Separation of alteration zones using remote sensing images and support vector machines, case study: Zaglic area, Arasbaran metallogenic zone, NW Iran

زمین شناسی اقتصادی

Articles in Press, Accepted Manuscript, Available Online from 18 May 2025   

Document Type: Research Article

DOI: 10.22067/econg.2025.1138

Authors

Ali Imamalipour^{* 1}; Habibollah Bazdar²

¹Associate Professor, Department of Mining Engineering, Faculty of Engineering, Urmia University, Urmia, Iran

²Ph.D. Student, Department of Mining Engineering, Faculty of Engineering, Urmia University, Urmia, Iran

Abstract

The separation of alteration zones plays a significant role in the exploration of porphyry copper-epithermal gold deposits and is one of the key issues in the exploration operations of these deposits. In the general exploration stage and in the large-scale exploration stage of these deposits, one of the most important guides for determining suitable areas for exploratory drilling in the detailed exploration stage is the recognition and separation of alteration zones. In this study, alteration zones have been separated using satellite images and support vector machine. The study area is the Zaglic area near the city of Ahar, located in East Azerbaijan province. The images obtained from the satellite were digitized for modeling using a support vector machine and four classes were determined for data classification, namely "silica vein", "argillic", "propylitic" and "stockwork". After data preparation, the data were classified into four defined classes using a support vector machine and the accuracy of the model in correctly classifying the data was calculated to be 90.24 percent. Finally, alteration map was drawn with the predicted data and compared with the previously collected map, which showed the appropriate performance of the model.
 
Introduction
Studies of the alteration of host rocks are one of the appropriate guides in the exploration of hydrothermal deposits, including porphyry deposits. In porphyry systems, alterations are usually observed that can be referred to as potassic, phyllic, advanced argillic and propylitic alterations. These alterations provide a very suitable exploration prospect for determining the location of the deposit. Potassic alteration is usually accompanied by mineralization. Therefore, by separating potassic alteration, areas with high mineralization potential can be distinguished. In this study, alteration zones are predicted using data obtained from ASTER satellite images and intelligent support vector machine modeling. The Zaglic region, as the study area of ​​this study, is located in the Arasbaran metallogenic zone in northwest Iran. This area is located at coordinates 20'26°38'N and 59'20°47'E, 25 km southeast of Ahar city and 5 km north of Naqduz Village in East Azerbaijan Province.
 
Materials and methods
In this study, satellite data obtained from the ASTER and the alteration map of the area were used to build an intelligent model. ASTER provides high-resolution satellite images of the Earth in 14 different bands of the electromagnetic spectrum in the visible to thermal infrared range. The resolution of ASTER images is ranges from 15 to 90 meters. ASTER bands were downloaded in the desired area through the relevant website (https://earthexplorer.usgs.gov). This website provides ASTER images in different areas for free. Of course, the downloaded data format is HDF, but we need the bands in numerical form to use the data. For this reason, the data were corrected and processed using ENVI version 5.6 software. Initially, radiometric and atmospheric corrections were made to the data. Then, the band data were obtained digitally through ENVI software and the file was extracted through the desired area tool and saved in Excel format. The resulting Excel file was such that 90-meter square grids were defined on the ground and the numerical value of each band was represented the numerical intensity of the absorbed reflection of the desired band at that point (center of the square). Therefore, the input to the model was the numerical ASTER bands and the output of the model was the type of alteration at that point. The type of alteration was extracted from the alteration map of the desired area.
 
