Research Article
BibTex RIS Cite

Demir Tenör Değerlerinin Kestiriminde Makine Öğrenme Yöntemlerinin Karşılaştırılması

Year 2024, Volume: 15 Issue: 4, 907 - 916
https://doi.org/10.24012/dumf.1569827

Abstract

Bu çalışmada günümüzde maden kaynak kestiriminde kullanım yaygınlığı artmaya başlayan derin sinir ağları, destek vektör makineleri ve XGBoost yaklaşımları kullanılarak bir demir yatağında tenör kestirimleri gerçekleştirilmiştir. Elde edilen sonuçlar endüstride yaygın bir şekilde kullanılan Krigleme yöntemi ile karşılaştırılmıştır. Çalışmaların gerçekleştirilebilmesi için öncelikle demir yatağını katı modeli yapılmış ve bu katı modeli temsil eden blok model oluşturulmuştur. Daha sonra girdi olarak bu kompozitlerin X, Y ve Z değerleri kullanılmış çıktı olarak ise tenör değerleri dikkate alınmıştır. Yukarıda değinilen üç makine öğrenmesi yaklaşımı ile modeller ayrı ayrı eğitilmiştir. Yaklaşımların kendine has parametrelerinin tahmininde deneme yanılma yöntemi tercih edilmiştir. Eğitilen modeller ile blok model kestirimleri gerçekleştirilmiştir. Sonuçlar makine öğrenme algoritmalarının da yaygın kullanılan Krigleme gibi yumuşatma özelliğinin bulunduğunu göstermektedir. Diğer bir değişle, elde edilen sonuçların standart sapması kompozitlerin standart sapmasından düşüktür. Diğer bir önemli bulgu da makine öğrenme yöntemlerinin veri kümesi dışında bulunan değerleri tahmin edecek şekilde eğitilebileceğidir. Bu durum konumsal tenör kestirimlerinde istenilen bir özellik değildir. Ayrıca eğitilen modeller genel itibari ile kompozitlerin ortalamalarına yakın sonuçlar çıkarsa da Derin Sinir Ağları modeli kompozitlerin ortalamasından ciddi sapma göstermiştir. Bu durum tüm makine öğrenme yaklaşımlarının doğrudan konumsal kestirimde kullanılamayacağını ve elde edilen sonuçların dikkatlice incelenmesi gerektiğini göstermektedir

