Advanced Applied Geology

Advanced Applied Geology

Reconnaissance of prospective zones using semi-supervised support vector machine algorithm in Sonajil porphyry copper-gold deposit

Authors
Majid mahboubiaghdam 1
Moharram Jahangiri 2
Aynur Nasseri 3
1 Ph.D. Mining Engineering, Faculty of Mining Engineering, Sahand University of Technology, Tabriz, Iran
2 PhD Mining Engineering, Shahrood University of Technology, Shahrood, Iran
3 Assistan Professor, Department of Mining Engineering, Ahar Branch, Islamic Azad University, Ahar, Iran.
10.22055/aag.2025.50114.2524
Abstract
Using the hybrid algorithm of machine learning along with homogeneous data in providing mineral potential prediction maps results in obtaining results with high efficiency and reliability.Therefore, by combining supervised and unsupervised methods and using training and experimental data, a potential map with high accuracy was provided. The semi-supervised support vector machine algorithm was used to provide the mineral perspective map. First, raster layers were provided from 10 reconnaissance properties. Then, 27 excavated reconnaissance bores were classified based on the copper density into 4 classes from C1 to C4. Two bores were selected from each class and 100 meters of buffering took place around these bores to yield 1113 training data. Then, the Gustafson method was used to cluster the available data, and all data and clustering data were imported into the support vector machine algorithm to inspect the accuracy of the classification method of the support vector machine in 4 different clusters. The results indicated the average accuracy increased when using clustered data instead of all data in providing the mineral potential map. Moreover, the highest classification accuracy of 97% was achieved when the data from Cluster 4 were excluded. The bores that were not used in the data training were used to validate the semi-supervised support vector machine method. The general findings based on the classification of bores and the provided potential map show the accuracy of the semi-supervised support vector machine method as an optimal result for more reconnaissance and delineation of additional mineralization targets.
Keywords
potential map
support vector machine
Gustafson kessel
semi-supervised algorithm
Sonajil
Subjects
Abedi, M., Norouzi, G.H., Fathianpour, N.J.I.J.o.A.E.O., 2013. Fuzzy outranking approach: a knowledge-driven method for mineral prospectivity mapping. International Journal of Applied Earth Observation and Geoinformation 21, 556-567. http://dx.doi.org/10.1016/j.jag.2012.07.012.
Aghazadeh, M., Hou, Z., Badrzadeh, Z., Zhou, L.J.O.g.r., 2015. Temporal–spatial distribution and tectonic setting of porphyry copper deposits in Iran: constraints from zircon U–Pb and molybdenite Re–Os geochronology. Ore Geology Reviews 70, 385-406. http://dx.doi.org/10.1016/j.oregeorev.2015.03.003.
Aryafar, A., Roshanravan, B.J.E.S.I., 2020. Improved index overlay mineral potential modeling in brown-and green-fields exploration using geochemical, geological, and remote sensing data. Earth Science Informatics 13, 1275-1291. https://doi.org/10.1007/s12145-020-00509-x.
BEANE, R.E.J.P.c.d.o.t.A.C., 1995. Hydrothermal fluids and hydrothermal alteration in porphyry copper deposits. Porphyry copper deposits of the American Cordillera 83-93. https://cir.nii.ac.jp/crid/1571698600835102592.
Bensaid, A.M., Hall, L.O., Bezdek, J.C., Clarke, L.P., Silbiger, M.L., Arrington, J.A., Murtagh, R.F.J.I.T.o.f.s., 1996. Validity-guided (re) clustering with applications to image segmentation. IEEE Transactions on Fuzzy Systems 4, 112-123. http://dx.doi.org/10.1109/91.493905. 
Bezdek, J.C., Bezdek, J.C.J.P.r.w.f.o.f.a., 1981. Objective function clustering. Pattern recognition with fuzzy objective function algorithms 43-93. http://dx.doi.org/10.1007/978-1-4757-0450-1.
Carranza, E.J.M.J.N.R.R., 2017. Natural resources research publications on geochemical anomaly and mineral potential mapping, and introduction to the special issue of papers in these fields. Natural Resources Research 26, 379-410. http://dx.doi.org/10.1007/s11053-017-9348-1.
Cheng, H., Zheng, Y., Wu, S., Lin, Y., Gao, F., Lin, D., 2023. GIS-based mineral prospectivity mapping using machine learning methods: a case study from Zhuonuo ore district, Tibet. Ore Geology Reviews 161, 105627. https://doi.org/10.1016/j.oregeorev.2023.105627.
