A Lasso and Elastic-Net Regularized Generalized Linear Model for Predicting Blast-Induced Air Over-pressure in Open-Pit Mines

Abstract

Air overpressure (AOp) is one of the products of blastingoperations in open-pit mines which have a great impact on the environmentand public health. It can be dangerous for the lungs, brain, hearing and theother human senses. In addition, the impact on the surroundingenvironment such as the vibration of buildings, break the glass doorsystems are also dangerous agents caused by AOp. Therefore, it should beproperly controlled and forecasted to minimize the impacts on theenvironment and public health. In this paper, a Lasso and Elastic-NetRegularized Generalized Linear Model (GLMNET) was developed forpredicting blast-induced AOp. The United States Bureau of Mines(USBM) empirical technique was also applied to estimate blast-inducedAOp and compare with the developed GLMNET model. Nui Beo open-pitcoal mine, Vietnam was selected as a case study. The performance indicesare used to evaluate the performance of the models, including Root MeanSquare Error (RMSE), Determination Coefficient (R2), and Mean AbsoluteError (MAE). For this aim, 108 blasting events were investigated with theMaximum of explosive charge capacity, monitoring distance, powderfactor, burden, and the length of stemming were considered as inputvariables for predicting AOp. As a result, a robust GLMNET model wasfound for predicting blast-induced AOp with an RMSE of 1.663, R2 of0.975, and MAE of 1.413 on testing datasets. Whereas, the USBMempirical method only reached an RMSE of 2.982, R2 of 0.838, and MAEof 2.162 on testing datasets.