Prediction of Manisa-Soma Coal Mine Shovel Production with Artificial Neural Networks and Multiple Regression

Şahin Yuvka; Sedat Toraman

Prediction of Manisa-Soma Coal Mine Shovel Production with Artificial Neural Networks and Multiple Regression

Abstract

One of the most critical operations in open-pit mining is stripping. Electric shovels have been used recently, and they are becoming increasingly common. This study uses artificial neural networks and multiple regression analyses to predict production quantities in the study area, accounting for electric shovels' electricity consumption and working hours. Electricity consumption (kW) and working hours (h) of electric shovels operating in open pit mine operations in the Manisa-Soma coal field were used as dependent variables to estimate production quantities. Relationships among electricity consumption and production, working hours, and theoretical and actual production amounts were examined before the estimation study. Five electric shovel data points were used monthly between 2020-2023 (August). Of 44 data points, 70% were used for training, 15% for validation, and 15% for testing. As a result of the study, 94% accuracy was obtained in both artificial neural networks and multiple regression models, and production values were predicted. As a result, the study achieved R2 values of 94.11% with multiple regression analysis and 94.30% with artificial neural networks. Based on regression and artificial neural network analyses, production forecasts were generated for the Manisa-Soma coal field. In addition, a forward forecast for November-December 2023 was generated using time-series analysis of seasonality.

Keywords

References

[1] Toraman, S., and Şensöğüt, C. “Estimation of calorific value of lignite field in Kütahya-Gürağaç (Turkey) by means of artificial neural network”, International Journal of Economic and Environmental Geology, 13(3), pp. 1-7, 2022.
[2] Montgomery, D. C. and Runger, G. C., “Applied statistics and probability for engineers”, John Wiley & Sons, Inc. 2010.
[3] Guo, H., Nguyen, H., Vu, D-A., and Bui X-N., “Forecasting mining capital cost for open-pit mining projects based on artificial neural network approach”, Resources Policy, vol. 74, 101474, 2021.
[4] Lal, B. and Tripathy S.S., “Prediction of dust concentration in open cast coal mine using artificial neural network”, Atmospheric Pollution Research, 3, pp. 211-218, 2012.
[5] Lu, X., Zhou W., Ly, H.B., Oi, C., Nguyen, T-A., Nguyen, M.H., Huang J., and Pham B.T., “Optimization of neural network parameters in improvement of particulate matter concentration prediction of open-pit mining”, Applied Soft Computing, 147, 110769, 2023.
[6] Nguyen, H., Tran, B.D., Bui, N.X., Nguyen, A.D., Pham, V.V., Le, H.T.T., Do, H.N., Le, N.T., and Nguyen, T.T., 2025. “Prediction of flyrock distance in open-pit mines using an optimized artificial neural network with evolution strategies”, Journal of Mining and Earth Sciences, vol. 66, issue 2, pp. 15-28, 2025.
[7] Tsae, N.B., Adachi, T., and Kawamura Y., “Application of artificial neural network for the prediction of copper ore grade”, Minerals, 13(5), 658, 2023.
[8] Zhu, M., Liu, L., Liu, W., and Zhang, A., “Application of neural network in stability analysis of open pit slope” 2010 International Conference on Computer Application and System Modeling (lCCASM 2010), 2010.

