A geostatistical predictive and prospecting model of gold mineralization (map of potential resource prospects) for the area of the Central Kolyma region (within the Inyali-Debinsky synclinorium) was built using machine learning methods.
Multispectral satellite images, materials of medium- and small-scale geological mapping, data of medium-scale geophysical and lithochemical surveys were used as source data. Based on this data, an exhaustive set of indicators related to the search criteria was calculated. To build a forecast, the Random Forest method was used using random negative samples and averaging the result. The obtained forecast maps allow localizing potential gold ore objects with a spatial resolution of 2 km, which makes it possible to select promising areas for licensing. In addition, the possibilities of using machine learning methods for metallogenic zoning of the territory are shown.

Ivan N. Goryachev
Researcher
Irkutsk Siberian School of Geosciences, National Research Technical University (INRTU)
83, Lermontov Str., Irkutsk, 664074, Russia
е-mail: ivan.goryachev@geo.istu.edu
ORCID: 0000-0002-5250-9410
ScopusID:57245822800, SPIN: 9927-3203

1. Goryachev N.A. Geology of Mesozoic gold-quartz vein belts of Northeast Asia. Magadan: SVKNII DVO RAN; 1998. – 210 p.
2. Zuo R. Geodata Science-Based Mineral Prospectivity Mapping: A Review. Natural Resources Research. 2020;29:3415–3424. DOI: 10.1007/s11053-020-09700-9.
3. Karamyshev A.V., Fedorova K.S., Tarasov A.V. Forecast for concealed gold mineralization within Central Kolyma region based on a set of geological and geophysical features by identification method. Ores and Metals. 2020;2:10-24. DOI 10.24411/0869-5997-2020-10010.
4. Parshin A.V., Auziņa L.I., Prosekin S.N., Blinov A.V., Kosterev A.N., Lonshakov Gr.S., Usmanova A.M., Shestakov S.A., Davydenko Yu.A. GIS-based approach to estimating area prospects for mineral deposits (on example of groundwater deposits of Eastern Siberia territory). Geoinformatika. 2017;1:11-20.
5. Carranza E.J.M., Laborte A.G. Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra (Philippines). Computers & Geosciences. 2015;74:60–70. DOI: 10.1016/j.cageo.2014.10.004
6. Chen Y., Wu W., Zhao Q. A Bat-Optimized One-Class Support Vector Machine for Mineral Prospectivity Mapping. Minerals. 2019;9(5):317. DOI: 10.3390/min9050317
7. Maepa F., Smith R.S., Tessema A. Support vector machine and artificial neural network modelling of orogenic gold prospectivity mapping in the Swayze greenstone belt, Ontario, Canada. Ore Geology Reviews. 2021;130:103968. DOI: 10.1016/j.oregeorev.2020.103968
8. Sun T., Li H., Wu K., Chen F., Zhu Z., Hu Z. Data-Driven Predictive Modelling of Mineral Prospectivity Using Machine Learning and Deep Learning Methods: A Case Study from Southern Jiangxi Province, China. Minerals. 2020;10(2):102. DOI: 10.3390/min10020102
9. Golubenko I.S., Goryachev N.A. Bank of geospatial information of the geological structure of the territory Magadan region (Northeast of Russia). In: Information Technologies in Earth Sciences and Applications for Geology, Mining and Economy. ITES&MP-2019: Proceedings of the 5th International Conference (Moscow, 14–18 October 2019). Moscow: VNIIgeosistem; 2019. p. 52.
10. Shpikerman V. I., Polubotko I. V., Vas’kin A. F., Petukhov V. V. et al. Gosudarstvennaya geologicheskaya karta Rossiiskoi Federatsii. Masshtab 1:1 000 000 (tret’e pokolenie). Seriya Verkhoyano-Kolymskaya. List R-55 – Susuman. Ob”yasnitel’naya zapiska [State geological map of the Russian Federation. Scale 1:1 000 000 (Third generation). Verkhoyans-Kolyma series. Sheet Р-55 – Susuman. Explanatory note]. Saint-Petersburg: Kartograficheskaya fabrika VSEGEI; 2016. 520
11. Kuznetsov V. M., Zhigalov S. V., Vedernikova T. A., Shpikerman V. I. Gosudarstvennaya geologicheskaya karta Rossiiskoi Federatsii. Masshtab 1:1 000 000 (tret’e pokolenie). Seriya Verkhoyano-Kolymskaya. List R-56 – Seimchan. Ob”yasnitel’naya zapiska [State geological map of the Russian Federation. Scale 1:1 000 000 (Third generation). Verkhoyans-Kolyma series. Sheet Р-56 – Seymchan. Explanatory note]. Saint-Petersburg: Kartograficheskaya fabrika VSEGEI; 2008. 426 p.
12. Mannafov N. G., Voznesenskii S. D., Ogorodov V. A. et al. Geologicheskaya karta i karta poleznykh iskopaemykh Okhotsko-Kolymskogo regiona. Masshtab 1:500 000. Ob”yasnitel’naya zapiska [Geologic map and Minerals map of Okhotsk-Kolyma region. Scale 1:500 000. Explanatory note]. Magadan, 1999.
13. Kuznetsov V. M., Palymskaya Z. A., Shashurina I. T., Mikhailova V. P., Koshkarev V.L. Metallogenicheskaya karta Kolymo-Omolonskogo regiona. Masshtab 1:500 000. Ob”yasnitel’naya zapiska. [Metallogenic map of Kolyma-Omolon region. Scale 1:500 000. Explanatory note.] Magadan: SVKNII DVO RAN; 2001. 190 p.