Bayesian neural networks for weak solution of PDEs with uncertainty quantification
arXiv:2101.04879
Abstract
Solving partial differential equations (PDEs) is the canonical approach for understanding the behavior of physical systems. However, large scale solutions of PDEs using state of the art discretization techniques remains an expensive proposition. In this work, a new physics-constrained neural network (NN) approach is proposed to solve PDEs without labels, with a view to enabling high-throughput solutions in support of design and decision-making. Distinct from existing physics-informed NN approaches, where the strong form or weak form of PDEs are used to construct the loss function, we write the loss function of NNs based on the discretized residual of PDEs through an efficient, convolutional operator-based, and vectorized implementation. We explore an encoder-decoder NN structure for both deterministic and probabilistic models, with Bayesian NNs (BNNs) for the latter, which allow us to quantify both epistemic uncertainty from model parameters and aleatoric uncertainty from noise in the data. For BNNs, the discretized residual is used to construct the likelihood function. In our approach, both deterministic and probabilistic convolutional layers are used to learn the applied boundary conditions (BCs) and to detect the problem domain. As both Dirichlet and Neumann BCs are specified as inputs to NNs, a single NN can solve for similar physics, but with different BCs and on a number of problem domains. The trained surrogate PDE solvers can also make interpolating and extrapolating (to a certain extent) predictions for BCs that they were not exposed to during training. Such surrogate models are of particular importance for problems, where similar types of PDEs need to be repeatedly solved for many times with slight variations. We demonstrate the capability and performance of the proposed framework by applying it to steady-state diffusion, linear elasticity, and nonlinear elasticity.
arXiv comment37 pages, 25 figures
References in corpus (29)
- Auto-Encoding Variational Bayes
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- DGM: A deep learning algorithm for solving partial differential equations
- An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
- A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
- Solving high-dimensional partial differential equations using deep learning
- NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
- B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
- 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
- hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
- Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
- PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs
- Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
- Weak Adversarial Networks for High-dimensional Partial Differential Equations
- Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
- Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
- Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks
- D3M: A deep domain decomposition method for partial differential equations
- Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning
- Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions
- Machine learning materials physics: Surrogate optimization and multi-fidelity algorithms predict precipitate morphology in an alternative to phase field dynamics
- Variational system identification of the partial differential equations governing pattern-forming physics: Inference under varying fidelity and noise
- Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
- Scale bridging materials physics: Active learning workflows and integrable deep neural networks for free energy function representations in alloys
- VarNet: Variational Neural Networks for the Solution of Partial Differential Equations
- A Perspective on Regression and Bayesian Approaches for System Identification of Pattern Formation Dynamics
- Predicting the mechanical response of oligocrystals with deep learning