Articles | Volume 14, issue 11
https://doi.org/10.5194/essd-14-5037-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/essd-14-5037-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Data description article
| 
18 Nov 2022
Data description article |
| 18 Nov 2022
| 18 Nov 2022
Reconstructing ocean subsurface salinity at high resolution using a machine learning approach
Tian Tian
College of Meteorology and Oceanography, National University of
Defense Technology, Changsha, 410073, China
Institute of Atmospheric Physics, Chinese Academy of Sciences,
Beijing, 100029, China
Institute of Atmospheric Physics, Chinese Academy of Sciences,
Beijing, 100029, China
Center for Ocean Mega-Science, Chinese Academy of Sciences, Qingdao,
266071, China
Gongjie Wang
National Climate Center, Chinese Meteorological Administration,
Beijing, 100081, China
John Abraham
School of Engineering, University of St. Thomas, St. Paul,
MN 55105, USA
Wangxu Wei
Institute of Atmospheric Physics, Chinese Academy of Sciences,
Beijing, 100029, China
Shihe Ren
Key Laboratory of Research on Marine Hazards Forecasting, National
Marine Environmental Forecasting Center, Ministry of Natural Resources,
Beijing, 100081, China
Jiang Zhu
Institute of Atmospheric Physics, Chinese Academy of Sciences,
Beijing, 100029, China
Junqiang Song
College of Meteorology and Oceanography, National University of
Defense Technology, Changsha, 410073, China
Hongze Leng
College of Meteorology and Oceanography, National University of
Defense Technology, Changsha, 410073, China
Viewed
Total article views: 7,007 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 19 Jul 2022)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 4,879 | 1,959 | 169 | 7,007 | 290 | 216 | 219 |
- HTML: 4,879
- PDF: 1,959
- XML: 169
- Total: 7,007
- Supplement: 290
- BibTeX: 216
- EndNote: 219
Total article views: 5,742 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 18 Nov 2022)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 4,147 | 1,445 | 150 | 5,742 | 290 | 201 | 201 |
- HTML: 4,147
- PDF: 1,445
- XML: 150
- Total: 5,742
- Supplement: 290
- BibTeX: 201
- EndNote: 201
Total article views: 1,265 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 19 Jul 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 732 | 514 | 19 | 1,265 | 15 | 18 |
- HTML: 732
- PDF: 514
- XML: 19
- Total: 1,265
- BibTeX: 15
- EndNote: 18
Viewed (geographical distribution)
Total article views: 7,007 (including HTML, PDF, and XML)
Thereof 6,707 with geography defined
and 300 with unknown origin.
Total article views: 5,742 (including HTML, PDF, and XML)
Thereof 5,526 with geography defined
and 216 with unknown origin.
Total article views: 1,265 (including HTML, PDF, and XML)
Thereof 1,181 with geography defined
and 84 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
47 citations as recorded by crossref.
- Neural Synthetic Profiles from Remote Sensing and Observations (NeSPReSO) — Reconstructing temperature and salinity fields in the Gulf of Mexico J. Miranda et al. https://doi.org/10.1016/j.ocemod.2025.102550
- An Updated Estimate of the Indonesian Throughflow Geostrophic Transport: Interannual Variability and Salinity Effect Y. Guo et al. https://doi.org/10.1029/2023GL103748
- A global high-resolution temperature and salinity reconstruction by spatiotemporal multiscale correlations and dynamic height constraints H. Wu et al. https://doi.org/10.5194/essd-18-5855-2026
- Reconstructing three-dimensional density from surface data in the North Atlantic Sea through the PIO-Net model Y. Chen et al. https://doi.org/10.1016/j.oceaneng.2025.122086
