Earthquake Prediction in California Using Feature Selection Techniques

Abstract

Predicting the magnitude of earthquakes is of vital importance and, at the same time, of extreme complexity, where each attribute contributes differently in the process, even introducing noise. Preprocessing using attribute selection techniques helps to alleviate this drawback. In this work, this is demonstrated through an extensive comparison of 47 years of data from the Northern California Earthquake Data Center, where a wide range of feature selection algorithms are applied composed by different search, like population, local and ranking search based; and evaluators, like Correlations, consistency and distance metrics. After that, prediction algorithms will allow to compare the result with and without the application of feature selection, showing that the number of existing attributes can be reduced by 80%, improving metrics of the original, ensuring that the use of attribute selection in this type of problem is quite promising.