Results
The most important parameter among the parameters of a support vector machine is the choice of kernel. Here we use the RBF kernel function in modeling because this function has a good ability to analyze high-dimensional data. On the other hand, for implementation, it requires setting two parameters; one is C (penalty parameter) and the other is λ which determines the width of the kernel function. The division of the number of training and test data is such that 80% of the data is considered for the training dataset and the remaining data is considered as the test dataset. This ratio was also optimized by keeping other parameters constant and changing the percentage of data in the training and test datasets and the value was determined to be 80%. After dividing the dataset into two sets of training and testing data, it is time to determine the two parameters λ and C. By considering the value of λ as a constant, we find the optimal value of C. According to the obtained values, the value of the parameter C was considered to be 2. The value of epsilon was also determined by trial and error to be 10^-7. The value of λ was optimized by using different values ​​and running the model, and its value was determined to be 1. Finally, by optimizing the required parameters, the best value obtained for modeling was an accuracy of 90.24%. After determining the optimized parameters of the support vector machine, modeling was performed using the data and the output map was drawn based on the prediction of the type of alteration in the study area. Also additionally, in order to compare with the existing alteration map of the study area, the predicted map was implemented on the alteration map of the area.
 
Discussion
As mentioned above, by optimizing the model, we achieved a resolution accuracy of 90.24%, which is adequate for modeling that only uses satellite images to separate alterations. Finally, the alteration map of the region was drawn using the model output based on the prediction of the alteration type of each point. According to the results obtained, the following are suggested:
- The obtained model is capable of separating alterations and rock units and it is recommended to use it in similar studies.
- It is recommended to use data from other satellites and compare it with the results obtained from the ASTER data.
- In order to conduct comparative research, classification should be performed with other intelligent methods.
- In addition to the alteration type, the amount of elements using geochemical data can also be considered as an output and modeling can be performed.
 
Acknowledgements
We sincerely thank the editor and reviewers of the Journal of Economic Geology for their useful and valuable comments.

Keywords

Separation of alteration zones; support vector machine; remote sensing; porphyry deposits; Arasbaran metallogenic zone

References

Abdi, M. and Karimpour, M.‌H., 2012. Geology, alteration, mineralization, petrogenesis, geochronology, geochemistry and airborne geophysics of Kuh Shah prospecting area, SW Birjand. Journal of Economic Geology, 4(1): 77–107. (in Persian with English abstract) https://doi.org/10.22067/econg.v4i1.13394

Adib, H., Kazerooni, N., Falsafi, A., Adhami, M.‌A., Dehghan, M. and Golnari, A., 2018. Prediction of sulfur content in propane and butane after gas purification on a treatment unit. Oil & Gas Science and Technology–Revue d’IFP Energies nouvelles, 73: 70.  https://doi.org/10.2516/ogst/2018021

Aghazadeh, M., Castro, A. and Badrzadeh, Z., 2012. U-Pb age dating of Cenozoic plutonism in the Arasbaran magmatic zone, NW Iran. 34th International Geological Congress, brisbane convention and exhibition centre, Brisbane, Australia.

Alikhani, M., Shamanian, G.H. and Jafari Zanglanlou, M., 2014. Mineralization and hydrothermal alteration of the Tajroud vein system, south of Neyshabour. Journal of Economic Geology, 5(2): 325–339. (in Persian with English abstract) https://doi.org/10.22067/econg.v5i2.31886

Bahrambeygi, B. and Moeinzadeh, H., 2017. Comparison of support vector machine and neutral network classification method in hyperspectral mapping of ophiolite mélanges–A case study of east of Iran. The Egyptian. Journal of Remote Sensing and Space Science, 20(1): 1–10. https://doi.org/10.1016/j.ejrs.2017.01.007

Bazi, Y. and Melgani, F., 2006. Toward an optimal SVM classification system for hyperspectral remote sensing images. IEEE Transactions on geoscience and remote sensing, 44(11): 3374–3385. https://doi.org/10.1109/TGRS.2006.880628

Boomeri, M., Biabangard, H. and Zeinadini, Z., 2019. Investigation of petrography, mineralogy and alteration of northern part of the Chahfiruzeh porphyry copper deposit, northwest of Shar-e-Babak, Kerman. Journal of Economic Geology, 11(1): 57–80. (in Persian with English abstract) https://doi.org/10.22067/econg.v11i1.63353

