With global climate change and accelerating urbanization， urban waterlogging disasters have become increasingly frequent and severe， making rapid waterlogging forecasting a key research focus. Compared with traditional numerical simulation methods， deep-learning-based artificial intelligence （AI） models can significantly improve computational efficiency. However， they often encounter training bottlenecks due to limited GPU memory. To address this， this study proposes an efficient AI urban waterlogging forecasting model named as UNet-KAN-SR. This model first employs the UNet-KAN module to efficiently simulate the spatio-temporal evolution of waterlogging over low-resolution grids， and then leverages the SR （super-resolution） module， along with high-resolution surface information， to progressively map the low-resolution waterlogging distribution to high-resolution distribution. This spatiotemporal decoupling strategy can ensure simulation accuracy while substantially reducing the computational resources required for training AI models. Experimental results demonstrate that the UNet-KAN-SR model can simulate a 3-hour waterlogging distribution within 3 minutes， achieving a root mean square error （RMSE） of 9 cm and a probability of detection （POD） of 0.84， demonstrating high accuracy and computational efficiency. Further analysis reveals that the integration of the KAN module can significantly enhance the model’s capability to capture nonlinear flood dynamics when compared with common CNN modules， reducing RMSE by 10%. Furthermore， this study finds that incorporating high-resolution features， such as surface topography， building coverage ratio， and land use， can significantly improve the simulation performance but performance improvement is similar under different feature combinations. This indicates that by optimizing the combination of input features during AI model construction， training speed can be enhanced， modeling costs controlled， and efficient intelligent forecasting achieved.

Shield tunnel excavation beneath levees induces settlement deformation that poses a direct threat to levee integrity. Focusing on the planar oblique crossing between a shield tunnel and an embankment， this study investigates the effect of the horizontal oblique angle on the parameters of the classical Peck formula within an oblique coordinate framework. A modified approach for determining Peck formula parameters， incorporating a correction for the horizontal oblique angle， is proposed. Based on the Huanggang Road Tunnel project crossing beneath the Yellow River in Jinan， a field monitoring system was established to measure post-construction embankment settlement. The ground loss ratio and settlement trough width parameter， considering the influence of the horizontal oblique angle， were back-analyzed using the least squares regression method. The results show that the average settlement trough width parameter for the embankment strata in the Jinan section of the Yellow River is approximately 0.43， and the average ground loss ratio is about 0.31%. Neglecting the horizontal oblique angle leads to an overestimation of these parameters by approximately 12%， which may result in improper judgments regarding code compliance. Validation using measured data from the Jiluo Road Tunnel crossing beneath the Yellow River demonstrates that the proposed parameters offer satisfactory predictive capability and practical engineering applicability.