Madencilikte Patlatma Verimliliğinin Tahmini: Boosting Tabanlı Makine Öğrenmesi Algoritmaları ile Kapsamlı Bir Değerlendirme

Abstract

Bu çalışma, gerçek dünya operasyon verilerini kullanarak yeraltı madencilik operasyonlarında patlatma verimliliğini tahmin etmeye odaklanmaktadır. Temel amaç, en son teknolojiye sahip boosting tabanlı makine öğrenimi (ML) algoritmalarının tahmin gücünden yararlanarak regresyon analizi yoluyla patlatma verimliliğini doğru bir şekilde tahmin etmektir. Veri setinin nispeten küçük ve çok değişkenli yapısı göz önüne alındığında, aşırı uyum riski düşük, esnek ve yüksek hızlı algoritmalar tercih edilmiştir. Beş farklı son teknoloji boosting algoritmasını karşılaştırmalı olarak değerlendiriyoruz: Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Natural Gradient Boosting (NGBoost) ve Histogram-based Gradient Boosting Machine (HistGBM). Ayrıca, tahmin performansını daha da artırmak için üç farklı ensemble öğrenme stratejisi (Basit Ortalama, Ağırlıklı Ortalama ve En İyi 3 Model ile Ağırlıklı Ortalama) uygulanmış ve test edilmiştir. Metodoloji, Tarih gibi alakasız değişkenlerin kaldırılması, Hedef Kodlama kullanılarak kategorik özelliklerin sayısal dönüşümü ve StandardScaler ile sayısal girdilerin normalleştirilmesi dahil olmak üzere kapsamlı veri ön işlemeyi içeriyordu. 2019-2020 yeraltı patlatma operasyonlarından elde edilen 652 gözlemden oluşan veri kümesi, %80 eğitim ve %20 test kümelerine ayrıldı ve model eğitimi için 10 Katlı Çapraz Doğrulama kullanıldı. Her bir güçlendirme algoritması için hiperparametre optimizasyonu, manuel ayarlama, GridSearchCV ve RandomizedSearchCV kullanılarak gerçekleştirildi. Model performansı, çapraz doğrulama ve test kümeleri için R2, Ortalama Karesel Hata (MSE), Kök Ortalama Karesel Hata (RMSE) ve Ortalama Mutlak Hata (MAE) metrikleri kullanılarak değerlendirildi. Bulgularımız, ensemble yöntemlerinin tahmin doğruluğunu önemli ölçüde artırdığını göstermektedir. Karşılaştırmalı analiz, patlatma verimliliği tahmini için en uygun makine öğrenimi yaklaşımının belirlenmesini sağlamıştır. Bu araştırma, madencilik ortamlarında veriye dayalı karar destek sistemleri aracılığıyla patlatma verimliliğini artırmak ve operasyonel süreçleri optimize etmek için sağlam bir çerçeve sağlayarak bilimsel literatüre önemli katkıda bulunmaktadır. Sonuçlar, doğru ve güvenilir patlatma verimliliği tahmini için birden fazla boosting algoritması ve ensemble tekniğinin birleştirilmesinin etkinliğini göstermektedir.

Keywords

• Patlatma Verimliliği
• Makine Öğrenmesi
• Maden Mühendisliği
• Boosting Algoritmaları
• Topluluk Öğrenmesi

Prediction of Blasting Efficiency in Mining: A Comprehensive Evaluation with Boosting-Based Machine Learning Algorithms

Abstract

This study focuses on predicting blasting efficiency in underground mining operations using real-world operational data. The primary objective is to accurately estimate blasting efficiency through regression analysis, leveraging the predictive power of state-of-the-art boosting-based machine learning (ML) algorithms. Given the relatively small and multi-variate nature of the dataset, algorithms with low overfitting risk, flexibility, and high speed were preferred. We comparatively evaluate five different cutting-edge boosting algorithms: Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Natural Gradient Boosting (NGBoost), and Histogram-based Gradient Boosting Machine (HistGBM). Additionally, to further enhance prediction performance, three distinct ensemble learning strategies—Simple Averaging, Weighted Averaging, and Weighted Average with the Best 3 Models—were implemented and tested. The methodology involved comprehensive data preprocessing, including the removal of irrelevant variables like Date, numerical transformation of categorical features using Target Encoding, and normalization of numerical inputs with StandardScaler. The dataset, comprising 652 observations from 2019-2020 underground blasting operations, was split into 80% training and 20% testing sets, and 10-Fold Cross Validation was employed for model training. Hyperparameter optimization for each boosting algorithm was performed using manual tuning, GridSearchCV, and RandomizedSearchCV. Model performance was assessed using R2, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) metrics for both cross-validation and test sets. Our findings indicate that ensemble methods significantly improve prediction accuracy. The comparative analysis allowed for the identification of the most suitable machine learning approach for blasting efficiency prediction. This research contributes significantly to the scientific literature by providing a robust framework for enhancing blasting efficiency and optimizing operational processes through data-driven decision support systems in mining environments. The results demonstrate the effectiveness of combining multiple boosting algorithms and ensemble techniques for accurate and reliable blasting efficiency prediction.

