Ocean Science
Ocean Science
OS
Articles | Volume 22, issue 4
Articles | Volume 22, issue 4
https://doi.org/10.5194/os-22-2161-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/os-22-2161-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 22, issue 4
Research article
 | 
16 Jul 2026
Research article |  | 16 Jul 2026

TS-Cast: deep learning for subsurface ocean reconstruction from satellite observations in the northwestern Pacific

Jeong-Yeob Chae, Kathleen A. Donohue, and Jae-Hun Park

Viewed

Total article views: 4,790 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
3,180 1,241 369 4,790 377 330
  • HTML: 3,180
  • PDF: 1,241
  • XML: 369
  • Total: 4,790
  • BibTeX: 377
  • EndNote: 330
Views and downloads (calculated since 19 Nov 2025)
Cumulative views and downloads (calculated since 19 Nov 2025)

Viewed (geographical distribution)

Total article views: 4,790 (including HTML, PDF, and XML) Thereof 4,720 with geography defined and 70 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved (final revised paper)

Latest update: 16 Oct 2026
Download
Short summary
We introduce TS (Temperature-Salinity)-Cast, a novel deep neural network that reconstructs subsurface thermohaline structures from satellite observations. Validated against independent time-series data, TS-Cast achieves root mean squared errors of < 1 °C and < 0.1 psu in the upper 500 m of the Kuroshio Extension, comparable or surpassing data-assimilated numerical models. Critically, we demonstrate that the physical limitations of the input satellite data fundamentally constrain the model's predictive skill.
Read more
Share