ATT-CNN mapping of the Udokan-type Cu-Mo porphyry deposits

A.O. Kuzmina, M.Yu. Ilyina, K.E. Lukichev, N.G. Presnyakova, A.A. Tatarnikov
Financial University under the Government of the Russian Federation, Moscow, Russian Federation
Russian Mining Industry №1/ 2026 p. 135-142

Abstract: Exploration of copper porphyry deposits requires integration of heterogeneous geospatial data to identify blind ore bodies at depths of up to 2000 m. Convolutional neural networks with attention-based mechanisms (ATT-CNN) demonstrate 95–98% classification accuracy in mineral prediction tasks. The Udokan copper deposit, with the reserves of 26.7 million tons of Cu at the grade of 1.05%, is a benchmark for stratiform Cu-Ag mineralization in Proterozoic metasedimentary complexes of Transbaikalia. The study is based on the integration of geochemical data for 20 elements, gravimetric and magnetic mapping, as well as multispecral images for a plot of 12,000 km2 in area. The ATT-CNN architecture includes four convolutional blocks with a channel attention-based mechanism after the second and the fourth blocks. Training was performed on a dataset of 473 copper porphyry-type ore occurrences in the North American Cordillera, followed by transfer learning for the Udokan region. The model achieved an accuracy of 94.87% with AUC = 0.987 compared to the baseline CNN with AUC = 0.970. Analysis of the attention weights revealed the dominant role of the Cu, Mo, Co geochemical anomalies and structural parameters. Six permissive tracts with an area of 100–800 km2 were identified with the probability of detecting commercial concentrations of 78–92%. Verification showed that 83% of the documented ore occurrences fall within the forecast contours, covering 9.7% of the territory.

Keywords: deep machine learning, attention-based mechanism, geochemical mapping, copper deposits, Udokan deposit, predictive modeling, transfer learning

For citation: Kuzmina A.O., Ilyina M.Yu., Lukichev K.E., Presnyakova N.G., Tatarnikov A.A. ATT-CNN mapping of the Udokan-type Cu-Mo porphyry deposits. Russian Mining Industry. 2026;(1):135–142. https://doi.org/10.30686/1609-9192-2026-1-135-142

Article info

Received: 14.10.2025

Revised: 16.12.2025

Accepted: 24.12.2025

Information about the authors

Anastasia O. Kuzmina – Cand. Sci. (Econ.), Associate Professor of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; https://orcid.org/0009-0001-0755-7675; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Maria Yu. Ilyina – Cand. Sci. (Econ.), Senior Lecturer, of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Konstantin E. Lukichev – Cand. Sci. (Law), Associate Professor of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; https://orcid.org/0000-0003-1873-2608; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Nadezhda G. Presnyakova – Cand. Sci. (Econ.), Assistant of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Artem A. Tatarnikov – Assistant of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

References

1. Panina O.V., Belyaev A.M., Zavalko N.A., Eremin S.G., Sagina O.A. Application of deep machine learning methods for structural analysis of ore bodies and prediction of optimal mining zones. Russian Mining Industry. 2025;(1):177–183. (In Russ.) https://doi.org/10.30686/1609-9192-2025-1-177-183

2. Zientek M.L., Chechetkin V.S., Parks H.L., Box S.E., Briggs D.A., Cossette P.M. et al. Assessment of undiscovered sandstone copper deposits of the Kodar-Udokan area, Russia. Scientific Investigations Report 2010-5090-M. Reston, VA: U.S. Geological Survey; 2014. 129 p. https://doi.org/10.3133/sir20105090M

3. Ali S.H., Giurco D., Arndt N., Nickless E., Brown G., Demetriades A. et al. Mineral supply for sustainable development requires resource governance. Nature. 2017;543(7645):367–372. https://doi.org/10.1038/nature21359

4. Popadyuk N.K., Bratarchuk T.V., Babayan L.K., Laffakh А.М. The green transition and development problems of fuel and energy sector in Russia. Eurasian Mining. 2024;(2):46–49. https://doi.org/10.17580/em.2024.02.10

5. Perelló J., Sillitoe R.H., Yakubchuk A.S., Valencia V.A., Cornejo P. Age and tectonic setting of the Udokan sedimenthosted copper-silver deposit, Transbaikalia, Russia. Ore Geology Reviews. 2017;86:856–866. https://doi.org/10.1016/j.oregeorev.2016.11.004

6. Xiong Y., Zuo R., Carranza E.J.M. Mapping mineral prospectivity through big data analytics and a deep learning algorithm. Ore Geology Reviews. 2018;102:811–817. https://doi.org/10.1016/j.oregeorev.2018.10.006

7. Chechetkin V.S., Yurgenson G.A., Narkelyun L.F., Trubachev A.I., Salikhov V.S. Geology and ores of the Udokan copper deposit: A review. Russian Geology and Geophysics. 2000;41(5):710–722. Available at: https://pubs.geoscienceworld.org/nsu/rgg/article-abstract/41/5/710/647434/GEOLOGY-AND-ORES-OF-THE-UDOKAN-COPPER-DEPOSIT-A (accessed: 11.10.2025).

