Variational system identification of the partial differential equations governing pattern-forming physics: Inference under varying fidelity and noise

Abstract

We present a contribution to the field of system identification of partial differential equations (PDEs), with emphasis on discerning between competing mathematical models of pattern-forming physics. The motivation comes from developmental biology, where pattern formation is central to the development of any multicellular organism, and from materials physics, where phase transitions similarly lead to microstructure. In both these fields there is a collection of nonlinear, parabolic PDEs that, over suitable parameter intervals and regimes of physics, can resolve the patterns or microstructures with comparable fidelity. This observation frames the question of which PDE best describes the data at hand. This question is particularly compelling because identification of the closest representation to the true PDE, while constrained by the functional spaces considered relative to the data at hand, immediately delivers insights to the physics underlying the systems. While building on recent work that uses stepwise regression, we present advances that leverage the variational framework and statistical tests. We also address the influences of variable fidelity and noise in the data.

To be appear in Computer Methods in Applied Mechanics and Engineering

References in corpus (7)

• Solving high-dimensional partial differential equations using deep learning
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
• Sparse Identification of Nonlinear Dynamics for Rapid Model Recovery
• Machine learning materials physics: Surrogate optimization and multi-fidelity algorithms predict precipitate morphology in an alternative to phase field dynamics
• Perspectives on the mathematics of biological patterning and morphogenesis
• A variational treatment of material configurations with application to interface motion and microstructural evolution

Cited by in corpus (24)

• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• Physics-informed learning of governing equations from scarce data
• A new family of Constitutive Artificial Neural Networks towards automated model discovery
• Weak SINDy For Partial Differential Equations
• Non-invasive Inference of Thrombus Material Properties with Physics-informed Neural Networks
• Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
• Variational Onsager Neural Networks (VONNs): A thermodynamics-based variational learning strategy for non-equilibrium PDEs
• Derivative-based SINDy (DSINDy): Addressing the challenge of discovering governing equations from noisy data
• Linking Machine Learning with Multiscale Numerics: Data-Driven Discovery of Homogenized Equations
• Variational system identification of the partial differential equations governing microstructure evolution in materials: Inference over sparse and spatially unrelated data
• Learning elliptic partial differential equations with randomized linear algebra
• Direct Estimation of Parameters in ODE Models Using WENDy: Weak-form Estimation of Nonlinear Dynamics
• A Perspective on Regression and Bayesian Approaches for System Identification of Pattern Formation Dynamics
• Image Inversion and Uncertainty Quantification for Constitutive Laws of Pattern Formation
• Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Dataset
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Ogden Material Calibration via Magnetic Resonance Cartography, Parameter Sensitivity, and Variational System Identification
• System inference for the spatio-temporal evolution of infectious diseases: Michigan in the time of COVID-19
• Physics-Informed Machine Learning Models for Predicting the Progress of Reactive-Mixing
• Hyperparameter Optimization in the Estimation of PDE and Delay-PDE models from data
• Numerical analysis of non-local calculus on finite weighted graphs, with application to reduced-order modelling of dynamical systems
• The Graph Theoretic Approach for Nodal Cross Section Parameterization
• System inference via field inversion for the spatio-temporal progression of infectious diseases: Studies of COVID-19 in Michigan and Mexico
• Constitutive parameter inference using physics-based data-driven modeling in full volume datasets of intact and torn rotator cuff tendons