Application of convolutional neural networks for hyperspectral classification of copper-nickel ores in Arctic conditions

S.E. Prokofiev, O.V. Panina, N.L. Krasyukova, S.G. Eremin, T.V. Butova
Financial University under the Government of the Russian Federation, Moscow, Russian Federation
Russian Mining Industry №1/ 2026 p. 114-121

Abstract: Classification of copper-nickel ores in the Arctic deposits in extreme climatic conditions and with limited access to these territories is a critical task for the mining industry. Traditional geochemical sampling methods are time-consuming and become economically inefficient in large-scale mapping of ore bodies. Hyperspectral remote sensing combined with deep learning architectures opens up prospects for automated classification of the ore types without the need for mass sampling. The study analyzes the possibilities of using convolutional neural networks to process hyperspectral data from copper-nickel deposits in the Arctic zone, including the Norilsk ore district (Russia), the Izok Lake deposit (Canadian Arctic), and the Olympic Dam deposit (Australia). A comparative analysis of one-dimensional and hybrid 3D-2D CNN architectures was performed for classification of sulfide ores based on the spectral data within the range of 400–2500 nm. A review of current research showed that optimized 3D-2D CNN architectures achieve 95.73% classification accuracy on reference mineral datasets, while onedimensional models demonstrate 93.86% accuracy. When used for quantitative assessment of the element content in predicting copper and nickel concentrations, regression CNN models show a coefficient of determination R2 = 0.73–0.86. Specific factors of the Arctic conditions affecting the quality of hyperspectral data were analyzed, including the snow cover, surface oxidation of sulfides, and a short period of cloud-free conditions for imaging. A methodology has been proposed for the Norilsk region, which produces 425,000 tons of copper annually, to integrate the Gaofen-5 and PRISMA satellite data with the CNN architectures for prompt mapping of the ore zones. The results demonstrate the applicability of the technology to monitor the content of useful components across deposits with the area exceeding 1,000 km2.

Keywords: convolutional neural network, hyperspectral sensing, copper-nickel ores, Arctic deposits, mineral classification, Norilsk, deep learning

For citation: Prokofiev S.E., Panina O.V., Krasyukova N.L., Eremin S.G., Butova T.V. Application of convolutional neural networks for hyperspectral classification of copper-nickel ores in Arctic conditions. Russian Mining Industry. 2026;(1):114–121. https://doi.org/10.30686/1609-9192-2026-1-114-121

Article info

Received: 24.10.2025

Revised: 16.12.2025

Accepted: 16.01.2025

Information about the authors

Stanislav E. Prokofiev – Dr. Sci. (Econ.), Professor 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.

Olga V. Panina – 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; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Natalya L. Krasyukova – Dr. Sci. (Econ.), Professor 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.

Sergey G. Eremin – Dr. 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; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Tatyana V. Butova – Dr. 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; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

References

1. Ahmad M., Distefano S., Khan A.M., Mazzara M., Li C., Li H. et al. A comprehensive survey for Hyperspectral Image Classification: The evolution from conventional to transformers and Mamba models. Neurocomputing. 2025;644:130428. https://doi.org/10.1016/j.neucom.2025.130428

2. Esmaeili M., Fathianpour N., Soltani-Mohammadi S. PRISMA hyperspectral imagery for mapping alteration zones associated with Kuhpanj porphyry copper deposit, Southern Iran. European Journal of Remote Sensing. 2024;57(1):2299369. https://doi.org/10.1080/22797254.2023.2299369

3. Prado E.M.G., de Souza Filho C.R., Carranza E.J.M. Ore-grade estimation from hyperspectral data using convolutional neural networks: A case study at the Olympic dam iron oxide copper-gold deposit, Australia. Economic Geology. 2023;118(8):1899–1921. https://doi.org/10.5382/econgeo.5023

4. Choros K.A., Job A.T., Edgar M.L., Austin K.J., McAree P.R. Can hyperspectral imaging and neural network classification be used for ore grade discrimination at the point of excavation? Sensors. 2022;22(7):2687. https://doi.org/10.3390/s22072687

5. Richards B. Mapping minerals remotely: how hyperspectral imaging can support exploration. Mine Magazine. July 2024. Issue 142. Available at: https://mine.h5mag.com/mine_jul24/hyperspectral-imaging-remote-mineral-exploration (accessed: 27.02.2025).

6. Boyarko G.Yu., Lapteva A.M., Bolsunovskaya L.M. Mineral resource base of Russia’s copper: current state and development prospects. Mining Science and Technology (Russia). 2024;9(4):352–386. (In Russ.) https://doi.org/10.17073/2500-0632-2024-05-248

7. Jansen K., Mohr C., Lügger K., Heller C., Siemens J., Mulder I. Widespread occurrence of quaternary alkylammonium disinfectants in soils of Hesse, Germany. Science of The Total Environment. 2023;857(1):159228. DOI: https://doi.org/10.1016/j.scitotenv.2022.159228

8. Laakso K., Rivard B., Peter J.M., White H.P., Maloley M., Harris J., Rogge D. Application of airborne, laboratory, and field hyperspectral methods to mineral exploration in the Canadian Arctic: Recognition and characterization of volcanogenic massive sulfide-associated hydrothermal alteration in the Izok lake deposit area, Nunavut, Canada. Economic Geology. 2015;110(4):925–941. https://doi.org/10.2113/econgeo.110.4.925

9. Clark R.N. Spectroscopy of rocks and minerals, and principles of spectroscopy. Manual of Remote Sensing. 1999;(3):3–58.

