Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations
Determining the dynamic processes of the subsurface ocean is a critical yet formidable undertaking given the sparse measurement resources available presently. In this study, using the light gradient boosting machine algorithm (LightGBM), we report for the first time a machine learning strategy for r...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs15245699 https://doaj.org/article/bb6dcec257124994938f3f48d1bfdc8c |
id |
ftdoajarticles:oai:doaj.org/article:bb6dcec257124994938f3f48d1bfdc8c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:bb6dcec257124994938f3f48d1bfdc8c 2024-01-21T10:10:32+01:00 Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations Liang Xiang Yongsheng Xu Hanwei Sun Qingjun Zhang Liqiang Zhang Lin Zhang Xiangguang Zhang Chao Huang Dandan Zhao 2023-12-01T00:00:00Z https://doi.org/10.3390/rs15245699 https://doaj.org/article/bb6dcec257124994938f3f48d1bfdc8c EN eng MDPI AG https://www.mdpi.com/2072-4292/15/24/5699 https://doaj.org/toc/2072-4292 doi:10.3390/rs15245699 2072-4292 https://doaj.org/article/bb6dcec257124994938f3f48d1bfdc8c Remote Sensing, Vol 15, Iss 24, p 5699 (2023) subsurface velocity light gradient boosting machine (LightGBM) The Southern Ocean satellite observations long-term variability Science Q article 2023 ftdoajarticles https://doi.org/10.3390/rs15245699 2023-12-24T01:36:22Z Determining the dynamic processes of the subsurface ocean is a critical yet formidable undertaking given the sparse measurement resources available presently. In this study, using the light gradient boosting machine algorithm (LightGBM), we report for the first time a machine learning strategy for retrieving subsurface velocities at 1000 dbar depth in the Southern Ocean from information derived from satellite observations. Argo velocity measurements are used in the training and validation of the LightGBM model. The results show that reconstructed subsurface velocity agrees better with Argo velocity than reanalysis datasets. In particular, the subsurface velocity estimates have a correlation coefficient of 0.78 and an RMSE of 4.09 cm/s, which is much better than the ECCO estimates, GODAS estimates, GLORYS12V1 estimates, and Ora-S5 estimates. The LightGBM model has a higher skill in the reconstruction of subsurface velocity than the random forest and the linear regressor models. The estimated subsurface velocity exhibits a statistically significant increase at 1000 dbar since the 1990s, providing new evidence for the deep acceleration of mean circulation in the Southern Ocean. This study demonstrates the great potential and advantages of statistical methods for subsurface velocity modeling and oceanic dynamical information retrieval. Article in Journal/Newspaper Southern Ocean Directory of Open Access Journals: DOAJ Articles Ora ENVELOPE(7.517,7.517,62.581,62.581) Southern Ocean Remote Sensing 15 24 5699 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
subsurface velocity light gradient boosting machine (LightGBM) The Southern Ocean satellite observations long-term variability Science Q |
spellingShingle |
subsurface velocity light gradient boosting machine (LightGBM) The Southern Ocean satellite observations long-term variability Science Q Liang Xiang Yongsheng Xu Hanwei Sun Qingjun Zhang Liqiang Zhang Lin Zhang Xiangguang Zhang Chao Huang Dandan Zhao Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations |
topic_facet |
subsurface velocity light gradient boosting machine (LightGBM) The Southern Ocean satellite observations long-term variability Science Q |
description |
Determining the dynamic processes of the subsurface ocean is a critical yet formidable undertaking given the sparse measurement resources available presently. In this study, using the light gradient boosting machine algorithm (LightGBM), we report for the first time a machine learning strategy for retrieving subsurface velocities at 1000 dbar depth in the Southern Ocean from information derived from satellite observations. Argo velocity measurements are used in the training and validation of the LightGBM model. The results show that reconstructed subsurface velocity agrees better with Argo velocity than reanalysis datasets. In particular, the subsurface velocity estimates have a correlation coefficient of 0.78 and an RMSE of 4.09 cm/s, which is much better than the ECCO estimates, GODAS estimates, GLORYS12V1 estimates, and Ora-S5 estimates. The LightGBM model has a higher skill in the reconstruction of subsurface velocity than the random forest and the linear regressor models. The estimated subsurface velocity exhibits a statistically significant increase at 1000 dbar since the 1990s, providing new evidence for the deep acceleration of mean circulation in the Southern Ocean. This study demonstrates the great potential and advantages of statistical methods for subsurface velocity modeling and oceanic dynamical information retrieval. |
format |
Article in Journal/Newspaper |
author |
Liang Xiang Yongsheng Xu Hanwei Sun Qingjun Zhang Liqiang Zhang Lin Zhang Xiangguang Zhang Chao Huang Dandan Zhao |
author_facet |
Liang Xiang Yongsheng Xu Hanwei Sun Qingjun Zhang Liqiang Zhang Lin Zhang Xiangguang Zhang Chao Huang Dandan Zhao |
author_sort |
Liang Xiang |
title |
Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations |
title_short |
Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations |
title_full |
Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations |
title_fullStr |
Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations |
title_full_unstemmed |
Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations |
title_sort |
retrieval of subsurface velocities in the southern ocean from satellite observations |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/rs15245699 https://doaj.org/article/bb6dcec257124994938f3f48d1bfdc8c |
long_lat |
ENVELOPE(7.517,7.517,62.581,62.581) |
geographic |
Ora Southern Ocean |
geographic_facet |
Ora Southern Ocean |
genre |
Southern Ocean |
genre_facet |
Southern Ocean |
op_source |
Remote Sensing, Vol 15, Iss 24, p 5699 (2023) |
op_relation |
https://www.mdpi.com/2072-4292/15/24/5699 https://doaj.org/toc/2072-4292 doi:10.3390/rs15245699 2072-4292 https://doaj.org/article/bb6dcec257124994938f3f48d1bfdc8c |
op_doi |
https://doi.org/10.3390/rs15245699 |
container_title |
Remote Sensing |
container_volume |
15 |
container_issue |
24 |
container_start_page |
5699 |
_version_ |
1788701873325211648 |