A Hybrid POD-Autoencoder Framework for Reduced Order Modeling of Turbulent Flow via Strategic Field Decomposition
Abstract
This study proposes a hybrid reduced-order modeling (ROM) framework for the simulation of turbulent flow. The central idea is to decompose flow dynamics according to their temporal characteristics and predict the resulting components individually. The full field is first divided into a sub-field represented by a limited number of proper orthogonal decomposition (POD) modes (named as POD-retained field) and the corresponding residual sub-field (named as POD-truncated field). A frequency-informed POD strategy identifies the retained modes by considering both modal energy and dominant frequency. The evolution of retained POD coefficients, which feature similar temporal scales, is described using a vector autoregressive (VAR) model. In parallel, the POD-truncated field is compressed into a low-dimensional latent space using a Fourier-neural-operator-based Koopman β-variational autoencoder (FK-β-VAE), with the latent variables subsequently predicted by a switching-VAR model. Turbulent statistics of the full field are recovered by combining the contributions from the two components. The framework is assessed using turbulent channel flow at a friction Reynolds number of $110$. The predicted Reynolds-stress components, turbulent kinetic energy (TKE), and dominant wavenumber spectra show good agreement with the reference. Moreover, in comparison with an alternative framework of full-field modeling (i.e., without field decomposition), the proposed framework yields more accurate and robust long-term statistical predictions.
Related
- A stochastic modeling framework to generate 2-D rough-wall high-Reynolds-number turbulent boundary layers
- A Priori Estimation of the Non-Linear Compression Potential and Quantification of Autoencoder Non-Linearity in Turbulent Flows
- Extended proper orthogonal decomposition of non-homogeneous thermal fields in a turbulent pipe flow
- A domain decomposition non-intrusive reduced order model for turbulent flows
- A Pre-trained Variational Autoencoder for Gyrokinetic Plasma Turbulence Surrogate Modeling
BibTeX
@misc{li2026hybrid,
title = {{A Hybrid POD-Autoencoder Framework for Reduced Order Modeling of Turbulent Flow via Strategic Field Decomposition}},
author = {Xianglong Li and Zeng Liu and Zhan Wang and Kai Wang and Shunxiang Cao and Guangyao Wang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.06992},
eprint = {2609.06992},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.06992},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - A Hybrid POD-Autoencoder Framework for Reduced Order Modeling of Turbulent Flow via Strategic Field Decomposition
AU - Xianglong Li
AU - Zeng Liu
AU - Zhan Wang
AU - Kai Wang
AU - Shunxiang Cao
AU - Guangyao Wang
PY - 2026
DA - 2026/09/07
PB - arXiv
DO - 10.48550/arxiv.2609.06992
UR - https://arxiv.org/abs/2609.06992
AB - This study proposes a hybrid reduced-order modeling (ROM) framework for the simulation of turbulent flow. The central idea is to decompose flow dynamics according to their temporal characteristics and predict the resulting components individually. The full field is first divided into a sub-field represented by a limited number of proper orthogonal decomposition (POD) modes (named as POD-retained field) and the corresponding residual sub-field (named as POD-truncated field). A frequency-informed POD strategy identifies the retained modes by considering both modal energy and dominant frequency. The evolution of retained POD coefficients, which feature similar temporal scales, is described using a vector autoregressive (VAR) model. In parallel, the POD-truncated field is compressed into a low-dimensional latent space using a Fourier-neural-operator-based Koopman β-variational autoencoder (FK-β-VAE), with the latent variables subsequently predicted by a switching-VAR model. Turbulent statistics of the full field are recovered by combining the contributions from the two components. The framework is assessed using turbulent channel flow at a friction Reynolds number of $110$. The predicted Reynolds-stress components, turbulent kinetic energy (TKE), and dominant wavenumber spectra show good agreement with the reference. Moreover, in comparison with an alternative framework of full-field modeling (i.e., without field decomposition), the proposed framework yields more accurate and robust long-term statistical predictions.
ER -