GINNs: Graph-Informed Neural Networks for Multiscale Physics

Abstract

We introduce the concept of a Graph-Informed Neural Network (GINN), a hybrid approach combining deep learning with probabilistic graphical models (PGMs) that acts as a surrogate for physics-based representations of multiscale and multiphysics systems. GINNs address the twin challenges of removing intrinsic computational bottlenecks in physics-based models and generating large data sets for estimating probability distributions of quantities of interest (QoIs) with a high degree of confidence. Both the selection of the complex physics learned by the NN and its supervised learning/prediction are informed by the PGM, which includes the formulation of structured priors for tunable control variables (CVs) to account for their mutual correlations and ensure physically sound CV and QoI distributions. GINNs accelerate the prediction of QoIs essential for simulation-based decision-making where generating sufficient sample data using physics-based models alone is often prohibitively expensive. Using a real-world application grounded in supercapacitor-based energy storage, we describe the construction of GINNs from a Bayesian network-embedded homogenized model for supercapacitor dynamics, and demonstrate their ability to produce kernel density estimates of relevant non-Gaussian, skewed QoIs with tight confidence intervals.

arXiv comment20 pages, 8 figures

References in corpus (19)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• Kernel density estimation via diffusion
• Graph Neural Networks: A Review of Methods and Applications
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• 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
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Data-Driven Deep Learning of Partial Differential Equations in Modal Space
• Simulator-free Solution of High-Dimensional Stochastic Elliptic Partial Differential Equations using Deep Neural Networks
• Modeling meso-scale energy localization in shocked HMX, Part I: machine- learned surrogate model for effect of loading and void size
• Path-space variational inference for non-equilibrium coarse-grained systems
• Estimation of distributions via multilevel Monte Carlo with stratified sampling
• Causality and Bayesian network PDEs for multiscale representations of porous media

Cited by in corpus (8)

• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)
• Prediction of transonic flow over supercritical airfoils using geometric-encoding and deep-learning strategies
• Mutual Information for Explainable Deep Learning of Multiscale Systems
• On the data-driven description of lattice materials mechanics
• Applying physics-based loss functions to neural networks for improved generalizability in mechanics problems
• A deep learning energy method for hyperelasticity and viscoelasticity
• Edge-Wise Graph-Instructed Neural Networks