Intense summer rainstorms can result in short-term urban flooding, leading to localized groundwater level rise and subsequent floor cracking and leakage in basements. Rational control of the surrounding water level is crucial for addressing existing basement leaks caused by short-term urban flooding. In this study, a combined approach of interception and seepage control using waterproof curtains and negative-pressure wells is proposed. Four different scenarios were considered, and experimental and numerical investigations were conducted on a 1.2 m x 1.2 m x 1.1 m model. The study analyzed the influence of factors such as water content, pore water pressure, soil properties, waterproof curtain insertion depth, and length of the filter in the negativepressure well on controlling the upward water level in the basement. The results showed that the installation of waterproof curtains alone can impede rainwater infiltration into the basement, delaying its penetration by approximately 48 h. The combined approach of interception and seepage control outperformed the sole use of waterproof curtains, with the reduction in water level becoming smaller as the insertion depth of the waterproof curtain increased. The reduction in water level decreased at a slower rate with increasing waterproof curtain insertion depth. The recommended waterproof curtain insertion ratio was equal to or greater than 83.5 %, while the filter length ratio in the negative pressure well should be less than 64 %. Compared to natural seepage drainage, negative-pressure pumping could maintain the basement floor's water content within the initial range 32 h earlier. The water-blocking and depressurization effect is best in sandy soil and worst in clay. Water-blocking and depressurization provide a new approach for controlling the uplift caused by summer urban waterlogging, especially offering a new method for controlling leaks in the basement.

This study introduces a cutting-edge, high-resolution tool leveraging the predictive prowess of convolutional neural networks to advance the field of hazard assessment in urban pluvial flooding scenarios. The tool uniquely accounts for the high heterogeneity of urban space and the potential impact of complex climate scenarios, which are often underestimated by traditional data-reliant methods. Employing Shenzhen as a case study, the model showcased superior accuracy, resilience, and interpretability, illuminating potential flood hazards. The performance analysis shows that the model can accurately predict the vast majority of urban flood depths, but has errors in extreme flood predictions (depths greater than 35 cm). Findings underscore escalating flood impacts under enhanced scenario loads, with western and central Shenzhen-regions rife with construction-highlighted as particularly vulnerable. Under the most severe matrix scenario (Scenario 25), economic losses are estimated to be about $25,484 million. These commercial and residential hotspots are anticipated to suffer maximum economic loss, with these two areas accounting for 39.6% and 25.1% of the total losses, necessitating reinforced mitigation efforts, especially during extreme rainfall events and high soil saturation levels. In addition, the flooding control strategies should prioritize the reduction of flood inundation areas and integrate functionally oriented land use characteristics in their development. By aiding in the precise identification of flood-prone areas, this research expedites the development of efficient evacuation plans, bolsters urban sustainability, and augments climate resilience, ultimately mitigating flood-induced economic tolls.