Document Type : Original Research Paper

Authors

1 Department of Mining Engineering, Imam Khomeini International University, Ghazvin, Iran

2 Mining plus company, Vancouver, Canada

3 Zarshouran gold mines and mineral industries development company, Tekab, Iran

Abstract

The exploration methods are divided into the direct and indirect categories. Among these, the indirect geophysical methods are more time- and cost-effective compared with the direct methods. The target of the geophysical investigations is to obtain an accurate image from the underground features. The Induced polarization (IP) is one of the common methods used for metal sulfide ore detection. Since metal ores are scattered in the host rock in the Zarshouran mine area, IP is considered as a major exploration method. Parallel to IP, the resistivity data gathering and processing are done to get a more accurate interpretation. In this work, we try to integrate the IP/RS geophysical attributes with borehole grade analyses and geological information using the cuckoo search machine-learning algorithm in order to estimate the silver grade values. The results obtained show that it is possible to estimate the grade values from the geophysical data accurately, especially in the areas without drilling data. This reduces the costs and time of the exploration and ore reserves estimation. Comparing the results of the intelligent inversion with the numerical methods, as the major tools to invert the geophysical data to the ore model, demonstrate a superior correlation between the results.

Keywords

[1]. Alimoradi, A. (2006). A comparison between RMR values of TSP-203 and the real values. MSc. Thesis in Mine Exploration Engineering (Third Chapter), Shahrood University of Technology, 45-64.
[2]. Alimoradi, A., Moradzadeh, A., Naderi, R., Zad Salehi, M. and Etemadi, A. (2008). Prediction of geological hazardous zones in front of a tunnel face using TSP-203 and artificial neural networks, Tunnelling and Underground Space Technology, 23, 711-717.
[3]. Alimoradi, A., Angorani, S., Ebrahimzadeh, M. and Shariat Panahi, M. (2011).  Magnetic inverse modelling of a dike using the artificial neural network approach, Near Surface Geophysics, 9, 339-347.
[4]. Bishop, C.M. (1995). Neural networks for pattern recognition, 1st edition, Oxford Clarendon.
[5]. Brown, W.M., Gedeon, T.D., Groves, D.I. and Barnes, R.G. (2000). Artificial neural networks: A new method for mineral prospectivity mapping, Auatrailian Journal of Earth Science, 47, 757-770.
[6]. Brown, W.M., Gedeon, T.D. and Groves, D.I. (2003). Use of noise to augment training data: A neural network method of mineral potential mapping in regions of limited known deposit examples, Journal of Natural Resource Research, 12, 141-152.
[7]. Calderón-Macías, C., Sen, M.K. and Stoffa, P.L. (2001). Artificial neural networks for parameter estimation in geophysics, Geophysical Prospecting, 48, 21–47.
[8]. Demuth, H., Beale, M. (2002). Neural network toolbox for use with MATLAB, Version 3.0.
[9]. Douglas, W., Oldenburg, Yaoguo, Li. (1999). Estimating depth of investigation in dc resistivity and IP surveys, Geophysics, 64, 403-416.
[10]. El-Qady, G., Ushijima, K. (2001). Inversion of DC resistivity data using neural networks, Geophysical Prospecting, 49, 417-430.
[11]. Hagan, M.T., Demuth, H.B. and Beale, M. (1996). Neural network design, PWS Publishing Company, Boston, MA.
[12]. Hasani Pak, A., Shoja-at, B. (2000). Metal-nonmetal ore modeling and their exploration application, University of Tehran.
[13]. Hosseinali, F. and Alesheikh, A.A. (2008). Weighting spatial information in GIS for copper mining exploration, Journal of Applied Science, 5, 1187-1198.
[14]. Loke, M. H. (1999). Electrical imaging surveys for environmental and engineering studies: A practical guide to 2-D and 3-D surveys, 1-4.
[15]. Nazri, M.N., Abdullah Khan, M.Z.R. (2013). A new Levenberg Marquardt based back propagation algorithm trained with Cuckoo search, Procedia Technology, 11, 18-23.
[16]. Porwal, A. (2006). Mineral potential mapping with mathematical geological models, PhD thesis, University of Utrecht.
[17]. Poulton, M., El-Fouly, A. (1991). Preprocessing GPR signatures for cascading neural network classification, 61st SEG meeting, Houston, USA, Expanded Abstracts 507–509.
[18]. Poulton, M., Sternberg, K., and Glass, C. (1992). Neural network pattern recognition of subsurface EM images, Journal of Applied Geophysics, 29, 21–36.
[19]. Sanchez, J.P., Chica-Olmo, M., and Abarca-Hernandez, F. (2003). Artificial neural network as a tool for mineral potential mapping with GIS, Journal of Remote Sensing, 24, 1151-1156.
[20]. Selley, R.C., Cocks, R.M. and Plimer, I.R. (2005). Encyclopedia of geology, Vol. 1, 1st edition, Elsevier Ltd, Oxford.
[21]. Skabar, A.A. (2005). Mapping mineralization probabilities using multilayer perceptrons, Journal of Natural Resource Research, 14, 109-123.
[22]. Singer, D.A. and Kouda, R.A. (1997). Classification of mineral deposit into types using mineralogy with a probabilistic neural network, Nonrenewable Resources, 6, 27-32.
[23]. Singer, D.A. and Kouda, R.A. (1999). Comparison of the weights-of-evidence method and probabilistic neural networks, Natural Resources Research, 8, 287-298.
[24]. Singh, U.K., Tiwari, R.K. and Singh, S.B. (2005). One-dimensional inversion of geoelectrical resistivity sounding data using artificial neural networks – a case study, Computational Geoscience, 31, 99– 108.
[25]. Spichak, V.V., Popova, I.V. (2000). Artificial neural network inversion of MT – data in terms of 3D earth macro – parameters, Geophysical Journal International, 42, 15–26.
[26]. Yang, X.S. and Deb, S. (2010). Engineering optimization by Cuckoo Search, International Journal of Mathematical Modelling and Numerical, 1, 330-343.
[30]. Yuval, Douglas, W., Oldenburg. (1995). DC resistivity and IP methods in acid mine drainage problems: results from the Copper Cliff mine tailings impoundments, Journal of Applied Geophysics, 34, 187-198.