Image Inversion and Uncertainty Quantification for Constitutive Laws of Pattern Formation

Abstract

The forward problems of pattern formation have been greatly empowered by extensive theoretical studies and simulations, however, the inverse problem is less well understood. It remains unclear how accurately one can use images of pattern formation to learn the functional forms of the nonlinear and nonlocal constitutive relations in the governing equation. We use PDE-constrained optimization to infer the governing dynamics and constitutive relations and use Bayesian inference and linearization to quantify their uncertainties in different systems, operating conditions, and imaging conditions. We discuss the conditions to reduce the uncertainty of the inferred functions and the correlation between them, such as state-dependent free energy and reaction kinetics (or diffusivity). We present the inversion algorithm and illustrate its robustness and uncertainties under limited spatiotemporal resolution, unknown boundary conditions, blurry initial conditions, and other non-ideal situations. Under certain situations, prior physical knowledge can be included to constrain the result. Phase-field, reaction-diffusion, and phase-field-crystal models are used as model systems. The approach developed here can find applications in inferring unknown physical properties of complex pattern-forming systems and in guiding their experimental design.

References in corpus (34)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Complex Patterns in a Simple System
• Meso-scale turbulence in living fluids
• Data-driven computational mechanics
• Theory of Chemical Kinetics and Charge Transfer based on Nonequilibrium Thermodynamics
• Fluid dynamics of bacterial turbulence
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• Suppression of Phase Separation in LiFePO4 Nanoparticles During Battery Discharge
• Hamiltonian Neural Networks
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Coherency strain and the kinetics of phase separation in LiFePO4
• Phase-field-crystal models for condensed matter dynamics on atomic length and diffusive time scales: an overview
• Free energy functionals for efficient phase field crystal modeling of structural phase transformations
• Dimension-independent likelihood-informed MCMC
• Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks
• Learning Constitutive Relations using Symmetric Positive Definite Neural Networks
• Thermodynamic Stability of Driven Open Systems and Control of Phase Separation by Electro-autocatalysis
• Inverse Uncertainty Quantification using the Modular Bayesian Approach based on Gaussian Process, Part 1: Theory
• Adaptive multi-fidelity polynomial chaos approach to Bayesian inference in inverse problems
• A self-driven phase transition drives Myxococcus xanthus fruiting body formation
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• Variational system identification of the partial differential equations governing pattern-forming physics: Inference under varying fidelity and noise
• Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
• Lagrangian Neural Networks
• A comparative study of physics-informed neural network models for learning unknown dynamics and constitutive relations
• Population dynamics of driven autocatalytic reactive mixtures
• Tuning the stability of Electrochemical Interfaces by Electron Transfer reactions
• Optimal Reconstruction of Material Properties in Complex Multiphysics Phenomena
• Bayesian parameter identification in Cahn-Hilliard models for biological growth
• Bayesian Uncertainty Quantification in Inverse Modelling of Electrochemical Systems
• Stability selection enables robust learning of partial differential equations from limited noisy data

Cited by in corpus (7)

• Correlative image learning of chemo-mechanics in phase-transforming solids
• Perspective: New directions in dynamical density functional theory
• Describing condensed matter from atomically resolved imaging data: from structure to generative and causal models
• Bayesian Parameterization of Continuum Battery Models from Featurized Electrochemical Measurements Considering Noise
• Mechanics Informatics: A paradigm for efficiently learning constitutive models
• Bayesian Modelling of Pattern Formation from One Snapshot of Pattern
• Deep learning for bioimage analysis