Data-driven discovery of closure models
From MaRDI portal
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.
Recommendations
- Bayesian operator inference for data-driven reduced-order modeling
- Data-driven closures for stochastic dynamical systems
- Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference
- Data-driven operator inference for nonintrusive projection-based model reduction
- Neural network closures for nonlinear model order reduction
Cites work
- \textit{A priori} estimation of memory effects in reduced-order models of nonlinear systems using the Mori-Zwanzig formalism
- A data-driven approximation of the koopman operator: extending dynamic mode decomposition
- A dynamic subgrid-scale eddy viscosity model
- A manifold learning approach to data-driven computational elasticity and inelasticity
- A paradigm for data-driven predictive modeling using field inversion and machine learning
- An approach to micro-macro modeling of heterogeneous materials
- An approximate deconvolution model for large-eddy simulation with application to incompressible wall-bounded flows
- Calibrated reduced-order POD-Galerkin system for fluid flow modelling
- Certified real‐time solution of the parametrized steady incompressible Navier–Stokes equations: rigorous reduced‐basis a posteriori error bounds
- Data-Driven Filtered Reduced Order Modeling of Fluid Flows
- Data-driven operator inference for nonintrusive projection-based model reduction
- Deep learning
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Dynamic mode decomposition of numerical and experimental data
- Estimating the uncertainty in underresolved nonlinear dynamics
- Experimental design for nonparametric correction of misspecified dynamical models
- False discoveries occur early on the Lasso path
- scientific article; zbMATH DE number 3810550 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Large Eddy Simulation for Incompressible Flows
- Learning-based robust stabilization for reduced-order models of 2D and 3D Boussinesq equations
- Modeling nonlinear dynamics and chaos: a review
- Multilayer feedforward networks are universal approximators
- Multiscale Methods
- Nonlinear system identification. NARMAX methods in the time, frequency, and spatio-temporal domains
- Optimal prediction with memory
- Prediction of Chaotic Time Series Based on the Recurrent Predictor Neural Network
- Reduced basis approximation and error bounds for potential flows in parametrized geometries
- Scikit-learn: machine learning in Python
- Synthesis of recurrent neural networks for dynamical system simulation
- The GNAT method for nonlinear model reduction: effective implementation and application to computational fluid dynamics and turbulent flows
- The Lasso problem and uniqueness
- The variational multiscale method -- a paradigm for computational mechanics
- Turbulence, coherent structures, dynamical systems and symmetry.
Cited in
(40)- Data-driven non-Markovian closure models
- Data-driven closures for stochastic dynamical systems
- Operator inference of non-Markovian terms for learning reduced models from partially observed state trajectories
- Error bounds of the invariant statistics in machine learning of ergodic Itô diffusions
- Kernel-based prediction of non-Markovian time series
- Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
- Machine learning for prediction with missing dynamics
- Physics-informed machine learning for backbone identification in discrete fracture networks
- Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
- Machine learning closures for model order reduction of thermal fluids
- Commutation error in reduced order modeling of fluid flows
- Physics-informed regularization and structure preservation for learning stable reduced models from data with operator inference
- Bayesian operator inference for data-driven reduced-order modeling
- Operator inference for non-intrusive model reduction with quadratic manifolds
- \textit{A priori} estimation of memory effects in reduced-order models of nonlinear systems using the Mori-Zwanzig formalism
- Physics-Informed Probabilistic Learning of Linear Embeddings of Nonlinear Dynamics with Guaranteed Stability
- On the structure of time-delay embedding in linear models of non-linear dynamical systems
- Model reduction for transport-dominated problems via online adaptive bases and adaptive sampling
- Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference
- Discovery of dynamics using linear multistep methods
- Optimal closures in a simple model for turbulent flows
- On the role of nonlinear correlations in reduced-order modelling
- A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems
- Physics-agnostic and physics-infused machine learning for thin films flows: modelling, and predictions from small data
- Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling
- Comparison of neural closure models for discretised PDEs
- Learning black- and gray-box chemotactic PDEs/closures from agent based Monte Carlo simulation data
- A multifidelity deep operator network approach to closure for multiscale systems
- Quantum Mechanics for Closure of Dynamical Systems
- Differentiable hybrid neural modeling for fluid-structure interaction
- Data-driven Whitney forms for structure-preserving control volume analysis
- Memory-based parameterization with differentiable solver: application to Lorenz '96
- Learning physics-based reduced-order models from data using nonlinear manifolds
- Regularized least absolute deviation-based sparse identification of dynamical systems
- Solving continuum and rarefied flows using differentiable programming
- Systematic construction of continuous-time neural networks for linear dynamical systems
- Neural closure models for dynamical systems
- Scientific machine learning for closure models in multiscale problems: a review
- Greedy construction of quadratic manifolds for nonlinear dimensionality reduction and nonlinear model reduction
- Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism
This page was built for publication: Data-driven discovery of closure models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4562411)
