3D mineral deposit modeling using concepts of blockmodeling and artificial neural networks

Digital technologies and geological information processing techniques create a framework for the comprehensive 3D modeling. The image identification technology using the method of identification and classification of engineering geological elements can enable 2D engineering geological modeling with the interpretation basis represented not by the subjective model but by the mathematical apparatus. The developed method allows the real-time 3D lithology modeling with elimination of the frameworking stage which takes much time today. The research findings make it possible to build lithological models adjustable automatically upon updating of geological data. This allows the real-time exploration activity control and mining operation planning toward the target quality characteristics of mineral production. The new method of 3D mineral deposit modeling using artificial neural networks improves the quality of the modeling and geological data interpretation, as well as greatly accelerates processing of the information provided by exploration at all stages of mining and manmade deposit formation at the required accuracy and reliability. The constructed geological block model of a mineral deposit using artificial neural network enables the model assessment using mathematical methods not only in a two-dimensional space but also the special zoning of the deposit for the more comprehensive analysis.

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;(10):5-19. [In Russ]. DOI: 10.25018/0236_1493_2022_10_0_5.

I.A. Melnichenko¹, Cand. Sci. (Eng.), Assistant of Chair, e-mail: kors-ilay@mail.ru, ORCID ID: 0000-0002-0205-6425,
A.A. Kozhukhov¹, Graduate Student, e-mail: kozhuh@inbox.ru, ORCID ID: 0000-0002-9137-6315,
D.R. Omelchenko¹, Magister, e-mail: omelched@gmail.com, ORCID ID: 0000-0001-5419-4881,
V.V. Moseykin¹, Dr. Sci. (Eng.), Professor, e-mail: moseykin@inbox.ru, ORCID ID: 0000-0002-2286-1480,
¹ National University of Science and Technology «MISiS», 119049, Moscow, Russia.

I.A. Melnichenko, e-mail: kors-ilay@mail.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. Mahmoodi O., Smith R. S., Tinkham D. K. Supervised classification of down-hole physical properties measurements using neural network to predict the lithology. Journal of Applied Geophysics. 2016, vol. 124, pp. 17—26. DOI: 10.1016/j.jappgeo.2015.11.006.

3. Sorokina A. S., Zagibalov A. V. Practical application of the Mineframe software in building a block model and calculating the reserves of gold deposits. MIAB. Mining Inf. Anal. Bull. 2018, special edition 27, pp. 65—72. [In Russ]. DOI: 10.25018/0236-1493-2018-6-27-65-72.

4. Gromov E. V., Toropov D. A. Improving the accuracy of reserves calculation using 3D modeling (on the example of the Partomchorr field). MIAB. Mining Inf. Anal. Bull. 2017, special edition 23, pp. 158—166. [In Russ]. DOI: 10.25018/0236-1493-2017-10-23-158-166.

5. Likhman A. A. Geological block model as the main asset of a mining enterprise. Nedropolzovanie XXI vek. 2020, no. 4 (87), pp. 170—175. [In Russ].

6. Alenichev V. M., Alenichev M. V. Increasing validity of geoinformation support in mining waste management. MIAB. Mining Inf. Anal. Bull. 2019, no. 11, pp. 172—179. [In Russ]. DOI: 10.25018/0236-1493-2019-11-0-172-179.

7. Shchenkova E. S. Use of statistical and geostatistical apparatus in block modeling (on the example of a vein-type gold deposit). Geologiya v razvivayushchemsya mire: sbornik nauchnykh statey [Geology in the Developing World: a collection of scientific articles], Perm', 2019, pp. 517—520.

8. Cheklar M., Rybar P., Mihok Ya., Engel Ya. Economic evaluation of mineral deposits on examples of block models of open pit mining. Economics and innovation management. 2018, no. 1, pp. 46—59. [In Russ]. DOI: 10.26730/2587-5574-2018-1-46-58.

9. Wang K., Zhang L. Predicting formation lithology from log data by using a neural network. Petroleum Science. 2008, vol. 5, no. 3, pp. 242—246. DOI: 10.1007/s12182-008-0038-9.

