Physics-constrained, data-driven discovery of coarse-grained dynamics
From MaRDI portal
Abstract: The combination of high-dimensionality and disparity of time scales encountered in many problems in computational physics has motivated the development of coarse-grained (CG) models. In this paper, we advocate the paradigm of data-driven discovery for extract- ing governing equations by employing fine-scale simulation data. In particular, we cast the coarse-graining process under a probabilistic state-space model where the transition law dic- tates the evolution of the CG state variables and the emission law the coarse-to-fine map. The directed probabilistic graphical model implied, suggests that given values for the fine- grained (FG) variables, probabilistic inference tools must be employed to identify the cor- responding values for the CG states and to that end, we employ Stochastic Variational In- ference. We advocate a sparse Bayesian learning perspective which avoids overfitting and reveals the most salient features in the CG evolution law. The formulation adopted enables the quantification of a crucial, and often neglected, component in the CG process, i.e. the pre- dictive uncertainty due to information loss. Furthermore, it is capable of reconstructing the evolution of the full, fine-scale system. We demonstrate the efficacy of the proposed frame- work in high-dimensional systems of random walkers.
Recommendations
- A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the small data regime
- Predictive coarse-graining
- Data-driven discovery of coordinates and governing equations
- Scalable Bayesian reduced-order models for simulating high-dimensional multiscale dynamical systems
- A new framework for extracting coarse-grained models from time series with multiscale structure
Cites work
- A coarse-grained molecular dynamics model for crystalline solids
- A probabilistic graphical model approach to stochastic multiscale partial differential equations
- A Stochastic Approximation Method
- Advanced Lectures on Machine Learning
- ATLAS: a geometric approach to learning high-dimensional stochastic systems near manifolds
- Convergence of a Random Walk Method for the Burgers Equation
- Data-driven non-Markovian closure models
- Data-driven parameterization of the generalized Langevin equation
- Deciding the Nature of the Coarse Equation through Microscopic Simulations: The Baby-Bathwater Scheme
- Deep hidden physics models: deep learning of nonlinear partial differential equations
- Deep Potential: A General Representation of a Many-Body Potential Energy Surface
- Diffusion maps, spectral clustering and reaction coordinates of dynamical systems
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Effective dynamics using conditional expectations
- Equation-free analysis of agent-based models and systematic parameter determination
- Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
- Extracting macroscopic dynamics: model problems and algorithms
- Free energy computations by minimization of Kullback-Leibler divergence: An efficient adaptive biasing potential method for sparse representations
- Graphical models, exponential families, and variational inference
- Heterogeneous multiscale methods: a review
- Hidden physics models: machine learning of nonlinear partial differential equations
- scientific article; zbMATH DE number 6377992 (Why is no real title available?)
- scientific article; zbMATH DE number 5885079 (Why is no real title available?)
- scientific article; zbMATH DE number 3896009 (Why is no real title available?)
- scientific article; zbMATH DE number 107482 (Why is no real title available?)
- scientific article; zbMATH DE number 3567782 (Why is no real title available?)
- scientific article; zbMATH DE number 1222290 (Why is no real title available?)
- scientific article; zbMATH DE number 1222291 (Why is no real title available?)
- scientific article; zbMATH DE number 711262 (Why is no real title available?)
- Inference in hidden Markov models.
- Information loss in coarse-graining of stochastic particle dynamics
- Learning partial differential equations via data discovery and sparse optimization
- Machine learning. A probabilistic perspective
- Normal forms for reduced stochastic climate models
- On a Measure of the Information Provided by an Experiment
- On a Minimum Property of the Free Energy
- Optimal prediction and the Mori–Zwanzig representation of irreversible processes
- Particle methods for dispersive equations
- Path-space variational inference for non-equilibrium coarse-grained systems
- Pattern recognition and machine learning.
- Physics constrained nonlinear regression models for time series
- Predictive coarse-graining
- Probabilistic Principal Component Analysis
- Probable networks and plausible predictions — a review of practical Bayesian methods for supervised neural networks
- Problem reduction, renormalization, and memory
- Reduced-space Gaussian process regression for data-driven probabilistic forecast of chaotic dynamical systems
- Renormalized Mori–Zwanzig-reduced models for systems without scale separation
- Sequential Monte Carlo Samplers
- Sparse Bayesian Learning for Basis Selection
- Sparse dynamics for partial differential equations
- Statistical field theory. With a foreword by David Pines
- Stochastic tools in mathematics and science
- Toward a unified theory of efficient, predictive, and sparse coding
- Transport, Collective Motion, and Brownian Motion
- Vortex Methods
Cited in
(12)- Predictive coarse-graining
- Data-driven stochastic modeling of coarse-grained dynamics with finite-size effects using Langevin regression
- A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables
- Data-driven discovery of coarse-grained equations
- Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
- Variational framework for distance-minimizing method in data-driven computational mechanics
- A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the small data regime
- Scalable Bayesian reduced-order models for simulating high-dimensional multiscale dynamical systems
- Construction of coarse-grained models by reproducing equilibrium probability density function
- Data-driven discovery of governing equations for fluid dynamics based on molecular simulation
- Data-Driven Discovery of Governing Equations for Coarse-Grained Heterogeneous Network Dynamics
- A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty
This page was built for publication: Physics-constrained, data-driven discovery of coarse-grained dynamics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5161415)
