Reconstructing ocean subsurface salinity at high resolution using a machine learning approach
A gridded ocean subsurface salinity dataset with global coverage is useful for research on climate change and its variability. Here, we explore the feed-forward neural network (FFNN) approach to reconstruct a high-resolution (0.25∘ × 0.25∘) ocean subsurface (1–2000 m) salinity dataset for the period...
Published in: | Earth System Science Data |
---|---|
Main Authors: | , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2022
|
Subjects: | |
Online Access: | https://doi.org/10.5194/essd-14-5037-2022 https://essd.copernicus.org/articles/14/5037/2022/essd-14-5037-2022.pdf https://doaj.org/article/584eceb101d24759a412cd39d004f295 |
id |
fttriple:oai:gotriple.eu:oai:doaj.org/article:584eceb101d24759a412cd39d004f295 |
---|---|
record_format |
openpolar |
spelling |
fttriple:oai:gotriple.eu:oai:doaj.org/article:584eceb101d24759a412cd39d004f295 2023-05-15T13:39:35+02:00 Reconstructing ocean subsurface salinity at high resolution using a machine learning approach T. Tian L. Cheng G. Wang J. Abraham W. Wei S. Ren J. Zhu J. Song H. Leng 2022-11-01 https://doi.org/10.5194/essd-14-5037-2022 https://essd.copernicus.org/articles/14/5037/2022/essd-14-5037-2022.pdf https://doaj.org/article/584eceb101d24759a412cd39d004f295 en eng Copernicus Publications doi:10.5194/essd-14-5037-2022 1866-3508 1866-3516 https://essd.copernicus.org/articles/14/5037/2022/essd-14-5037-2022.pdf https://doaj.org/article/584eceb101d24759a412cd39d004f295 undefined Earth System Science Data, Vol 14, Pp 5037-5060 (2022) geo envir Journal Article https://vocabularies.coar-repositories.org/resource_types/c_6501/ 2022 fttriple https://doi.org/10.5194/essd-14-5037-2022 2023-01-22T18:19:47Z A gridded ocean subsurface salinity dataset with global coverage is useful for research on climate change and its variability. Here, we explore the feed-forward neural network (FFNN) approach to reconstruct a high-resolution (0.25∘ × 0.25∘) ocean subsurface (1–2000 m) salinity dataset for the period 1993–2018 by merging in situ salinity profile observations with high-resolution (0.25∘ × 0.25∘) satellite remote-sensing altimetry absolute dynamic topography (ADT), sea surface temperature (SST), sea surface wind (SSW) field data, and a coarse-resolution (1∘ × 1∘) gridded salinity product. We show that the FFNN can effectively transfer small-scale spatial variations in ADT, SST, and SSW fields into the 0.25∘ × 0.25∘ salinity field. The root-mean-square error (RMSE) can be reduced by ∼11 % on a global-average basis compared with the 1∘ × 1∘ salinity gridded field. The reduction in RMSE is much larger in the upper ocean than the deep ocean because of stronger mesoscale variations in the upper layers. In addition, the new 0.25∘ × 0.25∘ reconstruction shows more realistic spatial signals in the regions with strong mesoscale variations, e.g., the Gulf Stream, Kuroshio, and Antarctic Circumpolar Current regions, than the 1∘ × 1∘ resolution product, indicating the efficiency of the machine learning approach in bringing satellite observations together with in situ observations. The large-scale salinity patterns from 0.25∘ × 0.25∘ data are consistent with the 1∘ × 1∘ gridded salinity field, suggesting the persistence of the large-scale signals in the high-resolution reconstruction. The successful application of machine learning in this study provides an alternative approach for ocean and climate data reconstruction that can complement the existing data assimilation and objective analysis methods. The reconstructed IAP0.25∘ dataset is freely available at https://doi.org/10.57760/sciencedb.o00122.00001 (Tian et al., 2022). Article in Journal/Newspaper Antarc* Antarctic Unknown Antarctic Earth System Science Data 14 11 5037 5060 |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
fttriple |
language |
English |
topic |
geo envir |
spellingShingle |
