Application of the rule extraction method to evaluate seismicity of Iran

Assessing seismic hazards involves specifying the likelihood, magnitude and location of earthquakes in a region. Predicting the seismic hazards is the first step in reducing the impact of the damage caused by an earthquake. In this study, to fully utilize all the known parameters which may possibly affect the occurrence of earthquakes (mb ≥ 4.5); a data-driven rule-extraction method called the Classification and Regression Tree (CART) was used to find the rules governing the earthquakes that occur. The method produces Predictive Rule Based Seismicity Map (PRBSM) of Iran that shows regions with high earthquake hazards. The rules are based on a large number of geophysical and geological parameters. The PRBSM has been built based on earthquake data from the year 1900 up to the end of 2006 and has been validated using earthquakes from 2007 to the end of 2015. In addition, this method allows for the identification of the most important combination of parameters associated with earthquakes. For example, the isostatic anomaly has the highest correlation with earthquakes in Iran. A distinctive character of this paper is the predictive rule based method which can create online as well as offline maps which are flexible and readily automated