Machine learning-based forecasting of ground surface settlement induced by metro shield tunneling construction

Urban rail transit systems, represented by subways, have significantly alleviated the traffic pressure brought by urbanization and have addressed issues such as traffic congestion. However, as a commonly used construction method for subway tunnels, shield tunneling inevitably disturbs the surrounding soil, leading to uneven ground surface settlement, which can impact the safety of nearby buildings. Therefore, it is crucial to promptly obtain and predict the ground surface settlement induced by shield tunneling construction to enable safety warnings and evaluations. This study collects multi-point surface settlement data from monitoring sections and proposes a data preprocessing method based on tangent circles to transform discrete monitored data into continuous and smooth data. On this basis, the Particle Swarm Optimization (PSO) algorithm is employed to optimize a Back Propagation Neural Network(BPNN) for the subsequent prediction of ground surface settlement. The influence of network structure and prediction mode on prediction accuracy is investigated. The study predicts and verifies the settlement over a 5-day period during both the slow settlement stage and the stable stage to evaluate the predictive performance of the proposed method. The maximum relative error of the prediction based on the data preprocessing method and PSO-BP algorithm is 0.46%, demonstrating a good fitting effect. The study indicates that this method can provide a valuable reference for safety warnings and control of ground surface settlement during shield tunneling construction.