Automatic discrimination approach of sea ice in the Arctic Ocean using Sentinel-1 Extra Wide Swath dual-polarized SAR data
SCIE
SCOPUS
Cited 21 time in
WEB OF SCIENCE
Cited 28 time in
Scopus
-
Title
- Automatic discrimination approach of sea ice in the Arctic Ocean using Sentinel-1 Extra Wide Swath dual-polarized SAR data
-
Author(s)
- Hong, Dan-Bee; Yang, Chan-Su
- KIOST Author(s)
- Yang, Chan Su(양찬수)
-
Alternative Author(s)
- 홍단비; 양찬수
-
Publication Year
- 2018
-
Abstract
- Mapping of sea ice in the Arctic region is essential for environmental monitoring and ship navigation. Synthetic Aperture Radar can be used to observe sea ice at high spatial and temporal resolutions over an extended range at high latitudes. The sea ice discrimination method based on Support Vector Machine was applied to 226 scenes of Sentinel-1 acquired in Extra Wide Swath Mode with dual-polarization (HH & HV) from 1 July 2016 to 31 August 2016 along the Northern Sea Route from the Kara Sea to the Chukchi Sea. The discriminated sea ice results were evaluated using both manually classified ice maps and Multisensor Analyzed Sea Ice Extent (MASIE). It is revealed that the proposed method based on the backscattering coefficient (sigma(0)), incidence angle, air temperature, and wind speed improves the sea ice and water discrimination, showing matching rates of approximately 93.4% for manual classification and 82.8% for MASIE. It is concluded that the method could be considered for an operational use to discriminate summer sea ice from open water in the Northern Sea Route.
-
ISSN
- 0143-1161
-
URI
- https://sciwatch.kiost.ac.kr/handle/2020.kiost/2117
-
DOI
- 10.1080/01431161.2017.1415486
-
Bibliographic Citation
- INTERNATIONAL JOURNAL OF REMOTE SENSING, v.39, no.13, pp.4469 - 4483, 2018
-
Publisher
- TAYLOR & FRANCIS LTD
-
Subject
- SYNTHETIC-APERTURE RADAR; WATER CLASSIFICATION; IMAGE CLASSIFICATION
-
Type
- Article
-
Language
- English
-
Document Type
- Article; Proceedings Paper
- Files in This Item:
-
There are no files associated with this item.
Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.