Arctic sea ice cover data from spaceborne synthetic  aperture radar by deep learning

Wang, Yi-Ran; Li, Xiao-Ming

doi:https://doi.org/10.5194/essd-13-2723-2021

Articles | Volume 13, issue 6

https://doi.org/10.5194/essd-13-2723-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/essd-13-2723-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 13, issue 6

Data description paper

|

15 Jun 2021

Data description paper |

| 15 Jun 2021

Arctic sea ice cover data from spaceborne synthetic aperture radar by deep learning

Yi-Ran Wang and Xiao-Ming Li

Download

Final revised paper (published on 15 Jun 2021)
Preprint (discussion started on 10 Nov 2020)

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

RC1: 'Questions about the Machine Learning Methodology', Anonymous Referee #1, 03 Jan 2021
- AC1: 'Reply on RC1', Xiaoming Li, 10 Feb 2021
RC2: 'review comments: Arctic sea ice cover data from spaceborne SAR by deep learning', Anonymous Referee #2, 11 Jan 2021
- AC2: 'Reply on RC2', Xiaoming Li, 10 Feb 2021

Peer-review completion

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

AR by Xiaoming Li on behalf of the Authors (10 Feb 2021) Author's response Author's tracked changes Manuscript

ED: Referee Nomination & Report Request started (22 Mar 2021) by Prasad Gogineni

RR by Anonymous Referee #1 (28 Mar 2021)

RR by Anonymous Referee #2 (17 Apr 2021)

ED: Publish as is (07 May 2021) by Prasad Gogineni

AR by Xiaoming Li on behalf of the Authors (14 May 2021) Author's response Manuscript

Short summary

Sea ice cover is the most fundamental factor that indicates the underlying great changes in the Arctic. We propose novel sea ice cover data in high resolution of a few hundred meters by spaceborne synthetic aperture radar, which is more than 10 times that of the operational sea ice cover and concentration data. The method is based on a deep learning architecture of U-Net. We have been processing data acquired by Sentinel-1 since 2014 to obtain high-quality sea ice cover data in the Arctic.