Fatehi, M., Asadi, H.H.J.O.G.R., 2017. Application of semi-supervised fuzzy c-means method in clustering multivariate geochemical data, a case study from the Dalli Cu-Au porphyry deposit in central Iran. Ore Geology Reviews 81, 245-255. https://doi.org/10.1016/j.oregeorev.2016.10.002.
Gao, Y., Zhang, Z., Xiong, Y., Zuo, R.J.O.G.R., 2016. Mapping mineral prospectivity for Cu polymetallic mineralization in southwest Fujian Province, China. Ore Geology Reviews 75, 16-28. http://dx.doi.org/10.1016/j.oregeorev.2015.12.005.
Ghezelbash, R., Maghsoudi, A., Bigdeli, A., Carranza, E.J.M.J.N.R.R., 2021. Regional-scale mineral prospectivity mapping: Support vector machines and an improved data-driven multi-criteria decision-making technique. Natural Resources Research 30, 1977-2005. http://dx.doi.org/10.1007/s11053-021-09842-4.
Ghezelbash, R., Maghsoudi, A., Carranza, E.J.M.J.N.R.R., 2019. An improved data-driven multiple criteria decision-making procedure for spatial modeling of mineral prospectivity: adaptation of prediction–area plot and logistic functions. Natural Resources Research 28, 1299-1316. https://doi.org/10.1007/s11053-018-9448-6.
Hosseini, S.A., Abedi, M.J.C., 2015. Data envelopment analysis: a knowledge-driven method for mineral prospectivity mapping. Computers & Geosciences 82, 111-119. http://dx.doi.org/10.1016/j.cageo.2015.06.006.
Hosseinzadeh, M.R., Maghfouri, S., Ghorbani, M., Moayyed, M., 2017. Different types of vein- veinlets related to mineralization and fluid inclusion studies in the Sonajil porphyry Cu- Mo deposit, Arasbaran magmatic zone. Scientific Quarterly Journal of Geosciences 101, 2219-230 (in Persian with extended English abstract).  https://doi.org/10.22071/gsj.2016.41069.
Jahangiri, M., Ghavami Riabi, S.R., Tokhmechi, B.J.J.o.M., 2018. Estimation of geochemical elements using a hybrid neural network-Gustafson-Kessel algorithm. Journal of Mining and Environment 9, 499-511. https://doi.org/10.22044/jme.2017.5513.1363.
Keykhay-Hosseinpoor, M., Kouhsari, A., Morshedy, A.H., Porwal, A., 2021. Porphyry Cu-Au prospectivity modelling using semi-supervised learning algorithm in Dehsalm district, eastern Iran. Journal of Economic Geology 13(1), 193-21378 (in Persian with extended English abstract). https://doi.org/10.22067/econg.v13i1.81382.
Kavzoglu, T., Colkesen, I.J.I.J.o.A.E.O., 2009. A kernel function analysis for support vector machines for land cover classification. International Journal of Applied Earth Observation and Geoinformation 11, 352-359. http://dx.doi.org/10.1016/j.jag.2009.06.002.
Lagat, J.J.D.d.s.c.I.o.e.f.g.r., 2009. Hydrothermal alteration mineralogy in geothermal fields with case examples from Olkaria domes geothermal field, Kenya. Dipresentasikan dalam short course IV on exploration for geothermal resources. 1-22. https://docslib.org/doc/11476342.
Lesot, M.J., Kruse, R., 2008. Gustafson-Kessel-like clustering algorithm based on typicality degrees, In: Uncertainty and Intelligent Information Systems. World Scientific. In Uncertainty and Intelligent Information Systems. 117-130. http://dx.doi.org/10.1142/9789812792358_0009.
Li, S., Chen, J., Liu, C., Wang, Y.J.J.o.E.S., 2021. Mineral prospectivity prediction via convolutional neural networks based on geological big data. Journal of Earth Science 32, 327-347 http://dx.doi.org/10.1007/s12583-020-1365-z.
Li, Q., Chen, G., Wang, D., 2025. Mineral Prospectivity Mapping Using Semi-supervised Machine Learning. Mathematical Geosciences 57(2), 275-305. http://dx.doi.org/10.1007/s11004-024-10161-6.
