Application of machine learning algorithms to predict gold mineralization in the Verkhneamginsky alkaline massif, Aldan-Stanovoy Shield
https://doi.org/10.31242/2618-9712-2025-30-2-205-219
Abstract
The study reports on the application of machine learning methods for predicting gold mineralization in the prospecting phase of geological exploration. It focuses on the Verkhneamginsky alkaline massif, situated within the Aldan-Stanovoy Shield, as a case study. The investigation included the analysis of 403 ore samples, which were evaluated through Inductively Coupled Plasma Atomic Emission Spectroscopy (ICP-AES) to determine the concentrations of 25 chemical elements. A total of eight classification algorithms were assessed in this investigation, including Random Forest, Support Vector Machine, Neural Network (Multilayer Perceptron), Boosting (AdaBoost), Decision Tree, K-Nearest Neighbors, Linear Discriminant Analysis, and Naive Bayes. The Random Forest and Support Vector Machine algorithms demonstrated the highest accuracy, achieving 89.6%, by identifying the relationships among ore elements (Au, Ag, As, Cu, Sb) and those elements that displayed negative correlations (Mg, Ca, Ti). These results were further validated through Receiver Operating Characteristic (ROC) analysis. In the process of developing the machine learning model, the values corresponding to the “ore” factor for each sample were designated as the target variable, while serving as predictors. To enable a comparative analysis between the parameters of established entities and the predicted regions, anomalous fields of the “ore” factor values were constructed. Additionally, machine learning methods enable the rapid and reliable interpretation of virtually any geochemical analytical data in the field, including data obtained through modern spectrometry methods and portable X-ray fluorescence (XRF) analyzers. The research further underscores the significance of integrating traditional statistical approaches, such as cluster and factor analysis, with contemporary machine learning algorithms to improve the accuracy of predictions.
Keywords
machine learning,
gold mineralization,
geochemical data,
exploration,
Verkhneamginsky alkaline massif,
Aldan-Stanovoy Shield
Supporting agencies: This study was conducted with financial support from JSC “Polyus Aldan” and within the research framework established by the Diamond and Precious Metal Geology Institute, Siberian Branch of the Russian Academy of Sciences (project No. FUFG-2024-0006).
About the Authors
P. L. Chudinov
JSC “Polyus Aldan”
Russian Federation
Russian Federation
CHUDINOV, Pavel Leonidovich, Senior Geologist
Nizhny Kuranakh
V. Yu. Fridovsky
Diamond and Precious Metal Geology Institute, Siberian Branch of the Russian Academy of Sciences
Russian Federation
Russian Federation
FRIDOVSKY, Valery Yurievich, Corresponding Member of the Russian Academy of Sciences, Dr. Sci. (Geol. And Mineral.), Director
Scopus Author ID: 6505824025
Yakutsk
References
1. Lindi O.T., Aladejare A.E., Ozoji T.M., et al. Uncertainty quantification in mineral resource estimation. Natural Resources Research. 2024;33:2503–2526. https://doi.org/10.1007/s11053-024-10394-6
2. Daya Sagar B.S., Cheng Q., Agterberg F. Handbook of Geosciences. Springer Cham; 2018. 366 p. https://doi.org/10.1007/978-3-319-78999-6
3. Mahboob M.A., Celik T., Genc B. Review of machine learning-based mineral resource estimation. The Journal of the Southern African Institute of Mining and Metallurgy. 2022;122(11):665-664. https://dx.doi.org/10.17159/2411-9717/1250/2022
4. Kanevski M., Foresti L., Kaiser C.,et al. Machine learning models for geospatial data. Handbook of theoretical and quantitative geography. Lausanne: University of Lausanne; 2009, pp. 175–227.
5. Han J., Kamber M., Pei J. Data Mining: Concepts and Techniques. Amsterdam: Elsevier; 2011. 432 p.
6. Akpan U.I., Starkey A. Review of classification algorithms with changing inter-class distances. Machine Learning with Applications. 2021;4:100031. https://doi.org/10.1016/j.mlwa.2021.100031
7. Prokopyev I.R., Doroshkevich A.G., Redina A.A., et al. Petrography of alkaline rocks, mineralogy and conditions of formation of ore mineralization of the Verkhneamginsky gold ore region (Aldan shield, Southern Yakutia). In: Ernst R.E. (ed.) Petrology of igneous and metamorphic complexes: Proceedings of the 9th All-Russian Conference with International Participation. Issue 9, Tomsk, November 28 – December 2, 2017. Tomsk: Izd-vo TsNTI; 2017, pp. 360–366. (In Russ.)
