A chilean seismic regionalization through a Kohonen neural network

TL;DR

This paper presents a neural network-based approach to seismic regionalization in central Chile, identifying six seismic zones with high correlation to geographical data, regardless of neighborhood size.

Contribution

It introduces a neural network method for seismic regionalization that reliably identifies seismic zones independent of neighborhood parameters.

Findings

Six seismic regions identified in central Chile

High correlation between seismic zones and geographical data

Method is robust to neighborhood size variations

Abstract

A study of seismic regionalization for central Chile based on a neural network is presented. A scenario with six seismic regions is obtained, independently of the size of the neighborhood or the reach of the correlation between the cells of the grid. The high correlation between the spatial distribution of the seismic zones and geographical data confirm our election of the training vectors of the neural network.