BROWSE

Related Researcher

Author's Photo

Im, Jungho
Intelligent Remote sensing and geospatial Information Science (IRIS) Lab
Research Interests
  • Remote sensing, Geospatial modeling, Disaster monitoring and management, Climate change

ITEM VIEW & DOWNLOAD

Machine learning approaches for detecting tropical cyclone formation using satellite data

DC Field Value Language
dc.contributor.author Kim, Minsang ko
dc.contributor.author Park, Myung-Sook ko
dc.contributor.author Im, Jungho ko
dc.contributor.author Park, S ko
dc.contributor.author Lee, Myong-In ko
dc.date.available 2019-07-31T06:19:05Z -
dc.date.created 2019-06-25 ko
dc.date.issued 2019-05 ko
dc.identifier.citation REMOTE SENSING, v.11, no.10, pp.1195 ko
dc.identifier.issn 2072-4292 ko
dc.identifier.uri https://scholarworks.unist.ac.kr/handle/201301/27201 -
dc.description.abstract This study compared detection skill for tropical cyclone (TC) formation using models based on three different machine learning (ML) algorithms-decision trees (DT), random forest (RF), and support vector machines (SVM)-and a model based on Linear Discriminant Analysis (LDA). Eight predictors were derived from WindSat satellite measurements of ocean surface wind and precipitation over the western North Pacific for 2005-2009. All of the ML approaches performed better with significantly higher hit rates ranging from 94 to 96% compared with LDA performance (~77%), although false alarm rate by MLs is slightly higher (21-28%) than that by LDA (~13%). Besides, MLs could detect TC formation at the time as early as 26-30 h before the first time diagnosed as tropical depression by the JTWC best track, which was also 5 to 9 h earlier than that by LDA. The skill differences across MLs were relatively smaller than difference between MLs and LDA. Large yearly variation in forecast lead time was common in all models due to the limitation in sampling from orbiting satellite. This study highlights that ML approaches provide an improved skill for detecting TC formation compared with conventional linear approaches. ko
dc.language 영어 ko
dc.publisher MDPI AG ko
dc.title Machine learning approaches for detecting tropical cyclone formation using satellite data ko
dc.type ARTICLE ko
dc.identifier.scopusid 2-s2.0-85066743716 ko
dc.identifier.wosid 000480524800053 ko
dc.type.rims ART ko
dc.identifier.doi 10.3390/rs11101195 ko
dc.identifier.url https://www.mdpi.com/2072-4292/11/10/1195 ko
Appears in Collections:
UEE_Journal Papers

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show simple item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU