Application of Tree-Based Predictive Models to Forecast Air Overpressure Induced by Mine Blasting

• Published in: Natural resources research (New York, N.Y.) Vol. 30; no. 2; pp. 1865 - 1887
• Main Authors: Ramesh Murlidhar, Bhatawdekar, Yazdani Bejarbaneh, Behnam, Jahed Armaghani, Danial, Mohammed, Ahmed Salih, Tonnizam Mohamad, Edy
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-04-2021; Springer Nature B.V
• Subjects: Air overpressure; Blasting; Chemistry and Earth Sciences; Civil engineering; Computer Science; Damage assessment; Data mining; Decision trees; Earth and Environmental Science; Earth Sciences; Environmental degradation; Environmental impact; Fossil Fuels (incl. Carbon Capture); Genetic algorithms; Geography; Mathematical Modeling and Industrial Mathematics; Mathematical models; Mineral Resources; Mines; Mining engineering; Original Paper; Parameter identification; Parameter sensitivity; Physics; Prediction models; R&D; Research & development; Root-mean-square errors; Sensitivity analysis; Statistics for Engineering; Support vector machines; Surface mines; Sustainable Development; Underground mines; Air overpressure; Sensitivity analysis; Parametric analysis; Blasting; Genetic programming; Elitism; M5′ decision tree; Bloat
• ISSN: 1520-7439; 1573-8981
• DOI: 10.1007/s11053-020-09770-9

In surface mines and underground excavations, every blasting operation can have some destructive environmental impacts, among which air overpressure (
AOp
) is of major significance. Therefore, it is essential to minimize the related environmental damage by precisely evaluating the intensity of
AOp
before any blasting operation. The present study primarily aimed to develop two different tree-based data mining algorithms, namely M5′ decision tree and genetic programming (GP) for accurately predicting blast-induced
AOp
in granite quarries. In addition, a multiple linear regression technique was adopted to check the accuracy of the GP and M5′ models. To achieve the aims of this research, 125 blasts were explored and their respective
AOp
values were carefully recorded. In each operation, six influential parameters of
AOp
, i.e., stemming length, powder factor, blasting index, joint aperture, maximum charge weight per delay and distance of the blast points, were recorded and considered as inputs for modeling. After developing the predictive models of
AOp
, their performances were examined in terms of coefficient of determination (
R
2
), root-mean-squared error (RMSE) and mean absolute error (MAE). Based on the computed results, the GP (with RMSE of 1.3997,
R
2
of 0.8621 and MAE of 0.9472) outperformed the other developed models. Then, a sensitivity analysis was employed to identify the most influential parameters in predicting the
AOp
values. Finally, the generality of the proposed GP model was validated by investigating its predictive results with respect to the two most effective predictor variables. The study findings demonstrated the robustness and applicability of the proposed GP model for predicting blast-induced
AOp
.