Earthquake prediction with meteorological data by particle filter-based support vector regression

Abstract

Prediction of earthquakes has been long of interest of scientists to create a timely warning to save lives and reduce the damage. During the last few decades, scientists could record and classify the earthquakes' effective parameters through careful studies. Precursor, as one of the most important parameters, presents the variation in the concentration of radon gas in the earth's crust released by faults. Measuring and comparing this precursor requires the installation of appropriate hardware in the vicinity of the faults. The extraction of this gas and its lead ions will create additional precursors in the atmosphere layers. Through intelligent analyzing such historical meteorological data sets which are being measured and recorded in most parts of the world, the earthquakes can be predicted. In order to predict the magnitude and number of the earthquakes in this study, the particle filter-based and support vector regression is used. To evaluate the validity of the proposed method, the results are compared with multi layered perceptron neural network and support vector regression. The proposed method indicated the relationship between climatic data and the occurrence of earthquake leading to a precision of 96% for predicting the mean magnitude of earthquakes and a high accuracy of 78% for the expected earthquake count in a month. The accuracy of the method was measured by the correlation coefficient index.