Ring structures of the Norilsk metallogenic district in neural network cluster analysis of geophysical data

An integrated geophysical and mathematical model of the Norilsk metallogenic region has been built according to the authors’ method of automatic express interpretation of areal geophysical data. It consists of fifteen levels of hierarchy. The model is based on the use of the mathematical apparatus of fuzzy logic — artificial neural networks without a teacher using the method of self-organizing Kohonen maps. Formation of cluster groups is justified. Clusters characterize to the greatest extent possible connections between multidimensional geophysical data. The presence of relationships between them is analyzed by identifying correlation dependences. Analysis of various geophysical transformants using self-organizing Kohonen maps is carried out. A number of input indicators-representatives of their groups are determined, on the basis of which a geophysical-mathematical model is built. A model in the form of a two-dimensional map of clusters using fuzzy logic tools. Terminological sets were formed for each group of clusters. The form of membership functions of previously unknown geological objects is given according to new interpreted data. The calculated clusters according to the results of the study reflect the northwestern fragment of the basaltic magmatism fields of the trap formation, within which two ring structures have been distinguished. In the western part of the study area, the model ring structure reflects the Bolgokhtokhsky stock of granodiorites. The second, the Pyasinskaya ring structure, previously unknown, indicates the presence of a dome-shaped object at a great depth — a possible source of root zones of intrusions of the Norilsk complex. The conducted experimental study confirmed the adequacy of the constructed model and the effectiveness of  its use for the purpose of express analysis of geophysical data and decision-making in geological prospecting tasks.

1. Геология Норильской металлогенической провинции / Под ред. И.И. Никулина. М.: МАКС Пресс, 2020. 524 с.

2. Карта самоорганизации (Self-orginizing map) на TensorFlow. [Электронный ресурс]. URL: https://habr.com/ru/post/334810 (дата обращения: 25.08.2020).

3. Кириллов И.И., Морозов И.Н., Олейник А.Г. Разработка моделей экспресс-анализа обогатительных процессов на основе нейросетей и нечеткой логики // Тр. КНЦ РАН. 2013. № 5 (18). С. 152–159.

4. Кохонен Т. Самоорганизующиеся карты. Сер. Адаптивные и интеллектуальные системы / Пер. с англ. М.: Бином, Лаборатория знаний, 2008. 656 с.

5. Никулин И.И., Савко А.Д. Железорудные коры выветривания Белгородского района Курской магнитной аномалии // Тр. НИИ геологии Воронежского гос. ун-та. 2015. Т. 85. 102 с.

6. Cамоорганизующиеся карты Кохонена — математический аппарат. [Электронный ресурс]. URL: https://basegroup.ru/community/articles/som (дата обращения: 25.08.2020).

7. Diachenko V., Liashenko Ol., Ibrahim B.F. et al. Kohonen Network with Parallel Training: Operation Structure and Algorithm // Intern. J. Advanced Trends in Computer Sci. and Engineering. 2019. Vol. 8, N 1.2. P. 35–38. DOI: org/10.30534/ijatcse/2019/0681.22019.

8. Hu Z., Bodyanskiy Y.V., Tyshchenko O.K. et al. Kohonen Maps and Their ensembles for Fuzzy Clustering Tasks / Self-Learning and Adaptive Algorithms for Business Applications, Emerald Publ. Lim. 2019. P. 51–77. DOI: org/10.1108/978-1-83867-171-620191004.

9. Kalashnikov A.O., Nikulin I.I., Stepenshchikov D.G. Unsupervised geochemical classification and automatic 3D mapping of the Bolshetroitskoe high-grade iron ore deposit (Belgorod Region, Russia) // Sci. Rep. 2020. 10. 17861. URL: https://doi.org/10.1038/s41598-020-74505-y.

10. Larose D.T., Larose C.D. Discovering Knowledge in Data: An Introduction to Data Mining. John Wiley & Sons, Inc., 2014. 336 p. DOI: org/10.1002/9781118874059.

11. Processing IDE. [Электронный ресурс]. URL: https://processing.org (дата обращения: 25.08.2020).

12. Rodrigo B., Cavalcanti C. de, Pimentel B.A. et al. A multivariate fuzzy Kohonen clustering network // Intern. Joint Conf. on Neural Networks (IJCNN), 2019. [Электронный ресурс]. URL: https://ieeexplore.ieee.org/document/8852243 (дата обращения: 25.08.2020). DOI: 10.1109/IJCNN.2019.8852243.

13. Samanta S., Utkarsha S., Gour B. et al. Fast character recognition using Kohonen Neural Network // International Conference on Advanced Computation and Telecommunication (ICACAT). 2018. [Электронный ресурс]. URL: https://ieeexplore.ieee.org/document/8933627 (дата обра- щения: 25.08.2020). DOI: 10.1109/ICACAT.2018.8933627.

14. Silva Iv.N. da., Spatti D.H., Flauzino R.An. et al. Self-organizing Kohonen networks / Artificial Neural Networks. Springer Internat. Publ. Switzerland. 2017. P. 157–172. DOI: org/10.1007/978-3-319-43162-8_8.

15. Todeva E., Knoke D., Keskinova D. Multi-stage clustering with complementary structural analysis of 2-mode networks // ASONAM’19: Proceed. of the 2019 IEEE/ACM Intern. Conf. on Advances in Social Networks Analysis and Mining. 2019. P. 771–778. DOI: org/10.1145/3341161.3344781.