8. Li Q., Chen G., Luo L. Mineral prospectivity mapping using attention-based convolutional neural network. Ore Geology Reviews. 2023;156:105381. https://doi.org/10.1016/j.oregeorev.2023.105381

9. Ilyina I.Yu., Krasyukova N.L. Remuneration of university teachers in the context of higher school modernization: Dynamics and differentiation. Economics, Taxes & Law. 2025;18(3):100–111. (In Russ.) https://doi.org/10.26794/1999-849X-2025-18-3-100-111

10. Shedko Yu.N., Kharchenko K.V., Zudenkova S.A., Moskvitina E.I., Babayan L.K. A synergetic approach to openpit mine management using big data and intelligent predictive analytics systems. Russian Mining Industry. 2025;(1):154–160. (In Russ.) https://doi.org/10.30686/1609-9192-2025-1-154-160

11. Zavalko N.A., Belyaev A.M., Krasyukova N.L., Eremin S.G. The use of green technologies by Russian oil and gas companies in oil and gas production and their effect on reduction of carbon footprint. Eurasian Mining. 2025;(1):65–68. https://doi.org/10.17580/em.2025.01.12

12. Dong Y.-L., Zhang Z.-J. Deep forest modeling: An interpretable deep learning method for mineral prospectivity mapping. Journal of Geophysical Research: Machine Learning and Computation. 2024;1(4):e2024JH000311. https://doi.org/10.1029/2024JH000311

13. Kharchenko K.V. Improving the Cluster Landscape of the Region as a Factor of Ensuring Economic Security. Economics, Taxes & Law. 2025;18(2):98–106. (In Russ.) https://doi.org/10.26794/1999-849X-2025-18-2-98-106

14. Izotova G.S., Eremin S.G., Galkin A.I. Optimization of Strategic Planning Processes in the System of State and Municipal Administration of the Russian Federation. Economics, Taxes & Law. 2025;18(1):87-94. (In Russ.) https://doi.org/10.26794/1999-849X-2025-18-1-87-94

15. Yang F., Zuo R., Xiong Y., Wang J., Zhang G. An interpretable attention branch convolutional neural network for identifying geochemical anomalies related to mineralization. Journal of Geochemical Exploration. 2023;252:107274. https://doi.org/10.1016/j.gexplo.2023.107274

16. McClenaghan M.B., Paulen R.C., Smith I.R., Rice J.M., Plouffe A., McMartin I. et al. Review of till geochemistry and indicator mineral methods for mineral exploration in glaciated terrain. Geochemistry: Exploration, Environment, Analysis. 2023;23(4):013. https://doi.org/10.1144/geochem2023-013

17. Sun K., Chen Y., Geng G., Lu Z., Zhang W., Song Z. et al. A review of mineral prospectivity mapping using deep learning. Minerals. 2024;14(10):1021. https://doi.org/10.3390/min14101021

18. Krasyukova N.L., Panina O.V., Eremin S.G., Zubenko A.V., Laffakh A.M. Smart prediction of ground displacement using parallel neural network models and high-precision geodetic measurements. Russian Mining Industry. 2025;(2):106–112. (In Russ.) https://doi.org/10.30686/1609-9192-2025-2-106-112

19. Gongalsky B., Velivetskaya T., Taskaev V. Mineral and S-Isotope Compositions of Cu-Sulfide Deposits in Southern Siberia (Kodar-Udokan Region), Russia. Minerals. 2024;14(3):228. https://doi.org/10.3390/min14030228

20. Krasyukova N.L., Zubets A.Z., Eremin S.G., Zubenko A.V., Laffakh A.M. Multi-agent techniques for planning stripping operations and minimizing environmental risks in mining operations. Russian Mining Industry. 2025;(1):170–176. (In Russ.) https://doi.org/10.30686/1609-9192-2025-1-170-176

21. Xu Y., Zuo R. An interpretable graph attention network for mineral prospectivity mapping. Mathematical Geosciences. 2024;56(2):169–190. https://doi.org/10.1007/s11004-023-10076-8

22. Ayuso R.A., Barton M.D., Blakely R.J., Bodnar R.J., Dilles J.H., Gray F. et al. Porphyry copper deposit model. Scientific Investigations Report 2010-5070-B. Reston, VA: U.S. Geological Survey; 2010. 169 p. https://doi.org/10.3133/sir20105070b

23. Kadyrova G.M., Krasyukova N.L., Rozhdestvenskaya I.A., Tokmurzin T.M., Voronova E.I. Adaptive optimization of traffic flows in underground mine workings based on artificial intelligence methods. Russian Mining Industry. 2025;(1):137–146. (In Russ.) https://doi.org/10.30686/1609-9192-2025-1-137-146

24. Hu J., Shen L., Sun G. Squeeze-and-Excitation Networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18–23 June 2018. IEEE; 2018, pp. 7132–7141. https://doi.org/10.1109/CVPR.2018.00745

25. Singer D.A., Berger V.I., Moring B.C. Porphyry Copper Deposits of the World: Database and Grade and Tonnage Models, 2008. Open-File Report 2008-1155. Reston, Virginia: U.S. Geological Survey; 2008. 45 p. Available at: https://pubs.usgs.gov/of/2008/1155/ (accessed: 27.12.2024).