Modeling mineral component distribution in iron ore deposits

The modern geological information system tools make it possible to construct framelike and block-like models of mineral deposits. However, some modeling stages remain yet manual, which conditions much time to be spent to update the models when new or additional information arrives. The developed method of three-dimensional modeling of mineral deposits using artificial neural networks enables the automated modeling and quantitative valuation of mineral component distribution. A lithological model of an iron ore deposit was constructed and used to model mineral component distribution in ore bodies. The artificial neural network learning used the data of standard geological exploration. The network structure was determined empirically, with regard to domestic and foreign experience of using the neural networks for geological data processing. The reliability of the models was evaluated using the methods of cross-validation. The results show good agreement of the model data and test samples. The proposed method of mineral deposit modeling may find wide application at the stages of prospecting and preliminary exploration, when the data on composition and structure of a deposit are few but need prompt processing.

Kozhukhov A. A., Omelchenko D. R., Melnichenko I. A., Cheskidov V. V., Moseykin V. V. Modeling mineral component distribution in iron ore deposits. MIAB. Mining Inf. Anal. Bull. 2023;(8):5-17. [In Russ]. DOI: 10.25018/0236_1493_2023_8_0_5.

A.A. Kozhukhov¹, Graduate Student, e-mail: kozhuh@inbox.ru, ORCID ID: 0000-0002-9137-6315,
D.R. Omelchenko¹, Graduate Student, e-mail: omelched@gmail.com, ORCID ID: 0000-0001-5419-4881,
I.A. Melnichenko¹, Cand. Sci. (Eng.), Assistant of Chair, e-mail: kors-ilay@mail.ru, ORCID ID: 0000-0002-0205-6425,
V.V. Cheskidov¹, Cand. Sci. (Eng.), Assistant Professor, e-mail vcheskidov@misis.ru, Vice-director, College of Mining,
V.V. Moseykin¹, Dr. Sci. (Eng.), Professor, e-mail: moseykin@inbox.ru,
¹ National University of Science and Technology «MISiS», 119049, Moscow, Russia.

A.A. Kozhukhov, e-mail: kozhuh@inbox.ru.

1. Mel'nichenko I. A. Trekhmernoe geomodelirovanie granits litologicheskikh raznostey zhelezorudnykh mestorozhdeniy na osnove prostranstvenno-koordinirovannykh dannykh [Three-dimensional geomodeling of the boundaries of lithological differences of iron ore deposits based on spatially coordinated data], Candidate’s thesis, Moscow, NITU «MISiS», 2021, 30 p.

2. Jalloh A. B., Kyuro S., Jalloh Y., Barrie A. K. Integrating artificial neural networks and geostatistics for optimum 3D geological block modeling in mineral reserve estimation. A case study. International Journal of Mining Science and Technology. 2016, vol. 26, no. 4, pp. 581—585. DOI: 10.1016/j.ijmst.2016.05.008.

3. Jiateng Guo, Xulei Wang, Jiangmei Wang, Xinwei Dai, Lixin Wu, Chaoling Li, Fengdan Li, Shanjun Liu, Jessell M. W. Three-dimensional geological modeling and spatial analysis from geotechnical borehole data using an implicit surface and marching tetrahedra algorithm. Engineering Geology. 2021, vol. 284, article 106047. DOI: 10.1016/j.enggeo.2021.106047.

4. Melchers H., Crommelin D., Koren B., Menkovski V., Sanderse B. Comparison of neural closure models for discretised PDEs. Computers & Mathematics with Applications. 2023, vol. 143, pp. 94—107. DOI: 10.1016/j.camwa.2023.04.030.

5. Melnichenko I. A., Kozhukhov A. A., Omelchenko D. R., Moseykin V. V. 3D mineral deposit modeling using concepts of blockmodeling and artificial neural networks. MIAB. Mining Inf. Anal. Bull. 2022, no. 10, pp. 5—19. [In Russ]. DOI: 10.25018/0236_1493_2022_10_0_5.

6. Kulawiak M., Dawidowicz A., Pacholczyk M. E. Analysis of server-side and client-side Web-GIS data processing methods on the example of JTS and JSTS using open data from OSM and geoportal. Computers & Geosciences. 2019, vol. 129, pp. 26—37. DOI: 10.1016/j. cageo.2019.04.011.

