Lift \& learn: physics-informed machine learning for large-scale nonlinear dynamical systems
From MaRDI portal
Publication:2115511
DOI10.1016/J.PHYSD.2020.132401zbMATH Open1493.62512arXiv1912.08177OpenAlexW3008005432MaRDI QIDQ2115511FDOQ2115511
Authors: Elizabeth Qian, Boris Kramer, Benjamin Peherstorfer, Karen Willcox 
Publication date: 17 March 2022
Published in: Physica D (Search for Journal in Brave)
Abstract: We present Lift & Learn, a physics-informed method for learning low-dimensional models for large-scale dynamical systems. The method exploits knowledge of a system's governing equations to identify a coordinate transformation in which the system dynamics have quadratic structure. This transformation is called a lifting map because it often adds auxiliary variables to the system state. The lifting map is applied to data obtained by evaluating a model for the original nonlinear system. This lifted data is projected onto its leading principal components, and low-dimensional linear and quadratic matrix operators are fit to the lifted reduced data using a least-squares operator inference procedure. Analysis of our method shows that the Lift & Learn models are able to capture the system physics in the lifted coordinates at least as accurately as traditional intrusive model reduction approaches. This preservation of system physics makes the Lift & Learn models robust to changes in inputs. Numerical experiments on the FitzHugh-Nagumo neuron activation model and the compressible Euler equations demonstrate the generalizability of our model.
Full work available at URL: https://arxiv.org/abs/1912.08177
Recommendations
- Reduced operator inference for nonlinear partial differential equations
- Linearly recurrent autoencoder networks for learning dynamics
- Operator inference and physics-informed learning of low-dimensional models for incompressible flows
- Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
- Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference
dynamical systemspartial differential equationsdata-driven model reductionscientific machine learninglifting map
Non-Markovian processes: estimation (62M09) Semilinear parabolic equations (35K58) Topological and differentiable equivalence, conjugacy, moduli, classification of dynamical systems (37C15)
Cites Work
- Title not available (Why is that?)
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Dynamic mode decomposition of numerical and experimental data
- Spectral analysis of nonlinear flows
- Turbulence, Coherent Structures, Dynamical Systems and Symmetry
- Nonlinear model reduction via discrete empirical interpolation
- Stochastic resonance in neuron models
- Turbulence and the dynamics of coherent structures. I. Coherent structures
- Computability of global solutions to factorable nonconvex programs: Part I — Convex underestimating problems
- A kernel-based method for data-driven Koopman spectral analysis
- Dynamical Systems of Continuous Spectra
- A data-driven approximation of the koopman operator: extending dynamic mode decomposition
- A new finite element formulation for computational fluid dynamics. I: Symmetric forms of the compressible Euler and Navier-Stokes equations and the second law of thermodynamics
- Title not available (Why is that?)
- Data-driven operator inference for nonintrusive projection-based model reduction
- Minimal subspace rotation on the Stiefel manifold for stabilization and enhancement of projection-based reduced order models for the compressible Navier-Stokes equations
- Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
- Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator
- Kernel Methods for the Approximation of Nonlinear Systems
- Nonintrusive reduced-order modeling of parametrized time-dependent partial differential equations
- Two-Sided Projection Methods for Nonlinear Model Order Reduction
- Projection-based model reduction: formulations for physics-based machine learning
- $\mathcal H_2$-Quasi-Optimal Model Order Reduction for Quadratic-Bilinear Control Systems
- Data‐driven model order reduction of quadratic‐bilinear systems
- Extracting Sparse High-Dimensional Dynamics from Limited Data
Cited In (61)
- Reduced Operator Inference for Nonlinear Partial Differential Equations
- Data-driven model order reduction for problems with parameter-dependent jump-discontinuities
- Operator inference with roll outs for learning reduced models from scarce and low-quality data
- Predicting solar wind streams from the inner-heliosphere to Earth via shifted operator inference
- Parsimony as the ultimate regularizer for physics-informed machine learning
- On the role of nonlinear correlations in reduced-order modelling
- Data-driven modeling of linear dynamical systems with quadratic output in the AAA framework
- Stability Domains for Quadratic-Bilinear Reduced-Order Models
