Criteria for the spatial distribution of polymetallic ore objects as a basis for creating a predictive search model using a neural network approach (using the example of the territory of South-Eastern Transbaikalia)

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

The work is aimed at identifying and substantiating criteria that indirectly or actually control ore objects in order to create a predictive neural network model of the metallogenic potential of southeastern Transbaikalia. For this purpose, geological, geophysical and cartographic materials were collected and processed, including the results of the analysis of remote sensing data. Statistical analysis of the array of collected data made it possible to establish a list of the minimum necessary information to identify criteria for the localization of polymetallic ore objects within the territory of southeastern Transbaikalia. As a result, thematic schemes have been prepared reflecting the relationship between the distribution of known polymetallic mineralization zones and the identified geological and spatial features. A correlation analysis was carried out between all the criteria in order to assess the suitability of using the selected features as input data for a future neural network model.

Full Text

Restricted Access

About the authors

G. A. Grishkov

Federal State Budgetary Institution of Science Institute of Geology of Ore Deposits, Petrography, Mineralogy and Geochemistry of the Russian Academy of Sciences (IGEM RAS)

Author for correspondence.
Email: gorgulini@yandex.ru
Russian Federation, Moscow

I. O. Nafigin

Federal State Budgetary Institution of Science Institute of Geology of Ore Deposits, Petrography, Mineralogy and Geochemistry of the Russian Academy of Sciences (IGEM RAS)

Email: gorgulini@yandex.ru
Russian Federation, Moscow

S. A. Ustinov

Federal State Budgetary Institution of Science Institute of Geology of Ore Deposits, Petrography, Mineralogy and Geochemistry of the Russian Academy of Sciences (IGEM RAS)

Email: gorgulini@yandex.ru
Russian Federation, Moscow

V. A. Petrov

Federal State Budgetary Institution of Science Institute of Geology of Ore Deposits, Petrography, Mineralogy and Geochemistry of the Russian Academy of Sciences (IGEM RAS)

Email: gorgulini@yandex.ru
Russian Federation, Moscow

V. A. Minaev

Federal State Budgetary Institution of Science Institute of Geology of Ore Deposits, Petrography, Mineralogy and Geochemistry of the Russian Academy of Sciences (IGEM RAS)

