A Domain-Adaptive Physics-Informed Neural Network for Inverse Problems of Maxwell’s Equations in Heterogeneous Media
Published in Journal 1, 2024
This paper aims to estimate physical parameters (e.g., dielectric constants) and physical quantities (e.g., electric and magnetic fields) in heterogeneous media. To address the limitations of existing physics-informed neural networks (PINNs) in handling media composed of multiple homogeneous media, we propose a domain-adaptive PINN framework tailored for such complex scenarios.
Recommended citation: Shiyuan Piao, H. Gu, A. Wang and P. Qin,. (2024).
Download Paper