Articles | Volume 14, issue 12
https://doi.org/10.5194/amt-14-7729-2021
https://doi.org/10.5194/amt-14-7729-2021
Research article
 | 
09 Dec 2021
Research article |  | 09 Dec 2021

Inpainting radar missing data regions with deep learning

Andrew Geiss and Joseph C. Hardin

Download

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2021-100', Andrew Black, 03 Aug 2021
    • AC1: 'Reply on RC1', Andrew Geiss, 23 Oct 2021
  • EC1: 'Comment on amt-2021-100', Gianfranco Vulpiani, 24 Sep 2021
    • AC2: 'Reply on EC1', Andrew Geiss, 23 Oct 2021
  • RC2: 'Comment on amt-2021-100', Anonymous Referee #2, 25 Sep 2021
    • AC3: 'Reply on RC2', Andrew Geiss, 23 Oct 2021

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Andrew Geiss on behalf of the Authors (23 Oct 2021)  Author's response    Author's tracked changes    Manuscript
ED: Publish as is (03 Nov 2021) by Gianfranco Vulpiani
AR by Andrew Geiss on behalf of the Authors (03 Nov 2021)  Author's response    Manuscript
Download
Short summary
Radars can suffer from missing or poor-quality data regions for several reasons: beam blockage, instrument failure, and near-ground blind zones, etc. Here, we demonstrate how deep convolutional neural networks can be used for filling in radar-missing data regions and that they can significantly outperform conventional approaches in terms of realism and accuracy.