Brown, M., Lewis, H.G. and Gunn, S.‌R., 2000. Linear spectral mixture models and support vector machines for remote sensing. IEEE Transactions on geoscience and remote sensing, 38(5): 2346–2360. https://doi.org/10.1109/36.868891

Cortes, C. and Vapnik, V., 1995. Support-Vector Networks. Machine Learning 20: 273–297. https://doi.org/10.1007/BF00994018 

Cracknell, M.‌J. and Reading, A.‌M., 2013. The upside of uncertainty: Identification of lithology contact zones from airborne geophysics and satellite data using random forests and support vector machines. Geophysics, 78(3): WB113–WB126. https://doi.org/10.1190/geo2012-0411.1

Cracknell, M.‌J. and Reading, A.‌M., 2014. Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Computers & Geosciences, 63: 22–33. https://doi.org/10.1016/j.cageo.2013.10.008

Curilem, M., Acuña, G., Cubillos, F. and Vyhmeister, E., 2011. Neural networks and support vector machine models applied to energy consumption optimization in semiautogeneous grinding. Chemical Engineering Transactions, 25: 761–766. http://dx.doi.org/10.3303/CET1125127

Ebrahimi, S., Alirezaei, S. and Pan, Y., 2011. Geological setting, alteration, and fluid inclusion characteristics of Zaglic and Safikhanloo epithermal gold prospects, NW Iran. A.‌N. Sial, J.‌‌‌S. Bettencourt, C.‌P.‌D. Campos and V.‌P. Ferreira, (Editors), Granite-Related Ore Deposits, Geological Society of London, England, pp. 133–147. https://doi.org/10.1144/SP350.8

Ezzati, S.‌A., Mehrnia, S.‌R. and Ajayebi, K.‌S., 2016. Remote Sensing Analysis of Mineralized Alteration in the Ramand Area (Qazvin Province). Journal of Economic Geology, 8(1): 223–238. (in Persian with English abstract) https://doi.org/10.22067/econg.v8i1.20972

Foody, G.‌M. and Mathur, A., 2004. A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on geoscience and remote sensing, 42(6): 1335–1343. https://doi.org/10.1109/TGRS.2004.827257

Forson, E.‌D. and Amponsah, P.‌O., 2023. Mineral prospectivity mapping over the Gomoa Area of Ghana's southern Kibi-Winneba belt using support vector machine and naive bayes. Journal of African Earth Sciences, 206: 105024. https://doi.org/10.1016/j.jafrearsci.2023.105024

Gasmi, A., Gomez, C., Zouari, H., Masse, A. and Ducrot, D., 2016. PCA and SVM as geo-computational methods for geological mapping in the southern of Tunisia, using ASTER remote sensing data set. Arabian Journal of Geosciences, 9(20): 753. https://doi.org/10.1007/s12517-016-2791-1

Ge, W., Cheng, Q., Jing, L., Armenakis, C. and Ding, H., 2018. Lithological discrimination using ASTER and Sentinel-2A in the Shibanjing ophiolite complex of Beishan orogenic in Inner Mongolia, China. Advances in Space Research, 62(7): 1702–1716. https://doi.org/10.1016/j.asr.2018.06.036

Ghoneim, S.‌M., Hamimi, Z., Abdelrahman, K., Khalifa, M.‌A., Shabban, M. and Abdelmaksoud, A.‌S., 2024. Machine learning and remote sensing-based lithological mapping of the Duwi Shear-Belt area, Central Eastern Desert, Egypt. Scientific Reports, 14(1): 17010. https://doi.org/10.1038/s41598-024-66199-3

Gualtieri, J.‌A. and Cromp, R.‌F., 1999. Support vector machines for hyperspectral remote sensing classification. 27th AIPR Workshop: Advances in Computer-Assisted Recognition, International Society for Optics and Photonics, Bellingham, USA.  https://doi.org/10.1117/12.339824