- CoastalBench-downscaling: a machine learning benchmark for reconstructing high-resolution three-dimensional coastal fields from surface data B. Yuan et al. https://doi.org/10.1016/j.oceaneng.2026.125851
- Assessment of wetland ecosystem health in Rarh Region, India through P-S-R (pressure-state-response) model R. Khatun & S. Das https://doi.org/10.1016/j.scitotenv.2024.175700
- Three-Dimensional Thermohaline Field Forecast Using a Numerical Model Assimilating AI-Reconstructed Parameters in the Western Indian Ocean Q. Yang et al. https://doi.org/10.3390/jmse14131214
- Super-resolution reconstruction of subsurface temperature field in South China Sea using satellite observations H. Wu et al. https://doi.org/10.1063/5.0253807
- Estimation of subsurface salinity and analysis of Changjiang diluted water volume in the East China Sea S. Kim et al. https://doi.org/10.3389/fmars.2023.1247462
- A deep learning approach to estimate ocean salinity with data sampled with expendable bathythermographs E. Campos et al. https://doi.org/10.1016/j.apor.2024.103997
- On the global reconstruction of ocean interior variables: a feasibility data-driven study with simulated surface and water column observations A. Garcia-Espriu et al. https://doi.org/10.5194/os-21-2579-2025
- Enhancing Subsurface Thermal Structures Reconstruction via a Dual-Branch Framework Integrating Surface Remote Sensing and Model-Predicted Upper-Layer Fields C. Zhou et al. https://doi.org/10.1109/JSTARS.2026.3680945
- Learn from Simulations, Adapt to Observations: Super-Resolution of Isoprene Emissions via Unpaired Domain Adaptation A. Giganti et al. https://doi.org/10.3390/rs16213963
- A continual-learning-based multilayer perceptron for improved reconstruction of three-dimensional nitrate concentrations X. Yu et al. https://doi.org/10.5194/essd-17-2735-2025
- Knowledge-Informed Deep Learning Model for Subsurface Thermohaline Reconstruction From Satellite Observations A. Wang et al. https://doi.org/10.1109/TGRS.2024.3509616
- Bias Correction of SMAP L2 Sea Surface Salinity Based on Physics-Informed Neural Network M. Wu et al. https://doi.org/10.3390/rs17183226
- Application of swarm-based deep neural networks and ensemble models for reconstruction of specific conductance data A. Mahdavi-Meymand et al. https://doi.org/10.1038/s41598-026-38136-z
- Probabilistic 3D geotechnical mapping of coupled Horizontal–Vertical heterogeneity in complex soil deposits Z. Ijaz et al. https://doi.org/10.1016/j.pce.2026.104669
- Leveraging Land Cover Priors for Isoprene Emission Super-Resolution C. Ummerle et al. https://doi.org/10.3390/rs17101715
- STMSNet: A Novel Spatiotemporal Deep Learning Model for Ocean Subsurface Temperature Reconstruction H. Chen et al. https://doi.org/10.1109/JSTARS.2026.3679664
- Uncertainty Quantification of Satellite-Based Essential Climate Variables Derived from Deep Learning J. Gou et al. https://doi.org/10.1007/s10712-025-09919-2
- Forecasting Vertical Profiles of Ocean Currents from Surface Characteristics: A Multivariate Multi-Head Convolutional Neural Network–Long Short-Term Memory Approach S. Kar et al. https://doi.org/10.3390/jmse11101964
- Comparison of Machine Learning Inversion Methods for Salinity in the Central Indian Ocean Based on SMOS Satellite Data Z. Gong et al. https://doi.org/10.1080/07038992.2023.2298575
- Reconstructing 3D ocean subsurface salinity (OSS) from T–S mapping via a data-driven deep learning model J. Zhang et al. https://doi.org/10.1016/j.ocemod.2023.102232
- Cross-scale 3-D thermohaline modeling via dual-residual swin transformer with multisource ocean observations A. Wang et al. https://doi.org/10.1080/17538947.2025.2607902
- AI in Satellite Remote Sensing of the Ocean X. Li et al. https://doi.org/10.1109/JPROC.2026.3664121
