Data Reconstruction for Remotely Sensed Chlorophyll-a Concentration in the Ross Sea Using Ensemble-Based Machine Learning
Polar regions are too harsh to be continuously observed using ocean color (OC) sensors because of various limitations due to low solar elevations, ice effects, peculiar phytoplankton photosynthetic parameters, optical complexity of seawater and persistence of clouds and fog. Therefore, the OC data u...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2020
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs12111898 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/12/11/1898/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/12/11/1898/ 2023-08-20T04:01:55+02:00 Data Reconstruction for Remotely Sensed Chlorophyll-a Concentration in the Ross Sea Using Ensemble-Based Machine Learning Jinku Park Hyun-Cheol Kim Dukwon Bae Young-Heon Jo agris 2020-06-11 application/pdf https://doi.org/10.3390/rs12111898 EN eng Multidisciplinary Digital Publishing Institute Ocean Remote Sensing https://dx.doi.org/10.3390/rs12111898 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 12; Issue 11; Pages: 1898 data reconstruction chlorophyll-a concentration (CHL) random forest (RF) Ross Sea Antarctica Text 2020 ftmdpi https://doi.org/10.3390/rs12111898 2023-07-31T23:37:35Z Polar regions are too harsh to be continuously observed using ocean color (OC) sensors because of various limitations due to low solar elevations, ice effects, peculiar phytoplankton photosynthetic parameters, optical complexity of seawater and persistence of clouds and fog. Therefore, the OC data undergo a quality-control process, eventually accompanied by considerable data loss. We attempted to reconstruct these missing values for chlorophyll-a concentration (CHL) data using a machine-learning technique based on multiple datasets (satellite and reanalysis datasets) in the Ross Sea, Antarctica. This technique—based on an ensemble tree called random forest (RF)—was used for the reconstruction. The performance of the RF model was robust, and the reconstructed CHL data were consistent with satellite measurements. The reconstructed CHL data allowed a high intrinsic resolution of OC to be used without specific techniques (e.g., spatial average). Therefore, we believe that it is possible to study multiple characteristics of phytoplankton dynamics more quantitatively, such as bloom initiation/termination timings and peaks, as well as the variability in time scales of phytoplankton growth. In addition, because the reconstructed CHL showed relatively higher accuracy than satellite observations compared with the in situ data, our product may enable more accurate planktonic research. Text Antarc* Antarctica Ross Sea MDPI Open Access Publishing Ross Sea Remote Sensing 12 11 1898 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
data reconstruction chlorophyll-a concentration (CHL) random forest (RF) Ross Sea Antarctica |
spellingShingle |
data reconstruction chlorophyll-a concentration (CHL) random forest (RF) Ross Sea Antarctica Jinku Park Hyun-Cheol Kim Dukwon Bae Young-Heon Jo Data Reconstruction for Remotely Sensed Chlorophyll-a Concentration in the Ross Sea Using Ensemble-Based Machine Learning |
topic_facet |
data reconstruction chlorophyll-a concentration (CHL) random forest (RF) Ross Sea Antarctica |
description |
Polar regions are too harsh to be continuously observed using ocean color (OC) sensors because of various limitations due to low solar elevations, ice effects, peculiar phytoplankton photosynthetic parameters, optical complexity of seawater and persistence of clouds and fog. Therefore, the OC data undergo a quality-control process, eventually accompanied by considerable data loss. We attempted to reconstruct these missing values for chlorophyll-a concentration (CHL) data using a machine-learning technique based on multiple datasets (satellite and reanalysis datasets) in the Ross Sea, Antarctica. This technique—based on an ensemble tree called random forest (RF)—was used for the reconstruction. The performance of the RF model was robust, and the reconstructed CHL data were consistent with satellite measurements. The reconstructed CHL data allowed a high intrinsic resolution of OC to be used without specific techniques (e.g., spatial average). Therefore, we believe that it is possible to study multiple characteristics of phytoplankton dynamics more quantitatively, such as bloom initiation/termination timings and peaks, as well as the variability in time scales of phytoplankton growth. In addition, because the reconstructed CHL showed relatively higher accuracy than satellite observations compared with the in situ data, our product may enable more accurate planktonic research. |
format |
Text |
author |
Jinku Park Hyun-Cheol Kim Dukwon Bae Young-Heon Jo |
author_facet |
Jinku Park Hyun-Cheol Kim Dukwon Bae Young-Heon Jo |
author_sort |
Jinku Park |
title |
Data Reconstruction for Remotely Sensed Chlorophyll-a Concentration in the Ross Sea Using Ensemble-Based Machine Learning |
title_short |
Data Reconstruction for Remotely Sensed Chlorophyll-a Concentration in the Ross Sea Using Ensemble-Based Machine Learning |
title_full |
Data Reconstruction for Remotely Sensed Chlorophyll-a Concentration in the Ross Sea Using Ensemble-Based Machine Learning |
title_fullStr |
Data Reconstruction for Remotely Sensed Chlorophyll-a Concentration in the Ross Sea Using Ensemble-Based Machine Learning |
title_full_unstemmed |
Data Reconstruction for Remotely Sensed Chlorophyll-a Concentration in the Ross Sea Using Ensemble-Based Machine Learning |
title_sort |
data reconstruction for remotely sensed chlorophyll-a concentration in the ross sea using ensemble-based machine learning |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2020 |
url |
https://doi.org/10.3390/rs12111898 |
op_coverage |
agris |
geographic |
Ross Sea |
geographic_facet |
Ross Sea |
genre |
Antarc* Antarctica Ross Sea |
genre_facet |
Antarc* Antarctica Ross Sea |
op_source |
Remote Sensing; Volume 12; Issue 11; Pages: 1898 |
op_relation |
Ocean Remote Sensing https://dx.doi.org/10.3390/rs12111898 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs12111898 |
container_title |
Remote Sensing |
container_volume |
12 |
container_issue |
11 |
container_start_page |
1898 |
_version_ |
1774712301977337856 |