Data Mining Techniques on Earthquake Data: Recent Data Mining Approaches

Data Mining Techniques on Earthquake Data: Recent Data Mining Approaches

Negar Sadat Soleimani Zakeri (University of Tabriz, Iran) and Saeid Pashazadeh (University of Tabriz, Iran)
DOI: 10.4018/978-1-4666-8513-0.ch010
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Active faults are sources of earthquakes and one of them is north fault of Tabriz in the northwest of Iran. The activation of faults can harm humans' life and constructions. The analysis of the seismic data in active regions can be helpful in dealing with earthquake hazards and devising prevention strategies. In this chapter, structure of earthquake events along with application of various intelligent data mining algorithms for earthquake prediction are studied. Main focus is on categorizing the seismic data of local regions according to the events' location using clustering algorithms for classification and then using intelligent artificial neural network for cluster prediction. As a result, the target data were clustered to six groups and proposed model with 10 fold cross validation yielded accuracy of 98.3%. Also, as a case study, the tectonic stress on concentration zones of Tabriz fault has been identified and five features of the events were used. Finally, the most important points have been proposed for evaluation of the nonlinear model predictions as future directions.
Chapter Preview
Top

Preliminary Concepts And Basic Methods

According to literature investigation, learning algorithms or data mining methods and in some cases combinations of these two methods are used as high-level classification methods in studies of earthquake data in the seismic regions. Each method has its own subdivisions. The learning algorithms are also known as machine learning algorithms in computer science. Most common methods that are used for this issue are ANNs, fuzzy systems and SVMs. Different types of neural networks have been used in different literature. Recurrent neural networks, PNNs, feed forward neural networks, SVMs and fuzzy based algorithms were used for predicting time and location of earthquakes. Collected data from various parts of the world and different extracted features such as sequence number, occurrence time are used by these methods while existing noises were removed along the preprocessing steps.

Complete Chapter List

Search this Book:
Reset