The Application of Artificial Neural Networks to Ore Reserve Estimation at Choghart Iron Ore Deposit

Document Type : Research Article

Authors

Dept. of Mining and Metallurgy, Yazd University, Iran

Abstract

Geo-statistical methods for reserve estimation are difficult to use when stationary conditions are not satisfied. Artificial Neural Networks (ANNs) provide an alternative to geo-statistical techniques while considerably reducing the processing time required for development and application. In this paper the ANNs was applied to the Choghart iron ore deposit in Yazd province of Iran. Initially, an optimum Multi Layer Perceptron (MLP) was constructed to estimate the Fe grade within orebody using the whole ore data of the deposit. Sensitivity analysis was applied for a number of hidden layers and neurons, different types of activation functions and learning rules. Optimal architectures for iron grade estimation were 3-20-10-1. In order to improve the network performance, the deposit was divided into four homogenous zones. Subsequently, all sensitivity analyses were carried out on each zone.  Finally, a different optimum network was trained and Fe was estimated separately for each zone. Comparison of correlation coefficient (R) and least mean squared error (MSE) showed that the ANNs performed on four homogenous zones were far better than the nets applied to the overall ore body. Therefore, these optimized neural networks were used to estimate the distribution of iron grades and the iron resource in Choghart deposit. As a result of applying ANNs, the tonnage of ore for Choghart deposit is approximately estimated at 135.8 million tones with average grade of Fe at 56.14 percent. Results of reserve estimation using ANNs showed a good agreement with the geo-statistical methods applied to this ore body in another work.

Keywords

Main Subjects

References

[1] Misra, D., Samanta, B., Dutta, S. and Bandopadhyay, S. Evaluation of artificial neural networks and Kriging for the prediction of arsenic in Alaskan bedrock-derived stream sediments using gold concentration data. International Journal of Mining, Reclamation and Environment, (2007). Vol. 21, pp. 282-294.
[2] Diehl, P.. Quantification of the term “geological assurance” in coal classification using geostatistical methods. Klassifikation von Lagerstätten, (1997) Vol. 79, pp. 187–203.
[3] Bardossy, G. and Fodor, J.. Evaluation of uncertainties and risks in geology. Springer Verlag, (2004) p. 222.
[4] Wu, X. and Zhou, Y.. Reserve estimation using neural network techniques. Computer and Geosciences, (1993) Vol. 19, pp. 567 – 575.
[5] Rizzo, D. M. and Dougherty, D. E.. Characterization of aquifer properties using artificial neural networks: neural kriging. Water resources, (1994) Vol. 30, pp. 483 – 497.
[6] Singer, D. A. and Kouda, R.. Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku district, Japan. Mathematical Geology, (1996) Vol. 28, pp. 1017-1023.
[7] Yama, B. R. and Lineberry, G. T.. Artificial neural network application for a predictive task in mining, Mining Engineering, (1999) Vol. 51, pp. 59-64.
[8] Ke, J., Neural network modeling for placer ore grade spatial variability. Ph.D. dissertation, (2002) University of Alaska, Fairbanks.
[9] Koike, K., Matsuda, S., Suzuki, T. and Ohmi, M.. Neural network-based estimation of principal metal contents in the Hokuroku District, northern Japan, for Exploring Kuroko-type deposits. Natural Resources, (2002) Vol. 11, pp. 135-156.
[10] Koike, K. and Matsuda, S.. Characterizing content distributions of impurities in a limestone mine using a feedforward neural network. Natural Resources, (2003) Vol. 12, pp. 209-223.
[11] Samanta, B., Bandopadhyay, S., Ganguli, R. and Dutta, S.. An application of neural networks to gold grade estimation in Nome placer deposit. Journal of South African Inst. Min. Metal., (2005) Vol. 105, pp.237-246.
[12] Dutta, S., Misra, D., Ganguli, R., Samanta, B. and Bandopadhyay, S.. A hybrid ensemble model of Kriging and neural network for ore grade estimation. International Journal of Mining, Reclamation and Environment, (2006) Vol. 20, pp. 33-45.
[13] Dutta, S.. predictive performance of machine learning algorithms for ore reserve estimation in sparse and imprecise data. Ph.D. dissertation, (2006) University of Alaska, fairbanks.
[14] Omid, M., Baharlooei, A. and Ahmadi, H. Modeling drying kinetics of pistachio nuts with multilayer feed-forward neural network, Drying Technology, (2009) 27(10), pp.1069-1077.
[15] Bishop, C. M.. Neural networks for pattern recognition. (1996) Oxford, oxford university press.
[16] Mittal, G. S. and Zhang, J.. Prediction of temperature and moisture content of frankfurters during thermal processing using neural network. Meat Science, (2000) Vol. 55, pp. 13-24.
[17] Lertworasirikul, S.. Drying kinetics of semi-finished cassava crackers: A comparative study. Lebensmittel-Wissenschaft und-Technologie, (2008) Vol. 41, pp. 1360-1371.
[18] Neurosolution 5 user manual. (2005). Gainesville : NeuroDimension.
[19] Foerster, H. and Jafarzadeh, A., The Bafq mining district in central Iran; a highly mineralized Infracambrian volcanic field. Economic Geology, (1994) 89 (8), 1697-1721.
[20] Moore, F. and Modabberi, S., Origin of Choghart iron oxide deposit, Bafgh mining district, Central Iran: new isotopic and geochemical evidence. Journal of Sciences, (2003) 14(3), 259-269.
[21] Dehghani, M., Geological remodeling of Choghart ore deposit based on production drilling using geostatistics. MSc. Thesis, (2008) University of Yazd, Iran.
[22] Morshedy, A. H., Torabi, S. A., and Memarian, H., A new method for 3D designing of complementary exploration drilling layout based on ore value and objective functions. Arabian Journal of Geosciences, (2015) 8(10), 8175-8195.
[23] Bowden, G. J., Maier, H. R. and Dandy, G. C., Optimal division of data for neural network models in water resources application. Water Resourc. Res., (2002)  Vol. 38(2), pp. 1-11.
[24] Samanta, B., Bandopadhyay, S., Ganguli, R. and Dutta, S.. Sparse data division using data segmentation and Kohonen network for neural network and geostatistical ore grade modeling in Nome offshore placer deposit. Natural Resources Research, (2004) Vol. 13, pp. 189-200.
[25] Surpac software international. (2002).  Surpac Vision 6.1.2 User Manual. Beijing, Surpac Minex Group.
[26] Blum, A. (1992). Neural Networks in C++. Wiley.
[27] Boger, Z. and Guterman, H.. Knowledge extraction from artificial neural network models. IEEE systems, Man and Cybernetics Conference, (1997) Orlando. 
[28] Swingler, K.. Applying neural networks. (1996) Landon, Academic Press.
[29] Berry, M. J. A. and Linoff, G.. Data Mining Techniques. (1997), John Wiley & Sons.
[30] Suykens, J. A. K., Joos, P. L. V. and Bart, L. R. D.. Artificial neural networks for modeling and control of non-linear systems. (1996) Kluwer Academic Publishers, p. 235.
[31] Ke, J., Bandopadhyay, S. and Ganguli R.. Sensitivity analysis of activation functions in neural network for ore grade estimation. (2007) APCOM, Santiago, Chile.
Journal of Analytical and Numerical Methods in Mining Engineering
Volume 6, Special Issue
January 2017
Pages 73-83

Files

History

  • Receive Date: 17 September 2015
  • Revise Date: 01 May 2016
  • Accept Date: 24 April 2017

Share

How to cite

Statistics