EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning-Based 3D Ocean Current Reconstruction Improved by Vertical Temperature and Salinity

Xinlong Li, Qin Duan, Ying Zhang, Yuhong Zhang, Yan Du

Remote Sensing · 26.12.2025 · 18 (1) · 96

DOI: 10.3390/rs18010096 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 26.12.2025. Verfasst von Xinlong Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Strategic Priority Research Program of the Chinese Academy of Sciences, Key Talent Project of Guangdong Province, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The ocean circulation in the Western Pacific is crucial for climate regulation and marine ecosystems, but reconstructing 3D subsurface currents remains challenging due to limited observations. This study presents SpadeUp, a novel deep learning model that fuses surface data (wind fields, sea surface height, and surface currents) with subsurface thermohaline data to achieve high-precision 3D ocean current reconstruction. We systematically compared SpadeUp against DiSpade (using only surface data through knowledge distillation) and U-Net (benchmark model). SpadeUp achieved superior performance with average root-mean-square error below 0.05 m/s, representing over 30% improvement compared to U-Net while using fewer parameters. The model successfully reproduced subsurface-intensified eddy in the South China Sea, and accurately captured complex vertical structures of the Kuroshio. Variable importance analysis confirmed that subsurface thermohaline information, especially temperature, is decisive for enhancing reconstruction accuracy, particularly below the thermocline.

Förderung

  • National Natural Science Foundation of China
  • Strategic Priority Research Program of the Chinese Academy of Sciences
  • Key Talent Project of Guangdong Province, China
  • Guangdong Natural Science Funds for Distinguished Young Scholar

Zitieren

APA

Li, X., Duan, Q., Zhang, Y., Zhang, Y., & Du, Y. (2025). Deep Learning-Based 3D Ocean Current Reconstruction Improved by Vertical Temperature and Salinity. Remote Sensing, 18(1), 96. https://doi.org/10.3390/rs18010096

Vancouver

Li X, Duan Q, Zhang Y, Zhang Y, Du Y. Deep Learning-Based 3D Ocean Current Reconstruction Improved by Vertical Temperature and Salinity. Remote Sensing. 2025;18(1):96. doi:10.3390/rs18010096

BibTeX
@article{Li2025,
  author = {Li, Xinlong and Duan, Qin and Zhang, Ying and Zhang, Yuhong and Du, Yan},
  title = {Deep Learning-Based 3D Ocean Current Reconstruction Improved by Vertical Temperature and Salinity},
  journal = {Remote Sensing},
  year = {2025},
  volume = {18},
  number = {1},
  pages = {96},
  doi = {10.3390/rs18010096}
}
Kostenlos starten →