Keywords

• Blasting Efficiency
• Machine Lerning
• Mining Engineering
• Boosting Algorithms
• Ensemble Learning

References

1. Abd Elwahab A., Topal E., Jang H. Review of machine learning application in mine blasting. Arabian Journal of Geosciences 2023; 16: 133.
2. Ağan Y., Hüdaverdi T. Application of machine learning algorithms for prediction of blast-induced ground vibration in view of stiffness ratio, energy coverage and scaled distance. Journal of Mining and Environment 2025; 1-18.
3. Aladejare AE., Idowu KA., Ozoji T. Reliability of Monte Carlo simulation approach for estimating uniaxial compressive strength of intact rock. Earth Science Informatics 2024; 17: 2043–2053.
4. Amoako R., Jha A., Zhong S. Rock fragmentation prediction using an artificial neural network and support vector regression hybrid approach. Mining 2022; 2: 233-247.
5. Bamford T., Esmaeili K., Schoellig AP. A deep learning approach for rock fragmentation analysis. International Journal of Rock Mechanics and Mining Sciences 2021; 145: 104839.
6. Bentéjac C., Csörgő A., Martínez-Muñoz G. A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review 2021; 54(3): 1937–1967.
7. Bui XN., Jaroonpattanapong P., Nguyen H., Tran QH., Long NQ. A novel hybrid model for predicting blast-induced ground vibration based on k-nearest neighbors and particle swarm optimization. Scientific Reports 2019; 9: 13971.
8. Chen T., Guestrin C. XGBoost: A scalable tree boosting system. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2016; 785–794.

