A system approach to geodynamic zoning based on artificial neural networks

Methodological aspects of applying artificial neural networks for geodynamic zoning of territories when selecting locations for environmentally hazardous facilities (as exemplified by nuclear fuel cycle facilities) are considered. To overcome the uncertainty caused by complexity of the analysis of information about the properties, processes, and structure of the geological environment, a system approach to analyzing the information is used. Geological environment is presented as a system of interacting anthropogenic facility and natural environment, between which connections are organized. When assessing safety of such system operation, it is important to monitor environmental condition indicators. According to modern regulatory requirements of both international and domestic organizations, one of the main, and at the same time difficult to determine indicators of the condition of the nuclear fuel cycle facilities sites, are modern movements of the earth's crust. In the paper, we presented a method for predicting modern movements of the earth's crust based on artificial neural networks. Based on the predicted kinematic characteristics of the earth's crust, it is possible to identify zones that are dangerous in the manifestation of geodynamic processes: tension, compression, elastic energy accumulation zones, and so on. Preliminary results obtained on the presented neural network architecture showed positive prospects of applying this methodology for solving geodynamic zoning problems.

1. Dennis A., Haley B., Wixon R. Systems analysis and design. Wiley Inc., 2012, 546 p.

2. Pankrushin V.K. Matematicheskoye modelirovaniye i identifikatsiya geodinamicheskikh system [Mathematical modeling and identification of geodynamic systems]. Novosibirsk: SGGA, 2002. 424 p. In Russ.

3. Tatarinov V.N., Kaftan, V.I., Seelev, I.N. Study of the Present-Day Geodynamics of the Nizhnekansk Massif for Safe Disposal of Radioactive Wastes. Atomic Energy. Springer. 2017. Vol. 121, Iss. 3, pp 203–207. DOI:10.1007/s10512-017-0184-5.

4. Zubovich, A.V., et al. GPS velocity field for the Tien Shan and surrounding regions. Tectonics. 2010. Vol. 29. TC6014. DOI: 10.1029/2010TC002772.

5. Barskiy A.B. Neyronnyye seti: raspoznavaniye, upravleniye, prinyatiye resheniy M.: Finansy i statistika [Neural networks: recognition, control, decision making M .: Finance and statistics]. 2004. 176 p. In Russ.

6. Haykin S. Neural networks and learning machines. Pearson LTD. 1999, 938 p.

7. Sh. Esmaeilzadeh, A. Afshari, R. Motafakkerfard. Integrating Artificial Neural Networks Technique and Geostatistical Approaches for 3D Geological Reservoir Porosity Modeling with an Example from One of Iran's Oil Fields. Petroleum Science and Technology Vol. 31. Iss. 11. 2013. doi.org/10.1080/10916466.2010.540617.

8. Vincenzo Barrile Giuseppe, M.Meduri Giuliana, Bilotta Ugo, Monardi Trungadi. GPS- GIS and Neural Networks for Monitoring Control, Cataloging the Prediction and Prevention in Tectonically Active Areas. Procedia - Social and Behavioral Sciences. Vol. 223. 2016. Pp. 909-914. doi.org/10.1016/j.sbspro.2016.05.314.

9. Tatarinov V.N., Tatarinova T.A. Uchet masshtabnogo effekta pri nablyudeniyakh za deformatsiyami zemnoy poverkhnosti sputnikovymi navigatsionnymi sistemami [Consideration of the scale effect when observing deformations of the Earth’s surface by satellite navigation systems]. Mine surveying bulletin. №5. 2012. p.15-19. In Russ.

10. Manevich A.I., Tatarinov V.N. Primeneniye iskusstvennykh neyronnykh setey dlya prognoza sovremennykh dvizheniy zemnoy kory [Explotation of artificial neural networks for the prediction of modern movements of the earth's crust]. Geoinformatics research. Geophysical Centre of RAS. 2017. Vol. 5. No. 2. pp. 37-48. In Russ. DOI: 10.2205/2017BS045

11. Chakraborty A., Goswami D. Prediction of slope stability using multiple linear regression (MLR) and artificial neural network (ANN). Arabian Journal of Geosciences. 2017. Vol. 10. Iss. 385. DOI: 10.1007/s12517-017-3167-x.

12. Miljanović, M., Ninkov, T., Sušić, Z., Tucikesic, S., Forecasting geodetic measurements using finite impulse response artificial neural networks. Indian journal of geo-marine sciences. 2017. Vol. 46. Iss. 9. pp. 1743-1750.

13. Reiterer A., et al. A 3D optical deformation measurement system supported by knowledge-based and learning techniques. Journal of Applied Geodesy. 2009. Vol. 3. No. 1. Pp. 1-13.

14. Cheskidov V. Data flows management of mining natural/man-made systems integrated state monitoring. Research in geoinformatics: the works of the Geophysical Center RAS. 2017. Т. 5. No. 1. Pp. 61-62.