Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems

Abstract

Data-based discovery of effective, coarse-grained (CG) models of high-dimensional dynamical systems presents a unique challenge in computational physics and particularly in the context of multiscale problems. The present paper offers a data-based, probablistic perspective that enables the quantification of predictive uncertainties. One of the outstanding problems has been the introduction of physical constraints in the probabilistic machine learning objectives. The primary utility of such constraints stems from the undisputed physical laws such as conservation of mass, energy etc. that they represent. Furthermore and apart from leading to physically realistic predictions, they can significantly reduce the requisite amount of training data which for high-dimensional, multiscale systems are expensive to obtain (Small Data regime). We formulate the coarse-graining process by employing a probabilistic state-space model and account for the aforementioned equality constraints as virtual observables in the associated densities. We demonstrate how probabilistic inference tools can be employed to identify the coarse-grained variables in combination with deep neural nets and their evolution model without ever needing to define a fine-to-coarse (restriction) projection and without needing time-derivatives of state variables. Furthermore, it is capable of reconstructing the evolution of the full, fine-scale system and therefore the observables of interest need not be selected a priori. We demonstrate the efficacy of the proposed framework by applying it to systems of interacting particles and an image-series of a nonlinear pendulum.

References in corpus (29)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Data-driven discovery of coordinates and governing equations
• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control
• Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
• Variational Relevance Vector Machines
• Data-driven model reduction and transfer operator approximation
• Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (2000)
• Data-driven parameterization of the generalized Langevin equation
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• Data-driven non-Markovian closure models
• Equation-Free Multiscale Computation: enabling microscopic simulators to perform system-level tasks
• A State Space Approach for Piecewise-Linear Recurrent Neural Networks for Reconstructing Nonlinear Dynamics from Neural Measurements
• Information-theoretic tools for parametrized coarse-graining of non-equilibrium extended systems
• Variational approach for learning Markov processes from time series data
• Path-space variational inference for non-equilibrium coarse-grained systems
• Deep Generative Markov State Models
• A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the Small Data regime
• Predictive Coarse-Graining
• Learning interpretable continuous-time models of latent stochastic dynamical systems
• Bayesian model and dimension reduction for uncertainty propagation: applications in random media
• Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networks
• On the estimation of the Mori-Zwanzig memory integral
• Nonparametric model reconstruction for stochastic differential equation from discretely observed time-series data

Cited by in corpus (9)

• Fully probabilistic deep models for forward and inverse problems in parametric PDEs
• A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables
• Generative Learning of the Solution of Parametric Partial Differential Equations Using Guided Diffusion Models and Virtual Observations
• Physics-Aware Neural Implicit Solvers for multiscale, parametric PDEs with applications in heterogeneous media
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
• Physics-aware, probabilistic model order reduction with guaranteed stability
• Physics-enhanced Neural Networks in the Small Data Regime
• Numerical analysis of non-local calculus on finite weighted graphs, with application to reduced-order modelling of dynamical systems
• Reinforcement Learning Closures for Underresolved Partial Differential Equations using Synthetic Data