Electromagnetic Field Reconstruction and Source Identification Using Conditional Variational Autoencoder and CNN

In this work, a Deep Learning approach based on a Conditional Variational Autoencoder (CVAE) and a Convolutional Neural Network (CNN) has been adopted for the solution of inverse problems and electromagnetic field reconstruction; the method is applied to the TEAM 35 benchmark magnetostatic problem. The aim of the proposed method is twofold: first, knowing the magnetic field distribution in a subdomain, the magnetic field distribution B in the whole domain is determined (field reconstruction problem). For this problem a CVAE is proposed and trained. The CVAE prediction is based on an optimization procedure in the latent space, which uses an automatic differentiation technique. Subsequently, knowing the magnetic field distribution in the whole domain, the aim is to find, using a CNN regression model, the geometrical characteristics of the source (source identification problem).

Automated summary

In this work, a Deep Learning approach based on a Conditional Variational Autoencoder (CVAE) and a Convolutional Neural Network (CNN) is used to solve inverse problems and electromagnetic field reconstruction. The method is applied to the TEAM 35 benchmark magnetostatic problem. The proposed method aims to determine the magnetic field distribution in the whole domain based on the known magnetic field distribution in a subdomain (field reconstruction problem), and identify the geometrical characteristics of the source based on the known magnetic field distribution in the whole domain (source identification problem), using a CVAE and a CNN regression model respectively.