Email: gorgulini@yandex.ru
Russian Federation, Moscow

References

  1. Bavrina A.P., Borisov I.B. Modern rules for the application of correlation analysis // Medical almanac. 2021. № 3 (68). P. 70–79. (In Russian).
  2. Gmurman V.E. Probability theory and mathematical statistics: a textbook for universities. M.: Higher School. 2003. 479 p. (In Russian).
  3. Grishkov G.A., Ustinov S.A., Nafigin I.O., Petrov V.A. Neural networks and the possibilities of their application for the analysis of spatial geological data // Proceedings of the XV International Scientific and Practical Conference. In 7 volumes. Vol. 4. Development of new ideas and trends in Earth sciences: innovative technologies of geological exploration of mining and oil and gas business, well drilling, mathematical modeling and exploration geophysics. Moscow: S. Ordzhonikidze Russian State Geological Exploration University. 2021. P. 33‒36. (In Russian).
  4. Heritov A.D. SPSS 15: Professional statistical data analysis. St. Petersburg: St. Petersburg. 2007. 416 p. (In Russian).
  5. Ishchukova L.P., Avdeev B.V., Gubkin G.N., Igoshin Yu.A., Makushin M.F., Popova A.I., Rogova V.P., Spirin E.K., Filipchenko Yu.A., Khomentovsky B.N. Geology of the Urulyunguyevsky ore district and molybdenum-uranium deposits of the Streltsovsky ore field. M.: Geoinformmark. 1998. 382 p. (In Russian).
  6. Katz Ya.G., Poletaev A.I., Rumyantseva E.F. Fundamentals of lineament tectonics. M.: Nedra. 1986. 140 p. (In Russian).
  7. Khalafyan A.A. Statistica 6. Statistical data analysis. 3rd ed. Textbook. M.: LLC “BinomPress”. 2008. 512 p. (In Russian).
  8. Kuznetsov V.V., Brel A.I., Bogoslavets N.N., Elshina S.L., Kuznetsova T.P., Seravina T.V. Metallogeny of the Priagrun structural-formation zone // Domestic Geology. 2018. № 2. P. 32‒43. (In Russian).
  9. Petrov V.A., Andreeva O.V., Poluektov V.V., Kovalenko D.V. Tectono-magmatic cycles and geodynamic settings of ore-bearing system formation in the Southern Cis-Argun Region // Geology of Ore Deposits. 2017. V. 59. № 6. P. 431‒452. (In Russian).
  10. Shivokhin E.A., Ozersky A.F., Artamonova N.A., Dukhovsky A.A., Karasev V.V., Kurylenko A.V., Nadezhdina T.N., Pavlenko Yu.V., Raitina N.I., Shor G.M. Explanatory note: State Geological Map of the Russian Federation. Scale 1:1000000 (third generation). Sheet M-50 (Borzya). St. Petersburg: Publishing house kartrofabrika VSEGEI. 2010. 553 p. (In Russian).
  11. Tikunov V.S. Geoinformatics: a textbook for students. Moscow: Moscow State University. 2008. 361 p. (In Russian).
  12. Zverev A.V., Zverev A.T. Application of automated lineament analysis of satellite images in the search for oil and gas fields, prediction of earthquakes, slope processes and migration routes of groundwater // Izvestia of Higher Educational Institutions. Geology and exploration. 2015. № 6. P. 14‒20. (In Russian).
  13. Farr T.G., Rosen P.A., Caro E., Crippen R., Duren R., Hensley S., Kobrick M., Paller M., Rodriguez E., Roth L., Seal D., Shaffer S., Shimada J., Umland J., Werner M., Oskin M., Burbank D., Alsdorf D. The Shuttle Radar Topography Mission // Reviews of Geophysics. 2007. V. 45. № 2. P. 1‒33.
  14. Glukhov A.N. Tectonic factors of ore genesis of Precambrian terranes on the example of the Prikolymsky uplift and the Omolon massif (Northeast Asia) // Bulletin of St. Petersburg University. Earth Sciences. 2019. V. 64. № 2. P. 219‒248. doi: 10.21638/spbu07.2019.204.
  15. Gonbadi A.B., Tabatabaei S.H., Carranza E.J.M. Supervised geochemical anomaly detection by pattern recognition // Journal of Geochemical Exploration. 2015. V. 157. P. 81–91.
  16. Kirkwood C., Cave M., Beamish D., Grebby S., Ferreira A. A machine learning approach to geochemical mapping // Journal of Geochemical Exploration. 2016. V. 167. P. 49–61.
  17. Kong Q., Trugman D.T., Ross Z.E., Bianco M.J., Meade B.J., Gerstoft P. Machine learning in seismology: Turning data into insights // Seismological Research Letters. 2019. V. 90. № 1. P. 3–14.
  18. Krizhevsky A., Sutskever I., Hinton G.E. ImageNet classification with deep convolutional neural networks // Communications of the ACM. 2017. V. 60. № 6. P. 84–90. doi: 10.1145/3065386.
  19. Lary D.J., Alavi A.H., Gandomi A.H., Walker A.L. Machine learning in geosciences and remote sensing // Geoscience Frontiers. 2016. V. 7. № 1. P. 3–10. doi: 10.1016/j.gsf.2015.07.003.
  20. Li S., Chen J., Xiang J. Applications of deep convolutional neural networks in prospecting prediction based on two-dimensional geological big data // Neural Computing and Applications. 2019. V. 32. P. 2037–2053. doi: 10.1007/s00521-019-04341-3.
  21. O’Brien J.J., Spry P.G., Nettleton D., Xu R., Teale G.S. Using random forests to distinguish gahnite compositions as an exploration guide to Broken Hill-type Pb–Zn–Ag deposits in the Broken Hill domain, Australia // Journal of Geochemical Exploration. 2015. V. 49. P. 74–86.
  22. Shen C. A transdisciplinary review of deep learning research and its relevance for water resources scientists // Water Resources Research. 2018. V. 54. № 11. P. 8558–8593.
  23. Twarakavi N.K.C., Misra D., Bandopadhyay S. Prediction of arsenic in bedrock derived stream sediments at a gold mine site under conditions of sparse data // Nat Resour Res. 2006. V. 15. № 1. P. 15–26.
  24. Valentine A.P., Kalnins L.M. An introduction to learning algorithms and potential applications in geomorphometry and earth surface dynamics // Earth Surface Dynamics. 2016. V. 4. P. 445–460.
  25. Wang Z., Di H., Shafiq M.A., Alaudah Y., AlRegib G. Successful leveraging of image processing and machine learning in seismic structural interpretation: A review // The Leading Edge. 2018. V. 37. № 6. P. 451–461.
  26. Xiong Y., Zuo R. Recognition of geochemical anomalies using a deep autoencoder network // Computers & Geosciences. 2016. V. 86. P. 75–82.
  27. Zhao J., Chen S., Zuo R. Identifying geochemical anomalies associated with Au–Cu mineralization using multifractal and artificial neural network models in the Ningqiang district, Shaanxi, China // Journal of Geochemical Exploration. 2016. V. 164. P. 54–64.
  28. Zuo R., Xiong Y., Wang J., Carranza E.J.M. Deep learning and its application in geochemical mapping // Earth-Science Reviews. 2019. V. 192. P. 1–14.
  29. Zuo R.G., Xiong Y.H. Big data analytics of identifying geochemical anomalies supported by machine learning methods // Nat Resour Res. 2018. V. 27. № 1. P. 5–13.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Research area: a – territorial location, b – simplified geological map on a million-scale (Shivokhin et al., 2010).

