EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reconstructing the Seawater Temperature Field of the Yellow Sea Using TCN-U-Net++

Jiapeng Bu, Zi Guo, Junqi Cui, Shuyi Zhou, Lei Lin, Shaolei Lu, Xiaodong Liu, Xiaoqian Gao

Journal of Marine Science and Engineering · 02.05.2026 · 14 (9) · 856

DOI: 10.3390/jmse14090856 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 02.05.2026. Verfasst von Jiapeng Bu und 7 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shandong Provincial Natural Science Foundation, Southern Marine Science and Engineering Guangdong Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Yellow Sea is an important offshore area in China, and the accurate prediction of its seawater temperature is of great significance for marine environmental monitoring and climate adaptation management. However, existing research on predicting the three-dimensional (3D) temperature field in the Yellow Sea is scarce and insufficiently accurate. This study proposes a TCN-U-Net++ fusion model to reconstruct the Yellow Sea temperature field using remote sensing satellite data and SODA reanalysis data, while considering the influence of a series of factors, including wind (USSW and VSSW), absolute bathymetric data (BAT), sea surface height anomaly (SSHA), latitude (LAT), longitude (LON), solar radiation (SR), surface runoff (SRO), and precipitation (P). The results show that the model can accurately capture the temporal and spatial distribution characteristics of the temperature field in the Yellow Sea. The results indicate that the deviations from SODA are generally within 2 °C, with errors being approximately 45% lower than those of other models, while the prediction errors relative to Argo and voyage observations are mostly within 1 °C, further demonstrating the accuracy and robustness of the proposed model. In addition, the predictions of the Yellow Sea Cold Water Mass (CWM) are highly consistent with SODA in terms of their evolution and key characteristic parameters. Specifically, the maximum deviation in core temperature is only 0.3 °C, and the difference in its spatial extent is less than 1%. The results demonstrate that TCN-U-Net++ effectively enhances the accuracy of 3D sea temperature prediction in the Yellow Sea, providing technical support for temperature monitoring, ecological early warning, and climate change research.

Förderung

  • National Natural Science Foundation of China
  • Shandong Provincial Natural Science Foundation
  • Southern Marine Science and Engineering Guangdong Laboratory

Zitieren

APA

Bu, J., Guo, Z., Cui, J., Zhou, S., Lin, L., Lu, S., Liu, X., & Gao, X. (2026). Reconstructing the Seawater Temperature Field of the Yellow Sea Using TCN-U-Net++. Journal of Marine Science and Engineering, 14(9), 856. https://doi.org/10.3390/jmse14090856

Vancouver

Bu J, Guo Z, Cui J, Zhou S, Lin L, Lu S, et al. Reconstructing the Seawater Temperature Field of the Yellow Sea Using TCN-U-Net++. Journal of Marine Science and Engineering. 2026;14(9):856. doi:10.3390/jmse14090856

BibTeX
@article{Bu2026,
  author = {Bu, Jiapeng and Guo, Zi and Cui, Junqi and Zhou, Shuyi and Lin, Lei and Lu, Shaolei and Liu, Xiaodong and Gao, Xiaoqian},
  title = {Reconstructing the Seawater Temperature Field of the Yellow Sea Using TCN-U-Net++},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {9},
  pages = {856},
  doi = {10.3390/jmse14090856}
}
Kostenlos starten →