CNN-Based Deep Learning Architecture for Electromagnetic Imaging of Rough Surface Profiles

Aydin I., Budak G., Sefer A., Yapar A.

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, vol.70, no.10, pp.9752-9763, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 70 Issue: 10
  • Publication Date: 2022
  • Doi Number: 10.1109/tap.2022.3177493
  • Journal Name: IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Aerospace Database, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, zbMATH, Civil Engineering Abstracts
  • Page Numbers: pp.9752-9763
  • Keywords: Surface roughness, Rough surfaces, Imaging, Surface waves, Surface treatment, Inverse problems, Electromagnetics, Convolutional neural network (CNN), deep learning (DL), electromagnetics (EMs), inverse scattering problems, rough surface imaging, INVERSE SCATTERING, NEURAL-NETWORK, RECONSTRUCTION, CLASSIFICATION, 2-D
  • Istanbul Technical University Affiliated: Yes

Abstract

A convolutional neural network (CNN)-based deep learning (DL) technique for electromagnetic (EM) imaging of rough surfaces separating two dielectric media is presented. The direct scattering problem is formulated through the conventional integral equations, and the synthetic scattered field data are produced by a fast numerical solution technique, which is based on method of moments (MoM). Two different special CNN architectures are designed and implemented for the solution of the inverse rough surface imaging problem, wherein both random and deterministic rough surface profiles can be imaged. It is shown by a comprehensive numerical analysis that the proposed DL inversion scheme is very effective and robust.