Feature Selection with Support Vector Machines Applied on Tornado Detection

Abstract

In this paper, a linear programming support vector machine which is based on L1-norm is applied to do feature selection in the tornado data set. The data is the ouputs of Weather Surveillance Radar 1998 Doppler (WSR-88D). The approach is evaluated based on the indices of probability of detection, false alarm rate, bias and Heidke skill. Tornado circulation attributes/variables derived largely from the National Severe Storms Laboratory Mesocyclone Detection Algorithm (MDA) have been investigated for their efficacy in distinguishing between mesocyclones that become tornadic from those which do not.