Efficient Seismic Stability Analysis of Embankment Slopes Subjected to Water Level Changes Using Gradient Boosting Algorithms

Abstract

Embankments are widespread throughout the world and their safety under seismic conditions is a primary concern in the geotechnical engineering community since the failure events may lead to disastrous consequences. This study proposes an efficient seismic slope stability analysis approach by introducing advanced gradient boosting algorithms, namely Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), and Extreme Gradient Boosting (XGBoost). A database consisting of 600 datasets is prepared for model calibration and evaluation, where the factor of safety (FS) is regarded as the output and four influential factors are selected as the inputs. For each dataset, the FS corresponding to the four inputs is evaluated using the commercial geotechnical software of Slide2. As an illustration, the proposed approach is applied to the seismic stability analysis of a hypothetical embankment example subjected to water level changes. For comparison, the predictive performance of CatBoost, LightGBM, and XGBoost is investigated. Moreover, the Shapley additive explanations (SHAP) method is used in this study to explore the relative importance of the four features. Results show that all the three gradient boosting algorithms (i.e., CatBoost, LightGBM, and XGBoost) perform well in the prediction of FS for both the training dataset and testing dataset. Among the four influencing factors, the friction angle φ is the most important feature variable, followed by horizontal seismic coefficient Kh, cohesion c, and saturated permeability ks.

Degradation of Typical Reverse Sand-Mudstone Interbedded Bank Slope Based on Multi-Source Field Experiments

“…Although only one cycle of water level fluctuation had occurred, the weak deformation could already be captured. Continuous monitoring could obtain a more obvious deterioration trend, which would provide an important reference for the degradation of reservoir banks [39][40][41][42][43].…”

CT Scanning of Structural Characteristics of Glacial Till in Moxi River Basin, Sichuan Province

“…When statistical methods such as Monte Carlo, the stochastic method and Flac3D are used to simulate the meso-structure and micro-structure of rock and soil mass in 3D, their internal structure is extremely complex, because most rock and soil mass materials are composed of a certain size of high-strength rock block and relatively low-strength soil filling and corresponding pores. However, the three-dimensional meso-structures of rock and soil mass generated by these methods are all random simulations, which cannot truly reflect the real threedimensional structure of rock and soil mass materials [38][39][40]. When the method of fractal theory is used to study and analyze the internal meso-structure and micro-structure, the rock and soil mass must be kept in their original state, and representative parts must be selected to reflect the structure during the sample preparation process; then, fractal theory should be used to perform fine measurement and digital representation of the internal structure of the loess, and further solve the structural parameters [41].…”

Landslide Susceptibility mapping using random forest and extreme gradient boosting: A case study of Fengjie, Chongqing

“…The Three Gorges Reservoir area has become one of the most severely affected by landslides in China (Wang, Zhang, et al, 2021; Wang, Wu, et al, 2021; Zhang et al, 2022). Because the geological structure of the reservoir area is complex, and both banks are affected by the fluctuation of reservoir water for a long time (Fang et al, 2023; C. D. Li et al, 2019; B.…”