Articles | Volume 18, issue 1
https://doi.org/10.5194/tc-18-153-2024
https://doi.org/10.5194/tc-18-153-2024
Research article
 | 
08 Jan 2024
Research article |  | 08 Jan 2024

Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods

Yungang Cao, Rumeng Pan, Meng Pan, Ruodan Lei, Puying Du, and Xueqin Bai

Download

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on tc-2022-267', Anonymous Referee #1, 18 Apr 2023
    • AC1: 'Reply on RC1', Yungang Cao, 10 Aug 2023
  • RC2: 'Comment on tc-2022-267', Connor Shiggins, 14 Jul 2023
    • AC2: 'Reply on RC2', Yungang Cao, 10 Aug 2023

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
ED: Publish subject to revisions (further review by editor and referees) (21 Aug 2023) by Homa Kheyrollah Pour
AR by Yungang Cao on behalf of the Authors (04 Sep 2023)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (19 Sep 2023) by Homa Kheyrollah Pour
RR by Connor Shiggins (05 Oct 2023)
ED: Publish subject to minor revisions (review by editor) (16 Oct 2023) by Homa Kheyrollah Pour
AR by Yungang Cao on behalf of the Authors (25 Oct 2023)  Author's response   Author's tracked changes   Manuscript 
ED: Publish as is (20 Nov 2023) by Homa Kheyrollah Pour
AR by Yungang Cao on behalf of the Authors (22 Nov 2023)
Download
Short summary
This study built a glacial lake dataset with 15376 samples in seven types and proposed an automatic method by two-stage (the semantic segmentation network and post-processing) optimizations to detect glacial lakes. The proposed method for glacial lake extraction has achieved the best results so far, in which the F1 score and IoU reached 0.945 and 0.907, respectively. The area of the minimum glacial lake that can be entirely and correctly extracted has been raised to the 100 m2 level.