Machine Learning Algorithms and Their Application to Ore Reserve Estimation of Sparse and Imprecise Data

ABSTRACT

Traditional geostatistical estimation techniques have been used predominantly by the mining industry for ore reserve estimation. Determination of mineral reserve has posed considerable challenge to mining engineers due to the geological complexities of ore body formation. Extensive research over the years has resulted in the development of several state-of-the-art methods for predictive spatial mapping, which could be used for ore reserve estimation; and recent advances in the use of machine learning algorithms (MLA) have provided a new approach for solving the prob-lem of ore reserve estimation. The focus of the present study was on the use of two MLA for estimating ore reserve: namely, neural networks (NN) and support vector machines (SVM). Application of MLA and the various issues involved with using them for reserve estimation have been elaborated with the help of a complex drill-hole dataset that exhibits the typical properties of sparseness and impreciseness that might be associated with a mining dataset. To investigate the accuracy and applicability of MLA for ore reserve estimation, the generalization ability of NN and SVM was compared with the geostatistical ordinary kriging (OK) method.

Traditional geostatistical estimation techniques have been used predominantly by the mining industry for ore reserve estimation. Determination of mineral reserve has posed considerable challenge to mining engineers due to the geological complexities of ore body formation. Extensive research over the years has resulted in the development of several state-of-the-art methods for predictive spatial mapping, which could be used for ore reserve estimation; and recent advances in the use of machine learning algorithms (MLA) have provided a new approach for solving the prob-lem of ore reserve estimation. The focus of the present study was on the use of two MLA for estimating ore reserve: namely, neural networks (NN) and support vector machines (SVM). Application of MLA and the various issues involved with using them for reserve estimation have been elaborated with the help of a complex drill-hole dataset that exhibits the typical properties of sparseness and impreciseness that might be associated with a mining dataset. To investigate the accuracy and applicability of MLA for ore reserve estimation, the generalization ability of NN and SVM was compared with the geostatistical ordinary kriging (OK) method.

KEYWORDS

Machine Learning Algorithms, Neural Networks, Support Vector Machine, Genetic Algorithms, Supervised

Machine Learning Algorithms, Neural Networks, Support Vector Machine, Genetic Algorithms, Supervised

Cite this paper

nullS. 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. 2 No. 2, 2010, pp. 86-96. doi: 10.4236/jilsa.2010.22012.

nullS. Dutta, S. Bandopadhyay, R. Ganguli and D. Misra, "Machine Learning Algorithms and Their Application to Ore Reserve Estimation of Sparse and Imprecise Data,"

References

[1] S. Dutta, D. Mishra, R. Ganguli and B. Samanta, “Investigation of two Neural Network Ensemble Methods for the Prediction of Bauxite Ore Deposit,” Proceedings of the 6th International Conference on Information Technology, Bhubaneswar, December 22-25, 2003.

[2] S. Dutta, R. Ganguli and B. Samanta, “Comparative Evaluation of Radial Basis Functions and Kriging for Ore Grade Estimation,” 32nd International Symposium of the application of Computers and Operation research in Mineral Industry, Arizona, USA, 2005, pp. 203-211.

[3] S. Dutta, D. Misra, R. Ganguli, B. Samanta and S. Ban-dopadhyay, “A Hybrid Ensemble Model of Kriging and Neural Network for Ore Grade Estimation,” International Journal of Surface Mining, Reclamation and Environment, Vol. 20, No. 1, 2006a, pp. 33-46.

[4] S. Dutta, S. Bandopadhyay and B. Samanta, “Support Vector Machines—An Emerging Technique for Ore Reserve Estimation,” Proceedings of the Sixth International Symposium on Information Technology Applied to Mining (CD), Peruvian Institute of Mining Engineers, 2006b.

[5] B. Samanta, S. Bandopadhyay, R. Ganguli and S. Dutta, “A Comparative Study of the Performance of Single Neural Network vs. Adaboost Algorithm Based Combination of Multiple Neural Networks for Mineral Resource Estimation,” Journal of South African Institute of Mining and Metallurgy, Vol. 105, No. 4, 2005a, pp. 237-246.

[6] B. Samanta, R. Ganguli and S. Bandopadhyay, “Comparing the Predictive Performance of Neural Networks with Ordinary Kriging in a Bauxite Deposit,” Transactions of Institute of Mining and Metallurgy, Section A, Mining Technology, Vol. 114, No. 3, 2005b, pp. 129-139.

[7] D. M. Hopkins and L. MacNeil, “Dredged Area: Alaska Division of Mines and Minerals,” 1960.

[8] P. C. Rusanowski, “Nome Offshore Gold Placer Project: Nova,” Natural Resources Corp., Alaska, 1994.

[9] J. Ke, “Neural Network Modeling for Placer Ore Grade Spatial Variability,” Ph.D. dissertation, University of Alaska Fairbanks, Fairbanks, 2002.

[10] G. J. Bowden, H. R. Maier and G. C. Dandy, “Optimal Division of Data for Neural Network Models in Water Resources Application,” Water Resources Research, Vol. 38, No. 2, 2002, pp. 1-11.

