Earthquake Prediction With Artificial Neural Network Method: The Application Of West Anatolian Fault In Turkey

TL;DR

This paper develops a neural network model based on the Gutenberg-Richter relationship to predict earthquakes in Western Turkey, showing high accuracy in predicting non-occurrences and variable results for actual events.

Contribution

It introduces a neural network approach incorporating the b value for earthquake prediction specific to the West Anatolian Fault region.

Findings

High accuracy in predicting no earthquake occurrence

Variable success in predicting actual earthquakes

Effective use of regional seismic data

Abstract

A method that exactly knows the earthquakes beforehand and can generalize them cannot still been developed. However, earthquakes are tried to be predicted through numerous methods. One of these methods, artificial neural networks give appropriate outputs to different patterns by learning the relationship between the determined inputs and outputs. In this study, a feedforward back propagation artificial neural network that is connected to Gutenberg-Richter relationship and that bases on b value used in earthquake predictions was developed. The artificial neural network was trained employing earthquake data belonging to four different regions which have intensive seismic activity in the west of Turkey. After the training process, the earthquake data belonging to later dates of the same regions were used for testing and the performance of the network was put forward. When the prediction results of the developed network are examined, the prediction results that the network predicts that an earthquake is not going to occur are quite high in all regions. Furthermore, the earthquake prediction results that the network predicts that an earthquake is going to occur are different to some extent for the studied regions.