Prediction of Au grade in Carlin type using pathfinder elements by GMDH and MCMC in Zarshuran deposit

Document Type : Research Paper

Author

Mining Department, Arak university of Technology, Arak, Iran.

10.22059/ijmge.2026.401315.595299

Abstract

Pathfinder elements play a crucial role in the exploration of concealed and deep-seated mineral deposits. Their significance is particularly pronounced in the context of epithermal gold (Au) deposits, where their presence may serve as an indicator of nearby gold mineralization. Among these pathfinder elements, arsenic (As) and antimony (Sb) are considered the most critical for the exploration of epithermal Au systems. This study investigated Au Carlin type in the Zarshuran to highlight the utility of pathfinder elements in gold estimation. The analysis was conducted using the concentrations of 35 elements measured across 108 samples. The mineralization characteristics of the Zarshuran deposit exhibit notable similarities to those of epithermal gold deposits hosted in sedimentary rocks (Carlin-type), thus presenting a suitable exploration model for the northern Takab region. Selection of pathfinder elements was carried out through factor analysis, which revealed a strong positive correlation among Au, As, Cd, Pb, Sb, and Zn. Two predictive approaches were employed to estimate gold content: the Group Method of Data Handling (GMDH) neural network, and the Monte Carlo Markov Chain (MCMC) simulation. Neural network techniques, such as GMDH, are particularly well-suited for modeling datasets with both linear and nonlinear characteristics. In these models, As, Cd, Pb, Sb, and Zn were used as input variables. The predictive performance of the models was assessed using the coefficient of determination (R²). The GMDH neural network achieved a superior performance with an R² value of 0.9483, outperforming the MCMC simulation. Based on these findings, the GMDH neural network is recommended as a robust and reliable method for predicting Au mineralization in other prospective exploration areas.

