Reconstruction of monthly CO distribution in the Ross Sea, Antarctica during 1998 -2018 using machine learning technique and observational data sets
The ocean is a major reservoir of anthropogenic carbon dioxide, especially the Southern Ocean has been known to absorb 40% of the carbon dioxide emitted by human activity. The Ross Sea is one of the most productive regions in the Southern Ocean; however, its carbon dioxide absorption capacity has no...
Published in: | GEO DATA |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English Korean |
Published: |
GeoAI Data Society
2022
|
Subjects: | |
Online Access: | https://doi.org/10.22761/DJ2022.4.3.003 https://doaj.org/article/936cc96eee86481d90df8773d09aa292 |
id |
ftdoajarticles:oai:doaj.org/article:936cc96eee86481d90df8773d09aa292 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:936cc96eee86481d90df8773d09aa292 2023-10-09T21:46:48+02:00 Reconstruction of monthly CO distribution in the Ross Sea, Antarctica during 1998 -2018 using machine learning technique and observational data sets Ahra Mo Jung-ok Choi Keyhong Park 2022-09-01T00:00:00Z https://doi.org/10.22761/DJ2022.4.3.003 https://doaj.org/article/936cc96eee86481d90df8773d09aa292 EN KO eng kor GeoAI Data Society http://geodata.kr/upload/pdf/geo-4-3-15.pdf https://doaj.org/toc/2713-5004 2713-5004 doi:10.22761/DJ2022.4.3.003 https://doaj.org/article/936cc96eee86481d90df8773d09aa292 Geo Data, Vol 4, Iss 3, Pp 15-24 (2022) ross sea machine learning carbon dioxide random forest Environmental sciences GE1-350 Geology QE1-996.5 article 2022 ftdoajarticles https://doi.org/10.22761/DJ2022.4.3.003 2023-09-10T00:35:21Z The ocean is a major reservoir of anthropogenic carbon dioxide, especially the Southern Ocean has been known to absorb 40% of the carbon dioxide emitted by human activity. The Ross Sea is one of the most productive regions in the Southern Ocean; however, its carbon dioxide absorption capacity has not been clearly evaluated yet. Because the Southern Ocean is geographically isolated from civilization and thus, its remoteness prevents making sufficient observations from proving reliable carbon dioxide sink strength estimates. Thus, in order to overcome the current spatial and temporal limitations of direct observations, the fugacity of carbon dioxide (fCO2) data was reproduced using a machine learning technique (i.e., random forest technique). The technique is a type of machine learning frequently used to reproduce marine environmental variations through training satellite data and modeled data as well as existing observational data. Furthermore, to reproduce more reliable fCO2 estimates, in addition to marine environmental variables (i.e., sea surface temperature, sea ice concentration, and chlorophyll-a concentration), cloud cover, wind speed, and El Niño index were included in the machine learning procedure. In this study, we provide the past 21 years (1998 – 2018) of monthly spatial and temporal variation information of dissolved carbon dioxide in the Ross Sea, Antarctica. Article in Journal/Newspaper Antarc* Antarctica Ross Sea Sea ice Southern Ocean Directory of Open Access Journals: DOAJ Articles Ross Sea Southern Ocean GEO DATA 4 3 15 24 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English Korean |
topic |
ross sea machine learning carbon dioxide random forest Environmental sciences GE1-350 Geology QE1-996.5 |
spellingShingle |
ross sea machine learning carbon dioxide random forest Environmental sciences GE1-350 Geology QE1-996.5 Ahra Mo Jung-ok Choi Keyhong Park Reconstruction of monthly CO distribution in the Ross Sea, Antarctica during 1998 -2018 using machine learning technique and observational data sets |
topic_facet |
ross sea machine learning carbon dioxide random forest Environmental sciences GE1-350 Geology QE1-996.5 |
description |
The ocean is a major reservoir of anthropogenic carbon dioxide, especially the Southern Ocean has been known to absorb 40% of the carbon dioxide emitted by human activity. The Ross Sea is one of the most productive regions in the Southern Ocean; however, its carbon dioxide absorption capacity has not been clearly evaluated yet. Because the Southern Ocean is geographically isolated from civilization and thus, its remoteness prevents making sufficient observations from proving reliable carbon dioxide sink strength estimates. Thus, in order to overcome the current spatial and temporal limitations of direct observations, the fugacity of carbon dioxide (fCO2) data was reproduced using a machine learning technique (i.e., random forest technique). The technique is a type of machine learning frequently used to reproduce marine environmental variations through training satellite data and modeled data as well as existing observational data. Furthermore, to reproduce more reliable fCO2 estimates, in addition to marine environmental variables (i.e., sea surface temperature, sea ice concentration, and chlorophyll-a concentration), cloud cover, wind speed, and El Niño index were included in the machine learning procedure. In this study, we provide the past 21 years (1998 – 2018) of monthly spatial and temporal variation information of dissolved carbon dioxide in the Ross Sea, Antarctica. |
format |
Article in Journal/Newspaper |
author |
Ahra Mo Jung-ok Choi Keyhong Park |
author_facet |
Ahra Mo Jung-ok Choi Keyhong Park |
author_sort |
Ahra Mo |
title |
Reconstruction of monthly CO distribution in the Ross Sea, Antarctica during 1998 -2018 using machine learning technique and observational data sets |
title_short |
Reconstruction of monthly CO distribution in the Ross Sea, Antarctica during 1998 -2018 using machine learning technique and observational data sets |
title_full |
Reconstruction of monthly CO distribution in the Ross Sea, Antarctica during 1998 -2018 using machine learning technique and observational data sets |
title_fullStr |
Reconstruction of monthly CO distribution in the Ross Sea, Antarctica during 1998 -2018 using machine learning technique and observational data sets |
title_full_unstemmed |
Reconstruction of monthly CO distribution in the Ross Sea, Antarctica during 1998 -2018 using machine learning technique and observational data sets |
title_sort |
reconstruction of monthly co distribution in the ross sea, antarctica during 1998 -2018 using machine learning technique and observational data sets |
publisher |
GeoAI Data Society |
publishDate |
2022 |
url |
https://doi.org/10.22761/DJ2022.4.3.003 https://doaj.org/article/936cc96eee86481d90df8773d09aa292 |
geographic |
Ross Sea Southern Ocean |
geographic_facet |
Ross Sea Southern Ocean |
genre |
Antarc* Antarctica Ross Sea Sea ice Southern Ocean |
genre_facet |
Antarc* Antarctica Ross Sea Sea ice Southern Ocean |
op_source |
Geo Data, Vol 4, Iss 3, Pp 15-24 (2022) |
op_relation |
http://geodata.kr/upload/pdf/geo-4-3-15.pdf https://doaj.org/toc/2713-5004 2713-5004 doi:10.22761/DJ2022.4.3.003 https://doaj.org/article/936cc96eee86481d90df8773d09aa292 |
op_doi |
https://doi.org/10.22761/DJ2022.4.3.003 |
container_title |
GEO DATA |
container_volume |
4 |
container_issue |
3 |
container_start_page |
15 |
op_container_end_page |
24 |
_version_ |
1779309336680464384 |