- A prior-knowledge-integrated downscaling approach for subsurface thermal structure reconstruction in the tropical Indian Ocean Z. Feng et al. https://doi.org/10.1016/j.dsr2.2025.105589
- Reconstructing ocean subsurface salinity at high resolution using a machine learning approach T. Tian et al. https://doi.org/10.5194/essd-14-5037-2022
- EOF-UViT Model: A New Deep Learning Model to Reconstruct the Three-Dimensional Salinity Based on Multi-Source Remote Sensing Data X. Han et al. https://doi.org/10.3390/rs18050802
- Deep learning-driven 3D marine nitrate estimation: uncertainty mitigation through underwater signal exploitation and label augmentation X. Yu et al. https://doi.org/10.3389/fmars.2025.1576558
- A comparative assessment of different machine learning algorithms for estimating near realistic salinity in the North Indian Ocean A. Paul et al. https://doi.org/10.1016/j.ocemod.2025.102561
- Daily Subsurface Salinity Reconstruction From Multisource Satellite Observations Using Wavelet-Enhanced 3-D Mamba Z. Liang et al. https://doi.org/10.1109/JSTARS.2025.3649568
- Decreases in South Pacific and South Atlantic sea-air CO2 fluxes caused by extreme precipitation Z. Li et al. https://doi.org/10.1038/s41467-026-69847-6
- Reconstructing high-resolution subsurface temperature of the global ocean using deep forest with combined remote sensing and in situ observations H. Su et al. https://doi.org/10.1016/j.isprsjprs.2024.09.022
- Reconstruction of the underwater sound speed field of mesoscale eddies in typical sea areas based on the physically-constrained deep learning model Y. Liu et al. https://doi.org/10.1016/j.apor.2026.104988
- OceanVP: A HYCOM based benchmark dataset and a relational spatiotemporal predictive network for oceanic variable prediction Z. Shi et al. https://doi.org/10.1016/j.oceaneng.2024.117748
- A Method for Predicting High-Resolution 3D Variations in Temperature and Salinity Fields Using Multi-Source Ocean Data X. Cao et al. https://doi.org/10.3390/jmse12081396
- A New Region Ocean Sound Velocity Field Model Considering Variation Mechanisms of Temperature and Salt X. Zhao et al. https://doi.org/10.1109/JOE.2025.3582350
- Attention-enhanced deep learning model for reconstruction and downscaling of thermocline depth in the tropical Indian Ocean Z. Feng et al. https://doi.org/10.1016/j.ocemod.2025.102537
- Strengthening ITF and weakening AMOC: time series evidence of trends and causal pathways to Agulhas variability S. Herho et al. https://doi.org/10.1590/2675-2824074.25092
- Enhancing Ocean Temperature and Salinity Reconstruction with Deep Learning: The Role of Surface Waves X. Yu et al. https://doi.org/10.3390/jmse13050910
- 3DV-Unet: Eddy-Resolving Reconstruction of Three-Dimensional Upper-Ocean Physical Fields from Satellite Observations Q. Zhu et al. https://doi.org/10.3390/rs17193394
- Skillful subseasonal Indian Ocean marine heatwave forecasts using a neural network L. Howard et al. https://doi.org/10.1017/eds.2026.10033
- An Intelligent Reconstruction Method for Ocean Subsurface Temperature Empowered by isQG X. Sun et al. https://doi.org/10.1109/JSTARS.2026.3709205
- Reconstruction of Three-Dimensional Temperature and Salinity in the Equatorial Ocean with Deep-Learning X. Yu et al. https://doi.org/10.3390/rs17122005
- Advancing ocean subsurface thermal structure estimation in the Pacific Ocean: A multi-model ensemble machine learning approach J. Qi et al. https://doi.org/10.1016/j.dynatmoce.2023.101403
- Machine learning reconstruction of multiyear missing nutrient data along the 137°E section, northwestern Pacific X. Song et al. https://doi.org/10.1016/j.dsr.2025.104638
47 citations as recorded by crossref.