[11] S. Yu, R. Ganguli, D. E. Walsh, S. Bandopadhyay and S. L. Patil, “Calibration of Online Analyzers Using Neural Networks,” Mining Engineering, Vol. 56, No. 9, 2003, pp. 99-102.

[12] R. Ganguli and S. Bandopadhyay, “Dealing with Sparse Data Issues in a Mineral Industry Neural Network Application,” Proceedings Computer Applications in the Mineral Industry (CAMI), Calgary, Alberta, Canada, 2003, pp. 1-5.

[13] B. Samanta, S. Bandopadhyay and R. Ganguli, “Data Segmentation and Genetic Algorithms for Sparse Data Division in Nome Placer Gold Grade Estimation Using Neural Network and Geostatistics,” Exploration and Mining Geology, Vol. 11, 2004, pp. 69-76.

[14] S. Dutta, “Predictive Performance of Machine Learning Algorithms for Ore Reserve Estimation in Sparse and Imprecise Data,” Ph.D. dissertation, University of Alaska Fairbanks, Fairbanks, 2006.

[15] M. T. Hagan, H. B. Demuth and M. Beale, “Neural Network Design,” PWS Publishing Company, Boston, MA, 1995.

[16] S. Haykins, “Neural Networks: A Comprehensive Foundation,” 2nd Edition, Prentice Hall, New Jersey, 1999.

[17] C. M. Bishop, “Neural Networks for Pattern Recognition,” Clarendon Press, Oxford, 1995.

[18] S. Dutta and R. Ganguli, “Application of Boosting Algorithm in Neural Network Based Ash Measurement Using Online Ash Analyzers,” 32nd International Symposium of the Application of Computers and Operation Research in Mineral Industry, Arizona, USA, 2005b.

[19] V. Kecman, “Learning and Soft Computing: Support Vector Machines, Neural Network and Fuzzy Logic Models,” MIT Publishers, USA, 2000.

[20] V. Kecman, “Support Vector Machines Basics—An Introduction Only,” University of Auckland, School of En-gineering Report, New Zealand, 2004.

[21] A. J. Smola and B. Scholkopf, “A Tutorial on Support Vector Regression,” Statistics and Computing, Vol. 14, No. 3, 2004, pp. 199-222.

[22] V. Vapnik, “Statistical Learning Theory,” John Wiley and Sons, New York, 1998.

[23] C. Cortes, and V. Vapnik, “Support Vector Networks,” Machine Learning, Vol. 20, No. 3, 1995, pp. 273-297.

[24] R. E. Miller, “Optimization-Foundations and Applica-tions,” John Wiley and Sons, New York, 2000.

[25] C. C. Chang and C. Lin, “LIBSVM: A Library for Support Vector Machines,” 2001. Internet Available: http:// www.csie.ntu.edu.tw/~cjlin/libsvm

[26] T. Hastie, R. Tibshirani and J. Friedman, “The Elements of Statistical Learning Theory—Data Mining, Inference and Prediction,” Springer, New York, 2001.

[27] G. Dubois, “European Report on Automatic Mapping Algorithms for Routine and Emergency Monitoring Data,” Office for Official Publications of the European Communities, Luxembourg, 2005.

[28] S. Dutta, R. Ganguli and B. Samanta, “Investigation of two Neural Network Methods in an Automatic Mapping Exercise,” Journal of Applied GIS, Vol. 1, No. 2, 2005a, pp. 1-19.

[29] S. Dutta, R. Ganguli and B. Samanta, “Investigation of two Neural Network Methods in an Automatic Aapping Exercise,” In: G. Dubois, Ed., European Report on Automatic Mapping Algorithms for Routine and Emergency Monitoring Data. Report on the Spatial Interpolation Comparison (SIC2004) Exercise, Office for Official Publications of the European Communities, Luxembourg, 2005c.

[1] S. Dutta, D. Mishra, R. Ganguli and B. Samanta, “Investigation of two Neural Network Ensemble Methods for the Prediction of Bauxite Ore Deposit,” Proceedings of the 6th International Conference on Information Technology, Bhubaneswar, December 22-25, 2003.

[2] S. Dutta, R. Ganguli and B. Samanta, “Comparative Evaluation of Radial Basis Functions and Kriging for Ore Grade Estimation,” 32nd International Symposium of the application of Computers and Operation research in Mineral Industry, Arizona, USA, 2005, pp. 203-211.

[3] S. Dutta, D. Misra, R. Ganguli, B. Samanta and S. Ban-dopadhyay, “A Hybrid Ensemble Model of Kriging and Neural Network for Ore Grade Estimation,” International Journal of Surface Mining, Reclamation and Environment, Vol. 20, No. 1, 2006a, pp. 33-46.

[4] S. Dutta, S. Bandopadhyay and B. Samanta, “Support Vector Machines—An Emerging Technique for Ore Reserve Estimation,” Proceedings of the Sixth International Symposium on Information Technology Applied to Mining (CD), Peruvian Institute of Mining Engineers, 2006b.

