A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder

Abstract

Traditional linear subspace reduced order models (LS-ROMs) are able to accelerate physical simulations, in which the intrinsic solution space falls into a subspace with a small dimension, i.e., the solution space has a small Kolmogorov n-width. However, for physical phenomena not of this type, e.g., any advection-dominated flow phenomena, such as in traffic flow, atmospheric flows, and air flow over vehicles, a low-dimensional linear subspace poorly approximates the solution. To address cases such as these, we have developed a fast and accurate physics-informed neural network ROM, namely nonlinear manifold ROM (NM-ROM), which can better approximate high-fidelity model solutions with a smaller latent space dimension than the LS-ROMs. Our method takes advantage of the existing numerical methods that are used to solve the corresponding full order models. The efficiency is achieved by developing a hyper-reduction technique in the context of the NM-ROM. Numerical results show that neural networks can learn a more efficient latent space representation on advection-dominated data from 1D and 2D Burgers' equations. A speedup of up to 2.6 for 1D Burgers' and a speedup of 11.7 for 2D Burgers' equations are achieved with an appropriate treatment of the nonlinear terms through a hyper-reduction technique. Finally, a posteriori error bounds for the NM-ROMs are derived that take account of the hyper-reduced operators.

33 pages, 17 figures

References in corpus (5)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Accelerating design optimization using reduced order models
• Depth separation for reduced deep networks in nonlinear model reduction: Distilling shock waves in nonlinear hyperbolic problems

Cited by in corpus (44)

• Enhancing Computational Fluid Dynamics with Machine Learning
• Multi-Objective Loss Balancing for Physics-Informed Deep Learning
• Operator inference for non-intrusive model reduction with quadratic manifolds
• LaSDI: Parametric Latent Space Dynamics Identification
• Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials
• Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions
• Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques
• Component-wise reduced order model lattice-type structure design
• Three-dimensional deep learning-based reduced order model for unsteady flow dynamics with variable Reynolds number
• Parametric Dynamic Mode Decomposition for Reduced Order Modeling
• SVD Perspectives for Augmenting DeepONet Flexibility and Interpretability
• Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks
• Neural Galerkin Schemes with Active Learning for High-Dimensional Evolution Equations
• gLaSDI: Parametric Physics-informed Greedy Latent Space Dynamics Identification
• Predictive Reduced Order Modeling of Chaotic Multi-scale Problems Using Adaptively Sampled Projections
• GPLaSDI: Gaussian Process-based Interpretable Latent Space Dynamics Identification through Deep Autoencoder
• Manifold embedding data-driven mechanics
• A fast and accurate domain-decomposition nonlinear manifold reduced order model
• Adaptive physics-informed neural operator for coarse-grained non-equilibrium flows
• Physics-informed cluster analysis and a priori efficiency criterion for the construction of local reduced-order bases
• S-OPT: A Points Selection Algorithm for Hyper-Reduction in Reduced Order Models
• Mapping of coherent structures in parameterized flows by learning optimal transportation with Gaussian models
• Adaptive sparse interpolation for accelerating nonlinear stochastic reduced-order modeling with time-dependent bases
• Bi-fidelity Variational Auto-encoder for Uncertainty Quantification
• Gappy AE: A Nonlinear Approach for Gappy Data Reconstruction using Auto-Encoder
• Damage Identification in Fiber Metal Laminates using Bayesian Analysis with Model Order Reduction
• Uncertainty quantification for industrial design using dictionaries of reduced order models
• Virtual twins of nonlinear vibrating multiphysics microstructures: physics-based versus deep learning-based approaches
• Deep learning for full-field ultrasonic characterization
• Simulation and Prediction of Countercurrent Spontaneous Imbibition at Early and Late Times Using Physics-Informed Neural Networks
• A physics-informed neural network method for the approximation of slow invariant manifolds for the general class of stiff systems of ODEs
• Transfer Learning as a Method to Reproduce High-Fidelity NLTE Opacities in Simulations
• Physics-informed active learning with simultaneous weak-form latent space dynamics identification
• A robust shifted proper orthogonal decomposition: Proximal methods for decomposing flows with multiple transports
• Controlling quantum many-body systems using reduced-order modelling
• Data-Driven Modeling of an Unsaturated Bentonite Buffer Model Test Under High Temperatures Using an Enhanced Axisymmetric Reproducing Kernel Particle Method
• Hamiltonian reduction using a convolutional auto-encoder coupled to an Hamiltonian neural network
• Matched Asymptotic Expansions-Based Transferable Neural Networks for Singular Perturbation Problems
• A Low Rank Neural Representation of Entropy Solutions
• A discrete physics-informed training for projection-based reduced order models with neural networks
• Interpretable and flexible non-intrusive reduced-order models using reproducing kernel Hilbert spaces
• System stabilization with policy optimization on unstable latent manifolds
• Real-Time Reconstruction of Ground Motion During Small Magnitude Earthquakes: A Pilot Study
• Projection-based model-order reduction via graph autoencoders suited for unstructured meshes