- Neural Synthetic Profiles from Remote Sensing and Observations (NeSPReSO) — Reconstructing temperature and salinity fields in the Gulf of Mexico J. Miranda et al. https://doi.org/10.1016/j.ocemod.2025.102550
- An Updated Estimate of the Indonesian Throughflow Geostrophic Transport: Interannual Variability and Salinity Effect Y. Guo et al. https://doi.org/10.1029/2023GL103748
- A global high-resolution temperature and salinity reconstruction by spatiotemporal multiscale correlations and dynamic height constraints H. Wu et al. https://doi.org/10.5194/essd-18-5855-2026
- Reconstructing three-dimensional density from surface data in the North Atlantic Sea through the PIO-Net model Y. Chen et al. https://doi.org/10.1016/j.oceaneng.2025.122086
- CoastalBench-downscaling: a machine learning benchmark for reconstructing high-resolution three-dimensional coastal fields from surface data B. Yuan et al. https://doi.org/10.1016/j.oceaneng.2026.125851
- Assessment of wetland ecosystem health in Rarh Region, India through P-S-R (pressure-state-response) model R. Khatun & S. Das https://doi.org/10.1016/j.scitotenv.2024.175700
- Three-Dimensional Thermohaline Field Forecast Using a Numerical Model Assimilating AI-Reconstructed Parameters in the Western Indian Ocean Q. Yang et al. https://doi.org/10.3390/jmse14131214
- Super-resolution reconstruction of subsurface temperature field in South China Sea using satellite observations H. Wu et al. https://doi.org/10.1063/5.0253807
- Estimation of subsurface salinity and analysis of Changjiang diluted water volume in the East China Sea S. Kim et al. https://doi.org/10.3389/fmars.2023.1247462
- A deep learning approach to estimate ocean salinity with data sampled with expendable bathythermographs E. Campos et al. https://doi.org/10.1016/j.apor.2024.103997
- On the global reconstruction of ocean interior variables: a feasibility data-driven study with simulated surface and water column observations A. Garcia-Espriu et al. https://doi.org/10.5194/os-21-2579-2025
- Enhancing Subsurface Thermal Structures Reconstruction via a Dual-Branch Framework Integrating Surface Remote Sensing and Model-Predicted Upper-Layer Fields C. Zhou et al. https://doi.org/10.1109/JSTARS.2026.3680945
- Learn from Simulations, Adapt to Observations: Super-Resolution of Isoprene Emissions via Unpaired Domain Adaptation A. Giganti et al. https://doi.org/10.3390/rs16213963
- A continual-learning-based multilayer perceptron for improved reconstruction of three-dimensional nitrate concentrations X. Yu et al. https://doi.org/10.5194/essd-17-2735-2025
- Knowledge-Informed Deep Learning Model for Subsurface Thermohaline Reconstruction From Satellite Observations A. Wang et al. https://doi.org/10.1109/TGRS.2024.3509616
- Bias Correction of SMAP L2 Sea Surface Salinity Based on Physics-Informed Neural Network M. Wu et al. https://doi.org/10.3390/rs17183226
- Application of swarm-based deep neural networks and ensemble models for reconstruction of specific conductance data A. Mahdavi-Meymand et al. https://doi.org/10.1038/s41598-026-38136-z
- Probabilistic 3D geotechnical mapping of coupled Horizontal–Vertical heterogeneity in complex soil deposits Z. Ijaz et al. https://doi.org/10.1016/j.pce.2026.104669
- Leveraging Land Cover Priors for Isoprene Emission Super-Resolution C. Ummerle et al. https://doi.org/10.3390/rs17101715
- STMSNet: A Novel Spatiotemporal Deep Learning Model for Ocean Subsurface Temperature Reconstruction H. Chen et al. https://doi.org/10.1109/JSTARS.2026.3679664
- Uncertainty Quantification of Satellite-Based Essential Climate Variables Derived from Deep Learning J. Gou et al. https://doi.org/10.1007/s10712-025-09919-2
- Forecasting Vertical Profiles of Ocean Currents from Surface Characteristics: A Multivariate Multi-Head Convolutional Neural Network–Long Short-Term Memory Approach S. Kar et al. https://doi.org/10.3390/jmse11101964
- Comparison of Machine Learning Inversion Methods for Salinity in the Central Indian Ocean Based on SMOS Satellite Data Z. Gong et al. https://doi.org/10.1080/07038992.2023.2298575
- Reconstructing 3D ocean subsurface salinity (OSS) from T–S mapping via a data-driven deep learning model J. Zhang et al. https://doi.org/10.1016/j.ocemod.2023.102232
- Cross-scale 3-D thermohaline modeling via dual-residual swin transformer with multisource ocean observations A. Wang et al. https://doi.org/10.1080/17538947.2025.2607902
