Assessing the Parameterization of RADARSAT-2 Dual-polarized ScanSAR Scenes on the Accuracy of a Convolutional Neural Network for Sea Ice Classification: Case Study over Coronation Gulf, Canada
Arctic amplification has many impacts on sea-ice extent, thickness, and flux. It becomes critical to monitor sea-ice conditions at finer spatio-temporal resolution. We used a simple convolutional neural network (CNN) on the RADARSAT-2 dual-polarized ScanSAR wide archive available over Coronation Gul...
Published in: | Canadian Journal of Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English French |
Published: |
Taylor & Francis Group
2023
|
Subjects: | |
Online Access: | https://doi.org/10.1080/07038992.2023.2247091 https://doaj.org/article/85d573f39c6942e7834ea5413f0d33f6 |
id |
ftdoajarticles:oai:doaj.org/article:85d573f39c6942e7834ea5413f0d33f6 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:85d573f39c6942e7834ea5413f0d33f6 2024-02-04T09:58:24+01:00 Assessing the Parameterization of RADARSAT-2 Dual-polarized ScanSAR Scenes on the Accuracy of a Convolutional Neural Network for Sea Ice Classification: Case Study over Coronation Gulf, Canada Benoit Montpetit Benjamin Deschamps Joshua King Jason Duffe 2023-01-01T00:00:00Z https://doi.org/10.1080/07038992.2023.2247091 https://doaj.org/article/85d573f39c6942e7834ea5413f0d33f6 EN FR eng fre Taylor & Francis Group http://dx.doi.org/10.1080/07038992.2023.2247091 https://doaj.org/toc/1712-7971 1712-7971 doi:10.1080/07038992.2023.2247091 https://doaj.org/article/85d573f39c6942e7834ea5413f0d33f6 Canadian Journal of Remote Sensing, Vol 49, Iss 1 (2023) Environmental sciences GE1-350 Technology T article 2023 ftdoajarticles https://doi.org/10.1080/07038992.2023.2247091 2024-01-07T01:41:03Z Arctic amplification has many impacts on sea-ice extent, thickness, and flux. It becomes critical to monitor sea-ice conditions at finer spatio-temporal resolution. We used a simple convolutional neural network (CNN) on the RADARSAT-2 dual-polarized ScanSAR wide archive available over Coronation Gulf, Canada, to assess which SAR parameter improves model performances to classify sea ice from water on a large volume of data covering 11 years of ice and surface water conditions. An overall accuracy of 90.1% was achieved on 989 scenes of 100% ice cover or ice-free conditions. An accuracy of 86.3% was achieved on the last year of data (134 scenes) which was kept out of the training process to test the model on an independent dataset. A better accuracy is obtained at lower incidence angles and the HH polarization provides the most information to classify ice from water. To achieve the best accuracy, the incidence angle and the noise equivalent sigma-nought had to be included as input to the model. A comparison done with the ASI passive microwave product shows similar errors in total sea ice concentration when using the Canadian Ice Service regional charts as reference. Nonetheless, errors from both datasets differ and the CNN outputs show greater potential to reduce masked areas, given the better spatial resolution, enabling data classification closer to land and identify features not captured by the ASI dataset. Article in Journal/Newspaper Arctic Coronation Gulf Sea ice Directory of Open Access Journals: DOAJ Articles Arctic Canada Coronation Gulf ENVELOPE(-112.003,-112.003,68.134,68.134) Canadian Journal of Remote Sensing 49 1 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English French |
topic |
Environmental sciences GE1-350 Technology T |
spellingShingle |
Environmental sciences GE1-350 Technology T Benoit Montpetit Benjamin Deschamps Joshua King Jason Duffe Assessing the Parameterization of RADARSAT-2 Dual-polarized ScanSAR Scenes on the Accuracy of a Convolutional Neural Network for Sea Ice Classification: Case Study over Coronation Gulf, Canada |
