Development of Machine Learning Models for Predicting Air Overpressure in an Open-pit Mine

Abstract

In this study, machine learning models were developed to predict air overpressure resulting from blasting in an open-pit mine. A total of 924 blasting data were collected from an open-pit mine at the Mt. Yogmang located in Changwon-si, Gyeongsangnam-do, Korea. The blasting data consisted of hole length, burden, spacing, maximum charge per delay, powder factor, number of holes, ratio of emulsion, monitoring distance and air overpressure. Four algorithms including k-nearest neighbors (kNN), random forest (RF), extreme gradient boosting (XGBoost) and deep neural network (DNN) were used to train the machine learning models. Mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE) were analyzed to evaluate the performance of the trained models. As a result, the RF model showed superior performance with MAE, MSE and RMSE of 4.938, 42.032 and 6.483, respectively.