EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Informed Fine-Tuned Neural Operator for Flow Field Modeling

Haodong Feng, Yuzhong Zhang, Dixia Fan

Journal of Marine Science and Engineering · 19.01.2026 · 14 (2) · 201

DOI: 10.3390/jmse14020201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 19.01.2026. Verfasst von Haodong Feng und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modeling flow field evolution accurately is important for numerous natural and engineering applications, such as pollutant dispersion in the ocean and atmosphere, yet remains challenging because of the highly nonlinear, multi-physics, and high-dimensional features of flow systems. While traditional equation-based numerical methods suffer from high computational costs, data-driven neural networks struggle with insufficient data and lack physical explainability. The physics-informed neural operator (PINO) addresses this by combining physics and data losses but faces a fundamental gradient imbalance problem. This work proposes a physics-informed fine-tuned neural operator for high-dimensional flow field modeling that decouples the optimization of physics and data losses. Our method first trains the neural network using data loss and then fine-tunes it with physics loss before inference, enabling the model to adapt to evaluation data while respecting physical constraints. This strategy requires no additional training data and can be applied to fit out-of-distribution (OOD) inputs faced during inference. We validate our method using the shallow water equation and advection–diffusion equation using a convolutional neural operator (CNO) as the base architecture. Experimental results show a 26.4% improvement in single-step prediction accuracy and a reduction in error accumulation for multi-step predictions.

Zitieren

APA

Feng, H., Zhang, Y., & Fan, D. (2026). Physics-Informed Fine-Tuned Neural Operator for Flow Field Modeling. Journal of Marine Science and Engineering, 14(2), 201. https://doi.org/10.3390/jmse14020201

Vancouver

Feng H, Zhang Y, Fan D. Physics-Informed Fine-Tuned Neural Operator for Flow Field Modeling. Journal of Marine Science and Engineering. 2026;14(2):201. doi:10.3390/jmse14020201

BibTeX
@article{Feng2026,
  author = {Feng, Haodong and Zhang, Yuzhong and Fan, Dixia},
  title = {Physics-Informed Fine-Tuned Neural Operator for Flow Field Modeling},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {2},
  pages = {201},
  doi = {10.3390/jmse14020201}
}
Kostenlos starten →