References

  • [1] F. Atalay, M. S. Ünal, and S. Y. Kıllıoğlu, "Bir Demir Yatağında Radyal Temelli Fonksiyon ve Ortalamasız Krigleme Kestirimlerinin Karşılaştırılması," Avrupa Bilim ve Teknoloji Dergisi, no. 27, pp. 303-310, 2021.
  • [2] A. M. Albora, "Investigation of Bingöl Iron Ore Reserves Using Wavelet Cellular Neural Networks," International Journal Of Scientific Advances, vol. 2, no. 1, 2021, doi: 10.51542/ijscia.v2i1.9.
  • [3] M. Badel, S. Angorani, and M. Shariat Panahi, "The application of median indicator kriging and neural network in modeling mixed population in an iron ore deposit," Computers & Geosciences, vol. 37, no. 4, pp. 530-540, 2011, doi: 10.1016/j.cageo.2010.07.009.
  • [4] S. Chatterjee, S. Bandopadhyay, and D. Machuca, "Ore Grade Prediction Using a Genetic Algorithm and Clustering Based Ensemble Neural Network Model," Mathematical Geosciences, vol. 42, no. 3, pp. 309-326, 2010, doi: 10.1007/s11004-010-9264-y.
  • [5] S. Dutta, D. Misra, R. Ganguli, B. Samanta, and S. Bandopadhyay, "A hybrid ensemble model of kriging and neural network for ore grade estimation," International Journal of Mining, Reclamation and Environment, vol. 20, no. 1, pp. 33-45, 2006, doi: 10.1080/13895260500322236.
  • [6] V. Rodriguez-Galiano, M. Sanchez-Castillo, M. Chica-Olmo, and M. Chica-Rivas, "Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines," Ore Geology Reviews, vol. 71, pp. 804-818, 2015, doi: 10.1016/j.oregeorev.2015.01.001.
  • [7] B. Samanta, S. Bandopadhyay, and R. Ganguli, "Comparative Evaluation of Neural Network Learning Algorithms for Ore Grade Estimation," Mathematical Geology, vol. 38, no. 2, pp. 175-197, 2006, doi: 10.1007/s11004-005-9010-z.
  • [8] M. Shabankareh and A. Hezarkhani, "Application of support vector machines for copper potential mapping in Kerman region, Iran," Journal of African Earth Sciences, vol. 128, pp. 116-126, 2017, doi: 10.1016/j.jafrearsci.2016.11.032.
  • [9] R. Shamsi, H. Dehghani, M. Jalali, and B. Jodeiri Shokri, "Ore grade estimation using the imperialist competitive algorithm (ICA)," Arabian Journal of Geosciences, vol. 14, no. 14, 2021, doi: 10.1007/s12517-021-07808-7.
  • [10] A. Skabar, "Modeling the Spatial Distribution of Mineral Deposits Using Neural Networks," Natural Resource Modeling, vol. 20, no. 3, pp. 435-450, 2008, doi: 10.1111/j.1939-7445.2007.tb00215.x.
  • [11] R. Zuo and E. J. M. Carranza, "Support vector machine: A tool for mapping mineral prospectivity," Computers & Geosciences, vol. 37, no. 12, pp. 1967-1975, 2011, doi: 10.1016/j.cageo.2010.09.014.
  • [12] T. B. Afeni, A. I. Lawal, and R. A. Adeyemi, "Re-examination of Itakpe iron ore deposit for reserve estimation using geostatistics and artificial neural network techniques," Arabian Journal of Geosciences, vol. 13, no. 14, 2020, doi: 10.1007/s12517-020-05644-9.
  • [13] B. Jafrasteh, N. Fathianpour, and A. Suárez, "Comparison of machine learning methods for copper ore grade estimation," Computational Geosciences, vol. 22, no. 5, pp. 1371-1388, 2018, doi: 10.1007/s10596-018-9758-0.
  • [14] A. D. Goswami, M. K. Mishra, and D. Patra, "Evaluation of machine learning algorithms for grade estimation using GRNN & SVR," Engineering Research Express, vol. 4, no. 3, 2022, doi: 10.1088/2631-8695/ac8912.
  • [15] M. M. Zaki et al., "A Novel Approach for Resource Estimation of Highly Skewed Gold Using Machine Learning Algorithms," Minerals, vol. 12, no. 7, 2022, doi: 10.3390/min12070900.
  • [16] S. Dutta, S. Bandopadhyay, R. Ganguli, and D. Misra, "Machine Learning Algorithms and Their Application to Ore Reserve Estimation of Sparse and Imprecise Data," Journal of Intelligent Learning Systems and Applications, vol. 02, no. 02, pp. 86-96, 2010, doi: 10.4236/jilsa.2010.22012.
  • [17] S. Soltani-Mohammadi, F. S. Hoseinian, M. Abbaszadeh, and M. Khodadadzadeh, "Grade estimation using a hybrid method of back-propagation artificial neural network and particle swarm optimization with integrated samples coordinate and local variability," Computers & Geosciences, vol. 159, 2022, doi: 10.1016/j.cageo.2021.104981.
