Chongzhi Wu

Accurate assessment of undrained shear strength (USS) for soft sensitive clays is a great concern in geotechnical engineering practice. This study applies novel data-driven extreme gradient boosting (XGBoost) and random forest (RF) ensemble learning methods for capturing the relationships between the USS and various basic soil parameters. Based on the soil data sets from TC304 database, a general approach is developed to predict the USS of soft clays using the two machine learning methods above, where five feature variables including the preconsolidation stress (PS), vertical effective stress (VES), liquid limit (LL), plastic limit (PL) and natural water content (W) are adopted. To reduce the dependence on the rule of thumb and inefficient brute-force search, the Bayesian optimization method is applied to determine the appropriate model hyper-parameters of both XGBoost and RF. The developed models are comprehensively compared with three comparison machine learning methods and two transformation models with respect to predictive accuracy and robustness under 5-fold cross-validation (CV). It is shown that XGBoost-based and RF-based methods outperform these approaches. Besides, the XGBoost-based model provides feature importance ranks, which makes it a promising tool in the prediction of geotechnical parameters and enhances the interpretability of model.

Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity, compared to the traditional methods. This paper presents an overview of some soft computing techniques as well as their applications in underground excavations. A case study is adopted to compare the predictive performances of soft computing techniques including eXtreme Gradient Boosting (XGBoost), Multivariate Adaptive Regression Splines (MARS), Artificial Neural Networks (ANN), and Support Vector Machine (SVM) in estimating the maximum lateral wall deflection induced by braced excavation. This study also discusses the merits and the limitations of some soft computing techniques, compared with the conventional approaches available.

Estimating surface settlement induced by excavation construction is an indispensable task in tunneling, particularly for earth pressure balance (EPB) shield machines. In this study, predictive models for assessing surface settlement caused by EPB tunneling were established based on extreme gradient boosting (XGBoost), artificial neural network, support vector machine, and multivariate adaptive regression spline. Datasets from three tunnel construction projects in Singapore were used, with main input parameters of cover depth, advance rate, earth pressure, mean standard penetration test (SPT) value above crown level, mean tunnel SPT value, mean moisture content, mean soil elastic modulus, and grout pressure. The performances of these soft computing models were evaluated by comparing predicted deformation with measured values. Results demonstrate the acceptable accuracy of the model in predicting ground settlement, while XGBoost demonstrates a slightly higher accuracy. In addition, the ensemble method of XGBoost is more computationally efficient and can be used as a reliable alternative in solving multivariate nonlinear geo-engineering problems.