A Method of Identification of Potential Earthquake Source Zones
- 29 September 2020
- book chapter
- Published by Springer Nature
- Vol. 12252, 405-414
Abstract
We propose a machine learning method for mapping potential earthquake source zones (ESZ). We use two hypotheses: (1) the recurrence of strong earthquakes and (2) the dependence of sources of strong earthquakes on the properties of the geological environment. To solve this problem, we know the catalog of earthquakes and a set of spatial fields of geological and geophysical features. We tested the method of identification of the potential ESZ with \(m\ge 6.0\) for the Caucasus region. The map of the potential earthquake source zones and a geological interpretation of the decision rule are presented.
Keywords
This publication has 11 references indexed in Scilit:
- Machine Learning Methods for Seismic Hazards ForecastGeosciences, 2019
- A Survey of Recent Trends in One Class Classification2010
- An introduction to ROC analysisPattern Recognition Letters, 2006
- Estimation of the Maximum Earthquake Magnitude, m maxPure and Applied Geophysics, 2004
- Predictive Inference: An Introduction1993
- Boolean function minimization in the class of disjunctive normal formsJournal of Mathematical Sciences, 1989
- The Caucasus: an actual example of the initial stages of continental collisionTectonophysics, 1989
- Seismic risk in southern Europe through to India examined using Gumbel's third distribution of extreme valuesGeophysical Journal International, 1979
- Pattern recognition applied to earthquake epicenters in CaliforniaPhysics of the Earth and Planetary Interiors, 1976
- Frictional constraints on thrust, wrench and normal faultsNature, 1974