Diurnal and nocturnal cloud segmentation of all-sky imager (ASI) images using enhancement fully convolutional networks

Shi, Chaojun; Zhou, Yatong; Qiu, Bo; He, Jingfei; Ding, Mu; Wei, Shiya

doi:https://doi.org/10.5194/amt-12-4713-2019

Articles | Volume 12, issue 9

Atmos. Meas. Tech., 12, 4713–4724, 2019

https://doi.org/10.5194/amt-12-4713-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Atmos. Meas. Tech., 12, 4713–4724, 2019

https://doi.org/10.5194/amt-12-4713-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 12, issue 9

Research article 04 Sep 2019

Research article | 04 Sep 2019

Diurnal and nocturnal cloud segmentation of all-sky imager (ASI) images using enhancement fully convolutional networks

Chaojun Shi et al.

Download

Final revised paper (published on 04 Sep 2019)
Preprint (discussion started on 06 Jun 2019)

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

RC1: 'accepted subject to minor revisions', Anonymous Referee #2, 03 Jul 2019
- AC2: 'Response to Anonymous Referee #2', Chaojun Shi, 26 Jul 2019
RC2: 'Reviews on Chaojun et al. manuscript', Anonymous Referee #1, 04 Jul 2019
- AC1: 'Response to Anonymous Referee #1', Chaojun Shi, 26 Jul 2019

Peer-review completion

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

AR by Chaojun Shi on behalf of the Authors (03 Aug 2019) Author's response Manuscript

ED: Publish subject to technical corrections (15 Aug 2019) by Murray Hamilton

AR by Chaojun Shi on behalf of the Authors (19 Aug 2019) Author's response Manuscript

Short summary

Cloud segmentation plays a very important role in astronomical observatory site selection. At present, few researchers segment cloud in nocturnal all-sky imager (ASI) images. We propose a new automatic cloud segmentation algorithm to segment cloud pixels from diurnal and nocturnal ASI images called an enhancement fully convolutional network (EFCN). Experiments showed that the proposed EFCN was much more accurate in cloud segmentation for diurnal and nocturnal ASI images.