Sea Surface Chlorophyll-a Concentration Retrieval from HY-1C Satellite Data Based on Residual Network
A residual network (ResNet) model was proposed for estimating Chl-a concentrations in global oceans from the remote sensing reflectance (Rrs) observed by the Chinese ocean color and temperature scanner (COCTS) onboard the HY-1C satellite. A total of 52 images from September 2018 to September 2019 we...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs15143696 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/15/14/3696/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/15/14/3696/ 2023-08-20T03:59:11+02:00 Sea Surface Chlorophyll-a Concentration Retrieval from HY-1C Satellite Data Based on Residual Network Guiying Yang Xiaomin Ye Qing Xu Xiaobin Yin Siyang Xu agris 2023-07-24 application/pdf https://doi.org/10.3390/rs15143696 EN eng Multidisciplinary Digital Publishing Institute Ocean Remote Sensing https://dx.doi.org/10.3390/rs15143696 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 15; Issue 14; Pages: 3696 sea surface chlorophyll-a concentration (Chl-a) Chinese ocean color and temperature scanner (COCTS) HY-1C residual neural network Text 2023 ftmdpi https://doi.org/10.3390/rs15143696 2023-08-01T10:59:26Z A residual network (ResNet) model was proposed for estimating Chl-a concentrations in global oceans from the remote sensing reflectance (Rrs) observed by the Chinese ocean color and temperature scanner (COCTS) onboard the HY-1C satellite. A total of 52 images from September 2018 to September 2019 were collected, and the label data were from the multi-task Ocean Color-Climate Change Initiative (OC-CCI) daily products. The results of feature selection and sensitivity experiments show that the logarithmic values of Rrs565 and Rrs520/Rrs443, Rrs565/Rrs490, Rrs520/Rrs490, Rrs490/Rrs443, and Rrs670/Rrs565 are the optimal input parameters for the model. Compared with the classical empirical OC4 algorithm and other machine learning models, including the artificial neural network (ANN), deep neural network (DNN), and random forest (RF), the ResNet retrievals are in better agreement with the OC-CCI Chl-a products. The root-mean-square error (RMSE), unbiased percentage difference (UPD), and correlation coefficient (logarithmic, R(log)) are 0.13 mg/m3, 17.31%, and 0.97, respectively. The performance of the ResNet model was also evaluated against in situ measurements from the Aerosol Robotic Network-Ocean Color (AERONET-OC) and field survey observations in the East and South China Seas. Compared with DNN, ANN, RF, and OC4 models, the UPD is reduced by 5.9%, 0.7%, 6.8%, and 6.3%, respectively. Text Aerosol Robotic Network MDPI Open Access Publishing Remote Sensing 15 14 3696 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
sea surface chlorophyll-a concentration (Chl-a) Chinese ocean color and temperature scanner (COCTS) HY-1C residual neural network |
spellingShingle |
sea surface chlorophyll-a concentration (Chl-a) Chinese ocean color and temperature scanner (COCTS) HY-1C residual neural network Guiying Yang Xiaomin Ye Qing Xu Xiaobin Yin Siyang Xu Sea Surface Chlorophyll-a Concentration Retrieval from HY-1C Satellite Data Based on Residual Network |
topic_facet |
sea surface chlorophyll-a concentration (Chl-a) Chinese ocean color and temperature scanner (COCTS) HY-1C residual neural network |
description |
A residual network (ResNet) model was proposed for estimating Chl-a concentrations in global oceans from the remote sensing reflectance (Rrs) observed by the Chinese ocean color and temperature scanner (COCTS) onboard the HY-1C satellite. A total of 52 images from September 2018 to September 2019 were collected, and the label data were from the multi-task Ocean Color-Climate Change Initiative (OC-CCI) daily products. The results of feature selection and sensitivity experiments show that the logarithmic values of Rrs565 and Rrs520/Rrs443, Rrs565/Rrs490, Rrs520/Rrs490, Rrs490/Rrs443, and Rrs670/Rrs565 are the optimal input parameters for the model. Compared with the classical empirical OC4 algorithm and other machine learning models, including the artificial neural network (ANN), deep neural network (DNN), and random forest (RF), the ResNet retrievals are in better agreement with the OC-CCI Chl-a products. The root-mean-square error (RMSE), unbiased percentage difference (UPD), and correlation coefficient (logarithmic, R(log)) are 0.13 mg/m3, 17.31%, and 0.97, respectively. The performance of the ResNet model was also evaluated against in situ measurements from the Aerosol Robotic Network-Ocean Color (AERONET-OC) and field survey observations in the East and South China Seas. Compared with DNN, ANN, RF, and OC4 models, the UPD is reduced by 5.9%, 0.7%, 6.8%, and 6.3%, respectively. |
format |
Text |
author |
Guiying Yang Xiaomin Ye Qing Xu Xiaobin Yin Siyang Xu |
author_facet |
Guiying Yang Xiaomin Ye Qing Xu Xiaobin Yin Siyang Xu |
author_sort |
Guiying Yang |
title |
Sea Surface Chlorophyll-a Concentration Retrieval from HY-1C Satellite Data Based on Residual Network |
title_short |
Sea Surface Chlorophyll-a Concentration Retrieval from HY-1C Satellite Data Based on Residual Network |
title_full |
Sea Surface Chlorophyll-a Concentration Retrieval from HY-1C Satellite Data Based on Residual Network |
title_fullStr |
Sea Surface Chlorophyll-a Concentration Retrieval from HY-1C Satellite Data Based on Residual Network |
title_full_unstemmed |
Sea Surface Chlorophyll-a Concentration Retrieval from HY-1C Satellite Data Based on Residual Network |
title_sort |
sea surface chlorophyll-a concentration retrieval from hy-1c satellite data based on residual network |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2023 |
url |
https://doi.org/10.3390/rs15143696 |
op_coverage |
agris |
genre |
Aerosol Robotic Network |
genre_facet |
Aerosol Robotic Network |
op_source |
Remote Sensing; Volume 15; Issue 14; Pages: 3696 |
op_relation |
Ocean Remote Sensing https://dx.doi.org/10.3390/rs15143696 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs15143696 |
container_title |
Remote Sensing |
container_volume |
15 |
container_issue |
14 |
container_start_page |
3696 |
_version_ |
1774719410082152448 |