Work

Reconstruction of Magnetic Fields with a Physics-Informed Neural Network

Year: 2026

Type: preprint

Abstract: Accurate reconstruction of magnetic fields and their gradients is essential for assessing and controlling systematic effects in precision measurement experiments. We have developed a physics-informed neural network (PINN) method which reconstructs three-dimensional magnetic fields subject to the source-free Maxwell equations, $\nabla\cdot\mathbf{B}=0$ and $\nabla\times\mathbf{B}=\mathbf{0}$. In an extension of our previous work on PINN methods for reconstruction of magnetic fields in inaccessible interior regions via measurements at exterior locations, we now demonstrate the feasibility of applying PINN methods to the extraction of magnetic field gradient terms from discrete measurement points subject to constraints from Maxwell's equations.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.23691

Authors: Adhikari, P., Bhattarai, R., Brewington, J., Buskirk, D., Hills, F. B., Hossain, Md F., McDonald, R., Palamure, P. A., Reid, A., Sharmin, S., Tewsley-Booth, A., Plaster, B.

Institutions: University of Kentucky, Tennessee Technological University

Language: English

Topic: Model Reduction and Neural Networks

Subfield: Statistical and Nonlinear Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: green

Funders: U.S. Department of Energy, University of Kentucky

OpenAlex ID: W7222942854

Cites: 13

Cited by:

Related to: 10