Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems

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.

References in corpus (5)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator
• Nonlinear Model Order Reduction via Lifting Transformations and Proper Orthogonal Decomposition
• Minimal subspace rotation on the Stiefel manifold for stabilization and enhancement of projection-based reduced order models for the compressible Navier-Stokes equations

Cited by in corpus (68)

• Enhancing Computational Fluid Dynamics with Machine Learning
• A Physics-Guided Neural Network Framework for Elastic Plates: Comparison of Governing Equations-Based and Energy-Based Approaches
• PySINDy: A comprehensive Python package for robust sparse system identification
• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Data-driven reduced-order models via regularized operator inference for a single-injector combustion process
• Physics guided machine learning using simplified theories
• Operator inference for non-intrusive model reduction with quadratic manifolds
• Data-driven resolvent analysis
• LaSDI: Parametric Latent Space Dynamics Identification
• Kernel Learning for Robust Dynamic Mode Decomposition: Linear and Nonlinear Disambiguation Optimization (LANDO)
• On the role of nonlinear correlations in reduced-order modeling
• Simulating progressive intramural damage leading to aortic dissection using an operator-regression neural network
• SVD Perspectives for Augmenting DeepONet Flexibility and Interpretability
• Asset management, condition monitoring and Digital Twins: damage detection and virtual inspection on a reinforced concrete bridge
• Bayesian operator inference for data-driven reduced-order modeling
• Non-intrusive reduced-order models for parametric partial differential equations via data-driven operator inference
• Neural Galerkin Schemes with Active Learning for High-Dimensional Evolution Equations
• gLaSDI: Parametric Physics-informed Greedy Latent Space Dynamics Identification
• A Novel Physics-Regularized Interpretable Machine Learning Model for Grain Growth
• Neural modal ordinary differential equations: Integrating physics-based modeling with neural ordinary differential equations for modeling high-dimensional monitored structures
• PySINDy: A Python package for the Sparse Identification of Nonlinear Dynamics from Data
• On analytical construction of observable functions in extended dynamic mode decomposition for nonlinear estimation and prediction
• Vehicular Applications of Koopman Operator Theory -- A Survey
• A DeepONet multi-fidelity approach for residual learning in reduced order modeling
• Identification of MIMO Wiener-type Koopman Models for Data-Driven Model Reduction using Deep Learning
• Predicting Solar Wind Streams from the Inner-Heliosphere to Earth via Shifted Operator Inference
• Lagrangian operator inference enhanced with structure-preserving machine learning for nonintrusive model reduction of mechanical systems
• Operator Learning Using Random Features: A Tool for Scientific Computing
• Parameter Estimation with Dense and Convolutional Neural Networks Applied to the FitzHugh-Nagumo ODE
• Solving multiphysics-based inverse problems with learned surrogates and constraints
• Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
• Scientific Machine Learning Based Reduced-Order Models for Plasma Turbulence Simulations
• Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
• Domain decomposition for data-driven reduced modeling of large-scale systems
• CGNSDE: Conditional Gaussian Neural Stochastic Differential Equation for Modeling Complex Systems and Data Assimilation
• Data-driven Discovery of Delay Differential Equations with Discrete Delays
• Distributed computing for physics-based data-driven reduced modeling at scale: Application to a rotating detonation rocket engine
• Data-Driven Control of Nonlinear Systems: Beyond Polynomial Dynamics
• Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows
• Discovery of Dynamics Using Linear Multistep Methods
• Physics-informed active learning with simultaneous weak-form latent space dynamics identification
• Promoting global stability in data-driven models of quadratic nonlinear dynamics
• Learning a Reduced Basis of Dynamical Systems using an Autoencoder
• Learning quantities of interest from parametric PDEs: An efficient neural-weighted Minimal Residual approach
• A generative adversarial network optimization method for damage detection and digital twinning by deep AI fault learning: Z24 Bridge structural health monitoring benchmark validation
• LQResNet: A Deep Neural Network Architecture for Learning Dynamic Processes
• Energy preserving reduced-order modelling of thermal shallow water equation
• An Extensible Benchmark Suite for Learning to Simulate Physical Systems
• Structured barycentric forms for interpolation-based data-driven reduced modeling of second-order systems
• Improve Unscented Kalman Inversion With Low-Rank Approximation and Reduced-Order Model
• Bayesian learning with Gaussian processes for low-dimensional representations of time-dependent nonlinear systems
• One-shot learning for solution operators of partial differential equations
• Energy-Preserving Reduced Operator Inference for Efficient Design and Control
• Extending the trapping theorem to provide local stability guarantees for quadratically nonlinear models
• Windowed space-time least-squares Petrov-Galerkin method for nonlinear model order reduction
• Structured interpolation for multivariate transfer functions of quadratic-bilinear systems
• Learning reduced order models from data for hyperbolic PDEs
• Stable Sparse Operator Inference for Nonlinear Structural Dynamics
• Interpretable and flexible non-intrusive reduced-order models using reproducing kernel Hilbert spaces
• A Differentiable Solver Approach to Operator Inference
• Block-structured Operator Inference for coupled multiphysics model reduction
• Learning Low-Dimensional Quadratic-Embeddings of High-Fidelity Nonlinear Dynamics using Deep Learning
• System stabilization with policy optimization on unstable latent manifolds
• Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems
• A parallel implementation of reduced-order modeling of large-scale systems
• Hyper-reduction-free reduced-order Newton solvers for projection-based model-order reduction of nonlinear dynamical systems
• Data-driven modeling of power networks
• Projection-based model-order reduction via graph autoencoders suited for unstructured meshes