SYSTEM APPROACH TO GEODYNAMIC ZONING BASED ON ARTIFICIAL NEURAL NETWORKS

In this research are presented methodological aspects of the using of artificial neural networks for the tasks of geodynamic zoning of territories are considered when choosing locations for environmentally hazardous objects (using the example of nuclear fuel cycle facilities). To overcome the uncert...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Gornye nauki i tehnologii 2018-12 (3), p.14-25
Hauptverfasser: Tatarinov, V. N., Manevich, A. I., Losev, I. V.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this research are presented methodological aspects of the using of artificial neural networks for the tasks of geodynamic zoning of territories are considered when choosing locations for environmentally hazardous objects (using the example of nuclear fuel cycle facilities). To overcome the uncertainty caused by the complexity of analyzing information about the properties, processes and structure of the geological environment, a systematic information analysis approach is used. The geological environment is represented as a system of interacting anthropogenic object and environment, between which connections are organized. In assessing the safety of operation of this type of system, it is important to monitor indicators of the state of the environment. According to modern regulatory requirements of international and domestic organizations, one of the main, and at the same time, difficult to determine indicators of the state of sites for the nuclear fuel cycle facilities are modern movements of the earth's crust. In this paper, we outlined a method for predicting modern movements of the earth's crust based on artificial neural networks. On the basis of the predicted kinematic characteristics of the earth's crust, it is possible to identify dangerous zones by the manifestation of geodynamic processes: zones of tension, compression, zones of accumulation of elastic energy, and so on. Preliminary results obtained on the presented neural network architecture have shown a positive outlook for the application of this methodology for geodynamic zoning tasks.
ISSN:2500-0632
2500-0632
DOI:10.17073/2500-0632-2018-3-14-25