Data-driven Discovery of Partial Differential Equations for Multiple-Physics Electromagnetic Problem
Abstract
Deriving governing equations in Electromagnetic (EM) environment based on first principles can be quite tough when there are some unknown sources of noise and other uncertainties in the system. For nonlinear multiple-physics electromagnetic systems, deep learning to solve these problems can achieve high efficiency and accuracy. In this paper, we propose a deep learning neutral network in combination with sparse regression to solve the hidden governing equations in multiple-physics EM problem. Pareto analysis is also adopted to preserve inversion as precise and simple as possible. This proposed network architecture can discover a set of governing partial differential equations (PDEs) based on few temporalspatial samples. The data-driven discovery method for partial differential equations (PDEs) in electromagnetic field may also contribute to solve more sophisticated problem which may not be solved by first principles.
Cite
@article{arxiv.1910.13531,
title = {Data-driven Discovery of Partial Differential Equations for Multiple-Physics Electromagnetic Problem},
author = {Bing Xiong and Haiyang Fu and Feng Xu and Yaqiu Jin},
journal= {arXiv preprint arXiv:1910.13531},
year = {2019}
}