9. Demir S., Sahin EK. Predicting occurrence of liquefaction-induced lateral spreading using gradient boosting algorithms integrated with particle swarm optimization: PSO-XGBoost, PSO-LightGBM, and PSO-CatBoost. Acta Geotechnica 2023; 18(6): 3403–3419.
10. Fabricius R., Such O., Tarabek P. Deep neural network ensembles using class-vs-class weighting. IEEE Access 2023; 11: 77703–77715.
11. Fatima S., Hussain A., Amir S. Bin., Ahmed SH., Aslam SMH. XGBoost and random forest algorithms: an in depth analysis. Pakistan Journal of Scientific Research 2023; 3(1): 26–31.
12. Fauzan MA., Murfi H. The accuracy of XGBoost for insurance claim prediction. International Journal of Advances in Soft Computing and Its Applications 2018; 10(2): 159–171.
13. Friedman JH. Greedy function approximation: A gradient boosting machine. Annals of Statistics 2001; 29(5): 1189-1232.
14. Gao Y., Wang L., Zhong G., Wang Y., Yang J. Potential of remote sensing ımages for soil moisture retrieving using ensemble learning methods in vegetation-covered area. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2023; 16: 8149–8165.
15. Gu Y., Zhang D., Lin Y., Ruan J., Bao Z. Data-driven lithology prediction for tight sandstone reservoirs based on new ensemble learning of conventional logs: A demonstration of a Yanchang member, Ordos Basin. Journal of Petroleum Science and Engineering 2021; 207: 109292.
16. Hajihosseinlou M., Maghsoudi A., Ghezelbash R. A novel scheme for mapping of mvt-type pb–zn prospectivity: lightgbm, a highly efficient gradient boosting decision tree machine learning algorithm. Natural Resources Research 2023; 32(6): 2417–2438.
17. Hartanto AD., Kholik YN., Pristyanto Y. Stock price time series data forecasting using the light gradient boosting machine (lightgbm) model. International Journal on Informatics Visualization 2023; 7(4): 2270–2279.
18. Harumy HF., Hardi SM., Al Banna MF. EarlyStage diabetes risk detection using comparison of xgboost, lightgbm, and catboost algorithms. 38nd International Conference on Advanced Information Networking and Applications 2024; 203: 12–24.
19. Hosseini S., Pourmirzaee R., Armaghani, DJ., Sabri MSS. Prediction of ground vibration due to mine blasting in a surface lead–zinc mine using machine learning ensemble techniques. Scientific Reports 2023; 13: 6591.
20. Jung D., Choi Y. Systematic review of machine learning applications in mining: exploration, exploitation, and Reclamation. Minerals 2021; 11(2): 148.
21. Kavzoglu T., Teke A. Predictive performances of ensemble machine learning algorithms in landslide susceptibility mapping using random forest, extreme gradient boosting (XGBoost) and natural gradient boosting (NGBoost). Arabian Journal for Science and Engineering 2022; 47(6): 7367–7385.
22. Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu T. LightGBM: a highly efficient gradient boosting decision tree. 31st Conference on Neural Information Processing Systems 2017; 1-9.
23. Komadja GC., Westman E., Rana A., Vitalis A. Predicting rock mass strength from drilling data using synergistic unsupervised and supervised machine learning approaches. Earth Science Informatics 2025; 18: 325.
24. Kriuchkova A., Toloknova V., Drin S. Predictive model for a product without history using LightGBM. Pricing model for a new product. Mohyla Mathematical Journal 2023; 6: 6–13.
25. Liu Y., Wang X., Long W. Detection of false Weibo repost based on XGBoost. International Conference on Web Intelligence Workshops, WI 2019; 97–105.
26. Madhuvappam CA., Vinod Kumar D., Kanna S., Vaishnodevi S., Murali G., Karthick M. Enhanced lung cancer detection using ensemble learning algorithms: a comparative study of lightgbm & catboost. 5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024; 324–328.
27. Mishra BR., Vogeti RK., Jauhari R., Raju KS., Kumar, DN. Boosting algorithms for projecting streamflow in the Lower Godavari Basin for different climate change scenarios. Water Science and Technology 2024; 89(3): 613–634.
28. Monteiro A., Ribeiro I., Tchepel O., Carvalho A., Sá, E., Ferreira J., Galmarini S., Miranda AI., Borrego C. Bias correction and ensemble techniques to improve air quality assessment: Focus on O3 and pm over Portugal. 14th International Conference on Harmonisation within Atmospheric Dispersion Modelling for Regulatory Purposes 2011; 22–26.
29. Munagala V., Thudumu S., Logothetis I., Bhandari S., Vasa R., Mouzakis K. A comprehensive survey on machine learning applications for drilling and blasting in surface mining. Machine Learning with Applications 2024; 15: 100517.
30. Pinsky E. Mathematical foundation for ensemble machine learning and ensemble portfolio analysis. SSRN Electronic Journal 2018; 1-48.
31. Prokhorenkova L., Gusev G., Voroninskiy A., Dorogush AV., Gulin A. CatBoost: unbiased boosting with categorical features. 32nd International Conference on Neural Information Processing Systems 2018; 6639 - 6649.
32. Sahin EK. Comparative analysis of gradient boosting algorithms for landslide susceptibility mapping. Geocarto International 2022; 37(9): 2441–2465.
33. Senthilvadivu S., Ramesh PS., Narang S., Praveena N., Shakila J., Sudha I. Impact of random forest and xgboost algorithms on improving patient outcomes compared to standard decision-making methods in healthcare predictive analytics. International Conference on Cybernation and Computation, CYBERCOM 2024; 694–699.
34. Shakeri J., Shokri BJ., Dehghani H. Prediction of blast-induced ground vibration using gene expression programming (GEP), artificial neural networks (ANNs), and linear multivariate regression (LMR). Archives of Mining Sciences 2020; 65(2): 317-355.
35. Szczepanek R. Daily streamflow forecasting in mountainous catchment using xgboost, lightgbm and catboost. Hydrology 2022; 9(12): 226.
36. Taiwo BO., Gebretsadik A., Abbas HH., Khishe M., Fissha Y., Kahraman E., Rabbani A., Akinlabi AA. Explosive utilization efficiency enhancement: An application of machine learning for powder factor prediction using critical rock characteristics. Heliyon 2024; 10(12): e33099.
37. Tuama MH. A Comparative evaluation of random forest and xgboost models for disease detection using medical ındicators. International Journal of Profesional Studies 2025; 19(1): 11–18.
38. Wang Y., Wang T. Application of improved lightgbm model in blood glucose prediction. Applied Sciences 2020; 10(9): 3227.
39. Yu R., Zhang K., Ramasubramanian B., Jiang S., Ramakrishna S., Tang Y. Ensemble learning for predicting average thermal extraction load of a hydrothermal geothermal field: A case study in Guanzhong Basin, China. Energy 2024; 296: 131146.
40. Zhang ZX., Sanchidrián JA., Ouchterlony F., Luukkanen S. Reduction of fragment size from mining to mineral processing: A review. Rock Mechanics and Rock Engineering 2023; 56: 747–778.
41. Zhu X., Chu J., Wang K., Wu S., Yan W., Chiam K. Prediction of rockhead using a hybrid N-XGBoost machine learning framework. Journal of Rock Mechanics and Geotechnical Engineering 2021; 13(6): 1231–1245.