Articles | Volume 18, issue 7
https://doi.org/10.5194/essd-18-4617-2026
https://doi.org/10.5194/essd-18-4617-2026
Data description article
 | 
06 Jul 2026
Data description article |  | 06 Jul 2026

Attention enhanced 3D-U-Net+ +  ocean temperature and salinity reconstruction in the northwestern Pacific based on transfer learning

Hao Wang, Linlin Zhang, Shuguo Yang, Xiaomei Yan, and Zhen Li

Viewed

Total article views: 1,716 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
877 765 74 1,716 25 71 70
  • HTML: 877
  • PDF: 765
  • XML: 74
  • Total: 1,716
  • Supplement: 25
  • BibTeX: 71
  • EndNote: 70
Views and downloads (calculated since 12 Dec 2025)
Cumulative views and downloads (calculated since 12 Dec 2025)

Viewed (geographical distribution)

Total article views: 1,716 (including HTML, PDF, and XML) Thereof 1,598 with geography defined and 118 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Saved (final revised paper)

Latest update: 11 Aug 2026
Download
Short summary
This study develops a new method to reconstruct daily three-dimensional ocean temperature and salinity fields in the northwestern Pacific using only real-time sea surface temperature and height data. By combining deep learning and attention mechanisms, the approach captures complex vertical structures and temporal changes. The results provide more accurate and consistent subsurface information, helping improve ocean monitoring and climate research.
Share
Altmetrics
Final-revised paper
Preprint