[9] Nguyen, H., Bui, X.-N., Tran, Q.‑H., Le, T.‑Q., Do N.H., and Hoa, L.T.T., “Evaluating and predicting blast‑induced ground vibration in open‑cast mine using ANN: a case study in Vietnam”, SN Applied Sciences, 1:125, 2019. https://doi.org/10.1007/s42452-018-0136-2.
[10] Hryhoriev, Y., Lutsenko, S., Hryhoriev,I., Shvets, Y., and Kuropiatnyk, I., “Dynamic design of technical and economic indicators of open-pit mining with the help of neuron network technologies”, Coll.res.pap.nat.min.univ,76, pp. 33–41, 2024. https://doi.org/10.33271/crpnmu/76.033.
[11] Krop, I., Takahashi, Y., Sasaoka, T., Shimada, H., Hamanaka A., and Onyango, J., "Assessment of selected machine learning models for intelligent classification of flyrock hazard in an open pit mine," in IEEE Access, vol. 12, pp. 8585-8608, 2024. https://doi.org/10.1109/ACCESS.2024.3352733.
[12] Patra, A., Gautam, S., Majumdar, S., and Kumar, P., “Prediction of particulate matter concentration profile in an opencast copper mine in India using an artificial neural network model”, Air Quality, Atmosphere and Health, 2015. https://doi.org/10.1007/s11869-015-0369-9.
[13] Kumah, F. N., Saim, A. K.; Oppong, M.N., and Arthur, C. K., “Predicting open-pit mine production using machine learning techniques”, Journal of Sustainable Mining, vol. 23, iss. 2, article 2, 2024 https://doi.org/10.46873/2300-3960.1411.
[14] Freeman, J. A., and Skapura, D. M., Neural networks algorithms, applications and program ming techniques. New York, USA: AddisonWesley Publishing Company, 1991.
[15] Negnevitsky, M., Artificial intelligence: A guide to intelligent systems. Pearson Education, 2005.
[16] Aran, O., Yıldız, O. T., and Alpaydın, E., “An incremental framework based on cross-validation for estimating the architecture of a multilayer perceptron”, Int. J. Pattern Recognit. Artif. Intell., 23 (2), pp. 159–190, 2009
[17] Arı A., and Berberler M. E., “Interface design for the solution of prediction and classification problems with ANN”, Acta Infologica, 1 (2), pp. 55-73, 2017.
[18] Gunst, R.F., and Mason, R.L., Regression Analysis and Its Applications, Marcel Dekker, New York, 1980.
[19] İyi, P., and Erol, H. “Best model selection in multiple linear regression”, Ç.U Graduate School of Natural and Applied Sciences, 17 (5), pp. 48-56, 2008.

Details

Primary Language

English

Subjects

Coal

Journal Section

Research Article

Authors

Şahin Yuvka ^*
0000-0002-3219-2321
Türkiye

Sedat Toraman
0000-0003-2503-7320
Türkiye

Publication Date

June 30, 2026

Submission Date

February 24, 2026

Acceptance Date

April 13, 2026

Published in Issue

Year 2026 Number: 065

IZ

https://izlik.org/JA95NR63PD

Cite

RIS / Bibtex

APA

Yuvka, Ş., & Toraman, S. (2026). Prediction of Manisa-Soma Coal Mine Shovel Production with Artificial Neural Networks and Multiple Regression. Journal of Scientific Reports-A, 065, 1-16. https://izlik.org/JA95NR63PD

AMA

1.Yuvka Ş, Toraman S. Prediction of Manisa-Soma Coal Mine Shovel Production with Artificial Neural Networks and Multiple Regression. JSR-A. 2026;(065):1-16. https://izlik.org/JA95NR63PD

Chicago

Yuvka, Şahin, and Sedat Toraman. 2026. “Prediction of Manisa-Soma Coal Mine Shovel Production With Artificial Neural Networks and Multiple Regression”. Journal of Scientific Reports-A, nos. 065: 1-16. https://izlik.org/JA95NR63PD.

EndNote

Yuvka Ş, Toraman S (June 1, 2026) Prediction of Manisa-Soma Coal Mine Shovel Production with Artificial Neural Networks and Multiple Regression. Journal of Scientific Reports-A 065 1–16.

IEEE

[1]Ş. Yuvka and S. Toraman, “Prediction of Manisa-Soma Coal Mine Shovel Production with Artificial Neural Networks and Multiple Regression”, JSR-A, no. 065, pp. 1–16, June 2026, [Online]. Available: https://izlik.org/JA95NR63PD

ISNAD

Yuvka, Şahin - Toraman, Sedat. “Prediction of Manisa-Soma Coal Mine Shovel Production With Artificial Neural Networks and Multiple Regression”. Journal of Scientific Reports-A. 065 (June 1, 2026): 1-16. https://izlik.org/JA95NR63PD.

JAMA

1.Yuvka Ş, Toraman S. Prediction of Manisa-Soma Coal Mine Shovel Production with Artificial Neural Networks and Multiple Regression. JSR-A. 2026;:1–16.

MLA

Yuvka, Şahin, and Sedat Toraman. “Prediction of Manisa-Soma Coal Mine Shovel Production With Artificial Neural Networks and Multiple Regression”. Journal of Scientific Reports-A, no. 065, June 2026, pp. 1-16, https://izlik.org/JA95NR63PD.

Vancouver

1.Şahin Yuvka, Sedat Toraman. Prediction of Manisa-Soma Coal Mine Shovel Production with Artificial Neural Networks and Multiple Regression. JSR-A [Internet]. 2026 Jun. 1;(065):1-16. Available from: https://izlik.org/JA95NR63PD