Harvey, A. and Fotopoulos, G., 2016. Geological mapping using machine learning algorithms. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences XLI-B8: 423–430. https://doi.org/10.5194/isprs-archives-XLI-B8-423-2016

Hashemian, E., Jamali, H. and Ahmadian, J., 2019. Mineralogy, alteration, fluid inclusion and geochemical constraints of the Tappeh-Khargoosh Cu-Au deposit (SW Ardestan). Journal of Economic Geology, 10(2): 299–324. (in Persian with English abstract) https://doi.org/10.22067/econg.v10i2.62445

Hassanpour, S., 2013. The alteration, mineralogy and geochronology (SHRIMP U–Pb and 40 Ar/39 Ar) of copper-bearing Anjerd skarn, north of the Shayvar Mountain, NW Iran. International Journal of Earth Sciences, 102: 687–699. (in Persian with English abstract) https://doi.org/10.1007/s00531-012-0819-7

Hassanpour, S., Alirezaei, S., Selby, D. and Sergeev, S., 2015. SHRIMP zircon U–Pb and biotite and hornblende Ar–Ar geochronology of Sungun, Haftcheshmeh, Kighal, and Niaz porphyry Cu–Mo systems: evidence for an early Miocene porphyry-style mineralization in northwest Iran. International Journal of Earth Sciences, 104: 45–59. (in Persian with English abstract) https://doi.org/10.1007/s00531-014-1071-0

Hassanpour, S. and Rajabpour, S., 2019. The kighal porphyry Cu–Mo deposit, NW Iran: insights into origin and evolution of the mineralizing fluids. Russian Geology and Geophysics, 60(10): 1141–1162. (in Persian with English abstract) https://doi.org/10.15372/RGG2019115

Hassanpour, S. and Rajabpour, S., 2020. Magmatic–hydrothermal evolution of the Anjerd Cu skarn deposit, NW Iran: perspectives on mineral chemistry, fluid inclusions and stable isotopes. Ore Geology Reviews, 117: 103269. (in Persian with English abstract) https://doi.org/10.1016/j.oregeorev.2019.103269

He, J., Harris, J., Sawada, M. and Behnia, P., 2015. A comparison of classification algorithms using Landsat-7 and Landsat-8 data for mapping lithology in Canada’s Arctic. International Journal of remote sensing, 36(8): 2252–2276. https://doi.org/10.1080/01431161.2015.1035410

Heshmatnia, S., Tale Fazel, E. and Oroji, A., 2022. The role of sulfidation of Fe-carbonate rocks in increasing gold contents at the Zarshuran deposit (northern Takab), Takab-Angouran metallogenic district. Journal of Economic Geology 14(4): 89–114. (in Persian with English abstract) https://doi.org/10.22067/econg.2022.75417.1042

Hosseini Dinani, H., Bagheri, H. and Shamsipour Dehkordi, R., 2012. Mineralization and geochemical studies in the Kalchouyeh occurrence, southwest of Naein. Journal of Economic Geology, 4(2): 241–256. (in Persian with English abstract) https://doi.org/10.22067/econg.v4i2.16494

Hosseinzadeh, G., 1999. Study of economic geology on the Anjerd skarn, North of Ahar Town. Unpublished MSc. Thesis. University of Tabriz, Tabriz, Iran. (in Persian)

Huang, C., Davis, L. and Townshend, J., 2002. An assessment of support vector machines for land cover classification. International Journal of remote sensing, 23(4): 725–-749. https://doi.org/10.1080/01431160110040323

Hussain, M., Li, H., Beshr, A.‌M. and Memon, F. A., 2025. Remote sensing-based structural and lithological mapping for prospecting polymetallic mineralization at Xiaoshan region, China. Earth Science Informatics 18(1): 82. https://doi.org/10.1007/s12145-024-01614-x

