Modern approaches to air overpressure prediction: evaluating ensemble machine learning and classical statistical models

• Autorzy: Ragam Prashanth , Divya Bonagiri

Identyfikatory

DOI

10.24425/ams.2025.156294

• Języki publikacji: EN

Abstrakty

EN

Mining provides essential raw materials for various sectors but carries significant risks due to hazardous processes. Taking valuable minerals or other geological materials out of the earth is known as mining. Resources like coal and metals, placer, underground, and surface mining are essential, but they also have negative environmental effects, such as air pollution from blasting and water pollution. Air noise, frequently caused by industrial operations like mining and construction, can harm wildlife and human health. Transportation, equipment, and blasting activities are examples of sources. To reduce the negative effects of high noise levels on the environment, stress, and hearing loss, noise management and predictive models are crucial by establishing correlations between variables such as charge weight, distance, and geological conditions. Statistical predictor equations calculate blast-induced Air Overpressure (AOp). In India, DGMS regulations ensure mining and blasting operations minimise environmental impacts and keep AOp levels safe for nearby communities. In this study, SVR, RF, GB, BPNN, and an ensemble hybrid XGBoost–RF model were developed to predict blast-induced AOp and compared with traditional statistical prediction equations. The performance of these models was evaluated using four metrics: RMSE, MSE, MAE, and R². The results showed high accuracy for machine learning models, with R² values up to 0.9991 for the ensemble hybrid model, compared to much lower R² values for classical statistical approaches. These findings demonstrate the effectiveness of modern machine learning methods in predicting blast-induced Air Overpressure and highlight their superiority over traditional statistical models.

Słowa kluczowe

EN

blasting; AOP; machine learning; R2; RMSE; MSE

PL

górnictwo; materiał geologiczny; ochrona środowiska

• Wydawca: Instytut Mechaniki Górotworu PAN
• Czasopismo: Archives of Mining Sciences
• Rocznik: 2025
• Tom: Vol. 70, no. 3
• Strony: 453--491
• Opis fizyczny: Bibliogr. 33 poz., rys., tab., wykr.

Twórcy

autor

Ragam Prashanth

• VIT-AP University, School of Computer Science and Engineering, Inavolu, Beside AP Secretariat, Amaravati, Andhra Pradesh, 522237, India

autor

Divya Bonagiri

• VIT-AP University, School of Computer Science and Engineering, Inavolu, Beside AP Secretariat, Amaravati, Andhra Pradesh, 522237, India

