2022
DOI: 10.1109/jstars.2022.3189277
|View full text |Cite
|
Sign up to set email alerts
|

Long Time-Series Glacier Outlines in the Three-Rivers Headwater Region From 1986 to 2021 Based on Deep Learning

Abstract: The deep-learning-based approach has drawn significant attention in glacier extraction due to its advantages over traditional techniques. In this study, to verify the feasibility and effectiveness of LandsNet architecture for glacier extraction, we applied a modified LandsNet (M-LandsNet) to extract the glacier outlines in the Three-Rivers Headwater Region. The band ratio method, U-Net, U-Net++, GlacierNet, SaU-Net, U-Net+cSE and LandsNet, and two scenes were used for comparison. Analysis of the two scenes ind… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
9
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(9 citation statements)
references
References 65 publications
0
9
0
Order By: Relevance
“…Given the identified limitations presented in the aforementioned methods for identification of glacier terminal points, along with the estimation of area, different techniques are required to improve the analytical process. Although many new models are being developed by research teams that involve Deep Learning computer vision models (Chen et al 2022, Robson et al 2020, this is not the approach that is pursued in the current research. This work is a fusion of image processing techniques and more traditional statistical modeling involving the selected climate factors.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…Given the identified limitations presented in the aforementioned methods for identification of glacier terminal points, along with the estimation of area, different techniques are required to improve the analytical process. Although many new models are being developed by research teams that involve Deep Learning computer vision models (Chen et al 2022, Robson et al 2020, this is not the approach that is pursued in the current research. This work is a fusion of image processing techniques and more traditional statistical modeling involving the selected climate factors.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…The topography of the TRHR is mainly mountainous, and the elevation in the TRHR ranges widely from 2000 to 6,580 m, with an average elevation of 4,430 m. The TRHR has a typical plateau continental climate, with alternating hot and cold seasons, distinct wet and dry seasons . In 2008, the TRHR contained 1,555 glaciers distributed in the northwest, southwest, central, and eastern parts of the region and covering an area of 2,297.93 km 2 (Chen et al, 2022). Alpine meadows and alpine grasslands are the main vegetation types in the TRHR .…”
Section: Study Areamentioning
confidence: 99%
“…The topography of the TRHR is mainly mountainous, and the elevation in the TRHR ranges widely from 2000 to 6,580 m, with an average elevation of 4,430 m. The TRHR has a typical plateau continental climate, with alternating hot and cold seasons, distinct wet and dry seasons (Jiang et al, 2017). In 2008, the TRHR contained 1,555 glaciers distributed in the northwest, southwest, central, and eastern parts of the region and covering an area of 2,297.93 km 2 (Chen et al, 2022). Alpine meadows and alpine grasslands are the main vegetation types in the TRHR (Liu et al, 2008).…”
Section: Study Areamentioning
confidence: 99%