Keywords

Main Subjects

References

[1].    Liu, H., Zhang, B.,   Wang, X.,   Wang, Q.,  Du, Y.,   Zhang, B.,   Cui, Y.,  Zhou, J.,  Liu, B., &  Li, J. (2024) Exploration indication of hidden gold deposits using the fine-grained soil prospecting method and its nano-micron metal migration evidence in the alluvial soil covered area, Jiaodong. Journal of Geochemical Exploration, 263: 107514. https://doi.org/10.1016/j.gexplo.2024.107514
[2]. Ohta, A., Imai, N., Terashima, S., &Tachibana, S. (2005). Influence of surface geology and mineral deposits on the spatial distributions of elemental concentrations in the stream sediments of Hokkaido, Japan. Journal of Geochemical Exploration, 86: 86-103. https://doi.org/10.1016/j.gexplo.2005.04.002
[3]. Li, X., Li, L.H.,   Zhang, B.L., & Guo, Q.J. (2013). Hybrid self-adaptive learning-based particle swarm optimization and support vector regression model for grade estimation. Neurocomputing 118(1): 179-190. https://doi.org/10.1016/j.neucom.2013.03.002
[4]. Cheng, Q. (2007). Mapping singularities with stream sediment geochemical data for prediction of undiscovered mineral deposits in Gejiu, Yunnan Province, China. Ore Geology Review, 32: 314–324. https://doi.org/10.1016/j.oregeorev.2006.10.002
[5]. Samal, R.A., Mohanty, K.M., & Fifarek, H.R. (2008). The Backward elimination procedure for a predictive model of gold concentration. Journal of Geochemical Exploration, 97: 69–82. https://doi.org/10.1016/j.gexplo.2007.11.004
[6]. Tabatabaei, H.S., Roshani Rodsari, P., & Mokhtari, R.A. (2015). Predicting Potential Mineralization Using Surface Geochemical Data and Multiple Linear Regression Model in the Kuh Panj Porphyry Cu Mineralization (Iran). Arabian Journal Science Engineering, 40:163–170. https://doi.org/10.1007/s13369-014-1482-z
[7]. Nazarpour, A., Rostami Paydar, G., & Carranza, E.J.M. (2016). Stepwise regression for recognition of geochemical anomalies: A case study in Takab area, NW Iran. Journal of Geochemical Exploration, 168:150-162. https://doi.org/10.1016/j.gexplo.2016.07.003
[8]. Li, S., Xu, L., Wang, Z., Yang, C., Tan, L., Nie, R., Meng, M., Li, J., Zhang, B., & Liu, J. (2023) Application of tectono-geochemistry method for weak information extraction of Carlin-type gold deposits in Yunnan–Guizhou–Guangxi, SW China. Ore Geology Reviews, 163: 105813. https://doi.org/10.1016/j.oregeorev.2023.105813
[9]. Saljoughia, S., & Hezarkha, A. (2019). Identification of geochemical anomalies associated with Cu mineralization by applying spectrum-area multi-fractal and wavelet neural network methods in the Shahr-e-Babak mining area, Kerman, Iran. Journal of Mining and Environment, 10(1): 49-73. https://doi.org/10.22044/jme.2018.6949.1533
[10]. Asadi Harooni, H. (2000). The Zarshuran gold deposit model was applied in a mineral exploration GIS in Iran. PH.D. Thesis, Delft University, the Netherlands.
[11]. Aliyari, F, Afzal, P., & Sharif, A. (2017). Determination of geochemical anomalies and gold mineralized stages based on litho-geochemical data for Zarshuran Carlin-like gold deposit (NW Iran) utilizing multi-fractal modeling and stepwise factor analysis. Journal of Mining and Environment, 8(4): 593-610.  https://doi.org/10.22044/jme.2017.5252.1340
[12]. Yousefi, T., Abedini, A., Aliyari, F., Calagari, A.A. (2019). Mineralogy and fluid inclusion investigations in the Zarshuran gold deposit, north of Takab, NW Iran. Iranian Journal of Crystallogrphy and Mineral, 27 (3): 537-550. https://doi.org/10.29252/ijcm.27.3.537
[13]. Rezaei, S., Lotfi, M., Afzal, P., Jafari, M.R., & Shamseddin Meigoony, M. (2015). Delineation of Cu prospects utilizing multifractal modeling and stepwise factor analysis in Noubaran 1:100,000 sheet, Center of Iran. Arabian Journal Geoscience, 8 (9): 7343–7357. https://doi.org/10.1007/s12517-014-1755-6
[14]. Seyedrahimi-Niaraq, M., & Mahdiyanfar, H. (2024) Fractal modeling of the Cu-Au mineralization principal component values by considering the rejection of multivariate outlier data. Iranian Society of Mining Engineering, 19(62):16-38. https://doi.org/10.22034/ijme.2024.2011288.1981
[15]. Mahdiyanfar, H., & Seyedrahimi-Niaraq, M. (2022) Improvement of geochemical prospectivity mapping using power spectrum–area fractal modelling of the multi-element mineralization factor (SAF-MF). Geochemistry: Exploration, Environment, Analysis, https://doi.org/10.1144/geochem2022-015