  • [18] R. K. Singh, D. Ray, and B. C. Sarkar, "Mineral deposit grade assessment using a hybrid model of kriging and generalized regression neural network," Neural Computing and Applications, vol. 34, no. 13, pp. 10611-10627, 2022, doi: 10.1007/s00521-022-06951-w.
  • [19] Y. Zhang, S. Song, K. You, X. Zhang, and C. Wu, "Relevance vector machines using weighted expected squared distance for ore grade estimation with incomplete data," International Journal of Machine Learning and Cybernetics, vol. 8, no. 5, pp. 1655-1666, 2016, doi: 10.1007/s13042-016-0535-x.
  • [20] M. A. Mahboob, T. Celik, and B. Genc, "Review of machine learning-based Mineral Resource estimation," Journal of the Southern African Institute of Mining and Metallurgy, vol. 122, no. 11, pp. 1-10, 2023, doi: 10.17159/2411-9717/1250/2022.
  • [21] F. Atalay, "Estimation of Fe Grade at an Ore Deposit Using Extreme Gradient Boosting Trees (XGBoost)," Mining, Metallurgy & Exploration, pp. 1-10, 2024.
  • [22] M. Galetakis, A. Vasileiou, A. Rogdaki, V. Deligiorgis, and S. Raka, "Estimation of Mineral Resources with Machine Learning Techniques," presented at the International Conference on Raw Materials and Circular Economy, 2022.
  • [23] X.-l. Li, Y.-l. Xie, Q.-j. Guo, and L.-h. Li, "Adaptive ore grade estimation method for the mineral deposit evaluation," Mathematical and Computer Modelling, vol. 52, no. 11-12, pp. 1947-1956, 2010, doi: 10.1016/j.mcm.2010.04.018.
  • [24] F. Maepa, R. S. Smith, and A. Tessema, "Support vector machine and artificial neural network modelling of orogenic gold prospectivity mapping in the Swayze greenstone belt, Ontario, Canada," Ore Geology Reviews, vol. 130, 2021, doi: 10.1016/j.oregeorev.2020.103968.
  • [25] N. Mery and D. Marcotte, "Quantifying Mineral Resources and Their Uncertainty Using Two Existing Machine Learning Methods," Mathematical Geosciences, vol. 54, no. 2, pp. 363-387, 2021, doi: 10.1007/s11004-021-09971-9.
  • [26] B. Samanta, R. Ganguli, and S. Bandopadhyay, "Comparing the predictive performance of neural networks with ordinary kriging in a bauxite deposit," Mining Technology, vol. 114, no. 3, pp. 129-139, 2013, doi: 10.1179/037178405x53980.
  • [27] K. Mostafaei, S. maleki, and B. Jodeiri, "A new gold grade estimation approach by using support vector machine (SVM) and back propagation neural network (BPNN)- A Case study: Dalli deposit, Iran," 2022, doi: 10.21203/rs.3.rs-2008568/v1.
  • [28] N. B. Tsae, T. Adachi, and Y. Kawamura, "Application of Artificial Neural Network for the Prediction of Copper Ore Grade," Minerals, vol. 13, no. 5, 2023, doi: 10.3390/min13050658.
  • [29] X. Zhang, S. Song, J. Li, and C. Wu, "Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit," Acta Oceanologica Sinica, vol. 32, no. 8, pp. 16-25, 2013, doi: 10.1007/s13131-013-0337-x.
  • [30] A. G. Journel and C. J. Huijbregts, "Mining geostatistics," 1976.
  • [31] T. Hossen, S. J. Plathottam, R. K. Angamuthu, P. Ranganathan, and H. Salehfar, "Short-term load forecasting using deep neural networks (DNN)," in 2017 North American Power Symposium (NAPS), 2017: IEEE, pp. 1-6.
  • [32] A. L. Maas et al., "Building DNN acoustic models for large vocabulary speech recognition," Computer Speech & Language, vol. 41, pp. 195-213, 2017.
  • [33] S. Wang, F. Shui, T. Stratford, J. Su, and B. Li, "Modelling nonlinear shear creep behaviour of a structural adhesive using deep neural networks (DNN)," Construction and Building Materials, vol. 414, p. 135083, 2024.
  • [34] W. Samek, G. Montavon, S. Lapuschkin, C. J. Anders, and K.-R. Müller, "Explaining deep neural networks and beyond: A review of methods and applications," Proceedings of the IEEE, vol. 109, no. 3, pp. 247-278, 2021.
  • [35] A. J. Smola and B. Schölkopf, "A tutorial on support vector regression," Statistics and computing, vol. 14, pp. 199-222, 2004.
  • [36] H. Drucker, C. J. Burges, L. Kaufman, A. Smola, and V. Vapnik, "Support vector regression machines," Advances in neural information processing systems, vol. 9, 1996. [37] T. Chen, "Xgboost: extreme gradient boosting," R package version 0.4-2, vol. 1, no. 4, 2015.
Year 2024, Volume: 15 Issue: 4, 907 - 916
https://doi.org/10.24012/dumf.1569827