geo envir T. Tian L. Cheng G. Wang J. Abraham W. Wei S. Ren J. Zhu J. Song H. Leng Reconstructing ocean subsurface salinity at high resolution using a machine learning approach |
topic_facet |
geo envir |
description |
A gridded ocean subsurface salinity dataset with global coverage is useful for research on climate change and its variability. Here, we explore the feed-forward neural network (FFNN) approach to reconstruct a high-resolution (0.25∘ × 0.25∘) ocean subsurface (1–2000 m) salinity dataset for the period 1993–2018 by merging in situ salinity profile observations with high-resolution (0.25∘ × 0.25∘) satellite remote-sensing altimetry absolute dynamic topography (ADT), sea surface temperature (SST), sea surface wind (SSW) field data, and a coarse-resolution (1∘ × 1∘) gridded salinity product. We show that the FFNN can effectively transfer small-scale spatial variations in ADT, SST, and SSW fields into the 0.25∘ × 0.25∘ salinity field. The root-mean-square error (RMSE) can be reduced by ∼11 % on a global-average basis compared with the 1∘ × 1∘ salinity gridded field. The reduction in RMSE is much larger in the upper ocean than the deep ocean because of stronger mesoscale variations in the upper layers. In addition, the new 0.25∘ × 0.25∘ reconstruction shows more realistic spatial signals in the regions with strong mesoscale variations, e.g., the Gulf Stream, Kuroshio, and Antarctic Circumpolar Current regions, than the 1∘ × 1∘ resolution product, indicating the efficiency of the machine learning approach in bringing satellite observations together with in situ observations. The large-scale salinity patterns from 0.25∘ × 0.25∘ data are consistent with the 1∘ × 1∘ gridded salinity field, suggesting the persistence of the large-scale signals in the high-resolution reconstruction. The successful application of machine learning in this study provides an alternative approach for ocean and climate data reconstruction that can complement the existing data assimilation and objective analysis methods. The reconstructed IAP0.25∘ dataset is freely available at https://doi.org/10.57760/sciencedb.o00122.00001 (Tian et al., 2022). |
format |
Article in Journal/Newspaper |
author |
T. Tian L. Cheng G. Wang J. Abraham W. Wei S. Ren J. Zhu J. Song H. Leng |
author_facet |
T. Tian L. Cheng G. Wang J. Abraham W. Wei S. Ren J. Zhu J. Song H. Leng |
author_sort |
T. Tian |
title |
Reconstructing ocean subsurface salinity at high resolution using a machine learning approach |
title_short |
Reconstructing ocean subsurface salinity at high resolution using a machine learning approach |
title_full |
Reconstructing ocean subsurface salinity at high resolution using a machine learning approach |
title_fullStr |
Reconstructing ocean subsurface salinity at high resolution using a machine learning approach |
title_full_unstemmed |
Reconstructing ocean subsurface salinity at high resolution using a machine learning approach |
title_sort |
reconstructing ocean subsurface salinity at high resolution using a machine learning approach |
publisher |
Copernicus Publications |
publishDate |
2022 |
url |
https://doi.org/10.5194/essd-14-5037-2022 https://essd.copernicus.org/articles/14/5037/2022/essd-14-5037-2022.pdf https://doaj.org/article/584eceb101d24759a412cd39d004f295 |
geographic |
Antarctic |
geographic_facet |
Antarctic |
genre |
Antarc* Antarctic |
genre_facet |
Antarc* Antarctic |
op_source |
Earth System Science Data, Vol 14, Pp 5037-5060 (2022) |
op_relation |
doi:10.5194/essd-14-5037-2022 1866-3508 1866-3516 https://essd.copernicus.org/articles/14/5037/2022/essd-14-5037-2022.pdf https://doaj.org/article/584eceb101d24759a412cd39d004f295 |
op_rights |
undefined |
op_doi |
https://doi.org/10.5194/essd-14-5037-2022 |
container_title |
Earth System Science Data |
container_volume |
14 |
container_issue |
11 |
container_start_page |
5037 |
op_container_end_page |
5060 |
_version_ |
1766120523046060032 |