A Combination of Expert-Based System and Advanced Decision-Tree Algorithms to Predict Air-Overpressure Resulting from Quarry Blasting

This study combined a fuzzy Delphi method (FDM) and two advanced decision-tree algorithms to predict air-overpressure (AOp) caused by mine blasting. The FDM was used for input selection. Thus, the panel of experts selected four inputs, including powder factor, max charge per delay, stemming length, and distance from the blast face. Once the input selection was completed, two decision-tree algorithms, namely extreme gradient boosting tree (XGBoost-tree) and random forest (RF), were applied using the inputs selected by the experts. The models are evaluated with the following criteria: correlation coefficient, mean absolute error, gains chart, and Taylor diagram. The applied models were compared with the XGBoost-tree and RF models using the full set of data without input selection results. The results of hybridization showed that the XGBoost-tree model outperformed the RF model. Concerning the gains, the XGBoost-tree again outperformed the RF model. In comparison with the single decision-tree models, the single models had slightly better correlation coefficients; however, the hybridized models were simpler and easier to understand, analyze and implement. In addition, the Taylor diagram showed that the models applied outperformed some other conventional machine learning models, including support vector machine, k-nearest neighbors, and artificial neural network. Overall, the findings of this study suggest that combining expert opinion and advanced decision-tree algorithms can result in accurate and easy to understand predictions of AOp resulting from blasting in quarry sites.