Learning reduced order models from data for hyperbolic PDEs
@article{Sarna2021LearningRO, title={Learning reduced order models from data for hyperbolic PDEs}, author={Neeraj Sarna and Peter Benner}, journal={ArXiv}, year={2021}, volume={abs/2109.06156} }
Given a set of solution snapshots of a hyperbolic PDE, we are interested in learning a reduced order model (ROM). To this end, we propose a novel decompose then learn approach. We decompose the solution by expressing it as a composition of a transformed solution and a de-transformer. Our idea is to learn a ROM for both these objects, which, unlike the solution, are well approximable in a linear reduced space. A ROM for the (untransformed) solution is then recovered via a recomposition. The…
Figures from this paper
References
SHOWING 1-10 OF 69 REFERENCES
A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
- Computer ScienceJ. Sci. Comput.
- 2021
Numerical results indicate that DL-ROMs whose dimension is equal to the intrinsic dimensionality of the PDE solutions manifold are able to efficiently approximate the solution of parametrized PDEs, especially in cases for which a huge number of POD modes would have been necessary to achieve the same degree of accuracy.
A Deep Learning approach to Reduced Order Modelling of Parameter Dependent Partial Differential Equations
- Computer ScienceArXiv
- 2021
Within the framework of parameter dependent PDEs, this work develops a constructive approach based on Deep Neural Networks for the efficient approximation of the parameter-to-solution map, based on a nonlinear version of the Kolmogorov n-width over which to base the concept of a minimal latent dimension.
Randomized dynamic mode decomposition for nonintrusive reduced order modelling
- Engineering, Mathematics
- 2016
This paper focuses on a new framework for obtaining a nonintrusive reduced order model for two‐dimensional fluid problems by developing a novel technique on the basis of randomized dynamic mode decomposition (DMD) as a fast and accurate option in model order reduction.
Data-Driven Snapshot Calibration via Monotonic Feature Matching
- Computer ScienceArXiv
- 2020
This work develops on the idea of inducing a faster singular value decay by computing snapshots on a transformed spatial domain, or the so-called snapshot calibration/transformation, and proposes a realizable algorithm to compute the spatial transform using monotonic feature matching.
Data-driven reduced order modeling for time-dependent problems
- Computer ScienceComputer Methods in Applied Mechanics and Engineering
- 2019
$h$ and $hp$-adaptive Interpolation by Transformed Snapshots for Parametric and Stochastic Hyperbolic PDEs
- Computer Science
- 2017
This paper explores $h and $hp$-adaptive methods to resolve local refinements of parametric or stochastic hyperbolic PDEs, and introduces an alternative "tensorized" adaption method.
Efficient nonlinear manifold reduced order model
- Computer ScienceArXiv
- 2020
An efficient nonlinear manifold ROM (NM-ROM) is developed, which can better approximate high-fidelity model solutions with a smaller latent space dimension than the LS-ROMs and shows that neural networks can learn a more efficient latent space representation on advection-dominated data from 2D Burgers' equations with a high Reynolds number.
Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Computer ScienceJ. Comput. Phys.
- 2020
Nonlinear Model Order Reduction via Dynamic Mode Decomposition
- MathematicsSIAM J. Sci. Comput.
- 2017
The use of the recently developed Dynamic Mode Decomposition (DMD), an equation-free method, to approximate the nonlinear term is advocated and a suite of numerical tests are presented to show the effectiveness of the method in comparison to existing approaches.
Physics-aware registration based auto-encoder for convection dominated PDEs
- Computer ScienceArXiv
- 2020
A physics-aware auto-encoder to specifically reduce the dimensionality of solutions arising from convection-dominated nonlinear physical systems and demonstrates the efficacy and interpretability of the approach to separate convection/advection from diffusion/scaling on various manufactured and physical systems.