Learning proper orthogonal decomposition of complex dynamics using heavy-ball neural ODEs
From MaRDI portal
Publication:6101554
DOI10.1007/S10915-023-02176-8zbMATH Open1515.65255arXiv2202.12373OpenAlexW4362560979MaRDI QIDQ6101554FDOQ6101554
Akil C. Narayan, Bao Wang, Justin Baker, Elena Cherkaev
Publication date: 20 June 2023
Published in: Journal of Scientific Computing (Search for Journal in Brave)
Abstract: Proper orthogonal decomposition (POD) allows reduced-order modeling of complex dynamical systems at a substantial level, while maintaining a high degree of accuracy in modeling the underlying dynamical systems. Advances in machine learning algorithms enable learning POD-based dynamics from data and making accurate and fast predictions of dynamical systems. In this paper, we leverage the recently proposed heavy-ball neural ODEs (HBNODEs) [Xia et al. NeurIPS, 2021] for learning data-driven reduced-order models (ROMs) in the POD context, in particular, for learning dynamics of time-varying coefficients generated by the POD analysis on training snapshots generated from solving full order models. HBNODE enjoys several practical advantages for learning POD-based ROMs with theoretical guarantees, including 1) HBNODE can learn long-term dependencies effectively from sequential observations and 2) HBNODE is computationally efficient in both training and testing. We compare HBNODE with other popular ROMs on several complex dynamical systems, including the von K'{a}rm'{a}n Street flow, the Kurganov-Petrova-Popov equation, and the one-dimensional Euler equations for fluids modeling.
Full work available at URL: https://arxiv.org/abs/2202.12373
Artificial neural networks and deep learning (68T07) Spectral, collocation and related methods for initial value and initial-boundary value problems involving PDEs (65M70) Numerical problems in dynamical systems (65P99)
Cites Work
- Title not available (Why is that?)
- On Upstream Differencing and Godunov-Type Schemes for Hyperbolic Conservation Laws
- Dynamic mode decomposition of numerical and experimental data
- Nonlinear analysis of hydrodynamic instability in laminar flames—I. Derivation of basic equations
- Approximation of Large-Scale Dynamical Systems
- A family of embedded Runge-Kutta formulae
- A dynamic subgrid-scale eddy viscosity model
- A survey of projection-based model reduction methods for parametric dynamical systems
- Interpolatory Model Reduction of Large-Scale Dynamical Systems
- Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
- A Survey of Model Reduction by Balanced Truncation and Some New Results
- DIRECT NUMERICAL SIMULATION: A Tool in Turbulence Research
- On Flame Propagation Under Conditions of Stoichiometry
- Some methods of speeding up the convergence of iteration methods
- Proper orthogonal decomposition and its applications-part. I: Theory
- Adaptive Semidiscrete Central-Upwind Schemes for Nonconvex Hyperbolic Conservation Laws
- A dynamic global-coefficient subgrid-scale eddy-viscosity model for large-eddy simulation in complex geometries
- Neural network closures for nonlinear model order reduction
- Machine learning closures for model order reduction of thermal fluids
- An artificial neural network framework for reduced order modeling of transient flows
- Construction of reduced-order models for fluid flows using deep feedforward neural networks
- Data-driven correction reduced order models for the quasi-geostrophic equations: a numerical investigation
- How does momentum benefit deep neural networks architecture design? A few case studies
- Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent
- Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
Recommendations
- Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations 👍 👎
- POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition 👍 👎
- NeuralPDE: modelling dynamical systems from data 👍 👎
- The neural network shifted-proper orthogonal decomposition: a machine learning approach for non-linear reduction of hyperbolic equations 👍 👎
- Deep learning nonlinear multiscale dynamic problems using Koopman operator 👍 👎
- Solving flows of dynamical systems by deep neural networks and a novel deep learning algorithm 👍 👎
- Stochastic physics-informed neural ordinary differential equations 👍 👎
- FROM STANDARD APPROACH TO ODE NEURAL NETWORKS 👍 👎
- Realization theory of recurrent neural ODEs using polynomial system embeddings 👍 👎
This page was built for publication: Learning proper orthogonal decomposition of complex dynamics using heavy-ball neural ODEs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6101554)
