Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images
In this study, bistatic interferometric Synthetic Aperture Radar (InSAR) data acquired by the TanDEM-X mission were used for automated classification of sea ice over the Baltic Sea, in the Bothnic Bay. A scene acquired in March of 2012 was used in the study. Backscatter-intensity, coherencemagnitude...
Published in: | IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE Institute of Electrical and Electronic Engineers
2018
|
Subjects: | |
Online Access: | https://cris.vtt.fi/en/publications/a82a7034-0fba-4d14-b4a4-b25a6cafeea5 https://doi.org/10.1109/IGARSS.2018.8518996 http://www.scopus.com/inward/record.url?scp=85064192218&partnerID=8YFLogxK |
id |
ftvttcrispub:oai:cris.vtt.fi:publications/a82a7034-0fba-4d14-b4a4-b25a6cafeea5 |
---|---|
record_format |
openpolar |
spelling |
ftvttcrispub:oai:cris.vtt.fi:publications/a82a7034-0fba-4d14-b4a4-b25a6cafeea5 2024-09-15T18:34:39+00:00 Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images Marbouti, Marjan Antropov, Oleg Eriksson, Patrick Praks, Jaan Arabzadeh, Vahid Rinne, Eero Leppäranta, Matti 2018-10-31 https://cris.vtt.fi/en/publications/a82a7034-0fba-4d14-b4a4-b25a6cafeea5 https://doi.org/10.1109/IGARSS.2018.8518996 http://www.scopus.com/inward/record.url?scp=85064192218&partnerID=8YFLogxK eng eng IEEE Institute of Electrical and Electronic Engineers https://cris.vtt.fi/en/publications/a82a7034-0fba-4d14-b4a4-b25a6cafeea5 urn:ISBN:978-1-5386-7151-1 info:eu-repo/semantics/closedAccess Marbouti , M , Antropov , O , Eriksson , P , Praks , J , Arabzadeh , V , Rinne , E & Leppäranta , M 2018 , Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images . in 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 . , 8518996 , IEEE Institute of Electrical and Electronic Engineers , IEEE International Geoscience and Remote Sensing Symposium Proceedings , vol. 38 , pp. 7328-7331 , 38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 , Valencia , Spain , 22/07/18 . https://doi.org/10.1109/IGARSS.2018.8518996 Maximum likelihood Random forests Remote sensing Sea ice classification TanDEM-X contributionToPeriodical 2018 ftvttcrispub https://doi.org/10.1109/IGARSS.2018.8518996 2024-08-07T23:31:40Z In this study, bistatic interferometric Synthetic Aperture Radar (InSAR) data acquired by the TanDEM-X mission were used for automated classification of sea ice over the Baltic Sea, in the Bothnic Bay. A scene acquired in March of 2012 was used in the study. Backscatter-intensity, coherencemagnitude and InSAR-phase, as well as their different combinations, were used as informative features in several classification approaches. In order to achieve the best discrimination between open water and several sea ice types (new ice, thin smooth ice, close ice, very close ice, ridged ice, heavily ridged ice and ship-track), Random Forests (RF) and Maximum likelihood (ML) classifiers were employed. The best overall accuracies were achieved using combination of backscatter-intensity & InSAR-phase and backscatterintensity & coherence-magnitude, and were 76.86% and 75.81% with RF and ML classifiers, respectively. Overall, the combination of backscatter-intensity & InSAR-phase with RF classifier was suggested due to the highest overall accuracy (OA) and smaller computing time in comparison to ML. In contrast to several earlier studies, we were able to discriminate water and the thin smooth ice. Article in Journal/Newspaper Sea ice VTT's Research Information Portal IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium 7328 7331 |
institution |
Open Polar |
collection |
VTT's Research Information Portal |
op_collection_id |
ftvttcrispub |
language |
English |
topic |
Maximum likelihood Random forests Remote sensing Sea ice classification TanDEM-X |
spellingShingle |
Maximum likelihood Random forests Remote sensing Sea ice classification TanDEM-X Marbouti, Marjan Antropov, Oleg Eriksson, Patrick Praks, Jaan Arabzadeh, Vahid Rinne, Eero Leppäranta, Matti Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images |
topic_facet |
Maximum likelihood Random forests Remote sensing Sea ice classification TanDEM-X |
description |
In this study, bistatic interferometric Synthetic Aperture Radar (InSAR) data acquired by the TanDEM-X mission were used for automated classification of sea ice over the Baltic Sea, in the Bothnic Bay. A scene acquired in March of 2012 was used in the study. Backscatter-intensity, coherencemagnitude and InSAR-phase, as well as their different combinations, were used as informative features in several classification approaches. In order to achieve the best discrimination between open water and several sea ice types (new ice, thin smooth ice, close ice, very close ice, ridged ice, heavily ridged ice and ship-track), Random Forests (RF) and Maximum likelihood (ML) classifiers were employed. The best overall accuracies were achieved using combination of backscatter-intensity & InSAR-phase and backscatterintensity & coherence-magnitude, and were 76.86% and 75.81% with RF and ML classifiers, respectively. Overall, the combination of backscatter-intensity & InSAR-phase with RF classifier was suggested due to the highest overall accuracy (OA) and smaller computing time in comparison to ML. In contrast to several earlier studies, we were able to discriminate water and the thin smooth ice. |
format |
Article in Journal/Newspaper |
author |
Marbouti, Marjan Antropov, Oleg Eriksson, Patrick Praks, Jaan Arabzadeh, Vahid Rinne, Eero Leppäranta, Matti |
author_facet |
Marbouti, Marjan Antropov, Oleg Eriksson, Patrick Praks, Jaan Arabzadeh, Vahid Rinne, Eero Leppäranta, Matti |
author_sort |
Marbouti, Marjan |
title |
Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images |
title_short |
Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images |
title_full |
Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images |
title_fullStr |
Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images |
title_full_unstemmed |
Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images |
title_sort |
automated sea ice classification over the baltic sea using multiparametric features of tandem-x insar images |
publisher |
IEEE Institute of Electrical and Electronic Engineers |
publishDate |
2018 |
url |
https://cris.vtt.fi/en/publications/a82a7034-0fba-4d14-b4a4-b25a6cafeea5 https://doi.org/10.1109/IGARSS.2018.8518996 http://www.scopus.com/inward/record.url?scp=85064192218&partnerID=8YFLogxK |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
Marbouti , M , Antropov , O , Eriksson , P , Praks , J , Arabzadeh , V , Rinne , E & Leppäranta , M 2018 , Automated sea ice classification over the baltic sea using multiparametric features of TanDEM-X InSAR images . in 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 . , 8518996 , IEEE Institute of Electrical and Electronic Engineers , IEEE International Geoscience and Remote Sensing Symposium Proceedings , vol. 38 , pp. 7328-7331 , 38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 , Valencia , Spain , 22/07/18 . https://doi.org/10.1109/IGARSS.2018.8518996 |
op_relation |
https://cris.vtt.fi/en/publications/a82a7034-0fba-4d14-b4a4-b25a6cafeea5 urn:ISBN:978-1-5386-7151-1 |
op_rights |
info:eu-repo/semantics/closedAccess |
op_doi |
https://doi.org/10.1109/IGARSS.2018.8518996 |
container_title |
IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium |
container_start_page |
7328 |
op_container_end_page |
7331 |
_version_ |
1810476561327980544 |