• https://orcid.org/0009-0007-2554-3641

Bibliografia

• [1] P. Ragam et al., Estimation of slope stability using ensemble-based hybrid machine learning approaches. Front. Mater. 11, (2024). DOI: https://doi.org/10.3389/fmats.2024.1330609.
• [2] C. Mueller, Mining goes digital. CRC Press / Taylor & Francis Group, 2019.
• [3] K. Manoj, M. Monjezi, Prediction of fly rock in open pit blasting operation using machine learning method. Int. J. Min. Sci. Technol. 23, 3, 313-316 (2013). DOI: https://doi.org/10.1016/j.ijmst.2013.05.005.
• [4] V. Munagala, S. Thudumu, I. Logothetis, S. Bhandari, R. Vasa, K. Mouzakis, A comprehensive survey on machine learning applications for drilling and blasting in surface mining. Mach. Learn. with Appl. 15, 100517, (2024).DOI: https://doi.org/10.1016/j.mlwa.2023.100517.
• [5] S.A. Baghaei Naeini, A. Badri, Identification and categorization of hazards in the mining industry: A systematic review of the literature. Akademiai Kiado ZRt. Jan. 22, (2024). DOI: https://doi.org/10.1556/1848.2023.00621.
• [6] P. Ragam, D.S. Nimaje, Monitoring of blast-induced ground vibration using WSN and prediction with an ANN approach of ACC dungri limestone mine, India. J. Vibroengineering 20, 2, 1051-1062 (2018).DOI: https://doi.org/10.21595/jve.2017.18647.
• [7] V.A. Temeng, Y.Y. Ziggah, C.K. Arthur, A novel artificial intelligent model for predicting air overpressure using brain inspired emotional neural network. Int. J. Min. Sci. Technol. 30, 5, 683-689 (2020).DOI: https://doi.org/10.1016/j.ijmst.2020.05.020.
• [8] P.J. Wen, C. Huang, Noise prediction using machine learning with measurements analysis. Appl. Sci. 10, 18 (2020).DOI: https://doi.org/10.3390/APP10186619.
• [9] D. Prasad Tripathy, S. Kumar Nanda, Noise Identification, Modeling and Control In Mining Industry. (2024).
• [10] H. Dehghani, F. Ali Mohammad Nia, Estimation of air overpressure using bat algorithm. Min. Sci. 28, 7, 7-92,(2020). DOI: https://doi.org/10.37190/msc212806.
• [11] C. Sawmliana, P. Pal Roy, R.K. Singh, T.N. Singh, Blast induced air overpressure and its prediction using artificial neural network. Trans. Institutions Min. Metall. Sect. A Min. Technol. 116, 2, 41-48 (2007).DOI: https://doi.org/10.1179/174328607X191065.
• [12] H. Nguyen, X.N. Bui, C. Drebenstedt, Y. Choi, Enhanced Prediction Model for Blast-Induced Air Over-Pressurein Open-Pit Mines Using Data Enrichment and Random Walk-Based Grey Wolf Optimization–Two-Layer ANN Model. Nat. Resour. Res. 33, 2, 943-972 (2024). DOI: https://doi.org/10.1007/s11053-023-10299-w.
• [13] R. Zhang, Y. Li, Y. Gui, Prediction of rock blasting induced air overpressure using a self-adaptive weighted kernelridge regression. Appl. Soft Comput. 148, (2023). DOI: https://doi.org/10.1016/j.asoc.2023.110851.
• [14] C. Chewu, T. Chikwere, D. Runganga, Elia Chipfupi, T. Nyamagudza, Prediction of Flyrocks, Airblasts and Ground Vibrations Using Neural Computing and Applications at ZCDC Mine. Malaysian J. Sci. Adv. Technol., 212-221,(2023). DOI: https://doi.org/10.56532/mjsat.v3i3.135.
• [15] S. Hosseini et al., Mine Induced Airblast prediction: An Application of Chaos Game Optimization based soft computing approaches. May 30, (2023). DOI: https://doi.org/10.21203/rs.3.rs-2992457/v1.
• [16] K.F. Lima, A. da C. Meireles, N. Barbieri, L.D. Fiorentin, Ground vibration and air overpressure prediction appliedto a blasting operation in a Gneiss quarry in southern Brazil. Feb. 05, (2024).DOI: https://doi.org/10.21203/rs.3.rs-3914158/v1.
• [17] C. Kuzu, A. Fisne, S.G. Ercelebi, Operational and geological parameters in the assessing blast induced airblast overpressurein quarries. Appl. Acoust. 70, 3, 404-411 (2009).DOI: https://doi.org/10.1016/j.apacoust.2008.06.004.
