Real-time prediction of subgrade settlement caused by shield tunneling is crucial in engineering applications. However, data-driven methods are prone to overfitting, while physical methods rely on certain assumptions, making it difficult to select satisfactory parameters. Although there are currently physics-data-driven methods, they typically require extensive iterative calculations with physical models, which makes them unavailable for real-time prediction. This paper introduces a lightweight physics-data-driven method for predicting subgrade settlement caused by shield tunneling. The core concept involves using a single calculation of the physical model to provide a weak constraint. Considering the influence of various construction parameters, the physical model can calculate the time-dependent evolution of railway subgrade settlement induced by shield tunneling beneath based on the Mindlin solution. In the physical model, the time parameters are introduced through coordinate transformation. It models soil loss due to shield tunneling as the gradual release of stress in the surrounding soil, treating the released stress as an equivalent additional load on the tunnel’s surrounding soil. Then, a deep learning network is then designed to capture spatiotemporal correlations based on ConvLSTM. By iteratively incorporating real-time data, the learning of physical constraints is further enhanced. This method combines the predictive power of data-driven method with the reasonable constraints of physical laws, validated a good performance in a practical project. The results demonstrate that this method meets real-time prediction requirements in engineering, achieving a coefficient of determination of 0.980, a root mean square error of 0.22 mm, and a mean absolute error of 0.15 mm. Furthermore, it outperforms both physical and data-driven models and demonstrates good generalization performance. This study provides effective guidance for engineering practices.