Physics-based deep kernel learning for parameter estimation in high dimensional PDEs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yan, Weihao, Brune, Christoph, Guo, Mengwu
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918143062966272
author Yan, Weihao
Brune, Christoph
Guo, Mengwu
author_facet Yan, Weihao
Brune, Christoph
Guo, Mengwu
contents Inferring parameters of high-dimensional partial differential equations (PDEs) poses significant computational and inferential challenges, primarily due to the curse of dimensionality and the inherent limitations of traditional numerical methods. This paper introduces a novel two-stage Bayesian framework that synergistically integrates training, physics-based deep kernel learning (DKL) with Hamiltonian Monte Carlo (HMC) to robustly infer unknown PDE parameters and quantify their uncertainties from sparse, exact observations. The first stage leverages physics-based DKL to train a surrogate model, which jointly yields an optimized neural network feature extractor and robust initial estimates for the PDE parameters. In the second stage, with the neural network weights fixed, HMC is employed within a full Bayesian framework to efficiently sample the joint posterior distribution of the kernel hyperparameters and the PDE parameters. Numerical experiments on canonical and high-dimensional inverse PDE problems demonstrate that our framework accurately estimates parameters, provides reliable uncertainty estimates, and effectively addresses challenges of data sparsity and model complexity, offering a robust and scalable tool for diverse scientific and engineering applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14054
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-based deep kernel learning for parameter estimation in high dimensional PDEs
Yan, Weihao
Brune, Christoph
Guo, Mengwu
Computational Engineering, Finance, and Science
Machine Learning
Numerical Analysis
68T05
I.2.6
Inferring parameters of high-dimensional partial differential equations (PDEs) poses significant computational and inferential challenges, primarily due to the curse of dimensionality and the inherent limitations of traditional numerical methods. This paper introduces a novel two-stage Bayesian framework that synergistically integrates training, physics-based deep kernel learning (DKL) with Hamiltonian Monte Carlo (HMC) to robustly infer unknown PDE parameters and quantify their uncertainties from sparse, exact observations. The first stage leverages physics-based DKL to train a surrogate model, which jointly yields an optimized neural network feature extractor and robust initial estimates for the PDE parameters. In the second stage, with the neural network weights fixed, HMC is employed within a full Bayesian framework to efficiently sample the joint posterior distribution of the kernel hyperparameters and the PDE parameters. Numerical experiments on canonical and high-dimensional inverse PDE problems demonstrate that our framework accurately estimates parameters, provides reliable uncertainty estimates, and effectively addresses challenges of data sparsity and model complexity, offering a robust and scalable tool for diverse scientific and engineering applications.
title Physics-based deep kernel learning for parameter estimation in high dimensional PDEs
topic Computational Engineering, Finance, and Science
Machine Learning
Numerical Analysis
68T05
I.2.6
url https://arxiv.org/abs/2509.14054