# Assessment of unsteady flow predictions using hybrid deep learning based reduced order models

arXiv: https://arxiv.org/abs/2009.04396 · HTML: https://mlsanity.com/paper/2009.04396/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2020.

## Built on by (most cited first, 20 of 20)

- [Physics-Guided Deep Learning for Dynamical Systems: A Survey](https://mlsanity.com/paper/2107.01272/) (2021)
- [Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques](https://mlsanity.com/paper/2107.11460/) (2021)
- [A Finite Element-Inspired Hypergraph Neural Network: Application to Fluid Dynamics Simulations](https://mlsanity.com/paper/2212.14545/) (2022)
- [Real-time simulation of parameter-dependent fluid flows through deep learning-based reduced order models](https://mlsanity.com/paper/2106.05722/) (2021)
- [Physics perception in sloshing scenes with guaranteed thermodynamic consistency](https://mlsanity.com/paper/2106.13301/) (2021)
- [Predicting fluid-structure interaction with graph neural networks](https://mlsanity.com/paper/2210.04193/) (2022)
- [CD-ROM: Complemented Deep-Reduced Order Model](https://mlsanity.com/paper/2202.10746/) (2022)
- [Predicting waves in fluids with deep neural network](https://mlsanity.com/paper/2201.06628/) (2022)
- [Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates](https://mlsanity.com/paper/2506.05513/) (2025)
- [An Implicit GNN Solver for Poisson-like problems](https://mlsanity.com/paper/2302.10891/) (2023)
- [Continual Learning of Range-Dependent Transmission Loss for Underwater Acoustic using Conditional Convolutional Neural Net](https://mlsanity.com/paper/2404.08091/) (2024)
- [Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling](https://mlsanity.com/paper/2510.00233/) (2025)
- [Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition](https://mlsanity.com/paper/2504.11433/) (2025)
- [Kinematically consistent recurrent neural networks for learning inverse problems in wave propagation](https://mlsanity.com/paper/2110.03903/) (2021)
- [Deep Learning for Stability Analysis of a Freely Vibrating Sphere at Moderate Reynolds Number](https://mlsanity.com/paper/2112.09858/) (2021)
- [Assessment of convolutional recurrent autoencoder network for learning wave propagation](https://mlsanity.com/paper/2204.05573/) (2022)
- [Combined space-time reduced-order model with 3D deep convolution for extrapolating fluid dynamics](https://mlsanity.com/paper/2211.00307/) (2022)
- [Machine-Learned Closure of URANS for Stably Stratified Turbulence: Connecting Physical Timescales & Data Hyperparameters of Deep Time-Series Models](https://mlsanity.com/paper/2404.16141/) (2024)
- [The balance between compactness and forecast accuracy of data-driven latent-space reduced-order models in controlled wake flows](https://mlsanity.com/paper/2607.24569/) (2026)
- [Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields](https://mlsanity.com/paper/2610.10430/) (2026)

## Abstract (arXiv)

In this paper, we present two deep learning-based hybrid data-driven reduced order models for the prediction of unsteady fluid flows. The first model projects the high-fidelity time series data from a finite element Navier-Stokes solver to a low-dimensional subspace via proper orthogonal decomposition (POD). The time-dependent coefficients in the POD subspace are propagated by the recurrent net (closed-loop encoder-decoder updates) and mapped to a high-dimensional state via the mean flow field and POD basis vectors. This model is referred as POD-RNN. The second model, referred to as convolution recurrent autoencoder network (CRAN), employs convolutional neural networks (CNN) as layers of linear kernels with nonlinear activations, to extract low-dimensional features from flow field snapshots. The flattened features are advanced using a recurrent (closed-loop manner) net and up-sampled (transpose convoluted) gradually to high-dimensional snapshots. Two benchmark problems of the flow past a cylinder and flow past a side-by-side cylinder are selected as the test problems to assess the efficacy of these models. For the problem of flow past a single cylinder, the performance of both the models is satisfactory, with CRAN being a bit overkill. However, it completely outperforms the POD-RNN model for a more complicated problem of flow past side-by-side cylinders. Owing to the scalability of CRAN, we briefly introduce an observer-corrector method for the calculation of integrated pressure force coefficients on the fluid-solid boundary on a reference grid. This reference grid, typically a structured and uniform grid, is used to interpolate scattered high-dimensional field data as snapshot images. These input images are convenient in training CRAN. This motivates us to further explore the application of CRAN models for the prediction of fluid flows.