Physics-informed information field theory for modeling physical systems with uncertainty quantification

DOI10.1016/j.jcp.2023.112100arXiv2301.07609OpenAlexW4362607138MaRDI QIDQ6147081

Alex Alberts, Ilias Bilionis

Publication date: 15 January 2024

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2301.07609

zbMATH Keywords

inverse problemsuncertainty quantificationphysics-informed machine learningstochastic gradient Langevin dynamicsmodel-form uncertaintyinformation field theory

Mathematics Subject Classification ID

Parametric inference (62Fxx) Artificial intelligence (68Txx) Probabilistic methods, stochastic differential equations (65Cxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• Multi-output local Gaussian process regression: applications to uncertainty quantification
• A generalization of the Sherman-Morrison-Woodbury formula
• Mathematical theory of Feynman path integrals
• The numerical solution of linear ordinary differential equations by feedforward neural networks
• Inferring solutions of differential equations using noisy multi-fidelity data
• Hidden physics models: machine learning of nonlinear partial differential equations
• A tutorial on Gaussian process regression: modelling, exploring, and exploiting functions
• Bayesian learning for neural networks
• Perturbation of eigenvalues of the Klein-Gordon operators
• Machine learning in cardiovascular flows modeling: predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• B-PINNs: Bayesian physics-informed neural networks for forward and inverse PDE problems with noisy data
• Solving and learning nonlinear PDEs with Gaussian processes
• Learning functional priors and posteriors from data and physics
• Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Simulator-free solution of high-dimensional stochastic elliptic partial differential equations using deep neural networks
• Comment on “Application of the extended Lie group analysis to the Hopf functional formulation of the Burgers equation” [J. Math. Phys. 54, 072901 (2013)]
• Approximation of Bayesian Inverse Problems for PDEs
• EMBEDDED MODEL ERROR REPRESENTATION FOR BAYESIAN MODEL CALIBRATION
• Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
• Quantum Field Theory for the Gifted Amateur
• MAP estimators and their consistency in Bayesian nonparametric inverse problems
• A Stochastic Approximation Method
• Functional Integration

This page was built for publication: Physics-informed information field theory for modeling physical systems with uncertainty quantification