Model reduction for nonlinear dynamical systems using deep convolutional autoencoders.

2019/11/15 by Kookjin Lee, Kevin T. Carlberg, Kevin Carlberg · 749 citations
Computer Science · Decision Sciences · Earth and Planetary Sciences · Engineering · Mathematics · Physics and Astronomy · #Algorithm #Applied mathematics #Artificial intelligence #Computer science #Dimensionality reduction #Galerkin method #Gaussian Processes and Bayesian Inference #Linear subspace #Manifold (fluid mechanics) #Mathematical analysis #Mathematics #Model Reduction and Neural Networks #Model order reduction #Nonlinear system #Nuclear reactor physics and engineering #Physics #Probabilistic and Robust Engineering Design #Projection (relational algebra) #Pure mathematics #Reduction (mathematics) #Seismic Imaging and Inversion Techniques #Subspace topology

paper · pdf · doi:10.1016/j.jcp.2019.108973

published in OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) 404, 108973 (Office of Scientific and Technical Information)

openalex publication_date 2023/07/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

Abstract

Abstract not provided.

Citations

• Principal component analysis in linear systems: Controllability, observability, and model reduction
• Analysis of a complex of statistical variables into principal components.
• Balanced Model Reduction via the Proper Orthogonal Decomposition
• Gradient-based learning applied to document recognition
• Coupling of substructures for dynamic analyses.

