Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network
The mass loss of the Greenland Ice Sheet (GrIS) has implications for global sea level rise, and surface meltwater is an important factor that affects the mass balance. Supraglacial lakes (SGLs), which are representative and identifiable hydrologic features of surface meltwater on GrIS, are a means o...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-03-01
|
Series: | Water |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4441/12/3/891 |
id |
doaj-3979c85b40e84d73b105eed57994a9b8 |
---|---|
record_format |
Article |
spelling |
doaj-3979c85b40e84d73b105eed57994a9b82020-11-25T03:10:15ZengMDPI AGWater2073-44412020-03-0112389110.3390/w12030891w12030891Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural NetworkJiawei Yuan0Zhaohui Chi1Xiao Cheng2Tao Zhang3Tian Li4Zhuoqi Chen5State Key Laboratory of Remote Sensing Science, College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, ChinaDepartment of Geography, Texas A&M University, College Station, TX 77843, USAState Key Laboratory of Remote Sensing Science, College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Jointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of Sciences, Beijing 100875, ChinaSchool of Geographical Sciences, University of Bristol, Bristol BS8 1QU, UKState Key Laboratory of Remote Sensing Science, College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, ChinaThe mass loss of the Greenland Ice Sheet (GrIS) has implications for global sea level rise, and surface meltwater is an important factor that affects the mass balance. Supraglacial lakes (SGLs), which are representative and identifiable hydrologic features of surface meltwater on GrIS, are a means of assessing surface ablation temporally and spatially. In this study, we have developed a robust method to automatically extract SGLs by testing the widely distributed SGLs area—in southwest Greenland (68°00′ N−70°00′ N, 48°00′ W−51°30′ W), and documented their dynamics from 2014 to 2018 using Landsat 8 OLI images. This method identifies water using Convolutional Neural Networks (CNN) and then extracts SGLs with morphological and geometrical algorithms. CNN combines spectral and spatial features and shows better water identification results than the widely used adaptive thresholding method (Otsu), and two machine learning methods (Random Forests (RF) and Support Vector Machine (SVM)). Our results show that the total SGLs area varied between 158 and 393 km<sup>2</sup> during 2014 to 2018; the area increased from 2014 to 2015, then decreased and reached the lowest point (158.73 km<sup>2</sup>) in 2018, when the most limited surface melting was observed. SGLs were most active during the melt season in 2015 with a quantity of 700 and a total area of 393.36 km<sup>2</sup>. The largest individual lake developed in 2016, with an area of 9.30 km<sup>2</sup>. As for the elevation, SGLs were most active in the area, with the elevation ranging from 1000 to 1500 m above sea level, and SGLs in 2016 were distributed at higher elevations than in other years. Our work proposes a method to extract SGLs accurately and efficiently. More importantly, this study is expected to provide data support to other studies monitoring the surface hydrological system and mass balance of the GrIS.https://www.mdpi.com/2073-4441/12/3/891supraglacial lakesconvolutional neural networks (cnn)landsat 8 oli imagesmorphological and geometrical algorithmschange detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jiawei Yuan Zhaohui Chi Xiao Cheng Tao Zhang Tian Li Zhuoqi Chen |
spellingShingle |
Jiawei Yuan Zhaohui Chi Xiao Cheng Tao Zhang Tian Li Zhuoqi Chen Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network Water supraglacial lakes convolutional neural networks (cnn) landsat 8 oli images morphological and geometrical algorithms change detection |
author_facet |
Jiawei Yuan Zhaohui Chi Xiao Cheng Tao Zhang Tian Li Zhuoqi Chen |
author_sort |
Jiawei Yuan |
title |
Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network |
title_short |
Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network |
title_full |
Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network |
title_fullStr |
Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network |
title_full_unstemmed |
Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network |
title_sort |
automatic extraction of supraglacial lakes in southwest greenland during the 2014–2018 melt seasons based on convolutional neural network |
publisher |
MDPI AG |
series |
Water |
issn |
2073-4441 |
publishDate |
2020-03-01 |
description |
The mass loss of the Greenland Ice Sheet (GrIS) has implications for global sea level rise, and surface meltwater is an important factor that affects the mass balance. Supraglacial lakes (SGLs), which are representative and identifiable hydrologic features of surface meltwater on GrIS, are a means of assessing surface ablation temporally and spatially. In this study, we have developed a robust method to automatically extract SGLs by testing the widely distributed SGLs area—in southwest Greenland (68°00′ N−70°00′ N, 48°00′ W−51°30′ W), and documented their dynamics from 2014 to 2018 using Landsat 8 OLI images. This method identifies water using Convolutional Neural Networks (CNN) and then extracts SGLs with morphological and geometrical algorithms. CNN combines spectral and spatial features and shows better water identification results than the widely used adaptive thresholding method (Otsu), and two machine learning methods (Random Forests (RF) and Support Vector Machine (SVM)). Our results show that the total SGLs area varied between 158 and 393 km<sup>2</sup> during 2014 to 2018; the area increased from 2014 to 2015, then decreased and reached the lowest point (158.73 km<sup>2</sup>) in 2018, when the most limited surface melting was observed. SGLs were most active during the melt season in 2015 with a quantity of 700 and a total area of 393.36 km<sup>2</sup>. The largest individual lake developed in 2016, with an area of 9.30 km<sup>2</sup>. As for the elevation, SGLs were most active in the area, with the elevation ranging from 1000 to 1500 m above sea level, and SGLs in 2016 were distributed at higher elevations than in other years. Our work proposes a method to extract SGLs accurately and efficiently. More importantly, this study is expected to provide data support to other studies monitoring the surface hydrological system and mass balance of the GrIS. |
topic |
supraglacial lakes convolutional neural networks (cnn) landsat 8 oli images morphological and geometrical algorithms change detection |
url |
https://www.mdpi.com/2073-4441/12/3/891 |
work_keys_str_mv |
AT jiaweiyuan automaticextractionofsupraglaciallakesinsouthwestgreenlandduringthe20142018meltseasonsbasedonconvolutionalneuralnetwork AT zhaohuichi automaticextractionofsupraglaciallakesinsouthwestgreenlandduringthe20142018meltseasonsbasedonconvolutionalneuralnetwork AT xiaocheng automaticextractionofsupraglaciallakesinsouthwestgreenlandduringthe20142018meltseasonsbasedonconvolutionalneuralnetwork AT taozhang automaticextractionofsupraglaciallakesinsouthwestgreenlandduringthe20142018meltseasonsbasedonconvolutionalneuralnetwork AT tianli automaticextractionofsupraglaciallakesinsouthwestgreenlandduringthe20142018meltseasonsbasedonconvolutionalneuralnetwork AT zhuoqichen automaticextractionofsupraglaciallakesinsouthwestgreenlandduringthe20142018meltseasonsbasedonconvolutionalneuralnetwork |
_version_ |
1724659625021669376 |