Abstract

References

  • [1] F. Atalay, M. S. Ünal, and S. Y. Kıllıoğlu, "Bir Demir Yatağında Radyal Temelli Fonksiyon ve Ortalamasız Krigleme Kestirimlerinin Karşılaştırılması," Avrupa Bilim ve Teknoloji Dergisi, no. 27, pp. 303-310, 2021.
  • [2] A. M. Albora, "Investigation of Bingöl Iron Ore Reserves Using Wavelet Cellular Neural Networks," International Journal Of Scientific Advances, vol. 2, no. 1, 2021, doi: 10.51542/ijscia.v2i1.9.
  • [3] M. Badel, S. Angorani, and M. Shariat Panahi, "The application of median indicator kriging and neural network in modeling mixed population in an iron ore deposit," Computers & Geosciences, vol. 37, no. 4, pp. 530-540, 2011, doi: 10.1016/j.cageo.2010.07.009.
  • [4] S. Chatterjee, S. Bandopadhyay, and D. Machuca, "Ore Grade Prediction Using a Genetic Algorithm and Clustering Based Ensemble Neural Network Model," Mathematical Geosciences, vol. 42, no. 3, pp. 309-326, 2010, doi: 10.1007/s11004-010-9264-y.
  • [5] S. Dutta, D. Misra, R. Ganguli, B. Samanta, and S. Bandopadhyay, "A hybrid ensemble model of kriging and neural network for ore grade estimation," International Journal of Mining, Reclamation and Environment, vol. 20, no. 1, pp. 33-45, 2006, doi: 10.1080/13895260500322236.
  • [6] V. Rodriguez-Galiano, M. Sanchez-Castillo, M. Chica-Olmo, and M. Chica-Rivas, "Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines," Ore Geology Reviews, vol. 71, pp. 804-818, 2015, doi: 10.1016/j.oregeorev.2015.01.001.
  • [7] B. Samanta, S. Bandopadhyay, and R. Ganguli, "Comparative Evaluation of Neural Network Learning Algorithms for Ore Grade Estimation," Mathematical Geology, vol. 38, no. 2, pp. 175-197, 2006, doi: 10.1007/s11004-005-9010-z.
  • [8] M. Shabankareh and A. Hezarkhani, "Application of support vector machines for copper potential mapping in Kerman region, Iran," Journal of African Earth Sciences, vol. 128, pp. 116-126, 2017, doi: 10.1016/j.jafrearsci.2016.11.032.
  • [9] R. Shamsi, H. Dehghani, M. Jalali, and B. Jodeiri Shokri, "Ore grade estimation using the imperialist competitive algorithm (ICA)," Arabian Journal of Geosciences, vol. 14, no. 14, 2021, doi: 10.1007/s12517-021-07808-7.
  • [10] A. Skabar, "Modeling the Spatial Distribution of Mineral Deposits Using Neural Networks," Natural Resource Modeling, vol. 20, no. 3, pp. 435-450, 2008, doi: 10.1111/j.1939-7445.2007.tb00215.x.
  • [11] R. Zuo and E. J. M. Carranza, "Support vector machine: A tool for mapping mineral prospectivity," Computers & Geosciences, vol. 37, no. 12, pp. 1967-1975, 2011, doi: 10.1016/j.cageo.2010.09.014.
  • [12] T. B. Afeni, A. I. Lawal, and R. A. Adeyemi, "Re-examination of Itakpe iron ore deposit for reserve estimation using geostatistics and artificial neural network techniques," Arabian Journal of Geosciences, vol. 13, no. 14, 2020, doi: 10.1007/s12517-020-05644-9.
  • [13] B. Jafrasteh, N. Fathianpour, and A. Suárez, "Comparison of machine learning methods for copper ore grade estimation," Computational Geosciences, vol. 22, no. 5, pp. 1371-1388, 2018, doi: 10.1007/s10596-018-9758-0.
