An ensemble method based on weight voting method for improved prediction of slope stability

This study proposes a novel ensemble method based on weighted majority voting to evaluate the slope stability. The ensemble classifier is composed of 5 base classifiers, including random forest, logistic regression, naive bayes, support vector classifier and back propagation. An integrated approach was developed using 213 slope cases collected from the literature and the performance of the proposed approach was validated. The selection of training parameters was carried out by the definition of safety factor and the correlation analysis of parameters. The search for the optimal hyperparameters of the base classifiers is performed using a grid search algorithm combined with a five-fold cross-validation. Weights to each base classifier is obtained by the AUC (area under the curve) value of the training dataset. Finally, the ensemble method based on weights is established to predict the stability of slopes in this paper. It is demonstrated that the ensemble algorithm is superior to the base classifier with regard to accuracy, kappa, precision, recall, F1 score and the receiver's operating characteristic curve AUC. Also, the importance scores of training parameters are obtained by the random forest theory.