CD-ROM: Complemented Deep-Reduced Order Model
arXiv:2202.10746 · doi:10.1016/j.cma.2023.115985
Abstract
Model order reduction through the POD-Galerkin method can lead to dramatic gains in terms of computational efficiency in solving physical problems. However, the applicability of the method to non linear high-dimensional dynamical systems such as the Navier-Stokes equations has been shown to be limited, producing inaccurate and sometimes unstable models. This paper proposes a deep learning based closure modeling approach for classical POD-Galerkin reduced order models (ROM). The proposed approach is theoretically grounded, using neural networks to approximate well studied operators. In contrast with most previous works, the present CD-ROM approach is based on an interpretable continuous memory formulation, derived from simple hypotheses on the behavior of partially observed dynamical systems. The final corrected models can hence be simulated using most classical time stepping schemes. The capabilities of the CD-ROM approach are demonstrated on two classical examples from Computational Fluid Dynamics, as well as a parametric case, the Kuramoto-Sivashinsky equation.
References in corpus (22)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Machine Learning for Fluid Mechanics
- DGM: A deep learning algorithm for solving partial differential equations
- A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
- A unified deep artificial neural network approach to partial differential equations in complex geometries
- Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator
- Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
- Stable Architectures for Deep Neural Networks
- Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
- Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
- Cluster-based reduced-order modelling of a mixing layer
- Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flows
- A deep learning enabler for non-intrusive reduced order modeling of fluid flows
- Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
- On closures for reduced order models A spectrum of first-principle to machine-learned avenues
- Time-series learning of latent-space dynamics for reduced-order model closure
- Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
- Data-driven recovery of hidden physics in reduced order modeling of fluid flows
- Physics-Informed Echo State Networks
- Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
- Route to Chaos in the Fluidic Pinball