[16]. Othman, A.A, Gloaguen, R. (2017). Integration of spectral, spatial and morphometric data into lithological mapping: A comparison of different Machine Learning Algorithms in the Kurdistan Region, NE Iraq. Journal Asian Earth Science, 146: 90-102. https://doi.org/10.1016/j.jseaes.2017.05.005
[17]. Zhang, H., Niu, F., Zhang, J., & Yu, X. (2022). Prediction of Three-Dimensional Fractal Dimension of Hematite Flocs Based on Particle Swarm Optimization Optimized Back Propagation Neural Network. Mining, Metallurgy & Exploration, 39: 2503–2515. https://doi.org/10.1007/s42461-022-00684-z
[18]. Nandi, B.P., Singh, G., Jain, A., & Tayal, D.K. (2024). Evolution of neural network to deep learning in prediction of air, water pollution and its Indian context. International Journal of Environment Science Technology, 21: 1021–1036. https://doi.org/10.1007/s13762-023-04911-y
[19]. Zuo, R., Cheng, Q., Xu, Y., Yang, F., Xiong, Y., Wang, X., & Kreuzer, O. (2024). Explainable artificial intelligence models for mineral prospectivity mapping. Sci. China Earth Science, 67: 2864–2875. https://doi.org/10.1007/s11430-024-1309-9
[20]. Jodeiri Shokri, B., Ramazi, H., Doulati Ardejani, F., & Sadeghi Amirshahidi, M.H. (2014). Prediction of pyrite oxidation in a coal washing waste pile applying artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS). Mine Water and the Environment, 33: 146-156. https://doi.org/ 10.1007/s10230-013-0247-3
[21]. Balogun, S., & Ogwueleka, T.C. (2023). Performance prediction for wastewater treatment plant effluent cod using artificial neural network. International Journal Environment Sciences Technology, 20: 12659–12668. https://doi.org/10.1007/s13762-023-04823-x
[22]. Pradhan, B., Jena, R., Talukdar, D., Mohanty, M., Sahu, B.K., Raul, A.K., &Abdul Maulud, K.N. (2022). A New Method to Evaluate Gold Mineralisation-Potential Mapping Using Deep Learning and an Explainable Artificial Intelligence (XAI) Model. Remote Sensing, 14: 4486. https://doi.org/10.3390/rs14184486
[23]. Chen, G., Huang, N., Wu, G., Luo, L., Wang, D., &Cheng, Q. (2022). Mineral prospectivity mapping based on wavelet neural network and Monte Carlo simulations in the Nanling W-Sn metallogenic province. Ore Geology Review, 143: 104765. https://doi.org/10.1016/j.oregeorev.2022.104765
[24]. Bazdar, H., & Imamalipour, A. (2024).   Application of an improved artificial neural network model for prediction of Cu and Au concentration in the porphyry copper-epithermal gold deposits, Case study: Masjed Daghi, NW Iran. International Journal of Mining and Geo-Engineering, 58(4): 327-339. https://doi.org/10.22059/IJMGE.2024.376761.595167
[25]. Shen, C., Asante-Okyere, S., Yevenyo- Ziggah, Y., Wang, L., & Zhu, X.  (2019) Group Method of Data Handling (GMDH) Lithology Identification Based on Wavelet Analysis and Dimensionality Reduction as Well Log Data Pre-Processing Techniques. Energies, 12(8): 1509; https://doi.org/10.3390/en12081509
[26]. Deng, S., Zhang, N., Kuang, B., Li, Y., & Sun, H. (2022) Bayesian Markov Chain Monte Carlo inversion of surface-based transient electromagnetic data. SN Applied. Sciences, 4:254 .https://doi.org/10.1007/s42452-022-05134-5
[27]. Liu, B. Yan Liang, Y. (2017) An introduction of Markov chain Monte Carlo method to geochemical inverse problems: Reading melting parameters from REE abundances in abyssal peridotites. Geochimica et Cosmochimica Acta, 203: 216-234. https://doi.org/10.1016/j.gca.2016.12.040
[28]. Mehrabi, B., Yardley, B.W.D.,  & Cann, J.R. (1999). Sediment-hosted disseminated gold mineralization at Zarshuran, NW Iran. Mineralium Deposita, 34: 673–696. https://doi.org/10.1007/s001260050227
[29]. Tale Fazel, E., Paˇsava, J., Wilke, F.D, H., Oroji, A., & Andronikova, I. (2023) Source of gold and ore-forming processes in the Zarshuran gold deposit, NW Iran: Insights from in situ elemental and sulfur isotopic compositions of pyrite, fluid inclusions, and O−H isotopes. Ore Geology Reviews, 156: 105382. https://doi.org/10.1016/j.oregeorev.2023.105382
[30]. Paravarzar, S., Maarefvand, P., Maghsoudi, A., & Afzal, P. (2015). Correlation between geological units and mineralized zones using fractal modeling in Zarshuran gold deposit (NW Iran). Arabian Journal of Geosciences, 8:3845–3854 https://doi.org/ 10.1007/s12517-014-1453-4
[31]. Aitchison, J. (1986). Statistical analysis of compositional data. UK: Chapman and Hall, London, 416 p
[32]. Ivakhnenko, A.G. (1971). Polynomial theory of complex systems IEEE Transactions on Systems, Man, and Cybernetics, 364-378.https://doi.org/ 10.1109/TSMC.1971.4308320