  • [14] A. D. Goswami, M. K. Mishra, and D. Patra, "Evaluation of machine learning algorithms for grade estimation using GRNN & SVR," Engineering Research Express, vol. 4, no. 3, 2022, doi: 10.1088/2631-8695/ac8912.
  • [15] M. M. Zaki et al., "A Novel Approach for Resource Estimation of Highly Skewed Gold Using Machine Learning Algorithms," Minerals, vol. 12, no. 7, 2022, doi: 10.3390/min12070900.
  • [16] S. Dutta, S. Bandopadhyay, R. Ganguli, and D. Misra, "Machine Learning Algorithms and Their Application to Ore Reserve Estimation of Sparse and Imprecise Data," Journal of Intelligent Learning Systems and Applications, vol. 02, no. 02, pp. 86-96, 2010, doi: 10.4236/jilsa.2010.22012.
  • [17] S. Soltani-Mohammadi, F. S. Hoseinian, M. Abbaszadeh, and M. Khodadadzadeh, "Grade estimation using a hybrid method of back-propagation artificial neural network and particle swarm optimization with integrated samples coordinate and local variability," Computers & Geosciences, vol. 159, 2022, doi: 10.1016/j.cageo.2021.104981.
  • [18] R. K. Singh, D. Ray, and B. C. Sarkar, "Mineral deposit grade assessment using a hybrid model of kriging and generalized regression neural network," Neural Computing and Applications, vol. 34, no. 13, pp. 10611-10627, 2022, doi: 10.1007/s00521-022-06951-w.
  • [19] Y. Zhang, S. Song, K. You, X. Zhang, and C. Wu, "Relevance vector machines using weighted expected squared distance for ore grade estimation with incomplete data," International Journal of Machine Learning and Cybernetics, vol. 8, no. 5, pp. 1655-1666, 2016, doi: 10.1007/s13042-016-0535-x.
  • [20] M. A. Mahboob, T. Celik, and B. Genc, "Review of machine learning-based Mineral Resource estimation," Journal of the Southern African Institute of Mining and Metallurgy, vol. 122, no. 11, pp. 1-10, 2023, doi: 10.17159/2411-9717/1250/2022.
  • [21] F. Atalay, "Estimation of Fe Grade at an Ore Deposit Using Extreme Gradient Boosting Trees (XGBoost)," Mining, Metallurgy & Exploration, pp. 1-10, 2024.
  • [22] M. Galetakis, A. Vasileiou, A. Rogdaki, V. Deligiorgis, and S. Raka, "Estimation of Mineral Resources with Machine Learning Techniques," presented at the International Conference on Raw Materials and Circular Economy, 2022.
  • [23] X.-l. Li, Y.-l. Xie, Q.-j. Guo, and L.-h. Li, "Adaptive ore grade estimation method for the mineral deposit evaluation," Mathematical and Computer Modelling, vol. 52, no. 11-12, pp. 1947-1956, 2010, doi: 10.1016/j.mcm.2010.04.018.
  • [24] F. Maepa, R. S. Smith, and A. Tessema, "Support vector machine and artificial neural network modelling of orogenic gold prospectivity mapping in the Swayze greenstone belt, Ontario, Canada," Ore Geology Reviews, vol. 130, 2021, doi: 10.1016/j.oregeorev.2020.103968.
  • [25] N. Mery and D. Marcotte, "Quantifying Mineral Resources and Their Uncertainty Using Two Existing Machine Learning Methods," Mathematical Geosciences, vol. 54, no. 2, pp. 363-387, 2021, doi: 10.1007/s11004-021-09971-9.
