Novel Ensemble Tree Solution for Rockburst Prediction Using Deep Forest

Abstract

The occurrence of rockburst can cause significant disasters in underground rock engineering. It is crucial to predict and prevent rockburst in deep tunnels and mines. In this paper, the deficiencies of ensemble learning algorithms in rockburst prediction were investigated. Aiming at these shortages, a novel machine learning model, deep forest, was proposed to predict rockburst risk. The deep forest combines the characteristics of deep learning and ensemble models, which can solve complex problems. To develop the deep forest model for rockburst prediction, 329 real rockburst cases were collected to build a comprehensive database for intelligent analysis. Bayesian optimization was proposed to tune the hyperparameters of the deep forest. As a result, the deep forest model achieved 100% training accuracy and 92.4% testing accuracy, and it has more outstanding capability to forecast rockburst disasters compared to other widely used models (i.e., random forest, boosting tree models, neural network, support vector machine, etc.). The results of sensitivity analysis revealed the impact of variables on rockburst levels and the applicability of deep forest with a few input parameters. Eventually, real cases of rockburst in two gold mines, China, were used for validation purposes while the needed data sets were prepared by field observations and laboratory tests. The promoting results of the developed model during the validation phase confirm that it can be used with a high level of accuracy by practicing engineers for predicting rockburst occurrences.

Study on the effect of multiple optimization algorithms on rockburst prediction models

“…Xue et al [10] optimized the ELM by particle swarm algorithm (PSO), selecting six quantitative rockburst parameters, such as the maximum tangential stress of the surrounding rock, uniaxial compressive strength of the rock, the tensile strength of the rock, the stress ratio, the brittleness ratio of the rock and the elastic energy index, on 344 sets of rockburst cases were learned and validated on the riverside hydropower station, and the results showed that the model has a better prediction effect.Yin et al [21] collected 400 groups of cases through microseismic monitoring data, optimized the CNN-Adam-BO integration algorithm by using adaptive matrix estimation and Bayesian to CNN-Adam-BO integration algorithms, respectively, and compared the model with the continuous wavelet transform and the cross-wavelet transform, which verified the superiority of the model. Barkat Ullah et al [2] predicted the short-term rockburst database by t-SNE, K-means clustering and XGBoost, which provided a reference for subsequent research.Liu et al [22] optimized BP, PNN, and SVM by PSO and compared the prediction effect of the three models.Qiu et al [23] optimized the short-term rockburst database by Sand Cat Swarm Optimization (SCSO) on Extreme Gradient Boosting (XGBoost), established a new model for predicting short-term rockburst damage, trained with 254 sets of data from Australia and Canada, developed a graphical presentation interface, and provided guidance and direction for subsequent research.Sun et al [24] used Yeo-Johnson transform, K-means SMOTE oversampling and optimal rockburst feature dimension determination to optimize the data structure and effectively improve the accuracy of rockburst prediction.Zhou et al [25] proposed a hybrid model of PSO, HHO, and MFO optimized SVM, selected six feature parameters such as angularfrequency ratio, total energy, and so on as the input variables, and used accuracy, precision, and kappa coefficients to compare the models.Li et al [26] roposed a new prediction model (deep forest) using Bayesian for hyper-parameter tuning and showed the superiority of the model by comparing it with other models.Qiu et al [27] developed a rockburst prediction fusion model by combining multiple machine learning models with D-S evidence theory, which improved the uncertainty and poor robustness of the prediction results of a single base classifier.Sun et al [28]. designed a beetle antenna search algorithm to optimize a random forest classifier, which was found to have good accuracy over single models and empirical formulas.Zhou et al [29].…”

A Novel Method for Predicting Rockburst Intensity Based on an Improved Unascertained Measurement and an Improved Game Theory

“…They were inspired by the principles of biological evolution and some physical phenomena. Among the mainstream intelligent optimization algorithms are PSO [16,42,43], BP neural networks [44,45], Bayesian networks [46,47], random forests [48,49], genetic algorithms [50], support vector machines [51], decision tree models [52,53], and so on. These algorithms have shown excellent performances in handling complex problems and exhibit high computational efficiency.…”

Lake eutrophication prediction based on improved MIMO-DD-3Q Learning

“…The long and short term memory network can accurately capture the internal relationship between the front and back elements in the time series data, and form short-term memory by forgetting the front elements to guide the back elements, while retaining the guidelines to form longterm memory [20,21]. In the deep random forest, key variables are found and sorted through the input data through the multi-grain scanning process, features are captured according to the sliding window, and features are fully captured and processed data are recorded in the cascade forest process [22,23]. Transformer is a kind of neural network with self-attention mechanism, which can use time series data as the input of encoder in Transformer model and predict future values in an autoregressive way in the decoder part [24,25].…”