Liu, Y., Cheng, Q., Xia, Q., Wang, X.J.F.o.E.S., 2015. The use of evidential belief functions for mineral potential mapping in the Nanling belt, South China. Frontiers of Earth Science 9, 342-354. http://dx.doi.org/10.1007/s11707-014-0465-4.
Liu, Y., Cheng, Q., Zhou, K.J.N.R.R., 2019. New insights into element distribution patterns in geochemistry: A perspective from fractal density. Natural Resources Research 28, 5-29. http://dx.doi.org/10.1007/s11053-018-9374-7.
McKay, G., Harris, J.J.N.R.R., 2016. Comparison of the data-driven random forests model and a knowledge-driven method for mineral prospectivity mapping: A case study for gold deposits around the Huritz Group and Nueltin Suite, Nunavut, Canada. Natural Resources Research 25, 125-143. http://dx.doi.org/10.1007/s11053-015-9274-z.
Mahdiyanfar, H., Seyedrahimi-Niaraq, M., 2023. Integration of Fractal and Multivariate Principal Component Models for Separating Pb-Zn Mineral Contaminated Areas. Journal of Mining and Environment, 14(3), 1019-1035. https://doi.org/10.22044/jme.2023.13227.2424.
Mohammadzadeh, M., Nasseri, A.J.J.o.A.E.S., 2018. Geochemical modeling of orogenic gold deposit using PCANN hybrid method in the Alut, Kurdistan province, Iran. Journal of African Earth Sciences 139, 173-183. http://dx.doi.org/10.1016/j.jafrearsci.2017.11.038.
Moshefi, P., Hosseinzadeh, M.R., Moayyed, M., Lentz, D.R.J.O.G.R., 2018. Comparative study of mineral chemistry of four biotite types as geochemical indicators of mineralized and barren intrusions in the Sungun Porphyry Cu-Mo deposit, northwestern Iran. Ore Geology Reviews 97, 1-20. http://dx.doi.org/10.1016/j.oregeorev.2018.05.003.
Nykänen, V., Groves, D., Ojala, V., Gardoll, S.J.A.J.o.E.S., 2008. Combined conceptual/empirical prospectivity mapping for orogenic gold in the northern Fennoscandian Shield, Finland. Australian Journal of Earth Sciences 55, 39-59 http://dx.doi.org/10.1080/08120090701581380.
Porwal, A., Carranza, E.J.M., Hale, M.J.C., Geosciences, 2006. Bayesian network classifiers for mineral potential mapping. Computers & Geosciences 32, 1-16 http://dx.doi.org/10.1016/j.cageo.2005.03.018.
Porwal, A., Carranza, E.J.M.J.O.g.r. 2015. Introduction to the Special Issue: GIS-based mineral potential modelling and geological data analyses for mineral exploration. Ore Geology Reviews 71, 477-483. http://dx.doi.org/10.1016/j.oregeorev.2015.04.017.
Rodriguez-Galiano, V., Sanchez-Castillo, M., Chica-Olmo, M., Chica-Rivas, M.J.O.G.R., 2015. Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees, and support vector machines. Ore Geology Reviews 71, 804-818. https://doi.org/10.1016/j.oregeorev.2015.01.001.
Sadeghi, M., Casey, P., Carranza, E. J. M., Lynch, E. P., 2024. Principal components analysis and K-means clustering of till geochemical data: Mapping and targeting of prospective areas for lithium exploration in Västernorrland Region, Sweden. Ore Geology Reviews 167, 106002. https://doi.org/10.1016/j.oregeorev.2024.106002.
Salehi, T., Tangestani, M.H.J.R.S.A.S., Environment, 2020. Per-pixel analysis of ASTER data for porphyry copper hydrothermal alteration mapping: a case study of NE Isfahan, Iran. Remote Sensing Applications: Society and Environment 20, 100377. http://dx.doi.org/10.1016/j.rsase.2020.100377.
Serir, L., Ramasso, E., Zerhouni, N.J.I.j.o.a.r., 2012. Evidential evolving Gustafson–Kessel algorithm for online data streams partitioning using belief function theory. International journal of approximate reasoning 53, 747-768. https://dx.doi.org/10.1016/j.ijar.2012.01.009.
Seyedrahimi-Niaraq, M., Hekmatnejad, A., 2021. The efficiency and accuracy of probability diagram, spatial statistic and fractal methods in the identification of shear zone gold mineralization: a case study of the Saqqez gold ore district, NW Iran. Acta Geochimica 40(1), 78-88. https://doi.org/10.1007/s11631-020-00413-7.