  • [26] B. Samanta, R. Ganguli, and S. Bandopadhyay, "Comparing the predictive performance of neural networks with ordinary kriging in a bauxite deposit," Mining Technology, vol. 114, no. 3, pp. 129-139, 2013, doi: 10.1179/037178405x53980.
  • [27] K. Mostafaei, S. maleki, and B. Jodeiri, "A new gold grade estimation approach by using support vector machine (SVM) and back propagation neural network (BPNN)- A Case study: Dalli deposit, Iran," 2022, doi: 10.21203/rs.3.rs-2008568/v1.
  • [28] N. B. Tsae, T. Adachi, and Y. Kawamura, "Application of Artificial Neural Network for the Prediction of Copper Ore Grade," Minerals, vol. 13, no. 5, 2023, doi: 10.3390/min13050658.
  • [29] X. Zhang, S. Song, J. Li, and C. Wu, "Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit," Acta Oceanologica Sinica, vol. 32, no. 8, pp. 16-25, 2013, doi: 10.1007/s13131-013-0337-x.
  • [30] A. G. Journel and C. J. Huijbregts, "Mining geostatistics," 1976.
  • [31] T. Hossen, S. J. Plathottam, R. K. Angamuthu, P. Ranganathan, and H. Salehfar, "Short-term load forecasting using deep neural networks (DNN)," in 2017 North American Power Symposium (NAPS), 2017: IEEE, pp. 1-6.
  • [32] A. L. Maas et al., "Building DNN acoustic models for large vocabulary speech recognition," Computer Speech & Language, vol. 41, pp. 195-213, 2017.
  • [33] S. Wang, F. Shui, T. Stratford, J. Su, and B. Li, "Modelling nonlinear shear creep behaviour of a structural adhesive using deep neural networks (DNN)," Construction and Building Materials, vol. 414, p. 135083, 2024.
  • [34] W. Samek, G. Montavon, S. Lapuschkin, C. J. Anders, and K.-R. Müller, "Explaining deep neural networks and beyond: A review of methods and applications," Proceedings of the IEEE, vol. 109, no. 3, pp. 247-278, 2021.
  • [35] A. J. Smola and B. Schölkopf, "A tutorial on support vector regression," Statistics and computing, vol. 14, pp. 199-222, 2004.
  • [36] H. Drucker, C. J. Burges, L. Kaufman, A. Smola, and V. Vapnik, "Support vector regression machines," Advances in neural information processing systems, vol. 9, 1996. [37] T. Chen, "Xgboost: extreme gradient boosting," R package version 0.4-2, vol. 1, no. 4, 2015.
There are 36 citations in total.

Details

Primary Language Turkish
Subjects Mining Engineering (Other)
Journal Section Articles
Authors

Fırat Atalay 0000-0001-6349-7745

Early Pub Date December 23, 2024
Publication Date
Submission Date October 18, 2024
Acceptance Date December 12, 2024
Published in Issue Year 2024 Volume: 15 Issue: 4

Cite

IEEE F. Atalay, “Demir Tenör Değerlerinin Kestiriminde Makine Öğrenme Yöntemlerinin Karşılaştırılması”, DUJE, vol. 15, no. 4, pp. 907–916, 2024, doi: 10.24012/dumf.1569827.
DUJE tarafından yayınlanan tüm makaleler, Creative Commons Atıf 4.0 Uluslararası Lisansı ile lisanslanmıştır. Bu, orijinal eser ve kaynağın uygun şekilde belirtilmesi koşuluyla, herkesin eseri kopyalamasına, yeniden dağıtmasına, yeniden düzenlemesine, iletmesine ve uyarlamasına izin verir. 24456