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 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...