Data-driven Discovery of Closure Models

Abstract

Derivation of reduced order representations of dynamical systems requires the modeling of the truncated dynamics on the retained dynamics. In its most general form, this so-called closure model has to account for memory effects. In this work, we present a framework of operator inference to extract the governing dynamics of closure from data in a compact, non-Markovian form. We employ sparse polynomial regression and artificial neural networks to extract the underlying operator. For a special class of non-linear systems, observability of the closure in terms of the resolved dynamics is analyzed and theoretical results are presented on the compactness of the memory. The proposed framework is evaluated on examples consisting of linear to nonlinear systems with and without chaotic dynamics, with an emphasis on predictive performance on unseen data.

arXiv comment33 pages

References in corpus (3)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• The GNAT method for nonlinear model reduction: effective implementation and application to computational fluid dynamics and turbulent flows

Cited by in corpus (26)

• Turbulence Modeling in the Age of Data
• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Robust learning from noisy, incomplete, high-dimensional experimental data via physically constrained symbolic regression
• Operator inference for non-intrusive model reduction with quadratic manifolds
• Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
• Deconvolutional artificial neural network models for large eddy simulation of turbulence
• On the Structure of Time-delay Embedding in Linear Models of Non-linear Dynamical Systems
• Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning
• Machine Learning for Prediction with Missing Dynamics
• On the role of nonlinear correlations in reduced-order modeling
• OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle
• Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
• Kernel-based Prediction of Non-Markovian Time Series
• Probing non-Markovian quantum dynamics with data-driven analysis: Beyond "black-box" machine learning models
• A Levenberg-Marquardt algorithm for sparse identification of dynamical systems
• Neural Closure Models for Dynamical Systems
• A Multifidelity deep operator network approach to closure for multiscale systems
• Data-driven model reduction for stochastic Burgers equations
• Physics-agnostic and Physics-infused machine learning for thin films flows: modeling, and predictions from small data
• Black and Gray Box Learning of Amplitude Equations: Application to Phase Field Systems
• Promoting global stability in data-driven models of quadratic nonlinear dynamics
• Non-intrusive Balancing Transformation of Highly Stiff Systems with Lightly-damped Impulse Response
• Optimal Closures in a Simple Model for Turbulent Flows
• Data-driven Selection of Coarse-Grained Models of Coupled Oscillators
• Solving continuum and rarefied flows using differentiable programming
• Error Bounds of the Invariant Statistics in Machine Learning of Ergodic Itô Diffusions