Imamalipour, A., Abdeli Eslamlo, H. and Haj Alilou, B., 2011. Geochemistry of hydrothermal alterations associated with epithermal gold mineralization in Masjeddaghi area, east of Jolfa, NW Iran. Journal of Economic Geology, 2(2): 199–215. (in Persian with English abstract)  https://doi.org/10.22067/econg.v2i2.7851

Kashkoei Jahroomi, M. and Qishlaqi, A., 2016. A new approach for hydrothermal alteration mapping by selecting and interpreting principal components in Landsat ETM+ images. Journal of Economic Geology, 8(1): 181–-199. (in Persian with English abstract) https://doi.org/10.22067/econg.v8i1.31997

Kavoshgaran, C. E., 2012. Final report on general gold exploration in the Zeglik-Sarilar area, National Iranian Copper Industries Company (NICICO), Tehran, 254 pp. (in Persian)

Khodadadzadeh, M., Li, J., Plaza, A., Ghassemian, H., Bioucas-Dias, J. M. and Li, X., 2014. Spectral–spatial classification of hyperspectral data using local and global probabilities for mixed pixel characterization. IEEE Transactions on geoscience and remote sensing, 52(10): 6298–6314. https://doi.org/10.1109/TGRS.2013.2296031

Komeili, S.S., Khalili, M., Asadi Haroni, H., Bagheri, H. and Ayati, F., 2017. The nature of hydrothermal fluids in the Kahang porphyry copper deposit (Northeast of Isfahan) based on mineralography, fluid inclusion and stable isotopic data. Journal of Economic Geology, 8(2): 285–305. (in Persian with English abstract), https://doi.org/10.22067/econg.v8i2.37178

Kovacevic, M., Bajat, B., Trivic, B. and Pavlovic, R., 2009. Geological units classification of multispectral images by using support vector machines. 2009 International Conference on Intelligent Networking and Collaborative Systems, United States, Ieee. https://doi.org/10.1109/INCOS.2009.44

Lu, J., Han, L., Liu, L., Wang, J., Xia, Z., Jin, D. and Zha, X., 2023. Lithology classification in semi-arid area combining multi-source remote sensing images using support vector machine optimized by improved particle swarm algorithm. International Journal of Applied Earth Observation and Geoinformation, 119: 103318. https://doi.org/10.1016/j.jag.2023.103318

Maanijou, M. and Mostaghimi, M., 2014. The mass balance calculation of hydrothermal alteration in Sarcheshmeh porphyry copper deposit. Journal of Economic Geology, 5(2): 175–199. (in Persian with English abstract) https://doi.org/10.22067/econg.v5i2.31718

Mazloumi Bajestani, A. and Rasa, I., 2010. Alteration and petrology of Intrusive Rocks associated with Gold Mineralization at Kuh-E-Zar Gold Deposit, Torbat-e-Heydaryeh. Journal of Economic Geology, 1(1): 57–69. (in Persian with English abstract) https://doi.org/10.22067/econg.v1i1.3681

Mehrabi, B., Chaghaneh, N. and Tale Fazel, E., 2014. Intermediate sulfidation epithermal mineralization of No. 4 anomaly of Golojeh deposit (N. Zanjan) based on mineralography, alteration and ore fluid geochemistry features. Journal of Economic Geology, 6(1): 1–22. (in Persian with English abstract) https://doi.org/10.22067/econg.v6i1.38302

Mehrabi, B., Ghasemi Siani, M. and Fazeli, T., 2021. Fluid inclusions, mineralogy and mineral chemistry of the porphyry-epithermal Sari Gunay epithermal ore deposit - the Kurdistan province. Journal of Economic Geology, 12(4): 509–530. (in Persian with English abstract) https://doi.org/10.22067/econg.v12i4.83516

Mehvari, R., Shamsipour Dehkordi, R., Bagheri, H., Noghreyan, M. and Mackizadeh, M. A., 2010. Mineralogy and fluid inclusion studies in kalchoye Copper- gold deposit, East of Esfahan. Journal of Economic Geology, 1(1): 47–55. (in Persian with English abstract) https://doi.org/10.22067/econg.v1i1.3680