10. Voitekhovsky Yu. L., Zakharova A. A. Petrographic structures and Hardy-Weinberg equilibria. Journal of Mining Institute. 2020, vol. 242, pp. 133—138. [In Russ]. DOI: 10.31897/ PMI.2020.2.133.

11. Wood D. A. Lithofacies and stratigraphy prediction methodology exploiting an optimized nearest-neighbour algorithm to mine well-log data. Marine and petroleum geology. 2019, vol. 110, pp. 347—367. DOI: 10.1016/j.marpetgeo.2019.07.026.

12. Abramyan G. O., Abramyan A. G. On the properties of binary functions of transition probabilities (in application to the geometry of the subsoil). Mine Surveying Bulletin. 2019, no. 3(130), pp. 57—60. [In Russ].

13. Sahoo S., Jha M. K. Pattern recognition in lithology classification: modeling using neural networks, self-organizing maps and genetic algorithms. Hydrogeology Journal. 2017, vol. 25, no. 2, pp. 311—330. DOI: 10.1007/s10040-016-1478-8.

14. Gu Y., Bao Z., Song X., Patil S., Ling K. Complex lithology prediction using probabilistic neural network improved by continuous restricted Boltzmann machine and particle swarm optimization. Journal of Petroleum Science and Engineering. 2019, vol. 149, pp. 966—978. DOI: 10.1016/j.petrol.2019.05.032.

15. Voronin A. Yu. Geological zoning from the standpoint of pattern recognition. Geoinformatika. 2008, no. 1, pp. 13—18. [In Russ].

16. Asfahani Jamal, Ghani B. Abdul Ghani Self organizing map neural networks approach for lithologic interpretation of nuclear and electrical well logs in basaltic environment, Southern Syria. Applied Radiation and Isotopes. 2018, vol. 137, pp. 50—55. DOI: 10.1016/j.apradiso.2018.03.008.

17. Junxi Chen, Jorge Pisonero, Sha Chen, Xu Wang, Qingwen Fan, Yixiang Duan Convolutional neural network as a novel classification approach for laser-induced breakdown spectroscopy applications in lithological recognition. Spectrochimica Acta. Part B: Atomic Spectroscopy. 2020, vol. 166, article 105801. DOI: 10.1016/j.sab.2020.105801.

18. Valentin M. B., Bom C. R., Coelho J. M., Correia M. D., M.P. de Albuquerque, M.P. de Albuquerque, Fari E. L. A deep residual convolutional neural network for automatic lithological facies identification in Brazilian pre-salt oilfield wellbore image logs. Journal of Petroleum Science and Engineering. 2019, vol. 179, pp. 474—503. DOI: 10.1016/j.petrol.2019.04.030.

19. 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.

20. Mahmoodi O., Smith R. S., Tinkham D. K. Supervised classification of down-hole physical properties measurements using neural network to predict the lithology. Journal of Applied Geophysics. 2016, vol. 124, pp. 17—26. DOI: 10.1016/j.jappgeo.2015.11.006.

21. Ameur O.-Zaimeche, Zeddouri A., Heddam S., Kechiched R. Lithofacies prediction in non-cored wells from the Sif Fatima oil field (Berkine basin, southern Algeria). A comparative study of multilayer perceptron neural network and cluster analysis-based approaches. Journal of African Earth Sciences. 2020, vol. 166, article 103826. DOI: 10.1016/j.jafrearsci.2020.103826.

22. 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.

23. Imamverdiyev Y., Sukhostat L. Lithological facies classification using deep convolutional neural network. Journal of Petroleum Science and Engineering. 2019, vol. 174, pp. 216—228. DOI: 10.1016/j.petrol.2018.11.023.

24. Yufeng Gu, Zhidong Bao, Xinmin Song, Shirish Patil, Kegang Ling Complex lithology prediction using probabilistic neural network improved by continuous restricted Boltzmann machine and particle swarm optimization. Journal of Petroleum Science and Engineering. 2019, vol. 179, pp. 966—978. DOI: 10.1016/j.petrol.2019.05.032.