduce damages and losses. A comprehensive overview of flood management systems and considerations are of great value. So in this paper, the major causes of flooding in Shanghai are investigated and their characteristics are analyzed. Based on the new strategy of flood management aiming at reducing future impacts of flood disaster, the authors’ considerations about the current flood control measurements in Shanghai are demonstrated, especially at the aspects of flood design standard and the potential threats existing in the engineering system and nonengineering system. Though it is clear that Shanghai has made remarkable achievements in flood management, flood management should be conducted from a strategic perspective of disaster prevention.