Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data
River ice is a major contributor to flood risk in cold regions due to the physical impediment of flow caused by ice jamming. Although a variety of classifiers have been developed to distinguish ice types using HH or VV intensity of SAR data, mostly based on data from RADARSAT-1 and -2, these classif...
Published in: | International Journal of Applied Earth Observation and Geoinformation |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | http://resolver.tudelft.nl/uuid:f34a0800-fae6-4057-9488-5aa2500578b5 https://doi.org/10.1016/j.jag.2021.102359 |
id |
fttudelft:oai:tudelft.nl:uuid:f34a0800-fae6-4057-9488-5aa2500578b5 |
---|---|
record_format |
openpolar |
spelling |
fttudelft:oai:tudelft.nl:uuid:f34a0800-fae6-4057-9488-5aa2500578b5 2024-02-11T10:01:55+01:00 Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data de Roda Husman, S. (author) Van der Sanden, Joost (author) Lhermitte, S.L.M. (author) Eleveld, M.A. (author) 2021 http://resolver.tudelft.nl/uuid:f34a0800-fae6-4057-9488-5aa2500578b5 https://doi.org/10.1016/j.jag.2021.102359 en eng https://github.com/SdeRodaHusman/remotesensing-of-river-ice International Journal of Applied Earth Observation and Geoinformation--0303-2434--0ba47ab5-2c34-450f-ada7-3b9edb6afe1b http://resolver.tudelft.nl/uuid:f34a0800-fae6-4057-9488-5aa2500578b5 https://doi.org/10.1016/j.jag.2021.102359 © 2021 S. de Roda Husman, Joost Van der Sanden, S.L.M. Lhermitte, M.A. Eleveld River ice Classification SAR Sentinel-1 Random Forest GLCM texture journal article 2021 fttudelft https://doi.org/10.1016/j.jag.2021.102359 2024-01-24T23:31:53Z River ice is a major contributor to flood risk in cold regions due to the physical impediment of flow caused by ice jamming. Although a variety of classifiers have been developed to distinguish ice types using HH or VV intensity of SAR data, mostly based on data from RADARSAT-1 and -2, these classifiers still experience problems with breakup classification, because meltwater development causes overlap in co-polarization backscatter intensities of open water and sheet ice pixels. In this study, we develop a Random Forest classifier based on multiple features of Sentinel-1 data for three main classes generally present during breakup: rubble ice, sheet ice and open water, in a case study over the Athabasca River in Canada. For each ice stage, intensity of the VV and VH backscatter, pseudo-polarimetric decomposition parameters and Grey Level Co-occurrence Matrix texture features were computed for 70 verified sample areas. Several classifiers were developed, based on i) solely intensity features or on ii) a combination of intensity, pseudo-polarimetric and texture features and each classifier was evaluated based on Recursive Feature Elimination with Cross-Validation and pair-wise correlation of the studied features. Results show improved classifier performance when including GLCM mean of VV intensity, and VH intensity features instead of the conventional classifier based solely on intensity. This highlights the complementary nature of texture and intensity for the classification of breaking river ice. GLCM mean incorporates spatial patterns of the co-polarized intensity and sensitivity to context, while VH intensity introduces cross-polarized surface and volume scattering signals and is less sensitive to wind than the commonly used co-polarized intensity. We conclude that the proposed method based on the combination of texture and intensity features is suitable for and performs well in physically complex situations such as breakup, which are hard to classify otherwise. This method has a high potential for classifying ... Article in Journal/Newspaper Athabasca River Ice Sheet Delft University of Technology: Institutional Repository Athabasca River Canada International Journal of Applied Earth Observation and Geoinformation 101 102359 |
institution |
Open Polar |
collection |
Delft University of Technology: Institutional Repository |
op_collection_id |
fttudelft |
language |
English |
topic |
River ice Classification SAR Sentinel-1 Random Forest GLCM texture |
spellingShingle |
River ice Classification SAR Sentinel-1 Random Forest GLCM texture de Roda Husman, S. (author) Van der Sanden, Joost (author) Lhermitte, S.L.M. (author) Eleveld, M.A. (author) Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data |
topic_facet |
River ice Classification SAR Sentinel-1 Random Forest GLCM texture |
description |
River ice is a major contributor to flood risk in cold regions due to the physical impediment of flow caused by ice jamming. Although a variety of classifiers have been developed to distinguish ice types using HH or VV intensity of SAR data, mostly based on data from RADARSAT-1 and -2, these classifiers still experience problems with breakup classification, because meltwater development causes overlap in co-polarization backscatter intensities of open water and sheet ice pixels. In this study, we develop a Random Forest classifier based on multiple features of Sentinel-1 data for three main classes generally present during breakup: rubble ice, sheet ice and open water, in a case study over the Athabasca River in Canada. For each ice stage, intensity of the VV and VH backscatter, pseudo-polarimetric decomposition parameters and Grey Level Co-occurrence Matrix texture features were computed for 70 verified sample areas. Several classifiers were developed, based on i) solely intensity features or on ii) a combination of intensity, pseudo-polarimetric and texture features and each classifier was evaluated based on Recursive Feature Elimination with Cross-Validation and pair-wise correlation of the studied features. Results show improved classifier performance when including GLCM mean of VV intensity, and VH intensity features instead of the conventional classifier based solely on intensity. This highlights the complementary nature of texture and intensity for the classification of breaking river ice. GLCM mean incorporates spatial patterns of the co-polarized intensity and sensitivity to context, while VH intensity introduces cross-polarized surface and volume scattering signals and is less sensitive to wind than the commonly used co-polarized intensity. We conclude that the proposed method based on the combination of texture and intensity features is suitable for and performs well in physically complex situations such as breakup, which are hard to classify otherwise. This method has a high potential for classifying ... |
format |
Article in Journal/Newspaper |
author |
de Roda Husman, S. (author) Van der Sanden, Joost (author) Lhermitte, S.L.M. (author) Eleveld, M.A. (author) |
author_facet |
de Roda Husman, S. (author) Van der Sanden, Joost (author) Lhermitte, S.L.M. (author) Eleveld, M.A. (author) |
author_sort |
de Roda Husman, S. (author) |
title |
Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data |
title_short |
Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data |
title_full |
Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data |
title_fullStr |
Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data |
title_full_unstemmed |
Integrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data |
title_sort |
integrating intensity and context for improved supervised river ice classification from dual-pol sentinel-1 sar data |
publishDate |
2021 |
url |
http://resolver.tudelft.nl/uuid:f34a0800-fae6-4057-9488-5aa2500578b5 https://doi.org/10.1016/j.jag.2021.102359 |
geographic |
Athabasca River Canada |
geographic_facet |
Athabasca River Canada |
genre |
Athabasca River Ice Sheet |
genre_facet |
Athabasca River Ice Sheet |
op_relation |
https://github.com/SdeRodaHusman/remotesensing-of-river-ice International Journal of Applied Earth Observation and Geoinformation--0303-2434--0ba47ab5-2c34-450f-ada7-3b9edb6afe1b http://resolver.tudelft.nl/uuid:f34a0800-fae6-4057-9488-5aa2500578b5 https://doi.org/10.1016/j.jag.2021.102359 |
op_rights |
© 2021 S. de Roda Husman, Joost Van der Sanden, S.L.M. Lhermitte, M.A. Eleveld |
op_doi |
https://doi.org/10.1016/j.jag.2021.102359 |
container_title |
International Journal of Applied Earth Observation and Geoinformation |
container_volume |
101 |
container_start_page |
102359 |
_version_ |
1790597794820521984 |