Cited by

• In-span learning: adapting reduced-order models using their own predictions
• A domain decomposition online-learning-enhanced nonlinear elimination preconditioner
• A Dynamical Approximation Scheme on the Stiefel manifold for Wasserstein Gradient Flows
• Surrogate-to-code verification of a non-intrusive POD-GPR machine-learning emulator of peak thermomechanical fields, with application to a carbon-carbon aircraft brake disc
• Hybrid coupling with operator inference and the overlapping Schwarz alternating method
• An Introduction to Sparse Identification of Nonlinear Dynamics for Engineering Applications
• ROM for Viscous, Incompressible Flow in Polygons -- exponential n-width bounds and convergence rate
• Extending Fourier Neural Operators for Modeling Parameterized and Coupled PDEs
• No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study
• A Riemannian View on Active Subspaces
• Variationally correct operator learning: Reduced basis neural operator with a posteriori error estimation
• Randomized time stepping of nonlinearly parametrized solutions of evolution problems
• Pattern recognition in complex systems via vector-field representations of spatio-temporal data
• Data-Driven Model Reduction using WeldNet: Windowed Encoders for Learning Dynamics
• Time Extrapolation with Graph Convolutional Autoencoder and Tensor Train Decomposition
• Reduced-Basis Deep Operator Learning for Parametric PDEs with Independently Varying Boundary and Source Data
• Nemytskii neural operator: a nonlinear model reduction method for parametrized partial differential equations
• Model order reduction via Lie groups
• In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularization
• Conditional neural field for spatial dimension reduction of turbulence data: a comparison study
• Learning Low Rank Neural Representations of Hyperbolic Wave Dynamics from Data
• EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale
• Sparse surface pressure-based reconstruction of the flow around a thick airfoil over a range of angles of attack
• A Review of Equation-Based and Data-Driven Reduced Order Models featuring a Hybrid cardiovascular application
• Progressive multi-fidelity learning with neural networks for physical system predictions
• Reservoir computing based predictive reduced order model for steel grade intermixing in an industrial continuous casting tundish
• Interpolated Adaptive Linear Reduced Order Modeling for Deformation Dynamics
• Model reduction of parametric ordinary differential equations via autoencoders: structure-preserving latent dynamics and convergence analysis
• Latent Twins
• Residual-Driven Lifting Identification for Nonlinear-Manifold Reduced-Order Models of Parametrized Linear PDEs
• Multiscale super-resolution reconstruction of fluid flows with deep neural networks
• Intrinsic Dimension Estimating Autoencoder (IDEA) Using CancelOut Layer and a Projected Loss
• DKFNet: Differentiable Kalman Filter for Field Inversion and Machine Learning
• Kernel manifolds: nonlinear-augmentation dimensionality reduction using reproducing kernel Hilbert spaces
• A hyperreduced manifold learning approach to nonlinear model order reduction for the homogenisation of hyperelastic RVEs
• Machine-precision energy conservative reduced models for Lagrangian hydrodynamics by quadrature methods
• A Dual Ensemble Kalman Filter Approach to Robust Control of Nonlinear Systems: An Application to Partial Differential Equations
• Blending data and physics for reduced-order modeling of systems with spatiotemporal chaotic dynamics
• Structure-Preserving Discretization and Model Reduction for Energy-Based Models
• Reduced-order modeling of large-scale turbulence using Koopman β-variational autoencoders
• RONOM: Reduced-Order Neural Operator Modeling
• An Improved Autoencoder Conjugacy Network to Learn Chaotic Maps
• Latent Space Dynamics Identification for Interface Tracking with Application to Shock-Induced Pore Collapse
• Thermodynamically Consistent Latent Dynamics Identification for Parametric Systems
• Meshless projection model-order reduction via reference spaces for smoothed-particle hydrodynamics
• Self-supervised Learning of Latent Space Dynamics
• A Discrete Empirical Interpolation Method for Interpretable Immersion and Embedding of Nonlinear Manifolds
• Learning Stochastic Multiscale Models
• ECLEIRS: Exact conservation law embedded identification of reduced states for parameterized partial differential equations from sparse and noisy data
• Reduced Particle in Cell method for the Vlasov-Poisson system using auto-encoder and Hamiltonian neural
• Quantized local reduced-order modeling in time (ql-ROM)
• Nonlinear Model Order Reduction of Dynamical Systems in Process Engineering: Review and Comparison
• Latent Representation Learning of Multi-scale Thermophysics: Application to Dynamics in Shocked Porous Energetic Material
• Interpretable and flexible non-intrusive reduced-order models using reproducing kernel Hilbert spaces
• Machine Learning-based quadratic closures for non-intrusive Reduced Order Models
• PLAID: A Unified Data Model for Machine Learning on Heterogeneous Physics Simulations
• Nonlinear model reduction on metric spaces. Application to one-dimensional conservative PDEs in Wasserstein spaces
• Defining Foundation Models for Computational Science: A Call for Clarity and Rigor
• Convex Neural Energy Elements: Monolithic Finite-Element Assembly of Geometry-Parameterized Neural Operators with Stability and Error Guarantees
• Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers
• FlowBERT: Prompt-tuned BERT for variable flow field prediction
• Adaptive and hybrid reduced order models to mitigate Kolmogorov barrier in a multiscale kinetic transport equation
• Good Things Come in Pairs: Paired Autoencoders for Inverse Problems
• On Geometry Regularization in Autoencoder Reduced-Order Models with Latent Neural ODE Dynamics
• Conformal risk control for model-form uncertainty in parametric non-intrusive reduced-order models
• Surrogate Trajectories Along Probability Flows: Pseudo Markovian Alternative to Mori Zwanzig
• A Goal-Oriented Adaptive Sampling Procedure for Projection-Based Reduced-Order Models with Hyperreduction
• Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition
• Modeling of dynamical systems through deep learning. [europepmc]
• POD-Enhanced Deep Learning-Based Reduced Order Models for the Real-Time Simulation of Cardiac Electrophysiology in the Left Atrium. [europepmc]
• Simulating progressive intramural damage leading to aortic dissection using DeepONet: an operator-regression neural network. [europepmc]
• Learning emergent partial differential equations in a learned emergent space. [europepmc]
• Data-driven prediction in dynamical systems: recent developments. [europepmc]
• Enhancing high-fidelity nonlinear solver with reduced order model. [europepmc]
• MR image reconstruction from undersampled data for image-guided radiation therapy using a patient-specific deep manifold image prior. [europepmc]
• Deep kernel learning of dynamical models from high-dimensional noisy data. [europepmc]
• Reduced Order Modeling of Nonlinear Vibrating Multiphysics Microstructures with Deep Learning-Based Approaches. [europepmc]
• Physics-informed neural ODE (PINODE): embedding physics into models using collocation points. [europepmc]
• Generative adversarial reduced order modelling. [europepmc]
• Learning the intrinsic dynamics of spatio-temporal processes through Latent Dynamics Networks. [europepmc]
• VpROM: a novel variational autoencoder-boosted reduced order model for the treatment of parametric dependencies in nonlinear systems. [europepmc]
• A reduced order model formulation for left atrium flow: an atrial fibrillation case. [europepmc]
• Reinforcement learning-based estimation for spatio-temporal systems. [europepmc]
• Calibration-Based ALE Model Order Reduction for Hyperbolic Problems with Self-Similar Travelling Discontinuities. [europepmc]
• Physics-informed two-tier neural network for non-linear model order reduction. [europepmc]
• Spatial-Frequency-Scale Variational Autoencoder for Enhanced Flow Diagnostics of Schlieren Data. [europepmc]
• A novel spatiotemporal decomposition and identification of sparse equations for human brain deformation. [europepmc]

Related

• Convolutional Autoencoders for Reduced-Order Modeling
• Model reduction of parametric ordinary differential equations via autoencoders: structure-preserving latent dynamics and convergence analysis
• Model reduction of dynamical systems on nonlinear manifolds using deep\n convolutional autoencoders
• Leveraging time and parameters for nonlinear model reduction methods
• Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems