EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reduced-order surrogates for forced flexible mesh coastal-ocean models

Freja Høgholm Petersen, Jesper Sandvig Mariegaard, Rocco Palmitessa, Allan Peter Engsig-Karup

Ocean Modelling · 2026-08 · 203 · 102772

DOI: 10.1016/j.ocemod.2026.102772 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ocean Modelling, 2026-08. Verfasst von Freja Høgholm Petersen und 3 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innovationsfonden, Uddannelses- og Forskningsministeriet, Danish Agency for Higher Education and Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While proper orthogonal decomposition (POD)-based surrogates are widely explored for hydrodynamic applications, the use of Koopman autoencoders for real-world coastal-ocean modelling remains relatively limited. This paper introduces a flexible Koopman autoencoder formulation that incorporates meteorological forcings and boundary conditions, and systematically compares its performance against POD-based surrogates. The Koopman autoencoder employs a learned linear temporal operator in latent space, enabling eigenvalue regularization to promote temporal stability. This strategy is evaluated alongside temporal unrolling techniques for achieving stable and accurate long-term predictions. The models are assessed on three test cases spanning distinct dynamical regimes, with prediction horizons up to one year at 30-minute temporal resolution. Across all cases, the reduced order surrogates with temporal unrolling achieve high accuracy with relative root-mean-squared-errors of 0.0068-0.14 and $R^2$-values of 0.61-0.995, where prediction errors are largest for current velocities, and smallest for water surface elevations. In two of the three cases, the Koopman Autoencoder have higher accuracy than the POD-based surrogates. Comparing to in-situ observations, the surrogate yields -0.64% to 12% increase in water surface elevation prediction error when compared to prediction errors of the physics-based model. These error levels, corresponding to a few centimeters, are acceptable for many practical applications, while inference speed-ups of 300-1400x enables workflows such as ensemble forecasting and long climate simulations for coastal-ocean modelling.

Förderung

  • Innovationsfonden
  • Uddannelses- og Forskningsministeriet
  • Danish Agency for Higher Education and Science

Zitieren

APA

Petersen, F. H., Mariegaard, J. S., Palmitessa, R., & Engsig-Karup, A. P. (2026). Reduced-order surrogates for forced flexible mesh coastal-ocean models. Ocean Modelling, 203, 102772. https://doi.org/10.1016/j.ocemod.2026.102772

Vancouver

Petersen FH, Mariegaard JS, Palmitessa R, Engsig-Karup AP. Reduced-order surrogates for forced flexible mesh coastal-ocean models. Ocean Modelling. 2026;203:102772. doi:10.1016/j.ocemod.2026.102772

BibTeX
@article{Petersen2026,
  author = {Petersen, Freja Høgholm and Mariegaard, Jesper Sandvig and Palmitessa, Rocco and Engsig-Karup, Allan Peter},
  title = {Reduced-order surrogates for forced flexible mesh coastal-ocean models},
  journal = {Ocean Modelling},
  year = {2026},
  volume = {203},
  pages = {102772},
  doi = {10.1016/j.ocemod.2026.102772}
}
Kostenlos starten →