227 / 2018-07-23 17:02:03

Slope stability analysis for circular mode failure: a gradient boosting machine approach

Slope stability; circular failure; Gradient boosting machine (GBM); Cross-validation; predictive modeling

矿山动力灾害 > 边坡

Slope stability analysis is one of the most crucial problems in civil and geotechnical engineering. This paper presents a gradient boosting machine (GBM) method to analyze the slope stability. The GBM- based model is developed by free R programs, trained and tested with the parameters obtained from the detailed investigation of 134 different actual slope cases available in the literature. The stability of the circular slope is taken as a function of unit weight (γ), cohesion (c), angle of internal friction (φ), slope angle (β), slope height (H) and pore water pressure coefficient (ru). A tenfold cross-validation procedure is implemented to determine the optimal parameter values during the GBM modeling and an external testing set is employed to validate the prediction performance of models. Classification accuracy rate and Cohen’s Kappa coefficient have been employed for measuring the performance of the proposed model. The analysis of accuracy together with kappa for the dataset demonstrate that the GBM model has high credibility as it achieves a comparable classification accuracy rate and Cohen’s kappa values of 87.10% and 0.7427 for the prediction of slope stability, respectively.