Enhancing ground loss rate prediction in soft-soil shield tunneling—A synergistic approach of Peck back analysis and eXtreme Gradient Boosting and Bayesian optimization

Abstract Due to the characteristics of soft soil, ground settlement is highly prone to occur in the construction process, and ground loss is one of the essential factors causing ground settlement in shield tunneling. This study calculates the ground loss rate of some shielded soft-soil sections in the Hangzhou area using Peck’s back analysis method. It examines the influences of the geological parameters and the geometric parameters of a tunnel on the ground loss rate through data analysis to develop a model for predicting the ground loss rate in soft-soil areas. Then the model for predicting the ground loss rate based on eXtreme Gradient Boosting (XGBoost) and Bayesian optimization is established, and the prediction method of the ground loss rate, combining the surface settlement value, detailed geological parameters, the geometric parameters of the tunnel, and construction parameters, is innovatively proposed. The results show that the soil properties and the grouting factors of the excavation face affect the duration of the instantaneous settlement of the ground surface. There is a specific correlation between the depth-to-diameter ratio, the coefficient of variation in the advancing speed of the shield machine, the maximum surface subsidence, and the ground loss rate. The prediction model of the ground loss rate based on the synergistic approach of Peck back analysis and eXtreme Gradient Boosting and Bayesian optimization has high reliability in soft-soil layers, and this method can provide a specific reference for predicting construction risk in related projects.