Melgani, F. and Bruzzone, L., 2004. Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on geoscience and remote sensing, 42(8): 1778–1790. https://doi.org/10.1109/TGRS.2004.831865

Mondal, S., Guha, A. and Pal, S.K., 2024. Support vector machine-based integration of AVIRIS NG hyperspectral and ground geophysical data for identifying potential zones for chromite exploration–A study in Tamil Nadu, India. Advances in Space Research, 73(2): 1475–1490. https://doi.org/10.1016/j.asr.2022.04.048

Moritz, R., Selby, D., Ovtcharowa, M., Mederer, J., Melkonyan, R., Hovakimyan, S., Tayan, R., Popkhadze, N., Gugushvili, V. and Ramazanov, V., 2012. Diversity of geodynamic settings during Cu, Au and Mo ore formation in the Lesser Caucasus: new age constraints. Proceedings 1st Triennial European Mineralogy and Crystallography Meeting, Frankfurt, Germany.

Nabavi, M., 1976. An introduction to the Iranian geology. Geological Survey of Iran, Tehran, 110 pp. (in Persian)

Othman, A. and Gloaguen, R., 2014. Improving lithological mapping by SVM classification of spectral and morphological features: The discovery of a new chromite body in the Mawat ophiolite complex (Kurdistan, NE Iraq). Remote Sensing, 6(8): 6867–-6896. https://doi.org/10.3390/rs6086867

Pal, M., 2005. Random forest classifier for remote sensing classification. International Journal of remote sensing, 26(1): 217–222. https://doi.org/10.1080/01431160412331269698

Pereira, J., Pereira, A., Gil, A. and Mantas, V. M., 2023. Lithology mapping with satellite images, fieldwork-based spectral data, and machine learning algorithms: The case study of Beiras Group (Central Portugal). Catena, 220: 106653. https://doi.org/10.1016/j.catena.2022.106653

Pournamdari, M. and Hashim, M., 2014. Detection of chromite bearing mineralized zones in Abdasht ophiolite complex using ASTER and ETM+ remote sensing data. Arabian Journal of Geosciences, 7(5): 1973–-1983. https://doi.org/10.1007/s12517-013-0927-0

Rahmani, N., Sekandari, M., Pour, A.B., Ranjbar, H. and Carranza, E.J.M., 2025. Evaluation of support vector machine classifiers for lithological mapping using PRISMA hyperspectral remote sensing data: Sahand–Bazman magmatic arc, central Iran. Remote Sensing Applications: Society and Environment, 37: 101449. https://doi.org/10.1016/j.rsase.2025.101449

Rajabpour, S., Hassanpour, S., Radmard, K. and Moghaddasi, S.J., 2022. Nature and genesis of the Zaglic Au deposit, NW Iran: Constraints from geochemical studies. Journal of Geochemical Exploration, 238: 107001. https://doi.org/10.1016/j.gexplo.2022.107001

Rajabzadeh, M.A. and Esmaeili, S., 2013. Study on mineralization at Jian copper deposit, Fars province, using petrographical and geochemical data. Journal of Economic Geology, 5(1): 93–104. (in Persian with English abstract) https://doi.org/10.22067/econg.v5i1.22912

Ramezani, Z., Alirezaei, S. and Einali, M., 2021. The mineralogy, texture and fluid inclusion characteristics of Meideh silicic zone, north Pariz, Kerman copper belt; investigation of genetic relations with porphyry systems. Journal of Economic Geology, 13(4): 667–695. (in Persian with English abstract) https://doi.org/10.22067/econg.2021.51673.84923

