TanDEM-X multiparametric data features in sea ice classification over the Baltic sea
In this study, we assess the potential of X-band Interferometric Synthetic Aperture Radar imagery for automated classification of sea ice over the Baltic Sea. A bistatic SAR scene acquired by the TanDEM-X mission over the Bothnian Bay in March of 2012 was used in the analysis. Backscatter intensity,...
Published in: | Geo-spatial Information Science |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Taylor & Francis Group
2021
|
Subjects: | |
Online Access: | https://doi.org/10.1080/10095020.2020.1845574 https://doaj.org/article/e4c6264f7bb4449e905529191577602a |
id |
ftdoajarticles:oai:doaj.org/article:e4c6264f7bb4449e905529191577602a |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:e4c6264f7bb4449e905529191577602a 2023-05-15T18:17:13+02:00 TanDEM-X multiparametric data features in sea ice classification over the Baltic sea Marjan Marbouti Oleg Antropov Jaan Praks Patrick B. Eriksson Vahid Arabzadeh Eero Rinne Matti Leppäranta 2021-04-01T00:00:00Z https://doi.org/10.1080/10095020.2020.1845574 https://doaj.org/article/e4c6264f7bb4449e905529191577602a EN eng Taylor & Francis Group http://dx.doi.org/10.1080/10095020.2020.1845574 https://doaj.org/toc/1009-5020 https://doaj.org/toc/1993-5153 1009-5020 1993-5153 doi:10.1080/10095020.2020.1845574 https://doaj.org/article/e4c6264f7bb4449e905529191577602a Geo-spatial Information Science, Vol 24, Iss 2, Pp 313-332 (2021) sea ice classification random forests (rf) maximum likelihood (ml) support vector machine (svm) backscatter coherence sar interferometry synthetic aperture radar (sar) Mathematical geography. Cartography GA1-1776 Geodesy QB275-343 article 2021 ftdoajarticles https://doi.org/10.1080/10095020.2020.1845574 2022-12-31T06:59:11Z In this study, we assess the potential of X-band Interferometric Synthetic Aperture Radar imagery for automated classification of sea ice over the Baltic Sea. A bistatic SAR scene acquired by the TanDEM-X mission over the Bothnian Bay in March of 2012 was used in the analysis. Backscatter intensity, interferometric coherence magnitude, and interferometric phase have been used as informative features in several classification experiments. Various combinations of classification features were evaluated using Maximum likelihood (ML), Random Forests (RF) and Support Vector Machine (SVM) classifiers to achieve the best possible discrimination between open water and several sea ice types (undeformed ice, ridged ice, moderately deformed ice, brash ice, thick level ice, and new ice). Adding interferometric phase and coherence-magnitude to backscatter-intensity resulted in improved overall classification performance compared to using only backscatter-intensity. The RF algorithm appeared to be slightly superior to SVM and ML due to higher overall accuracies, however, at the expense of somewhat longer processing time. The best overall accuracy (OA) for three methodologies were achieved using combination of all tested features were 71.56, 72.93, and 72.91% for ML, RF and SVM classifiers, respectively. Compared to OAs of 62.28, 66.51, and 63.05% using only backscatter intensity, this indicates strong benefit of SAR interferometry in discriminating different types of sea ice. In contrast to several earlier studies, we were particularly able to successfully discriminate open water and new ice classes. Article in Journal/Newspaper Sea ice Directory of Open Access Journals: DOAJ Articles Geo-spatial Information Science 24 2 313 332 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
sea ice classification random forests (rf) maximum likelihood (ml) support vector machine (svm) backscatter coherence sar interferometry synthetic aperture radar (sar) Mathematical geography. Cartography GA1-1776 Geodesy QB275-343 |
spellingShingle |
sea ice classification random forests (rf) maximum likelihood (ml) support vector machine (svm) backscatter coherence sar interferometry synthetic aperture radar (sar) Mathematical geography. Cartography GA1-1776 Geodesy QB275-343 Marjan Marbouti Oleg Antropov Jaan Praks Patrick B. Eriksson Vahid Arabzadeh Eero Rinne Matti Leppäranta TanDEM-X multiparametric data features in sea ice classification over the Baltic sea |
topic_facet |
sea ice classification random forests (rf) maximum likelihood (ml) support vector machine (svm) backscatter coherence sar interferometry synthetic aperture radar (sar) Mathematical geography. Cartography GA1-1776 Geodesy QB275-343 |
description |
In this study, we assess the potential of X-band Interferometric Synthetic Aperture Radar imagery for automated classification of sea ice over the Baltic Sea. A bistatic SAR scene acquired by the TanDEM-X mission over the Bothnian Bay in March of 2012 was used in the analysis. Backscatter intensity, interferometric coherence magnitude, and interferometric phase have been used as informative features in several classification experiments. Various combinations of classification features were evaluated using Maximum likelihood (ML), Random Forests (RF) and Support Vector Machine (SVM) classifiers to achieve the best possible discrimination between open water and several sea ice types (undeformed ice, ridged ice, moderately deformed ice, brash ice, thick level ice, and new ice). Adding interferometric phase and coherence-magnitude to backscatter-intensity resulted in improved overall classification performance compared to using only backscatter-intensity. The RF algorithm appeared to be slightly superior to SVM and ML due to higher overall accuracies, however, at the expense of somewhat longer processing time. The best overall accuracy (OA) for three methodologies were achieved using combination of all tested features were 71.56, 72.93, and 72.91% for ML, RF and SVM classifiers, respectively. Compared to OAs of 62.28, 66.51, and 63.05% using only backscatter intensity, this indicates strong benefit of SAR interferometry in discriminating different types of sea ice. In contrast to several earlier studies, we were particularly able to successfully discriminate open water and new ice classes. |
format |
Article in Journal/Newspaper |
author |
Marjan Marbouti Oleg Antropov Jaan Praks Patrick B. Eriksson Vahid Arabzadeh Eero Rinne Matti Leppäranta |
author_facet |
Marjan Marbouti Oleg Antropov Jaan Praks Patrick B. Eriksson Vahid Arabzadeh Eero Rinne Matti Leppäranta |
author_sort |
Marjan Marbouti |
title |
TanDEM-X multiparametric data features in sea ice classification over the Baltic sea |
title_short |
TanDEM-X multiparametric data features in sea ice classification over the Baltic sea |
title_full |
TanDEM-X multiparametric data features in sea ice classification over the Baltic sea |
title_fullStr |
TanDEM-X multiparametric data features in sea ice classification over the Baltic sea |
title_full_unstemmed |
TanDEM-X multiparametric data features in sea ice classification over the Baltic sea |
title_sort |
tandem-x multiparametric data features in sea ice classification over the baltic sea |
publisher |
Taylor & Francis Group |
publishDate |
2021 |
url |
https://doi.org/10.1080/10095020.2020.1845574 https://doaj.org/article/e4c6264f7bb4449e905529191577602a |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
Geo-spatial Information Science, Vol 24, Iss 2, Pp 313-332 (2021) |
op_relation |
http://dx.doi.org/10.1080/10095020.2020.1845574 https://doaj.org/toc/1009-5020 https://doaj.org/toc/1993-5153 1009-5020 1993-5153 doi:10.1080/10095020.2020.1845574 https://doaj.org/article/e4c6264f7bb4449e905529191577602a |
op_doi |
https://doi.org/10.1080/10095020.2020.1845574 |
container_title |
Geo-spatial Information Science |
container_volume |
24 |
container_issue |
2 |
container_start_page |
313 |
op_container_end_page |
332 |
_version_ |
1766191304509751296 |