EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of global mesoscale eddy trajectories using a Temporal Convolutional Network

Fenyuan Han, Jianing Li, Qingxuan Yang, Hui Sun

Environmental Research Communications · 01.11.2026 · 8 (11) · 115016

DOI: 10.1088/2515-7620/aebd52 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Research Communications, online erschienen am 12.11.2026. Verfasst von Fenyuan Han und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Postdoctoral Science Foundation, Postdoctoral Fellowship Program of CPSF, Natural Science Foundation of Shandong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mesoscale eddies are ubiquitous throughout the global ocean, and their propagation and evolution exert important influences on oceanic energy transport and salt exchange. Accurate prediction of short-term mesoscale eddy propagation is therefore crucial for advancing understanding of mesoscale dynamics and improving marine forecasting skill. To address the limited ability of traditional statistical approaches to represent complex nonlinear propagation, a Temporal Convolutional Network (TCN) is developed for future eddy position prediction. The results show that the TCN, when constrained by multi-source background information including surface winds, sea surface currents and bathymetry, can effectively capture the nonlinear short-term propagation behavior of mesoscale eddies. For 7 d lead time prediction on a global scale, the model yields a median distance error of 19.85 km, outperforming widely used baselines including Long Short-Term Memory, multilayer perceptron and maximum likelihood estimation. However, discrepancies remain under low-latitude, strong background-flow, and high-speed propagation conditions, suggesting that stronger physical constraints should be incorporated in future work to improve generalization and physical consistency.

Förderung

  • China Postdoctoral Science Foundation
  • Postdoctoral Fellowship Program of CPSF
  • Natural Science Foundation of Shandong Province
  • National Natural Science Foundation of China

Zitieren

APA

Han, F., Li, J., Yang, Q., & Sun, H. (2026). Prediction of global mesoscale eddy trajectories using a Temporal Convolutional Network. Environmental Research Communications, 8(11), 115016. https://doi.org/10.1088/2515-7620/aebd52

Vancouver

Han F, Li J, Yang Q, Sun H. Prediction of global mesoscale eddy trajectories using a Temporal Convolutional Network. Environmental Research Communications. 2026;8(11):115016. doi:10.1088/2515-7620/aebd52

BibTeX
@article{Han2026,
  author = {Han, Fenyuan and Li, Jianing and Yang, Qingxuan and Sun, Hui},
  title = {Prediction of global mesoscale eddy trajectories using a Temporal Convolutional Network},
  journal = {Environmental Research Communications},
  year = {2026},
  volume = {8},
  number = {11},
  pages = {115016},
  doi = {10.1088/2515-7620/aebd52}
}
Kostenlos starten →