Forecasting post-extratropical transition outcomes for tropical cyclones using support vector machine classifiers

Steven R. Felker, Brian Lacasse, J Scott Tyo, Elizabeth A Ritchie

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Intensity changes following the multistage process of extratropical transition have proven to be especially difficult to forecast because of the extremely similar storm evolutions prior to and during the first stages of the transformation from a warm-cored axisymmetric tropical storm to a cold-cored asymmetrical extratropical low pressure system. In this study, differences in surrounding synoptic environments between dissipating and reintensifying extratropical transitioning tropical cyclones are used to develop a predictive technique for extratropical transition intensity change that can be used to enhance the standard numerical guidance. Using a set of all historical transitioning storms between 2000 and 2008 in the western North Pacific, common differences between 850-hPa potential temperature fields surrounding extratropical transition intensifiers and extratropical transition dissipaters, respectively, were identified. These features were then used as inputs into a support vector machine classification system in the hopes of creating a robust prediction system. Once the system was trained on a random subset of the data (80%), performance was tested on the remaining test set (20%). Overall, it was found that the prediction system was able to correctly predict extratropical transition intensity outcome in >75% of the test cases at 72 h prior to extratropical transition. This paper discusses the feature selection and classification system used, as well as the performance results, in detail.

Original languageEnglish (US)
Pages (from-to)709-719
Number of pages11
JournalJournal of Atmospheric and Oceanic Technology
Volume28
Issue number5
DOIs
StatePublished - May 2011

Fingerprint

tropical cyclone
Support vector machines
Classifiers
low pressure system
potential temperature
prediction
Feature extraction
Temperature distribution
support vector machine
test

Keywords

  • Extratropical cyclones
  • Forecasting
  • Tropical Cyclones

ASJC Scopus subject areas

  • Atmospheric Science
  • Ocean Engineering

Cite this

Forecasting post-extratropical transition outcomes for tropical cyclones using support vector machine classifiers. / Felker, Steven R.; Lacasse, Brian; Tyo, J Scott; Ritchie, Elizabeth A.

In: Journal of Atmospheric and Oceanic Technology, Vol. 28, No. 5, 05.2011, p. 709-719.

Research output: Contribution to journalArticle

@article{c808cb16d4e6460bbc5c8264056b61e3,
title = "Forecasting post-extratropical transition outcomes for tropical cyclones using support vector machine classifiers",
abstract = "Intensity changes following the multistage process of extratropical transition have proven to be especially difficult to forecast because of the extremely similar storm evolutions prior to and during the first stages of the transformation from a warm-cored axisymmetric tropical storm to a cold-cored asymmetrical extratropical low pressure system. In this study, differences in surrounding synoptic environments between dissipating and reintensifying extratropical transitioning tropical cyclones are used to develop a predictive technique for extratropical transition intensity change that can be used to enhance the standard numerical guidance. Using a set of all historical transitioning storms between 2000 and 2008 in the western North Pacific, common differences between 850-hPa potential temperature fields surrounding extratropical transition intensifiers and extratropical transition dissipaters, respectively, were identified. These features were then used as inputs into a support vector machine classification system in the hopes of creating a robust prediction system. Once the system was trained on a random subset of the data (80{\%}), performance was tested on the remaining test set (20{\%}). Overall, it was found that the prediction system was able to correctly predict extratropical transition intensity outcome in >75{\%} of the test cases at 72 h prior to extratropical transition. This paper discusses the feature selection and classification system used, as well as the performance results, in detail.",
keywords = "Extratropical cyclones, Forecasting, Tropical Cyclones",
author = "Felker, {Steven R.} and Brian Lacasse and Tyo, {J Scott} and Ritchie, {Elizabeth A}",
year = "2011",
month = "5",
doi = "10.1175/2010JTECHA1449.1",
language = "English (US)",
volume = "28",
pages = "709--719",
journal = "Journal of Atmospheric and Oceanic Technology",
issn = "0739-0572",
publisher = "American Meteorological Society",
number = "5",

}

TY - JOUR

T1 - Forecasting post-extratropical transition outcomes for tropical cyclones using support vector machine classifiers

AU - Felker, Steven R.

AU - Lacasse, Brian

AU - Tyo, J Scott

AU - Ritchie, Elizabeth A

PY - 2011/5

Y1 - 2011/5

N2 - Intensity changes following the multistage process of extratropical transition have proven to be especially difficult to forecast because of the extremely similar storm evolutions prior to and during the first stages of the transformation from a warm-cored axisymmetric tropical storm to a cold-cored asymmetrical extratropical low pressure system. In this study, differences in surrounding synoptic environments between dissipating and reintensifying extratropical transitioning tropical cyclones are used to develop a predictive technique for extratropical transition intensity change that can be used to enhance the standard numerical guidance. Using a set of all historical transitioning storms between 2000 and 2008 in the western North Pacific, common differences between 850-hPa potential temperature fields surrounding extratropical transition intensifiers and extratropical transition dissipaters, respectively, were identified. These features were then used as inputs into a support vector machine classification system in the hopes of creating a robust prediction system. Once the system was trained on a random subset of the data (80%), performance was tested on the remaining test set (20%). Overall, it was found that the prediction system was able to correctly predict extratropical transition intensity outcome in >75% of the test cases at 72 h prior to extratropical transition. This paper discusses the feature selection and classification system used, as well as the performance results, in detail.

AB - Intensity changes following the multistage process of extratropical transition have proven to be especially difficult to forecast because of the extremely similar storm evolutions prior to and during the first stages of the transformation from a warm-cored axisymmetric tropical storm to a cold-cored asymmetrical extratropical low pressure system. In this study, differences in surrounding synoptic environments between dissipating and reintensifying extratropical transitioning tropical cyclones are used to develop a predictive technique for extratropical transition intensity change that can be used to enhance the standard numerical guidance. Using a set of all historical transitioning storms between 2000 and 2008 in the western North Pacific, common differences between 850-hPa potential temperature fields surrounding extratropical transition intensifiers and extratropical transition dissipaters, respectively, were identified. These features were then used as inputs into a support vector machine classification system in the hopes of creating a robust prediction system. Once the system was trained on a random subset of the data (80%), performance was tested on the remaining test set (20%). Overall, it was found that the prediction system was able to correctly predict extratropical transition intensity outcome in >75% of the test cases at 72 h prior to extratropical transition. This paper discusses the feature selection and classification system used, as well as the performance results, in detail.

KW - Extratropical cyclones

KW - Forecasting

KW - Tropical Cyclones

UR - http://www.scopus.com/inward/record.url?scp=79959666319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959666319&partnerID=8YFLogxK

U2 - 10.1175/2010JTECHA1449.1

DO - 10.1175/2010JTECHA1449.1

M3 - Article

AN - SCOPUS:79959666319

VL - 28

SP - 709

EP - 719

JO - Journal of Atmospheric and Oceanic Technology

JF - Journal of Atmospheric and Oceanic Technology

SN - 0739-0572

IS - 5

ER -