EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

New insights into experimental stratified flows obtained through physics-informed neural networks

Lu Zhu, Xianyang Jiang, Adrien Lefauve, Rich R. Kerswell, P.F. Linden

Journal of Fluid Mechanics · 25.02.2024 · 981

DOI: 10.1017/jfm.2024.49 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Fluid Mechanics, online erschienen am 23.02.2024. Verfasst von Lu Zhu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Natural Environment Research Council, H2020 European Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We develop a physics-informed neural network (PINN) to significantly augment state-of-the-art experimental data of stratified flows. A fully connected deep neural network is trained using time-resolved experimental data in a salt-stratified inclined duct experiment, consisting of three-component velocity fields and density fields measured simultaneously in three dimensions at Reynolds number $= O(10^3)$ and at Prandtl or Schmidt number $=700$ . The PINN enforces incompressibility, the governing equations for momentum and buoyancy, and the boundary conditions at the duct walls. These physics-constrained, augmented data are output at an increased spatio-temporal resolution and demonstrate five key results: (i) the elimination of measurement noise; (ii) the correction of distortion caused by the scanning measurement technique; (iii) the identification of weak but dynamically important three-dimensional vortices of Holmboe waves; (iv) the revision of turbulent energy budgets and mixing efficiency; and (v) the prediction of the latent pressure field and its role in the observed asymmetric Holmboe wave dynamics. These results mark a significant step forward in furthering the reach of experiments, especially in the context of stratified turbulence, where accurately computing three-dimensional gradients and resolving small scales remain enduring challenges.

Förderung

  • Natural Environment Research Council
  • H2020 European Research Council

Zitieren

APA

Zhu, L., Jiang, X., Lefauve, A., Kerswell, R. R., & Linden, P. (2024). New insights into experimental stratified flows obtained through physics-informed neural networks. Journal of Fluid Mechanics, 981. https://doi.org/10.1017/jfm.2024.49

Vancouver

Zhu L, Jiang X, Lefauve A, Kerswell RR, Linden P. New insights into experimental stratified flows obtained through physics-informed neural networks. Journal of Fluid Mechanics. 2024;981. doi:10.1017/jfm.2024.49

BibTeX
@article{Zhu2024,
  author = {Zhu, Lu and Jiang, Xianyang and Lefauve, Adrien and Kerswell, Rich R. and Linden, P.F.},
  title = {New insights into experimental stratified flows obtained through physics-informed neural networks},
  journal = {Journal of Fluid Mechanics},
  year = {2024},
  volume = {981},
  doi = {10.1017/jfm.2024.49}
}
Kostenlos starten →