topic_facet |
Environmental sciences GE1-350 Technology T |
description |
Arctic amplification has many impacts on sea-ice extent, thickness, and flux. It becomes critical to monitor sea-ice conditions at finer spatio-temporal resolution. We used a simple convolutional neural network (CNN) on the RADARSAT-2 dual-polarized ScanSAR wide archive available over Coronation Gulf, Canada, to assess which SAR parameter improves model performances to classify sea ice from water on a large volume of data covering 11 years of ice and surface water conditions. An overall accuracy of 90.1% was achieved on 989 scenes of 100% ice cover or ice-free conditions. An accuracy of 86.3% was achieved on the last year of data (134 scenes) which was kept out of the training process to test the model on an independent dataset. A better accuracy is obtained at lower incidence angles and the HH polarization provides the most information to classify ice from water. To achieve the best accuracy, the incidence angle and the noise equivalent sigma-nought had to be included as input to the model. A comparison done with the ASI passive microwave product shows similar errors in total sea ice concentration when using the Canadian Ice Service regional charts as reference. Nonetheless, errors from both datasets differ and the CNN outputs show greater potential to reduce masked areas, given the better spatial resolution, enabling data classification closer to land and identify features not captured by the ASI dataset. |
format |
Article in Journal/Newspaper |
author |
Benoit Montpetit Benjamin Deschamps Joshua King Jason Duffe |
author_facet |
Benoit Montpetit Benjamin Deschamps Joshua King Jason Duffe |
author_sort |
Benoit Montpetit |
title |
Assessing the Parameterization of RADARSAT-2 Dual-polarized ScanSAR Scenes on the Accuracy of a Convolutional Neural Network for Sea Ice Classification: Case Study over Coronation Gulf, Canada |
title_short |
Assessing the Parameterization of RADARSAT-2 Dual-polarized ScanSAR Scenes on the Accuracy of a Convolutional Neural Network for Sea Ice Classification: Case Study over Coronation Gulf, Canada |
title_full |
Assessing the Parameterization of RADARSAT-2 Dual-polarized ScanSAR Scenes on the Accuracy of a Convolutional Neural Network for Sea Ice Classification: Case Study over Coronation Gulf, Canada |
title_fullStr |
Assessing the Parameterization of RADARSAT-2 Dual-polarized ScanSAR Scenes on the Accuracy of a Convolutional Neural Network for Sea Ice Classification: Case Study over Coronation Gulf, Canada |
title_full_unstemmed |
Assessing the Parameterization of RADARSAT-2 Dual-polarized ScanSAR Scenes on the Accuracy of a Convolutional Neural Network for Sea Ice Classification: Case Study over Coronation Gulf, Canada |
title_sort |
assessing the parameterization of radarsat-2 dual-polarized scansar scenes on the accuracy of a convolutional neural network for sea ice classification: case study over coronation gulf, canada |
publisher |
Taylor & Francis Group |
publishDate |
2023 |
url |
https://doi.org/10.1080/07038992.2023.2247091 https://doaj.org/article/85d573f39c6942e7834ea5413f0d33f6 |
long_lat |
ENVELOPE(-112.003,-112.003,68.134,68.134) |
geographic |
Arctic Canada Coronation Gulf |
geographic_facet |
Arctic Canada Coronation Gulf |
genre |
Arctic Coronation Gulf Sea ice |
genre_facet |
Arctic Coronation Gulf Sea ice |
op_source |
Canadian Journal of Remote Sensing, Vol 49, Iss 1 (2023) |
op_relation |
http://dx.doi.org/10.1080/07038992.2023.2247091 https://doaj.org/toc/1712-7971 1712-7971 doi:10.1080/07038992.2023.2247091 https://doaj.org/article/85d573f39c6942e7834ea5413f0d33f6 |
op_doi |
https://doi.org/10.1080/07038992.2023.2247091 |
container_title |
Canadian Journal of Remote Sensing |
container_volume |
49 |
container_issue |
1 |
_version_ |
1789962851443539968 |