- AI in Satellite Remote Sensing of the Ocean X. Li et al. https://doi.org/10.1109/JPROC.2026.3664121
- A prior-knowledge-integrated downscaling approach for subsurface thermal structure reconstruction in the tropical Indian Ocean Z. Feng et al. https://doi.org/10.1016/j.dsr2.2025.105589
- Reconstructing ocean subsurface salinity at high resolution using a machine learning approach T. Tian et al. https://doi.org/10.5194/essd-14-5037-2022
- EOF-UViT Model: A New Deep Learning Model to Reconstruct the Three-Dimensional Salinity Based on Multi-Source Remote Sensing Data X. Han et al. https://doi.org/10.3390/rs18050802
- Deep learning-driven 3D marine nitrate estimation: uncertainty mitigation through underwater signal exploitation and label augmentation X. Yu et al. https://doi.org/10.3389/fmars.2025.1576558
- A comparative assessment of different machine learning algorithms for estimating near realistic salinity in the North Indian Ocean A. Paul et al. https://doi.org/10.1016/j.ocemod.2025.102561
- Daily Subsurface Salinity Reconstruction From Multisource Satellite Observations Using Wavelet-Enhanced 3-D Mamba Z. Liang et al. https://doi.org/10.1109/JSTARS.2025.3649568
- Decreases in South Pacific and South Atlantic sea-air CO2 fluxes caused by extreme precipitation Z. Li et al. https://doi.org/10.1038/s41467-026-69847-6
- Reconstructing high-resolution subsurface temperature of the global ocean using deep forest with combined remote sensing and in situ observations H. Su et al. https://doi.org/10.1016/j.isprsjprs.2024.09.022
- Reconstruction of the underwater sound speed field of mesoscale eddies in typical sea areas based on the physically-constrained deep learning model Y. Liu et al. https://doi.org/10.1016/j.apor.2026.104988
- OceanVP: A HYCOM based benchmark dataset and a relational spatiotemporal predictive network for oceanic variable prediction Z. Shi et al. https://doi.org/10.1016/j.oceaneng.2024.117748
- A Method for Predicting High-Resolution 3D Variations in Temperature and Salinity Fields Using Multi-Source Ocean Data X. Cao et al. https://doi.org/10.3390/jmse12081396
- A New Region Ocean Sound Velocity Field Model Considering Variation Mechanisms of Temperature and Salt X. Zhao et al. https://doi.org/10.1109/JOE.2025.3582350
- Attention-enhanced deep learning model for reconstruction and downscaling of thermocline depth in the tropical Indian Ocean Z. Feng et al. https://doi.org/10.1016/j.ocemod.2025.102537
- Strengthening ITF and weakening AMOC: time series evidence of trends and causal pathways to Agulhas variability S. Herho et al. https://doi.org/10.1590/2675-2824074.25092
- Enhancing Ocean Temperature and Salinity Reconstruction with Deep Learning: The Role of Surface Waves X. Yu et al. https://doi.org/10.3390/jmse13050910
- 3DV-Unet: Eddy-Resolving Reconstruction of Three-Dimensional Upper-Ocean Physical Fields from Satellite Observations Q. Zhu et al. https://doi.org/10.3390/rs17193394
- Skillful subseasonal Indian Ocean marine heatwave forecasts using a neural network L. Howard et al. https://doi.org/10.1017/eds.2026.10033
- An Intelligent Reconstruction Method for Ocean Subsurface Temperature Empowered by isQG X. Sun et al. https://doi.org/10.1109/JSTARS.2026.3709205
- Reconstruction of Three-Dimensional Temperature and Salinity in the Equatorial Ocean with Deep-Learning X. Yu et al. https://doi.org/10.3390/rs17122005
- Advancing ocean subsurface thermal structure estimation in the Pacific Ocean: A multi-model ensemble machine learning approach J. Qi et al. https://doi.org/10.1016/j.dynatmoce.2023.101403
- Machine learning reconstruction of multiyear missing nutrient data along the 137°E section, northwestern Pacific X. Song et al. https://doi.org/10.1016/j.dsr.2025.104638
Saved (final revised paper)
Latest update: 30 Aug 2026
Short summary
A high-resolution gridded dataset is crucial for understanding ocean processes at various spatiotemporal scales. Here we used a machine learning approach and successfully reconstructed a high-resolution (0.25° × 0.25°) ocean subsurface (1–2000 m) salinity dataset for the period 1993–2018 (monthly) by merging in situ salinity profile observations with high-resolution satellite remote-sensing data. This new product could be useful in various applications in ocean and climate fields.
A high-resolution gridded dataset is crucial for understanding ocean processes at various...
Altmetrics
Final-revised paper
Preprint