EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

AI performs on high-resolution three-dimensional ocean temperature forecasting: remote sensing data-driven becomes a new possibility

Jiawei Jiang, Huier Mo, Lin Zhang, Liying Wan, Xiangguang Zhang, Marie Drévillon, Boya Xu, Jun Wang, Jinyuan Xin, Yining Ma

International Journal of Digital Earth · 31.12.2025 · 18 (2)

DOI: 10.1080/17538947.2025.2595786 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Digital Earth, online erschienen am 09.12.2025. Verfasst von Jiawei Jiang und 9 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, the CAS (Chinese Academy of Sciences) Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of three-dimensional (3D) ocean structures is essential for understanding oceanic processes. While AI-based ocean models demonstrate superior forecasting performance, they typically depend on numerically simulated 3D background structures as input, leading to operational limitations and significant computational expenses. This study explores a method for directly forecasting high-spatiotemporal resolution 3D ocean temperature structures using multisource remote sensing data in ‘2D-to-3D’ mode, comparing it with predictions from 3D numerical simulation background structure profiles in ‘3D-to-3D’ mode. We propose a multiscale residual spatiotemporal window attention model (MSWO) for 1/12° resolution forecasting. Extensive experiments are conducted using the world-leading ocean prediction intercomparison and validation task team (IV-TT) Class4 intercomparison framework to evaluate the model's performance. Benchmarked against mainstream forecasting systems, MSWO achieves comparable accuracy to operational models in 2D-to-3D mode and superior accuracy in 3D-to-3D mode. Furthermore, the MSWO model outperforms other data-driven artificial intelligence models in terms of training cost and accuracy. This study demonstrates the feasibility of deriving high-spatiotemporal-resolution 3D ocean forecasts from satellite remote sensing. Article highlights Exploring the possibility of using remote sensing imagery to directly forecast high-resolution ocean temperature structure. Validated via IV-TT Class4 framework, enabling global benchmark comparisons. MSWO model achieves superior forecasting performance relative to other spatiotemporal prediction models in experiments.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • the CAS (Chinese Academy of Sciences) Program

Zitieren

APA

Jiang, J., Mo, H., Zhang, L., Wan, L., Zhang, X., Drévillon, M., Xu, B., Wang, J., Xin, J., & Ma, Y. (2025). AI performs on high-resolution three-dimensional ocean temperature forecasting: remote sensing data-driven becomes a new possibility. International Journal of Digital Earth, 18(2). https://doi.org/10.1080/17538947.2025.2595786

Vancouver

Jiang J, Mo H, Zhang L, Wan L, Zhang X, Drévillon M, et al. AI performs on high-resolution three-dimensional ocean temperature forecasting: remote sensing data-driven becomes a new possibility. International Journal of Digital Earth. 2025;18(2). doi:10.1080/17538947.2025.2595786

BibTeX
@article{Jiang2025,
  author = {Jiang, Jiawei and Mo, Huier and Zhang, Lin and Wan, Liying and Zhang, Xiangguang and Drévillon, Marie and Xu, Boya and Wang, Jun and Xin, Jinyuan and Ma, Yining},
  title = {AI performs on high-resolution three-dimensional ocean temperature forecasting: remote sensing data-driven becomes a new possibility},
  journal = {International Journal of Digital Earth},
  year = {2025},
  volume = {18},
  number = {2},
  doi = {10.1080/17538947.2025.2595786}
}
Kostenlos starten →