Fully probabilistic deep models for forward and inverse problems in parametric PDEs
arXiv:2208.04856 · doi:10.1016/j.jcp.2023.112369
Abstract
We introduce a physics-driven deep latent variable model (PDDLVM) to learn simultaneously parameter-to-solution (forward) and solution-to-parameter (inverse) maps of parametric partial differential equations (PDEs). Our formulation leverages conventional PDE discretization techniques, deep neural networks, probabilistic modelling, and variational inference to assemble a fully probabilistic coherent framework. In the posited probabilistic model, both the forward and inverse maps are approximated as Gaussian distributions with a mean and covariance parameterized by deep neural networks. The PDE residual is assumed to be an observed random vector of value zero, hence we model it as a random vector with a zero mean and a user-prescribed covariance. The model is trained by maximizing the probability, that is the evidence or marginal likelihood, of observing a residual of zero by maximizing the evidence lower bound (ELBO). Consequently, the proposed methodology does not require any independent PDE solves and is physics-informed at training time, allowing the real-time solution of PDE forward and inverse problems after training. The proposed framework can be easily extended to seamlessly integrate observed data to solve inverse problems and to build generative models. We demonstrate the efficiency and robustness of our method on finite element discretized parametric PDE problems such as linear and nonlinear Poisson problems, elastic shells with complex 3D geometries, and time-dependent nonlinear and inhomogeneous PDEs using a physics-informed neural network (PINN) discretization. We achieve up to three orders of magnitude speed-up after training compared to traditional finite element method (FEM), while outputting coherent uncertainty estimates.
References in corpus (26)
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
- An Introduction to Variational Autoencoders
- DGM: A deep learning algorithm for solving partial differential equations
- Solving high-dimensional partial differential equations using deep learning
- Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
- fPINNs: Fractional Physics-Informed Neural Networks
- 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
- Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
- CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
- Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
- Deep Fluids: A Generative Network for Parameterized Fluid Simulations
- Neural Operator: Graph Kernel Network for Partial Differential Equations
- Interfacing Finite Elements with Deep Neural Operators for Fast Multiscale Modeling of Mechanics Problems
- A physics-informed operator regression framework for extracting data-driven continuum models
- Bayesian Probabilistic Numerical Methods
- The statistical finite element method (statFEM) for coherent synthesis of observation data and model predictions
- Subdivision surfaces with isogeometric analysis adapted refinement weights
- PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
- Normalizing field flows: Solving forward and inverse stochastic differential equations using physics-informed flow models
- Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
- A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables
- Variational Bayesian Approximation of Inverse Problems using Sparse Precision Matrices
- Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression
- Learning to regularize with a variational autoencoder for hydrologic inverse analysis