OPINE: Orthogonal Projection in Invertible Nonlinear Embeddings for Turbulent Flows

Abstract

Proper orthogonal decomposition (POD) represents physical fields with orthogonal modes ordered by variance, so that one decomposition gives reduced coordinates in every dimension, but it needs many modes when the data lie near a curved manifold. Nonlinear autoencoders are more compact, but their information loss happens inside a nonlinear encoder, and a model trained with one latent dimension gives no model with a smaller one. We introduce Orthogonal Projection in Invertible Nonlinear Embeddings (OPINE), which learns an invertible nonlinear change of coordinates and performs POD in the transformed coordinates. Because the map is invertible, all information loss occurs in the POD projection, and ordering its basis after training gives reduced coordinates of every smaller dimension from a single model. Training alternates gradient updates of the map with a damped update that tracks the evolving POD subspace, and we prove that this update converges locally to the exact POD subspace. We evaluate OPINE on synthetic manifolds, chaotic Kuramoto-Sivashinsky dynamics, forced Burgers turbulence, two-dimensional Kolmogorov flow, and three-dimensional minimal channel flow. OPINE is more accurate than POD at every tested retained dimension above one, and on the Kuramoto-Sivashinsky and Burgers dynamics, it is more accurate than convolutional and fully connected autoencoders by more than two orders of magnitude at the largest retained dimension.

Extended proper orthogonal decomposition of non-homogeneous thermal fields in a turbulent pipe flow
Antonio Antoranz, Andrea Ianiro, Oscar Flores +1
International Journal of Heat and Mass Transfer6 Oct 2026Peer-reviewedLicence not statedFull text45 citedFluid dynamicsHAL
Exact solutions of the nuclear shell-model secular problem: Discrete Non-Orthogonal Shell Model within a Variation After Projection approach
Duy Duc Dao, Frédéric Nowacki
Physical Review C28 Sep 2026Peer-reviewedHAL deposit licenceFull text2 citedNuclear physicsHAL
Sparse Carleman Embeddings for Nonlinear Discrete Dynamical Systems
Hsuan-Cheng Wu, Xiantao Li
arXiv26 Oct 2026PreprintCC BY 4.0Full textQuantum physics & quantum informationarXiv
Quantum Complexity of Ancilla-Free Unitary Embeddings for Nonlinear Dynamics via Generalized State-Dependent Double-Bracket Flows
Yuki Ito, Hideaki Hakoshima, Keisuke Fujii
arXiv29 Sep 2026PreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
On the numerical limitations of dual Koopman von Neumann embeddings for solving conservative nonlinear ordinary differential equations on quantum computers
Thibault Fredon, Abhay K. Ram, Fabrice Debbasch +2
arXiv25 Sep 2026PreprintarXiv licenceFull textMathematical physics Quantum physics & quantum informationarXiv

Cite

BibTeX RIS

BibTeX

@misc{ouyang2026opine,
  title = {{OPINE: Orthogonal Projection in Invertible Nonlinear Embeddings for Turbulent Flows}},
  author = {Anqiao Ouyang and Hongyi Ke and Qi Wang},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.00216},
  eprint = {2611.00216},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.00216},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - OPINE: Orthogonal Projection in Invertible Nonlinear Embeddings for Turbulent Flows
AU  - Anqiao Ouyang
AU  - Hongyi Ke
AU  - Qi Wang
PY  - 2026
DA  - 2026/11/01
PB  - arXiv
DO  - 10.48550/arxiv.2611.00216
UR  - https://arxiv.org/abs/2611.00216
AB  - Proper orthogonal decomposition (POD) represents physical fields with orthogonal modes ordered by variance, so that one decomposition gives reduced coordinates in every dimension, but it needs many modes when the data lie near a curved manifold. Nonlinear autoencoders are more compact, but their information loss happens inside a nonlinear encoder, and a model trained with one latent dimension gives no model with a smaller one. We introduce Orthogonal Projection in Invertible Nonlinear Embeddings (OPINE), which learns an invertible nonlinear change of coordinates and performs POD in the transformed coordinates. Because the map is invertible, all information loss occurs in the POD projection, and ordering its basis after training gives reduced coordinates of every smaller dimension from a single model. Training alternates gradient updates of the map with a damped update that tracks the evolving POD subspace, and we prove that this update converges locally to the exact POD subspace. We evaluate OPINE on synthetic manifolds, chaotic Kuramoto-Sivashinsky dynamics, forced Burgers turbulence, two-dimensional Kolmogorov flow, and three-dimensional minimal channel flow. OPINE is more accurate than POD at every tested retained dimension above one, and on the Kuramoto-Sivashinsky and Burgers dynamics, it is more accurate than convolutional and fully connected autoencoders by more than two orders of magnitude at the largest retained dimension.
ER  -

Abstract

Related

Cite