Classification of Databases and Methods for Seismic Data Analysis and Earthquake Prediction

Earthquake is one the most important disasters in the world. In order to save lives and building substructures of countries, more research in this field should be carried out as a matter of severity. Computer modeling and different artificial intelligence algorithms are known as applicable tools for the earthquake hazards prediction and prevention. This article tries to review the recent studies that have been conducted in this field. For this purpose, the literature methods have been classified into three categories including machine learning, data mining, and seismic feature extraction methods. The machine learning methods are also divided into several subcategories such as Artificial Neural Networks (ANNs), fuzzy systems and Support Vector Machines (SVMs) methods. The similar condition goes with the data mining methods in categorization. Moreover, the seismic feature extraction methods explain the important features used by aforementioned methods. Most of the recent researches are related to the prediction issues (e.g., the ultimate goal of data mining is for predicting the location of earthquake). Furthermore, the clustering methods can help us to predict the high risk areas. Although the problem of earthquake prediction and the related issues have not been completely solved in the world, researchers have tried to reduce the prediction error to provide predictions that are more accurate.