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...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/24/5699 |
| _version_ | 1827573657888620544 |
|---|---|
| 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 |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-08T20:24:26Z |
| format | Article |
| id | doaj.art-bb6dcec257124994938f3f48d1bfdc8c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T20:24:26Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-bb6dcec257124994938f3f48d1bfdc8c2023-12-22T14:39:04ZengMDPI AGRemote Sensing2072-42922023-12-011524569910.3390/rs15245699Retrieval of Subsurface Velocities in the Southern Ocean from Satellite ObservationsLiang Xiang0Yongsheng Xu1Hanwei Sun2Qingjun Zhang3Liqiang Zhang4Lin Zhang5Xiangguang Zhang6Chao Huang7Dandan Zhao8Laboratory of Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, ChinaLaboratory of Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, ChinaSpaceborne Radar Research Center, Beijing Institude of Radio Measurement, Beijing 100039, ChinaInstitute of Remote Sensing Satellite, Chinese Academy of Space Technology, Beijing 100094, ChinaInstitute of Remote Sensing Satellite, Chinese Academy of Space Technology, Beijing 100094, ChinaNaval Submarine Academy, Qingdao 266199, ChinaLaboratory of Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, ChinaLaboratory of Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, ChinaInstitute of Oceanographic Instrumentation, Qilu University of Technology (Shandong Academy of Sciences), Qingdao 266061, ChinaDetermining 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.https://www.mdpi.com/2072-4292/15/24/5699subsurface velocitylight gradient boosting machine (LightGBM)The Southern Oceansatellite observationslong-term variability |
| spellingShingle | 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 Remote Sensing subsurface velocity light gradient boosting machine (LightGBM) The Southern Ocean satellite observations long-term variability |
| title | 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_short | Retrieval of Subsurface Velocities in the Southern Ocean from Satellite Observations |
| title_sort | retrieval of subsurface velocities in the southern ocean from satellite observations |
| topic | subsurface velocity light gradient boosting machine (LightGBM) The Southern Ocean satellite observations long-term variability |
| url | https://www.mdpi.com/2072-4292/15/24/5699 |
| work_keys_str_mv | AT liangxiang retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations AT yongshengxu retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations AT hanweisun retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations AT qingjunzhang retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations AT liqiangzhang retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations AT linzhang retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations AT xiangguangzhang retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations AT chaohuang retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations AT dandanzhao retrievalofsubsurfacevelocitiesinthesouthernoceanfromsatelliteobservations |