• [18] M.M.K. Kazemi, Z. Nabavi, M. Khandelwal, Prediction of blast-induced air overpressure using a hybrid machine learning model and gene expression programming (GEP): A case study from an iron ore mine. AIMS Geosci. 9,23, 57-381 (2023). DOI: https://doi.org/10.3934/geosci.2023019.
• [19] S. Jayanthu, C. Naveen, G.V. Rao, B.R.V. Susheel Kumar, Ground vibrations in opencast mine blast on structuresvis-à-vis a local environmental effect and its mitigation through mining technology.
• [20] P.P. Roy, C. Sawmliana, R.K. Singh, Strategic planning to reduce ground vibration, air overpressure and fly rock ina mine at a sensitive area. Curr. Sci. 123, 8, 995-1004 (2022). DOI: https://doi.org/10.18520/cs/v123/i8/995-1004.
• [21] X. Zhou et al., Propagation characteristics and prediction of airblast overpressure outside tunnel: a case study. Sci.Rep. 12, 1 (2022). DOI: https://doi.org/10.1038/s41598-022-24917-9.
• [22] N.K. Dumakor-Dupey, S. Arya, A. Jha, Advances in blast-induced impact prediction – a review of machine learning applications. Minerals 11, 6 (2021). DOI: https://doi.org/10.3390/min11060601.
• [23] M. Khandelwal, P.K. Kankar, Prediction of blast-induced air overpressure using support vector machine. Arab. J. Geosci. 4, 3-4, 427-433 (2011). DOI: https://doi.org/10.1007/s12517-009-0092-7.
• [24] P. Hajikhodaverdikhan, M. Nazari, M. Mohsenizadeh, S. Shamshirband, K.W. Chau, Earthquake prediction with meteorological data by particle filter-based support vector regression. Eng. Appl. Comput. Fluid Mech. 12, 1,679-688 (2018). DOI: https://doi.org/10.1080/19942060.2018.1512010.
• [25] V.A. Temeng, C.K. Arthur, Y.Y. Ziggah, Suitability assessment of different vector machine regression techniques for blast-induced ground vibration prediction in Ghana. Model. Earth Syst. Environ. 8, 1, 897-909 (2022).DOI: https://doi.org/10.1007/s40808-021-01129-0.
• [26] S. Hosen, R. Amin, Significant of Gradient Boosting Algorithm in Data Management System. Eng. Int. 9, 2 (2021).
• [27] G. Komarasamy, S.C.B. Jaganathan, K. Sridharan, A. Mital, S. Awal, Harmony Gradient Boosting Random Forest Machine Learning Algorithms for Sentiment Classification. In Proceedings – 2022 IEEE 2nd International Symposium on Sustainable Energy, Signal Processing and Cyber Security, iSSSC 2022, Institute of Electrical and Electronics Engineers Inc.,(2022). DOI: https://doi.org/10.1109/iSSSC56467.2022.10051210.
• [28] J. Renaud, R. Karam, M. Salomon, R. Couturier, Deep learning and gradient boosting for urban environmental noise monitoring in smart cities. Expert Syst. Appl. 218, May (2022). DOI: https://doi.org/10.1016/j.eswa.2023.119568.
• [29] A.-L. Boulesteix, S. Janitza, J. Kruppa, I.R. König, Overview of Random Forest Methodology and Practical Guidance with Emphasis on Computational Biology and Bioinformatics Overview of Random Forest Methodology and Practical Guidance with Emphasis on Computational Biology and Bioinformatics pre-review version of a manuscript accepted for publication in WIREs Data Mining & Knowledge Discovery. 2012. [Online]. Available:http://www.stat.uni-muenchen.de.
• [30] M. Savargiv, B. Masoumi, M.R. Keyvanpour, A new random forest algorithm based on learning automata. Comput. Intell. Neurosci. 2021, (2021). DOI: https://doi.org/10.1155/2021/5572781.
• [31] W. Lin, Z. Wu, L. Lin, A. Wen, J. Li, An ensemble random forest algorithm for insurance big data analysis. IEEE Access 5, 16568-16575 (2017). DOI: https://doi.org/10.1109/ACCESS.2017.2738069.
• [32] P. Ragam, A.R. Komalla, N. Kanne, Estimation of blast-induced peak particle velocity using ensemble machine learning algorithms: A case study. Noise Vib. Worldw. 53, 7-8, 404-413 (2022).DOI: https://doi.org/10.1177/09574565221114662.
• [33] https://github.com/kamleshiitb/Ground-Vibration-Prediction-in-blasting-using- Neural- Network/blob/main/Blasting%20dataset.csvp.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025)