[5] B. Samanta, S. Bandopadhyay, R. Ganguli and S. Dutta, “A Comparative Study of the Performance of Single Neural Network vs. Adaboost Algorithm Based Combination of Multiple Neural Networks for Mineral Resource Estimation,” Journal of South African Institute of Mining and Metallurgy, Vol. 105, No. 4, 2005a, pp. 237-246.

[6] B. Samanta, R. Ganguli and S. Bandopadhyay, “Comparing the Predictive Performance of Neural Networks with Ordinary Kriging in a Bauxite Deposit,” Transactions of Institute of Mining and Metallurgy, Section A, Mining Technology, Vol. 114, No. 3, 2005b, pp. 129-139.

[7] D. M. Hopkins and L. MacNeil, “Dredged Area: Alaska Division of Mines and Minerals,” 1960.

[8] P. C. Rusanowski, “Nome Offshore Gold Placer Project: Nova,” Natural Resources Corp., Alaska, 1994.

[9] J. Ke, “Neural Network Modeling for Placer Ore Grade Spatial Variability,” Ph.D. dissertation, University of Alaska Fairbanks, Fairbanks, 2002.

[10] G. J. Bowden, H. R. Maier and G. C. Dandy, “Optimal Division of Data for Neural Network Models in Water Resources Application,” Water Resources Research, Vol. 38, No. 2, 2002, pp. 1-11.

[11] S. Yu, R. Ganguli, D. E. Walsh, S. Bandopadhyay and S. L. Patil, “Calibration of Online Analyzers Using Neural Networks,” Mining Engineering, Vol. 56, No. 9, 2003, pp. 99-102.

[12] R. Ganguli and S. Bandopadhyay, “Dealing with Sparse Data Issues in a Mineral Industry Neural Network Application,” Proceedings Computer Applications in the Mineral Industry (CAMI), Calgary, Alberta, Canada, 2003, pp. 1-5.

[13] B. Samanta, S. Bandopadhyay and R. Ganguli, “Data Segmentation and Genetic Algorithms for Sparse Data Division in Nome Placer Gold Grade Estimation Using Neural Network and Geostatistics,” Exploration and Mining Geology, Vol. 11, 2004, pp. 69-76.

[14] S. Dutta, “Predictive Performance of Machine Learning Algorithms for Ore Reserve Estimation in Sparse and Imprecise Data,” Ph.D. dissertation, University of Alaska Fairbanks, Fairbanks, 2006.

[15] M. T. Hagan, H. B. Demuth and M. Beale, “Neural Network Design,” PWS Publishing Company, Boston, MA, 1995.

[16] S. Haykins, “Neural Networks: A Comprehensive Foundation,” 2nd Edition, Prentice Hall, New Jersey, 1999.

[17] C. M. Bishop, “Neural Networks for Pattern Recognition,” Clarendon Press, Oxford, 1995.

[18] S. Dutta and R. Ganguli, “Application of Boosting Algorithm in Neural Network Based Ash Measurement Using Online Ash Analyzers,” 32nd International Symposium of the Application of Computers and Operation Research in Mineral Industry, Arizona, USA, 2005b.

[19] V. Kecman, “Learning and Soft Computing: Support Vector Machines, Neural Network and Fuzzy Logic Models,” MIT Publishers, USA, 2000.

[20] V. Kecman, “Support Vector Machines Basics—An Introduction Only,” University of Auckland, School of En-gineering Report, New Zealand, 2004.

[21] A. J. Smola and B. Scholkopf, “A Tutorial on Support Vector Regression,” Statistics and Computing, Vol. 14, No. 3, 2004, pp. 199-222.

[22] V. Vapnik, “Statistical Learning Theory,” John Wiley and Sons, New York, 1998.

[23] C. Cortes, and V. Vapnik, “Support Vector Networks,” Machine Learning, Vol. 20, No. 3, 1995, pp. 273-297.

[24] R. E. Miller, “Optimization-Foundations and Applica-tions,” John Wiley and Sons, New York, 2000.

[25] C. C. Chang and C. Lin, “LIBSVM: A Library for Support Vector Machines,” 2001. Internet Available: http:// www.csie.ntu.edu.tw/~cjlin/libsvm

[26] T. Hastie, R. Tibshirani and J. Friedman, “The Elements of Statistical Learning Theory—Data Mining, Inference and Prediction,” Springer, New York, 2001.

[27] G. Dubois, “European Report on Automatic Mapping Algorithms for Routine and Emergency Monitoring Data,” Office for Official Publications of the European Communities, Luxembourg, 2005.

[28] S. Dutta, R. Ganguli and B. Samanta, “Investigation of two Neural Network Methods in an Automatic Mapping Exercise,” Journal of Applied GIS, Vol. 1, No. 2, 2005a, pp. 1-19.

[29] S. Dutta, R. Ganguli and B. Samanta, “Investigation of two Neural Network Methods in an Automatic Aapping Exercise,” In: G. Dubois, Ed., European Report on Automatic Mapping Algorithms for Routine and Emergency Monitoring Data. Report on the Spatial Interpolation Comparison (SIC2004) Exercise, Office for Official Publications of the European Communities, Luxembourg, 2005c.