Machine-Learning-Based Prediction of Gushing-Induced Ground Disturbance Around Shield Tunnels

Water-soil gushing caused by tunnel leakage can induce severe ground disturbance and threaten the safety of shield tunnels, yet rapid prediction remains difficult because high-fidelity numerical simulations are computationally expensive. This study develops an interpretable machine-learning framework for predicting gushing-induced ground disturbance around shield tunnels based on a validated two-phase Material Point Method database. Six governing variables are considered, including the tunnel depth ratio, gushing location, soil friction angle, Young’s modulus, intrinsic permeability, and soil gushing mass. Three representative response variables were selected, namely the maximum ground settlement, flow-zone width, and flow-zone centroid angle. Five algorithms, including MLP, RF, XGBoost, SVR, and Ridge, were established and compared, with hyperparameters optimised using Optuna. The results show that nonlinear models consistently outperform the linear baseline, among which MLP, RF, and XGBoost achieve the best overall accuracy and robustness. Error-distribution analysis further indicates that MLP and RF yield the highest proportion of low-error predictions. SHAP interpretation shows that SGM is the dominant factor governing maximum settlement and flow-zone width, whereas gushing location primarily controls the flow-zone centroid angle. The proposed framework provides an efficient and physically interpretable surrogate for rapid hazard assessment of gushing-induced ground disturbance in shield tunnelling.