Sea Ice Monitoring with CFOSAT Scatterometer Measurements Using Random Forest Classifier
The Ku-band scatterometer called CSCAT onboard the Chinese–French Oceanography Satellite (CFOSAT) is the first spaceborne rotating fan-beam scatterometer (RFSCAT). This paper performs sea ice monitoring with the CSCAT backscatter measurements in polar areas. The CSCAT measurements have the character...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13224686 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/13/22/4686/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/13/22/4686/ 2023-08-20T04:01:22+02:00 Sea Ice Monitoring with CFOSAT Scatterometer Measurements Using Random Forest Classifier Xiaochun Zhai Zhixiong Wang Zhaojun Zheng Rui Xu Fangli Dou Na Xu Xingying Zhang agris 2021-11-19 application/pdf https://doi.org/10.3390/rs13224686 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/rs13224686 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 13; Issue 22; Pages: 4686 CSCAT RFSCAT sea ice distribution random forest classifier microwave feature extraction Text 2021 ftmdpi https://doi.org/10.3390/rs13224686 2023-08-01T03:18:44Z The Ku-band scatterometer called CSCAT onboard the Chinese–French Oceanography Satellite (CFOSAT) is the first spaceborne rotating fan-beam scatterometer (RFSCAT). This paper performs sea ice monitoring with the CSCAT backscatter measurements in polar areas. The CSCAT measurements have the characteristics of diverse incidence and azimuth angles and separation between open water and sea ice. Hence, five microwave feature parameters, which show different sensitivity to ice or water, are defined and derived from the CSCAT measurements firstly. Then the random forest classifier is selected for sea ice monitoring because of its high overall accuracy of 99.66% and 93.31% in the Arctic and Antarctic, respectively. The difference of features ranked by importance in different seasons and regions shows that the combination of these parameters is effective in discriminating sea ice from water under various conditions. The performance of the algorithm is validated against the sea ice edge data from the EUMETSAT Ocean and Sea Ice Satellite Application Facility (OSI SAF) on a global scale in a period from 1 January 2019 to 10 May 2021. The mean sea ice area differences between CSCAT and OSI SAF product in the Arctic and Antarctic are 0.2673 million km2 and −0.4446 million km2, respectively, and the sea ice area relative errors of CSCAT are less than 10% except for summer season in both poles. However, the overall sea ice area derived from CSCAT is lower than the OSI SAF sea ice area in summer. This may be because the CSCAT is trained by radiometer sea ice concentration data while the radiometer measurement of sea ice is significantly affected by melting in the summer season. In conclusion, this research verifies the capability of CSCAT in monitoring polar sea ice using a machine learning-aided random forest classifier. This presented work can give guidance to sea ice monitoring with radar backscatter measurements from other spaceborne scatterometers, particular for the recently launched FY-3E scatterometer (called WindRad). Text Antarc* Antarctic Arctic Sea ice MDPI Open Access Publishing Antarctic Arctic Remote Sensing 13 22 4686 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
CSCAT RFSCAT sea ice distribution random forest classifier microwave feature extraction |
spellingShingle |
CSCAT RFSCAT sea ice distribution random forest classifier microwave feature extraction Xiaochun Zhai Zhixiong Wang Zhaojun Zheng Rui Xu Fangli Dou Na Xu Xingying Zhang Sea Ice Monitoring with CFOSAT Scatterometer Measurements Using Random Forest Classifier |
topic_facet |
CSCAT RFSCAT sea ice distribution random forest classifier microwave feature extraction |
description |
The Ku-band scatterometer called CSCAT onboard the Chinese–French Oceanography Satellite (CFOSAT) is the first spaceborne rotating fan-beam scatterometer (RFSCAT). This paper performs sea ice monitoring with the CSCAT backscatter measurements in polar areas. The CSCAT measurements have the characteristics of diverse incidence and azimuth angles and separation between open water and sea ice. Hence, five microwave feature parameters, which show different sensitivity to ice or water, are defined and derived from the CSCAT measurements firstly. Then the random forest classifier is selected for sea ice monitoring because of its high overall accuracy of 99.66% and 93.31% in the Arctic and Antarctic, respectively. The difference of features ranked by importance in different seasons and regions shows that the combination of these parameters is effective in discriminating sea ice from water under various conditions. The performance of the algorithm is validated against the sea ice edge data from the EUMETSAT Ocean and Sea Ice Satellite Application Facility (OSI SAF) on a global scale in a period from 1 January 2019 to 10 May 2021. The mean sea ice area differences between CSCAT and OSI SAF product in the Arctic and Antarctic are 0.2673 million km2 and −0.4446 million km2, respectively, and the sea ice area relative errors of CSCAT are less than 10% except for summer season in both poles. However, the overall sea ice area derived from CSCAT is lower than the OSI SAF sea ice area in summer. This may be because the CSCAT is trained by radiometer sea ice concentration data while the radiometer measurement of sea ice is significantly affected by melting in the summer season. In conclusion, this research verifies the capability of CSCAT in monitoring polar sea ice using a machine learning-aided random forest classifier. This presented work can give guidance to sea ice monitoring with radar backscatter measurements from other spaceborne scatterometers, particular for the recently launched FY-3E scatterometer (called WindRad). |
format |
Text |
author |
Xiaochun Zhai Zhixiong Wang Zhaojun Zheng Rui Xu Fangli Dou Na Xu Xingying Zhang |
author_facet |
Xiaochun Zhai Zhixiong Wang Zhaojun Zheng Rui Xu Fangli Dou Na Xu Xingying Zhang |
author_sort |
Xiaochun Zhai |
title |
Sea Ice Monitoring with CFOSAT Scatterometer Measurements Using Random Forest Classifier |
title_short |
Sea Ice Monitoring with CFOSAT Scatterometer Measurements Using Random Forest Classifier |
title_full |
Sea Ice Monitoring with CFOSAT Scatterometer Measurements Using Random Forest Classifier |
title_fullStr |
Sea Ice Monitoring with CFOSAT Scatterometer Measurements Using Random Forest Classifier |
title_full_unstemmed |
Sea Ice Monitoring with CFOSAT Scatterometer Measurements Using Random Forest Classifier |
title_sort |
sea ice monitoring with cfosat scatterometer measurements using random forest classifier |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13224686 |
op_coverage |
agris |
geographic |
Antarctic Arctic |
geographic_facet |
Antarctic Arctic |
genre |
Antarc* Antarctic Arctic Sea ice |
genre_facet |
Antarc* Antarctic Arctic Sea ice |
op_source |
Remote Sensing; Volume 13; Issue 22; Pages: 4686 |
op_relation |
https://dx.doi.org/10.3390/rs13224686 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs13224686 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
22 |
container_start_page |
4686 |
_version_ |
1774724659253608448 |