Download (541KB)
Indexing metadata
3. Fig. 2. Architecture of the AlexNet neural network.

Download (234KB)
Indexing metadata
4. Fig. 3. Visualization of the digital elevation model of the study area based on SRTM. Known polymetallic ore objects are highlighted with pink dots.

Download (180KB)
Indexing metadata
5. Fig. 4. Criteria identified on the basis of the DEM: a – erosion cut levels, b – lineament density map. Pink dots indicate known polymetallic ore objects.

Download (569KB)
Indexing metadata
6. Fig. 5. Geological map at a scale of 1:1,000,000 and a complex of geological maps at a scale of 1:200,000. Known polymetallic ore objects are highlighted with pink dots.

Download (386KB)
Indexing metadata
7. Fig. 6. Criteria identified on the basis of the GGC: a – lithology, b – fault tectonics, c – contact zones of intrusive bodies. Pink dots indicate known polymetallic ore objects.

Download (430KB)
Indexing metadata
8. Fig. 7. Geophysical data: a ‒ complex of magnetic field anomaly schemes (1:200,000) (M-IV, V, VI, X, XI, XII, XVI, XVII, XVIII, XXII, XXIII), b ‒ complex of gravity field anomaly schemes (1:200,000) (M-IV, V, VI, X, XI, XII, XVI, XVII, XVIII, XXII, XXIII), c ‒ magnetic field anomaly scheme (digitized), d ‒ gravity field anomaly scheme (digitized). Known polymetallic ore objects are highlighted with pink dots.

Download (385KB)
Indexing metadata
9. Fig. 8. Criteria identified on the basis of the mineral resource map: a ‒ ore node map, b ‒ ore object distribution scheme (Fl, Mn, Mo, Sn, U and W ore objects are highlighted by triangles; Zn and Pb by squares; positive areas are in blue; negative areas are in red). Known polymetallic ore objects are highlighted by pink dots.

Download (608KB)
Indexing metadata
10. Fig. 9. Histogram of the belonging of polymetallic ore objects to lithological differences, i.e. classes, presented on the histogram.

Download (95KB)
Indexing metadata
11. Fig. 10. Histograms of the belonging of the established productive lithological classes to: a ‒ conventional levels of erosion cut, b ‒ lineament density values, c ‒ magnetic field values, d ‒ gravitational field values.

Download (391KB)
Indexing metadata
12. Table 3. Correlation analysis between prepared data

Download (385KB)
Indexing metadata
13. Table 4. Result of calculating Student's coefficients

Download (202KB)
Indexing metadata

Copyright (c) 2024 Russian Academy of Sciences