Adversarial Uncertainty Quantification in Physics-Informed Neural Networks

Abstract

We present a deep learning framework for quantifying and propagating uncertainty in systems governed by non-linear differential equations using physics-informed neural networks. Specifically, we employ latent variable models to construct probabilistic representations for the system states, and put forth an adversarial inference procedure for training them on data, while constraining their predictions to satisfy given physical laws expressed by partial differential equations. Such physics-informed constraints provide a regularization mechanism for effectively training deep generative models as surrogates of physical systems in which the cost of data acquisition is high, and training data-sets are typically small. This provides a flexible framework for characterizing uncertainty in the outputs of physical systems due to randomness in their inputs or noise in their observations that entirely bypasses the need for repeatedly sampling expensive experiments or numerical simulators. We demonstrate the effectiveness of our approach through a series of examples involving uncertainty propagation in non-linear conservation laws, and the discovery of constitutive laws for flow through porous media directly from noisy data.

arXiv commentThis paper has been submitted to Journal of Computational Physics. 33 pages, 7 figures

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• TensorFlow: A system for large-scale machine learning
• Variational Inference: A Review for Statisticians
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Improved Techniques for Training GANs
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Adversarially Learned Inference
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Inferring solutions of differential equations using noisy multi-fidelity data
• Adversarial Autoencoders
• Wasserstein Auto-Encoders
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
• Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
• Symmetric Variational Autoencoder and Connections to Adversarial Learning
• Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders
• Optimal fidelity multi-level Monte Carlo for quantification of uncertainty in simulations of cloud cavitation collapse

Cited by in corpus (100)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• 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
• On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks
• PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs
• Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• Physics-informed learning of governing equations from scarce data
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Efficient training of physics-informed neural networks via importance sampling
• A Physics Informed Neural Network for Time-Dependent Nonlinear and Higher Order Partial Differential Equations
• A Physics-Informed Deep Learning Paradigm for Car-Following Models
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
• A two-stage physics-informed neural network method based on conserved quantities and applications in localized wave solutions
• Tackling the Curse of Dimensionality with Physics-Informed Neural Networks
• Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method
• Augmented Physics-Informed Neural Networks (APINNs): A gating network-based soft domain decomposition methodology
• When and why PINNs fail to train: A neural tangent kernel perspective
• Deep learning of free boundary and Stefan problems
• Deep Learning for One-dimensional Consolidation
• Variational Physics Informed Neural Networks: the role of quadratures and test functions
• Physics-informed neural networks (PINNs) for fluid mechanics: A review
• Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
• On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton--Jacobi partial differential equations
• Stochastic Physics-Informed Neural Ordinary Differential Equations
• Physics-informed neural networks method in high-dimensional integrable systems
• Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
• PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
• Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priors
• Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems
• Bayesian Physics-Informed Extreme Learning Machine for Forward and Inverse PDE Problems with Noisy Data
• Low-temperature plasma simulation based on physics-informed neural networks: frameworks and preliminary applications
• Bayesian Physics Informed Neural Networks for Data Assimilation and Spatio-Temporal Modelling of Wildfires
• Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors
• Recipes for when Physics Fails: Recovering Robust Learning of Physics Informed Neural Networks
• Using neural networks to accelerate the solution of the Boltzmann equation
• Hutchinson Trace Estimation for High-Dimensional and High-Order Physics-Informed Neural Networks
• PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics
• GINNs: Graph-Informed Neural Networks for Multiscale Physics
• Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Fully probabilistic deep models for forward and inverse problems in parametric PDEs
• Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations
• A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
• Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
• Physics-informed neural networks for inverse problems in supersonic flows
• Solving PDEs by Variational Physics-Informed Neural Networks: an a posteriori error analysis
• Solving time dependent Fokker-Planck equations via temporal normalizing flow
• Sparse Polynomial Chaos expansions using Variational Relevance Vector Machines
• A hybrid data driven-physics constrained Gaussian process regression framework with deep kernel for uncertainty quantification
• Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem
• Image Inversion and Uncertainty Quantification for Constitutive Laws of Pattern Formation
• Neural network architectures using min-plus algebra for solving certain high dimensional optimal control problems and Hamilton-Jacobi PDEs
• PCNN: A physics-constrained neural network for multiphase flows
• A Survey on Autonomous Vehicle Control in the Era of Mixed-Autonomy: From Physics-Based to AI-Guided Driving Policy Learning
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
• Mutual Information for Explainable Deep Learning of Multiscale Systems
• Highly-scalable, physics-informed GANs for learning solutions of stochastic PDEs
• Physics-informed deep learning for flow and deformation in poroelastic media
• Learning Free-Surface Flow with Physics-Informed Neural Networks
• SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition
• Improved Surrogate Modeling of Fluid Dynamics with Physics-Informed Neural Networks
• Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data
• Physics-Aware Neural Implicit Solvers for multiscale, parametric PDEs with applications in heterogeneous media
• The mixed deep energy method for resolving concentration features in finite strain hyperelasticity
• Physics-Informed Deep Learning for Traffic State Estimation
• Transfer Learning as a Method to Reproduce High-Fidelity NLTE Opacities in Simulations
• Modeling Global Surface Dust Deposition Using Physics-Informed Neural Networks
• Exact artificial boundary conditions of 1D semi-discretized peridynamics
• Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures
• Connecting GANs, MFGs, and OT
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models
• Adaptive Sparse Polynomial Chaos Expansions via Leja Interpolation
• Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN
• Generating artificial digital image correlation data using physics-guided adversarial networks
• Inferring the Langevin Equation with Uncertainty via Bayesian Neural Networks
• Quantum Extremal Learning
• Adaptive Physics-Informed Neural Networks for Markov-Chain Monte Carlo
• BINet: Learning to Solve Partial Differential Equations with Boundary Integral Networks
• A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems
• Deep Domain Decomposition Method: Elliptic Problems
• SRoll3: A neural network approach to reduce large-scale systematic effects in the Planck High Frequency Instrument maps
• A Physics-Informed Neural Network Framework For Partial Differential Equations on 3D Surfaces: Time-Dependent Problems
• Deep learning of parameterized equations with applications to uncertainty quantification
• A Linear Algebraic Approach to Model Parallelism in Deep Learning
• Prediction of liquid fuel properties using machine learning models with Gaussian processes and probabilistic conditional generative learning
• Physics-Informed Machine Learning Models for Predicting the Progress of Reactive-Mixing
• Measure-conditional Discriminator with Stationary Optimum for GANs and Statistical Distance Surrogates
• Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
• Reversible and irreversible bracket-based dynamics for deep graph neural networks
• Learning To Solve Differential Equations Across Initial Conditions
• Recurrent convolutional neural network for the surrogate modeling of subsurface flow simulation
• A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems
• Generative Adversarial Network: Some Analytical Perspectives
• Learning To Estimate Regions Of Attraction Of Autonomous Dynamical Systems Using Physics-Informed Neural Networks