Bayesian Reasoning for Physics Informed Neural Networks

Abstract

We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights between PDE residuals, boundary conditions, and observational data. Unlike existing Bayesian PINN approaches based on sampling or variational inference, the proposed method uses a Laplace approximation to compute model evidence analytically, enabling efficient hyperparameter tuning and model comparison without posterior sampling. We demonstrate the method on the heat, wave, and Burgers' equations, obtaining solutions in agreement with exact or reference results. In the Burgers' equation example, we further show that the framework naturally integrates information from governing equations and noisy measurements, providing predictive uncertainties within a unified Bayesian setting.

21 pages, 12 figures, re-edit the description of the Bayesian framework, some of the content moved to Appendix. Discussion of numerical performance added, as well as related approaches

References in corpus (26)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• MCMC using Hamiltonian dynamics
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• A high-bias, low-variance introduction to Machine Learning for physicists
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Machine Learning of Linear Differential Equations using Gaussian Processes
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• Self-adaptive loss balanced Physics-informed neural networks for the incompressible Navier-Stokes equations
• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Inferring solutions of differential equations using noisy multi-fidelity data
• Predicting Porosity, Permeability, and Tortuosity of Porous Media from Images by Deep Learning
• Multi-Objective Loss Balancing for Physics-Informed Deep Learning
• Artificial Neural Network Methods in Quantum Mechanics
• Physics Informed Neural Networks for Simulating Radiative Transfer
• The Proton Radius from Bayesian Inference
• Nucleon axial form factor from a Bayesian neural-network analysis of neutrino-scattering data
• Two-Photon Exchange Effect Studied with Neural Networks
• Applications of Neural Networks in Hadron Physics
• Neural Network Parameterizations of Electromagnetic Nucleon Form Factors
• Solving Non-local Fokker-Planck Equations by Deep Learning
• Electron-nucleus cross sections from transfer learning
• Transfer Learning for Neutrino Scattering: Domain Adaptation with GANs