Estimation of diaphragm wall deflections for deep braced excavation in anisotropic clays using ensemble learning

This paper adopts the NGI-ADP soil model to carry out finite element analysis, based on which the effects of soft clay anisotropy on the diaphragm wall deflections in the braced excavation were evaluated. More than one thousand finite element cases were numerically analyzed, followed by extensive parametric studies. Surrogate models were developed via ensemble learning methods (ELMs), including the eXtreme Gradient Boosting (XGBoost), and Random Forest Regression (RFR) to predict the maximum lateral wall deformation (delta(hmax)). Then the results of ELMs were compared with conventional soft computing methods such as Decision Tree Regression (DTR), Multilayer Perceptron Regression (MLPR), and Multivariate Adaptive Regression Splines (MARS). This study presents a cuffing-edge application of ensemble learning in geotechnical engineering and a reasonable methodology that allows engineers to determine the wall deflection in a fast, alternative way.

Automated summary

This study used the NGI-ADP soil model for finite element analysis to evaluate the effects of soft clay anisotropy on diaphragm wall deflections in braced excavation. Ensemble learning methods were employed to develop surrogate models for predicting wall deformation, which were compared with conventional soft computing methods. The research highlights the cutting-edge application of ensemble learning in geotechnical engineering and provides engineers with a fast, alternative way to determine wall deflection.