8. Anisimova G.S., Kondratyeva L.A., Sokolov E.P., at al. Gold mineralization of the Lebedinsky and Kuranakh types in the Verkhneamginsky region (Southern Yakutia). Otechestvennaya Geologiya = [Domestic geology]. 2018;(5):3–13. (In Russ.) https://doi.org/10.24411/0869-7175-2018-10010
9. Wang Q. Reservoir permeability prediction based on machine learning. International Journal of Natural Resources and Environmental Studies. 2024;3(1):129-138. https://doi.org/10.62051/ijnres.v3n1.17
10. Smelov A.P., Zedgenizov A.N., Timofeev V.F. Foundation of the North Asian Craton. Aldano-Stanovoy shield. In: Tectonics, Geodynamics and Metallogeny of the Republic of Sakha (Yakutia). Moscow: MAIK “Nauka/Interperiodica”; 2001, pp. 81–100. (In Russ.)
11. Parfenov L.M., Kuzmin M.I. Tectonics, Geodinamics and Metallogeny of the Republic Sakha (Yakutia). Moscow: MAIK “Nauka/Interperiodica”; 2001. 571 p. (In Russ.)
12. Sokolov E.P. Ore gold of the Verkhneamginsky goldbearing region. In: Biller A.Ya. (ed.) Geology and mineral resources of the northeast of Russia: materials of the All-Russian scientific and practical conference, Yakutsk, March 31 – April 2, 2015. Yakutsk: NEFU Publishing House; 2015, pp. 458–462. (In Russ.)
13. Zhumadilova D.V., Prokopyev I.R., Doroshkevich A.G., et al. Gold-bearing capacity of the Verkhneamginsky ore region (Aldan shield, Yakutia). In: Scientific and methodological foundations for forecasting, prospecting, and evaluating deposits of diamonds, precious and non-ferrous metals. Moscow: Central Research Institute of Geology of Non-Ferrous Metals; 2019, pp. 25–28. (In Russ.)
14. Ponomarchuk A.V., Prokopyev I.R., Doroshkevich A.G., et al. 40Ar / 39Ar age of alkaline rocks of the Verkhneamginsky massif (Aldan shield, South Yakutia). Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering. 2019;330(3):28–39. (In Russ.)
15. Nikiforova Z.S., Kazhenkina A.G. Typomorphism of placer gold of the Khatyrkhay ore-placer cluster (Upper-Amga area). Arctic and Subarctic Natural Resources. 2018;23(2):39–48. (In Russ.) https://doi.org/10.31242/2618-9712-2018-24-2-39-48
16. Shatova N.V., Shatov V.V., Molchanov A.V., et al. Geochemistry and petrography of hydrothermally altered rocks of the Ryabinovoye ore field (South Yakutia) as a basis for prediction gold-copper-porphyry ore mineralization. Regional Geology and Metallogeny. 2020;(84):71–96. (In Russ.)
17. Dvornik G.P. Searching criterions and indications of gold mineralization in potash alkaline massifs (on example deposits and displays ore Aldanskiy Shield). LITHOSPHERE (Russia). 2017;17(6):118–135. (In Russ.) https://doi.org/10.24930/1681-9004-2017-6-118-135
18. Barnes H.L. Geochemistry of Hydrothermal Ore Deposits. New York: Wily & Sons. 1979. 798 p.
19. Dwarampudi T.M., Alugolu A. Review of machine learning classification algorithms. International Journal of Progressive Research in Engineering Management and Science (IJPREMS). 2024;4(11):1104–1106 https://www.doi.org/10.58257/IJPREMS36877
Review
For citations:
Chudinov P.L., Fridovsky V.Yu. Application of machine learning algorithms to predict gold mineralization in the Verkhneamginsky alkaline massif, Aldan-Stanovoy Shield. Arctic and Subarctic Natural Resources. 2025;30(2):205-219. (In Russ.) https://doi.org/10.31242/2618-9712-2025-30-2-205-219
Views:
21
Email this article 