Classification of Rockburst in Underground Projects: Comparison of Ten Supervised Learning Methods

Abstract

Rockburst prediction is of crucial importance to the design and construction of many underground projects. Insufficient knowledge, lack of characterizing information, and noisy data restrain rock mechanics engineers from achieving optimal prediction results. In this paper, a data set of 246 rockburst events was examined for rockburst classification using supervised learning (SL) methods. The data set was analyzed with 8 potentially relevant indicators. Eleven algorithms from 10 categories of SL algorithms were evaluated for their ability to learn rockburst, including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), partial least-squares discriminant analysis (PLSDA), naïve Bayes (NB), k-nearest neighbor (KNN), multilayer perceptron neural network (MLPNN), classification tree (CT), support vector machine (SVM), random forest (RF), and gradient-boosting machine (GBM). The data set was randomly split into two parts: training (70%) and test (30%). A 10-fold cross-validation (CV) method was applied during modeling, and an external testing set was employed to validate the prediction performance of the SL models. Two accuracy measures for multiclass problems were employed: classification rate and Cohen’s Kappa. The accuracy analysis, together with Cohen’s kappa and a nonparametric statistical test for the rockburst data set, revealed that the best models for the prediction of rockburst were GBM and RF when compared with other learning algorithms.