- Data-driven resolvent analysis
- Multiscale model reduction for incompressible flows
- LaSDI: parametric latent space dynamics identification
- Operator inference for non-intrusive model reduction with quadratic manifolds
- Hamiltonian operator inference: physics-preserving learning of reduced-order models for canonical Hamiltonian systems
- Operator inference and physics-informed learning of low-dimensional models for incompressible flows
- Bayesian operator inference for data-driven reduced-order modeling
- Discovery of Dynamics Using Linear Multistep Methods
- A data-driven, physics-informed framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings
- Model reduction and neural networks for parametric PDEs
- DRIPS: a framework for dimension reduction and interpolation in parameter space
- Model reduction for multi-scale transport problems using model-form preserving least-squares projections with variable transformation
- A fully adaptive nonintrusive reduced-order modelling approach for parametrized time-dependent problems
- Learning physics-based models from data: perspectives from inverse problems and model reduction
- Nonintrusive Reduced-Order Models for Parametric Partial Differential Equations via Data-Driven Operator Inference
- A New Artificial Neural Network Method for Solving Schrödinger Equations on Unbounded Domains
- Active Operator Inference for Learning Low-Dimensional Dynamical-System Models from Noisy Data
- Canonical and noncanonical Hamiltonian operator inference
- Observer normal form design for the nonlinear MIMO systems using coupled auxiliary dynamics
- Physics-informed regularization and structure preservation for learning stable reduced models from data with operator inference
- Dynamically learning the parameters of a chaotic system using partial observations
- Model reduction for stochastic systems with nonlinear drift
- Modern Koopman Theory for Dynamical Systems
- Operator inference of non-Markovian terms for learning reduced models from partially observed state trajectories
- Learning to Forecast Dynamical Systems from Streaming Data
- Probabilistic error estimation for non-intrusive reduced models learned from data of systems governed by linear parabolic partial differential equations
- Regression-Based Projection for Learning Mori–Zwanzig Operators
- Learning Markovian Homogenized Models in Viscoelasticity
- Output-weighted and relative entropy loss functions for deep learning precursors of extreme events
- SVD perspectives for augmenting DeepONet flexibility and interpretability
- Windowed space-time least-squares Petrov-Galerkin model order reduction for nonlinear dynamical systems
- gLaSDI: parametric physics-informed greedy latent space dynamics identification
- Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
- Non-intrusive data-driven model reduction for differential-algebraic equations derived from lifting transformations
- A structure-preserving neural differential operator with embedded Hamiltonian constraints for modeling structural dynamics
- Intrusive and data-driven reduced order modelling of the rotating thermal shallow water equation
- Bridging the gap: machine learning to resolve improperly modeled dynamics
- Reduced order modeling for parametrized generalized Newtonian fluid flows
- A physics-guided neural network framework for elastic plates: comparison of governing equations-based and energy-based approaches
- Physics-Informed Probabilistic Learning of Linear Embeddings of Nonlinear Dynamics with Guaranteed Stability
- A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems
- Structured interpolation for multivariate transfer functions of quadratic-bilinear systems
- Generalized quadratic embeddings for nonlinear dynamics using deep learning
- Operator learning using random features: a tool for scientific computing
- CGNSDE: conditional Gaussian neural stochastic differential equation for modeling complex systems and data assimilation
- Model reduction on manifolds: a differential geometric framework
- Nonlinear embeddings for conserving Hamiltonians and other quantities with neural Galerkin schemes
- Physics-informed ConvNet: learning physical field from a shallow neural network
- Structured barycentric forms for interpolation-based data-driven reduced modeling of second-order systems
- System stabilization with policy optimization on unstable latent manifolds
- Learning quantities of interest from parametric PDEs: an efficient neural-weighted minimal residual approach
- Learning physics-based reduced-order models from data using nonlinear manifolds
- Preserving Lagrangian structure in data-driven reduced-order modeling of large-scale dynamical systems
This page was built for publication: Lift \& learn: physics-informed machine learning for large-scale nonlinear dynamical systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2115511)