Sun, G., Zeng, Q., Zhou, J.-X.J.O.G.R., 2022. Machine learning coupled with mineral geochemistry reveals the origin of ore deposits. Ore Geology Reviews 142, 104753. http://dx.doi.org/10.1016/j.oregeorev.2022.104753.
Tao, J., Zhang, N., Chang, J., Chen, L., Zhang, H., Chi, Y.J.N.R.R., 2022. Unlabeled sample selection for mineral prospectivity mapping by semi-supervised support vector machine. Natural Resources Research 31, 2247-2269. https://doi.org/10.1007/s11053-022-10093-0.
Wang, J., Zuo, R., Xiong, Y.J.N.R.R., 2020a. Mapping mineral prospectivity via semi-supervised random forest. Natural Resources Research 29, 189-202. http://dx.doi.org/10.1007/s11053-019-09510-8.
Wang, Z., Zhou, C., Qin, H.J.A.i.S.R., 2020b. Detection of hydrothermal alteration zones using ASTER data in Nimu porphyry copper deposit, south Tibet, China. Advances in Space Research 65, 1818-1830. http://dx.doi.org/10.1016/j.asr.2020.01.008.
Wang, Z., Zuo, R.J.C., Geosciences, 2022. Mineral prospectivity mapping using a joint singularity-based weighting method and long short-term memory network. Computers & geosciences 158, 104974 http://dx.doi.org/10.1016/j.cageo.2021.104974.
Xie, X., Beni, G., 1991. A new fuzzy clustering validity criterion and its application to color image segmentation. In: Proceedings of the 1991 IEEE International Symposium on Intelligent Control. https://doi.org/10.1109/ISIC.1991.187401.pp. 463-468.
Yang, Q., Li, X., Shi, X.J.C., geosciences, 2008. Cellular automata for simulating land use changes based on support vector machines. Computers & Geosciences 34, 592-602. http://dx.doi.org/10.1016/j.cageo.2007.08.003.
Zekri, H., Cohen, D.R., Mokhtari, A.R., Esmaeili, A.J.N.R.R., 2019. Geochemical prospectivity mapping through a feature extraction–selection classification scheme. Natural Resources Research 28, 849-865. https://doi.org/10.1007/s11053-018-9422-3
Zhang, D., Ren, N., Hou, X.J.G.M.D., 2018. An improved logistic regression model based on a spatially weighted technique (ILRBSWT v1.0) and its application to mineral prospectivity mapping. Geoscientific Model Development 11, 2525-2539. https://doi.org/10.5194/gmd-11-2525-2018.
Zhang, Z., Zuo, R., Xiong, Y.J.S.C.E.S., 2016. A comparative study of fuzzy weights of evidence and random forests for mapping mineral prospectivity for skarn-type Fe deposits in the southwestern Fujian metallogenic belt, China. Science China Earth Sciences 59, 556-572. http://dx.doi.org/10.1007/s11430-015-5178-3.
Zhao, Z.-F., Zhou, J.-X., Lu, Y.-X., Chen, Q., Cao, X.-M., He, X.-H., Fu, X.-H., Zeng, S.-H., Feng, W.-j.J.O.G.R., 2021. Mapping alteration minerals in the Pulang porphyry copper ore district, SW China, using ASTER and WorldView-3 data: Implications for exploration targeting. Ore Geology Reviews 134, 104171. http://dx.doi.org/10.1016/j.oregeorev.2021.104171.
Zuo, R., Carranza, E.J.M.J.C., Geosciences, 2011. Support vector machine: A tool for mapping mineral prospectivity. Computers & Geosciences 37, 1967-1975. http://dx.doi.org/10.1016/j.cageo.2010.09.014.
Zuo, R., Kreuzer, O.P., Wang, J., Xiong, Y., Zhang, Z., Wang, Z.J.N.R.R., 2021. Uncertainties in GIS-based mineral prospectivity mapping: Key types, potential impacts, and possible solutions. Natural Resources Research 30, 3059-3079. http://dx.doi.org/10.1007/s11053-021-09871-z.
Zuo, R.J.N.R.R., 2017. Machine learning of mineralization-related geochemical anomalies: A review of potential methods. Natural Resources Research 26, 457-464. https://doi.org/10.1016/j.cageo.2015.06.006.
Advanced Applied Geology
Volume 15, Issue 2
Summer 2025
Pages 164-191