Riahi, S., Fathianpour, N. and Tabatabaei, S.H., 2017. Presenting a mapping method based on fuzzy Logic and TOPSIS multi criteria decision-making methods to detect promising porphyry copper mineralization areas in the east of the Sarcheshmeh copper metallogenic district. Journal of Economic Geology, 9(2): 357–374. (in Persian with English abstract) https://doi.org/10.22067/econg.v9i2.45829

Shebl, A., Abriha, D., Fahil, A.S., El-Dokouny, H.A., Elrasheed, A.A. and Csámer, Á., 2023. PRISMA hyperspectral data for lithological mapping in the Egyptian Eastern Desert: Evaluating the support vector machine, random forest, and XG boost machine learning algorithms. Ore Geology Reviews, 161: 105652. https://doi.org/10.1016/j.oregeorev.2023.105652

Shereif, A.S., Shebl, A., Mahmoud, A.S. and Csámer, Á., 2024. Enhanced Lithological Mapping in El-Missikat and El-Erediya Areas, Central Eastern Desert, Egypt, Leveraging Remote Sensing Techniques and Machine Learning Algorithms. IEEE Transactions on geoscience and remote sensing, 62: 4512527. https://doi.org/10.1109/TGRS.2024.3471982

Suykens, J.A., De Brabanter, J., Lukas, L. and Vandewalle, J., 2002. Weighted least squares support vector machines: robustness and sparse approximation. Neurocomputing, 48(1–4): 85–105. https://doi.org/10.1016/S0925-2312(01)00644-0

Taghipour, B. and Mackizadeh, M.A., 2011. Petrogenesis of skarn related Cu-porphyry intrusion deposit, Ali-Abad- Darreh Zereshk, Yazd. Journal of Economic Geology, 3(1): 79–92. (in Persian with English abstract) https://doi.org/10.22067/econg.v3i1.11444

Wang, Z. and ChangYu, Z., 2010. Rocks/Minerals Information Extraction from EO-1 Hyperion Data Base on SVM. 2010 International Conference on Intelligent Computation Technology and Automation, IEEE Computer Society, Changsha, China. https://doi.org/10.1109/ICICTA.2010.341

Yousefi, S.J. and Moradian, A., 2012. Mineralization model for Chahar Gonbad copper-gold deposit (Sirjan), using mineralogical, alteration and geochemical data and multivariate statistical methods. Journal of Economic Geology, 4(1): 135–153. (in Persian with English abstract) https://doi.org/10.22067/econg.v4i1.13397

Yu, L., Porwal, A., Holden, E.-J. and Dentith, M. C., 2012. Towards automatic lithological classification from remote sensing data using support vector machines. Computers & Geosciences, 45: 229–239. https://doi.org/10.1016/j.cageo.2011.11.019

Zarasvandi, A., Asadi, F., Pourkaseb, H., Ahmadnejad, F. and Zamanian, H., 2015.

Hydrothermal Fluid evolution in the Dalli porphyry Cu-Au Deposit: Fluid Inclusion microthermometry studies. Journal of Economic Geology, 7(2): 277–306. (in Persian with English abstract) https://doi.org/10.22067/econg.v7i2.38447

Zarasvandi, A., Tashi, M., Rezaei, M., Saki, A. and Mousivand, F., 2022. Geology and geochemistry of the Choran porphyry-epithermal Cu-Au deposit in the Dehej-Sarduveyeh subzone, Urumieh-Dokhtar magmatic arc. Journal of Economic Geology, 14(1): 39–66. (in Persian with English abstract)  https://doi.org/10.22067/econg.2021.52017.87614

Ziaii, M., Abedi, A. and Ziaii, M., 2007, September. Prediction of hidden ore bodies by new integrated computational model in marginal Lut region in east of Iran. In Proceedings of Exploration 07: Fifth Decennial International Conference Mineral Exploration, Toronto, Canada. https://www.911metallurgist.com/wp-content/uploads/2015/10/Prediction-of-Hidden-Ore-Bodies-by-New-Integrated-Computational-Model-in-Marginal-Lut-region-in-East-of-Iran.pdf