Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods
Remote sensing extraction of glacial lakes is an effective way of monitoring water body distribution and outburst events. At present, the lack of glacial lake datasets and the edge recognition problem of semantic segmentation networks lead to poor accuracy and inaccurate outlines of glacial lakes. T...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2024
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-18-153-2024 https://doaj.org/article/a5292ed4e63b4e32a46ae824b307df9e |
id |
ftdoajarticles:oai:doaj.org/article:a5292ed4e63b4e32a46ae824b307df9e |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:a5292ed4e63b4e32a46ae824b307df9e 2024-02-11T10:09:08+01:00 Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods Y. Cao R. Pan M. Pan R. Lei P. Du X. Bai 2024-01-01T00:00:00Z https://doi.org/10.5194/tc-18-153-2024 https://doaj.org/article/a5292ed4e63b4e32a46ae824b307df9e EN eng Copernicus Publications https://tc.copernicus.org/articles/18/153/2024/tc-18-153-2024.pdf https://doaj.org/toc/1994-0416 https://doaj.org/toc/1994-0424 doi:10.5194/tc-18-153-2024 1994-0416 1994-0424 https://doaj.org/article/a5292ed4e63b4e32a46ae824b307df9e The Cryosphere, Vol 18, Pp 153-168 (2024) Environmental sciences GE1-350 Geology QE1-996.5 article 2024 ftdoajarticles https://doi.org/10.5194/tc-18-153-2024 2024-01-14T01:51:33Z Remote sensing extraction of glacial lakes is an effective way of monitoring water body distribution and outburst events. At present, the lack of glacial lake datasets and the edge recognition problem of semantic segmentation networks lead to poor accuracy and inaccurate outlines of glacial lakes. Therefore, this study constructed a high-resolution dataset containing seven types of glacial lakes and proposed a refined glacial lake extraction method, which combines the LinkNet50 network for rough extraction and simple linear iterative clustering (SLIC) dense conditional random field (DenseCRF) for optimization. The results show that (1) with Google Earth images of 0.52 m resolution in the study area, the recall, precision, F1 score, and intersection over union (IoU) of glacial lake extraction based on the proposed method are 96.52 %, 92.49 %, 94.46 %, and 90.69 %, respectively, and (2) with the Google Earth images of 2.11 m resolution in the Qomolangma National Nature Reserve, 2300 glacial lakes with a total area of 65.17 km 2 were detected by the proposed method. The area of the minimum glacial lake that can be extracted is 160 m 2 (less than 6×6 pixels). This method has advantages in small glacial lake extraction and refined outline detection, which can be applied to extracting glacial lakes in the high-Asia region with high-resolution images. Article in Journal/Newspaper The Cryosphere Directory of Open Access Journals: DOAJ Articles Glacial Lake ENVELOPE(-129.463,-129.463,58.259,58.259) The Cryosphere 18 1 153 168 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Environmental sciences GE1-350 Geology QE1-996.5 |
spellingShingle |
Environmental sciences GE1-350 Geology QE1-996.5 Y. Cao R. Pan M. Pan R. Lei P. Du X. Bai Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods |
topic_facet |
Environmental sciences GE1-350 Geology QE1-996.5 |
description |
Remote sensing extraction of glacial lakes is an effective way of monitoring water body distribution and outburst events. At present, the lack of glacial lake datasets and the edge recognition problem of semantic segmentation networks lead to poor accuracy and inaccurate outlines of glacial lakes. Therefore, this study constructed a high-resolution dataset containing seven types of glacial lakes and proposed a refined glacial lake extraction method, which combines the LinkNet50 network for rough extraction and simple linear iterative clustering (SLIC) dense conditional random field (DenseCRF) for optimization. The results show that (1) with Google Earth images of 0.52 m resolution in the study area, the recall, precision, F1 score, and intersection over union (IoU) of glacial lake extraction based on the proposed method are 96.52 %, 92.49 %, 94.46 %, and 90.69 %, respectively, and (2) with the Google Earth images of 2.11 m resolution in the Qomolangma National Nature Reserve, 2300 glacial lakes with a total area of 65.17 km 2 were detected by the proposed method. The area of the minimum glacial lake that can be extracted is 160 m 2 (less than 6×6 pixels). This method has advantages in small glacial lake extraction and refined outline detection, which can be applied to extracting glacial lakes in the high-Asia region with high-resolution images. |
format |
Article in Journal/Newspaper |
author |
Y. Cao R. Pan M. Pan R. Lei P. Du X. Bai |
author_facet |
Y. Cao R. Pan M. Pan R. Lei P. Du X. Bai |
author_sort |
Y. Cao |
title |
Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods |
title_short |
Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods |
title_full |
Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods |
title_fullStr |
Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods |
title_full_unstemmed |
Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods |
title_sort |
refined glacial lake extraction in a high-asia region by deep neural network and superpixel-based conditional random field methods |
publisher |
Copernicus Publications |
publishDate |
2024 |
url |
https://doi.org/10.5194/tc-18-153-2024 https://doaj.org/article/a5292ed4e63b4e32a46ae824b307df9e |
long_lat |
ENVELOPE(-129.463,-129.463,58.259,58.259) |
geographic |
Glacial Lake |
geographic_facet |
Glacial Lake |
genre |
The Cryosphere |
genre_facet |
The Cryosphere |
op_source |
The Cryosphere, Vol 18, Pp 153-168 (2024) |
op_relation |
https://tc.copernicus.org/articles/18/153/2024/tc-18-153-2024.pdf https://doaj.org/toc/1994-0416 https://doaj.org/toc/1994-0424 doi:10.5194/tc-18-153-2024 1994-0416 1994-0424 https://doaj.org/article/a5292ed4e63b4e32a46ae824b307df9e |
op_doi |
https://doi.org/10.5194/tc-18-153-2024 |
container_title |
The Cryosphere |
container_volume |
18 |
container_issue |
1 |
container_start_page |
153 |
op_container_end_page |
168 |
_version_ |
1790608864686637056 |