DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations

Barth, Alexander; Alvera-Azcárate, Aida; Licer, Matjaz; Beckers, Jean-Marie

doi:https://doi.org/10.5194/gmd-13-1609-2020

Articles | Volume 13, issue 3

https://doi.org/10.5194/gmd-13-1609-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-13-1609-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 13, issue 3

Model description paper

|

27 Mar 2020

Model description paper |

| 27 Mar 2020

DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations

Alexander Barth, Aida Alvera-Azcárate, Matjaz Licer, and Jean-Marie Beckers

Download

Final revised paper (published on 27 Mar 2020)
Preprint (discussion started on 25 Jun 2019)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Comments', Anonymous Referee #1, 03 Dec 2019
- AC1: 'Reply to anonymous Referee #1', Alexander Barth, 11 Dec 2019
  - RC2: 'Reply to AC1', Anonymous Referee #1, 13 Dec 2019
    - AC2: 'Reply to Reply to AC1', Alexander Barth, 17 Dec 2019
      - RC3: 'Reply.', Anonymous Referee #1, 18 Dec 2019
SC1: 'DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations', Zhaohui Han, 01 Jan 2020
- AC3: 'Reply', Alexander Barth, 08 Jan 2020
RC4: 'A promising method, which would deserve bette rpresentation', Anonymous Referee #2, 08 Feb 2020
- AC4: 'Reply to Anonymous Referee #2', Alexander Barth, 25 Feb 2020

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

AR by Alexander Barth on behalf of the Authors (25 Feb 2020) Author's response Manuscript

ED: Publish as is (28 Feb 2020) by Patrick Jöckel

AR by Alexander Barth on behalf of the Authors (28 Feb 2020)

Short summary

DINCAE is a method for reconstructing missing data in satellite datasets using a neural network. Satellite observations working in the optical and infrared bands are affected by clouds, which obscure part of the ocean underneath. In this paper, a neural network with the structure of a convolutional auto-encoder is developed to reconstruct the missing data based on the available cloud-free pixels in satellite images.