10. NorNickel. Staying Strong: Annual Report 2023/PJSC MMC Norilsk Nickel. Moscow; 2024. 297 p. Available at: https://ar2023.nornickel.com/download/full-reports/ar_en_annual-report_pages_nornickel_2023.pdf (accessed: 04.12.2025).

11. Attallah Y., Zigh E., Adda A.P. Optimized 3D-2D CNN for automatic mineral classification in hyperspectral images. Reports on Geodesy and Geoinformatics. 2024;118:82–91. https://doi.org/10.2478/rgg-2024-0017

12. Peyghambari S., Zhang Y., Heidarian H., Sekandari M. One-dimensional-mixed convolution neural network and covariance pooling model for mineral mapping of porphyry copper deposit using PRISMA hyperspectral data. Photogrammetric Engineering & Remote Sensing. 2024;90(8):511–522. https://doi.org/10.14358/PERS.24-00006R2

13. Zhong Q., Eziz M., Sawut R., Ainiwaer M., Li H., Wang L. Application of a hyperspectral remote sensing model for the inversion of nickel content in urban soil. Sustainability. 2023;15(18):13948. https://doi.org/10.3390/su151813948

14. Lin Y., Gao J., Tu Y., Zhang Y., Gao J. Estimating low concentration heavy metals in water through hyperspectral analysis and genetic algorithm-partial least squares regression. Science of The Total Environment. 2024;916:170225. https://doi.org/10.1016/j.scitotenv.2024.170225

15. Popadyuk N.К., Bratarchuk T.V., Babayan L.К., 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

16. Bedini E. The use of hyperspectral remote sensing for mineral exploration: a review. Journal of Hyperspectral Remote Sensing. 2017;7(4):189–211. https://doi.org/10.29150/jhrs.v7.4.p189-211

17. Rajendran S., Sadooni F.N., Al-Kuwari H.A.-S., Anisimov O., Govil H., Nasir S., Vethamony P. Monitoring oil spill in Norilsk, Russia using satellite data. Scientific Reports. 2021;11:3817. https://doi.org/10.1038/s41598-021-83260-7

18. Jiang G., Zhou S., Cui S., Chen T., Wang J., Chen X. et al. Exploring the potential of HySpex hyperspectral imagery for extraction of copper content. Sensors. 2020;20(21):6325. https://doi.org/10.3390/s20216325

19. Zhang J., Wang M., Yang K., Li Y., Li Y., Wu B., Han Q. The new hyperspectral analysis method for distinguishing the types of heavy metal copper and lead pollution elements. International Journal of Environmental Research and Public Health. 2022;19(13):7755. https://doi.org/10.3390/ijerph19137755

20. 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

21. Rozhdestvenskaya I.A., Belyaev A.M., Lukichev K.E., Zubenko A.V., Laffakh A.M. Development of smart distributed data storage and analysis systems for optimization of mining operations and coal mining management. Russian Mining Industry. 2025;(2):56–64. (In Russ.) https://doi.org/10.30686/1609-9192-2025-2-56-64

22. Kharchenko K.V., Zubets A.Zh., Moskvitina E.I., Babayan L.K., Laffah A.M. Analyzing the efficiency of implementing predictive maintenance of mining equipment based on Industry 4.0 technologies. Russian Mining Industry. 2024;(4):130–138. (In Russ.) https://doi.org/10.30686/1609-9192-2024-4-130-138

23. Kharchenko K.V., Zubets A.Zh., Razumova E.V., Moskvitina E.I., Voronova E.I. Integration of distributed cloud computing to improve coal mining efficiency and monitoring of mining processes. Russian Mining Industry. 2025;(2):82–90. (In Russ.) https://doi.org/10.30686/1609-9192-2025-2-82-90

24. Abzhanova A., Bykov A., Surzhik D., Mukhamejanova A., Orazbayev B., Svirina A. Methods for assessing the layered structure of the geological environment in the drilling process by analyzing recorded phase geoelectric signals. Mathematics. 2024;12(14):2194. https://doi.org/10.3390/math12142194

25. Novoselova I.Yu., Novoselov A.L. Economic and Spatial Objectives of the Development of New Hydrocarbon Deposits in the Arctic Zone of the Russian Federation. Economics, Taxes & Law. 2024;17(2):95–105. (In Russ.) https://doi.org/10.26794/1999-849X-2024-17-2-95-105

26. Mokryshev I.S. Spatial classification of Russian regions by potential for distributed generation based on renewable energy sources. Economics, Taxes & Law. 2025;18(2):107–118. (In Russ.) https://doi.org/10.26794/1999-849X-2025-18-2-107-118