[33]. Oh, H.J.S., & Lee, S. (2010). Application of artificial neural network for gold–silver deposits potential mapping: a case study of Korea. National Resources Research, 19(2): 103-124. https://doi.org/10.1007/s11053-010-9112-2
[34]. Rigol-Sanchez, J.P., Chica-Olmo, M., & Abarca-Hernandez, F. (2003). The Artificial neural networks as a tool for mineral potential mapping with GIS. International Journal Remote Sensing, 24(5): 1151-1156. https://doi.org/10.1080/0143116021000031791
[35]. Gimenez, O., Bonner, S.J., King, Ruth., Parker, R.A., Brooks, S.P., Jamieson, L.E., Grosbois, V., Morgan B.J.T., & Len, T. (2009). WinBUGS for population ecologists: Bayesian modeling using Markov Chain Monte Carlo methods. In:  Modeling demographic processes in marked populations. Springer, pp 883-915. https://hdl.handle.net/10023/677
[36]. Brook, S., Gelman, A., Jones, G., & Meng, X.L. (2011). Handbook of Markov chain Monte- Carlo. CRC Press
[37]. Li, H., Li, X., Yuan, F., Jowitt, S., Zhang, M., Zhou, J., Zhou, T., Li, X., Ge, C., & Wu, B. (2020). Convolutional neural network and transfer learning based mineral prospectivity modeling for geochemical exploration of Au mineralization within the Guandian-Zhangbaling area, Anhui province, China. Applied Geochemistry, 122: 104747. https://doi.org/10.1016/j.apgeochem.2020.104747
[38]. Reimann, C., & Filzmoser, P. (2000). Normal and lognormal data distribution in geochemistry: death of a myth, Consequences for the statistical treatment of geochemical and environmental data. Environmental Geology, 39: 1001–1014. https://doi.org/10.1007/s002549900081
[39]. Jolliffe, T. (2002). Principal component analysis. Springer Verlag, New York, 488 pp.
[40]. Kaiser, H.F. (1958). Varimax criterion for analytic rotation in factor analysis. Psychometrika, 23:187-200. https://doi.org/10.1007/BF02289233
[41]. Cheng, Q. (2012). Singularity theory and methods for mapping geochemical anomalies caused by buried sources and for predicting undiscovered mineral deposits in covered areas. Journal of Geochemical Exploration, 122: 55–70. https://doi.org/10.1016/j.gexplo.2012.07.007
[42]. Nazarpour, A., Omran, N.R., Paydar, G.R., Sadeghi, B., Matroud, F., & Mehrabi Nejad, A. (2015). Application of classical statistics, log-ratio transformation, and multifractal approaches to delineate geochemical anomalies in the Zarshuran gold district, NW Iran. Chemie der Erde Geochemistry, 75: 117-132. https://doi.org/10.1016/j.chemer.2014.11.002
[43]. Nazarpour, A. (2018). Application of C-A fractal model and exploratory data analysis (EDA) to delineate geochemical anomalies in the: Takab 1:25,000 geochemical sheet, NW Iran. Iranian Journal of Earth Science, 10: 173-180.
[44]. Misra, D., Samanta, B., & Bandopadhyay, S.  (2007). 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, 21(4): 282-294. https://
doi.org/10.1080/17480930701259294
[45]. Xiong, Y., & Zuo, R. (2020). Recognizing multivariate geochemical anomalies for mineral exploration by combining deep learning and one-class support vector machine. Computer Geoscience, 140: 104484. https://doi.org/10.1016/j.cageo.2020.104484
[46]. Boucher, T.F.,   Ozanne, M.V.,   Carmosino, M.L., Dyar, M.D., Mahadevan, S., Breves, S.E., Lepore, K.H.,   & Clegg, S.M. (2015). A study of machine learning regression methods for major elemental analysis of rocks using laser-induced breakdown spectroscopy. Spectrochimica Acta Part B: Atomic Spectroscopy, 107: 1-10. https://doi.org/10.1016/j.sab.2015.02.003
[47]. Pambudi, E.A., Badharudin, A.Y., &Wicaksono, A.P. (2021). Enhanced k-means by using grey wolf optimizer for brain MRI segmentation, ICTACT. Journal of Soft Computer, 11(3): 2353-2358. https://doi.org/10.21917/ijsc.2021.0336
[48]. Wong, T.T. (2015) Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 48(9): 2839-2846. https://doi.org/10.1016/j.patcog.2015.03.009
[49]. Mostafaei, K.,  Shahoo Maleki, S.,   Jodeiri Shokri, B.,  & Yousefi, M.(2023) Predicting gold grade by using support vector machine and neural network to generate an evidence layer for 3D prospectivity analysis. International Journal of Mining and Geo-Engineering, 57(4):435-444. https://doi.org/10.22059/IJMGE.2023.362951.595087
[50].  Moradi, M.,  Asghari, O.,  Norouzi, G.H.,  Riahi, M.,  & Sokooti, R. (2015). Joint Bayesian Stochastic Inversion of Well Logs and Seismic Data for Volumetric Uncertainty Analysis. International Journal of Mining and Geo-Engineering, 49(1): 131-142. https://doi.org/10.22059/IJMGE.2015.54636
International Journal of Mining and Geo-Engineering
Volume 60, Issue 1
March 2026
Pages 43-55

Files

Share

How to cite

Statistics