Tornado detection with Kernel-based classifiers from WSR-88D radar data

Theodore B. Trafalis*, Budi Santosa, Michael B. Richman

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Detection of tornadoes that provides warning times sufficient for evasive action prior to a tornado strike has been a well-established objective of weather forecasters. With modern technology, progress has been made on increasing the average lead time of such warnings, which translates into a number of lives saved. Recently, machine learning (e.g., kernel methods) has been added to the collection of techniques brought to bear on severe weather prediction. In this chapter, we seek to extend this innovation by introducing and applying two types of kernel-based methods, support vector machines and minimax probability machines to detect tornadoes, using attributes from radar derived velocity data. These two approaches utilize kernel methods to address nonlinearity of the data in the input space. The approaches are based on maximizing the margin between two different classes: tornado and no tornado. The use of the Weather Surveillance Radar 1988 Doppler, with continuous data streaming every 6min, presents a source for a dynamic data driven application system. The results are compared to those produced by neural networks (NN). Findings indicate that these kernel approaches are significantly more accurate than NN for the tornado detection problem.

Original languageEnglish
Title of host publicationDynamics of Disasters–Key Concepts, Models, Algorithms, and Insights, 2015
EditorsAnna Nagurney, Ilias S. Kotsireas, Panos M. Pardalos
PublisherSpringer New York LLC
Pages329-344
Number of pages16
ISBN (Print)9783319437071
DOIs
Publication statusPublished - 2016
Event2nd International Conference on Dynamics of Disasters, 2015 - Kalamata, Greece
Duration: 29 Jun 20152 Jul 2015

Publication series

NameSpringer Proceedings in Mathematics and Statistics
Volume185
ISSN (Print)2194-1009
ISSN (Electronic)2194-1017

Conference

Conference2nd International Conference on Dynamics of Disasters, 2015
Country/TerritoryGreece
CityKalamata
Period29/06/152/07/15

Keywords

  • Dynamic data driven application
  • Feedforward neural networks
  • Generalization error
  • Kernel methods
  • Tornado detection

Fingerprint

Dive into the research topics of 'Tornado detection with Kernel-based classifiers from WSR-88D radar data'. Together they form a unique fingerprint.

Cite this