| description abstract | The construction of metro tunnels in response to global urban traffic congestion presents challenges such as face stability, excessive cutter wear, cutter head clogging, and groundwater ingress during excavation. Surface settlement (SS) resulting from tunneling is a common issue that can lead to cracks in existing structures. Existing empirical and numerical solutions have limitations, including low accuracy and time-consuming calculations. To overcome these challenges, this study proposes the use of a combination of well-established theories and machine learning (ML), specifically theory-guided machine learning (TGML), to predict SS caused by twin tunnels. The TGML strategy incorporates data verification from a case study in Malaysia and data generation from numerical analysis. Within the realm of SS, tree-based techniques—including random forest, adaptive boost, gradient boosting tree, extreme gradient boost, light gradient boosting, and categorical boosting (CatBoost)—were employed in this study. The tree-based ML algorithms consistently demonstrated robust predictive performance, with coefficient of determination (R2) values consistently exceeding 0.9 and low root mean square error (RMSE) and mean absolute error (MAE) with high variance accounted for (VAF). Among these algorithms, CatBoost exhibited the highest R2 showcasing the lowest errors and highest explanatory power on both training and testing data which outperformed its counterparts. This observation highlights CatBoost’s superior predictive capabilities compared to other tree-based algorithms, emphasizing its efficiency in capturing underlying patterns in the data set. TGML emerges as an effective, easy-to-apply, and practical solution for predicting SS induced by twin tunnels in future projects. | |
