“…As a result of the algorithm application, the conditions for the values of the characteristics (recognition rule) are formulated, which allow us to classify the vectors corresponding to nodes and classification is obtained in accordance with this rule of all nodes into two classes: seismogenic nodes D where the target events may occur and nodes N, at which only the earthquakes of < 0 are possible. The approach described above was successfully applied to determine the strong earthquake-prone areas in many seismically active regions [e.g., Bhatia et al, 1992;Caputo etal., 1980;Chunga et al, 2010;Cisternas et al, 1985;Gelfand et al, 1972Gelfand et al, , 1976Gorshkov et al, 2000Gorshkov et al, , 2002Gorshkov et al, , 2003bGorshkov et al, , 2004Gorshkov et al, , 2009aGorshkov et al, , 2009bGorshkov et al, , 2010Gorshkov et al, , 2012Gorshkov et al, , 2017Gorshkov et al, , 2019Gorshkov et al, , 2020Gorshkov and Gaudemer, 2019;Gvishiani and Soloviev, 1984;Gvishiani et al, 1987Gvishiani et al, , 1988Kossobokov, 1983;Soloviev et al, 2013Soloviev et al, , 2016. The locations of the earthquake epicenters that occurred in these regions after obtaining the corresponding results provide arguments in favor of the fact that these re-sults are reliable: about 87% of these epicenters fall in the recognized earthquake-prone areas Soloviev et al, 2014].…”