Recovery of impenetrable rough surface profiles via CNN-based deep learning architecture

İzde Aydin, Güven Budak, Ahmet Sefer*, Ali Yapar

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)


In this paper, a convolutional neural network (CNN)-based deep learning (DL) architecture for the solution of an electromagnetic inverse problem related to imaging of the shape of the perfectly electric conducting (PEC) rough surfaces is addressed. The rough surface is illuminated by a plane wave and scattered field data is obtained synthetically through the numerical solution of surface integral equations. An effective CNN-DL architecture is implemented through the modelling of the rough surface variation in terms of convenient spline type base functions. The algorithm is numerically tested with various scenarios including amplitude only data and shown that it is very effective and useful.

Original languageEnglish
Pages (from-to)5658-5685
Number of pages28
JournalInternational Journal of Remote Sensing
Issue number15-16
Publication statusPublished - 2022

Bibliographical note

Publisher Copyright:
© 2022 Informa UK Limited, trading as Taylor & Francis Group.


  • Convolutional neural network
  • deep learning
  • inverse scattering problems
  • rough surface imaging


Dive into the research topics of 'Recovery of impenetrable rough surface profiles via CNN-based deep learning architecture'. Together they form a unique fingerprint.

Cite this