7. Dhont D., Monod B., Hervouët Y., Backé G., Klarica S., Choy J. E. 3D geological modeling of the Trujillo block: Insights for crustal escape models of the Venezuelan Andes. Journal of South American Earth Sciences. 2012, vol. 39, pp. 245—251. DOI: 10.1016/j.jsames.2012.04.003.

8. Melnichenko I A., Kirichenko Yu V. Spatial zoning of mineral deposits. MIAB. Mining Inf. Anal. Bull. 2021, no. 4, pp. 46—56. [In Russ]. DOI: 10.25018/0236_1493_2021_4_0_46.

9. Lazreg M. B., Goodwin M., Granmo O.-C. Combining a context aware neural network with a denoising autoencoder for measuring string similarities. Computer Speech & Language. 2020, vol. 60, article 101028. DOI: 10.1016/j.csl.2019.101028.

10. Mohammadzaheri M., Chen L., Ghaffari A., Willison J. A combination of linear and nonlinear activation functions in neural networks for modeling a de-superheater. Simulation Modelling Practice and Theory. 2009, vol. 17, no. 2, pp. 398—407. DOI: 10.1016/j.simpat.2008.09.015.

11. Liang Yang, Ling-Xiao Zhao, Chun-Lu Zhang, Bo Gu Loss-efficiency model of single and variable-speed compressors using neural networks. International Journal of Refrigeration. 2009, vol. 32, no. 6, pp. 1423—1432. DOI: 10.1016/j.ijrefrig.2009.03.006.

12. Qi Gong, Wei Kang, Fariba Fahroo Approximation of compositional functions with ReLU neural networks. Systems & Control Letters. 2023, vol. 175, article 105508. DOI: 10.1016/ j.sysconle.2023.105508.

13. Gorbatenko V. D., Cheskidov V. V., Yakubov M. M. Modeling quality of concentration factory feedstock in ferruginous quartzite mining at the Lebedinskoe deposit. Gornyi Zhurnal. 2022, no. 6, pp. 15—20. [In Russ]. DOI: 10.17580/gzh.2022.06.02.

14. Cheskidov V. V., Barabanov N. N., Lozhkin M. O., Smirnov P. A., Lagutina A. A. Distribution of iron and sulfur compounds: A case study of hydraulic waste fills. MIAB. Mining Inf. Anal. Bull. 2021, no. 3, pp. 142—153. [In Russ]. DOI: 10.25018/0236-1493-2021-3-0-142-153.

15. Vostrikov A. V., Prokofeva E. N., Goncharenko S. N., Gribanov I. V. Analytical modeling for the modern mining industry. Eurasian Mining. 2019, no. 2, pp. 30—35. DOI: 10.17580/em. 2019.02.07.

16. Goncharenko S. N., Berdaliev B. A. Methods to predict and estimate residual and technological concentrations of uranium ore in in-situ leaching mining. MIAB. Mining Inf. Anal. Bull. 2018, no. 5, pp. 43—48. [In Russ]. DOI: 10.25018/0236-1493-2018-5-0-43-48.

17. Stadnik D. A., Stadnik N. M., Zhilin A. G., Lopushnyak E. V. Methodological framework for implicit modeling of solid mineral deposits in automated design. MIAB. Mining Inf. Anal. Bull. 2023, no. 5-1, pp. 185—197. [In Russ]. DOI: 10.25018/0236_1493_2023_51_0_185.

18. Voitekhovsky Yu. L., Zakharova A. A., Klimochenkov M. D. Modeling of petrographic structures. Article 2. Vestnik of Geosciences. 2020, no. 12, pp. 32—35. [In Russ]. DOI: 10.19110/ geov.2020.12.3.

19. Agafonov V. V., Zaitseva Е. V., Yakheev V. V., Snigirev V. V., Gurkov A. A. Simulation modeling of functional structures of technological systems of mining enterprises. Ugol'. 2022, no. 2, pp. 57—60. [In Russ]. DOI: 10.18796/0041-5790-2022-2-57-60.

20. Voitekhovsky Yu. L., Zakharova V. V. Modeling of petrographic structures. Vestnik of Geosciences. 2020, no. 10, pp. 38—42. [In Russ]. DOI: 10.19110/geov.2020.10.5.