Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study
The continuous and precise mapping of glacier calving fronts is essential for monitoring and understanding rapid glacier changes in Antarctica and Greenland, which have the potential for significant sea level rise within the current century. This effort has been mostly restricted to the slow and pai...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2019
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs11010074 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/11/1/74/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/11/1/74/ 2023-08-20T04:01:58+02:00 Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study Yara Mohajerani Michael Wood Isabella Velicogna Eric Rignot agris 2019-01-03 application/pdf https://doi.org/10.3390/rs11010074 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/rs11010074 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 11; Issue 1; Pages: 74 calving front image segmentation U-Net convolutional neural network machine learning Greenland Text 2019 ftmdpi https://doi.org/10.3390/rs11010074 2023-07-31T21:56:41Z The continuous and precise mapping of glacier calving fronts is essential for monitoring and understanding rapid glacier changes in Antarctica and Greenland, which have the potential for significant sea level rise within the current century. This effort has been mostly restricted to the slow and painstaking manual digitalization of the calving front positions in thousands of satellite imagery products. Here, we have developed a machine learning toolkit to automatically detect glacier calving front margins in satellite imagery. The toolkit is based on semantic image segmentation using Convolutional Neural Networks (CNN) with a modified U-Net architecture to isolate the calving fronts from satellite images after having been trained with a dataset of images and their corresponding manually-determined calving fronts. As a case study we train our neural network on a varied set of Landsat images with lowered resolutions from Jakobshavn, Sverdrup, and Kangerlussuaq glaciers, Greenland and test the results on images from Helheim glacier, Greenland to evaluate the performance of the approach. The neural network is able to identify the calving front in new images with a mean deviation of 96.3 m from the true fronts, equivalent to 1.97 pixels on average, while the corresponding error for manually-determined fronts on the same resolution images is 92.5 m (1.89 pixels). We find that the trained neural network significantly outperforms common edge detection techniques, and can be used to continuously map out calving-ice fronts with a variety of data products. Text Antarc* Antarctica glacier Greenland Jakobshavn Kangerlussuaq MDPI Open Access Publishing Greenland Kangerlussuaq ENVELOPE(-55.633,-55.633,72.633,72.633) Remote Sensing 11 1 74 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
calving front image segmentation U-Net convolutional neural network machine learning Greenland |
spellingShingle |
calving front image segmentation U-Net convolutional neural network machine learning Greenland Yara Mohajerani Michael Wood Isabella Velicogna Eric Rignot Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study |
topic_facet |
calving front image segmentation U-Net convolutional neural network machine learning Greenland |
description |
The continuous and precise mapping of glacier calving fronts is essential for monitoring and understanding rapid glacier changes in Antarctica and Greenland, which have the potential for significant sea level rise within the current century. This effort has been mostly restricted to the slow and painstaking manual digitalization of the calving front positions in thousands of satellite imagery products. Here, we have developed a machine learning toolkit to automatically detect glacier calving front margins in satellite imagery. The toolkit is based on semantic image segmentation using Convolutional Neural Networks (CNN) with a modified U-Net architecture to isolate the calving fronts from satellite images after having been trained with a dataset of images and their corresponding manually-determined calving fronts. As a case study we train our neural network on a varied set of Landsat images with lowered resolutions from Jakobshavn, Sverdrup, and Kangerlussuaq glaciers, Greenland and test the results on images from Helheim glacier, Greenland to evaluate the performance of the approach. The neural network is able to identify the calving front in new images with a mean deviation of 96.3 m from the true fronts, equivalent to 1.97 pixels on average, while the corresponding error for manually-determined fronts on the same resolution images is 92.5 m (1.89 pixels). We find that the trained neural network significantly outperforms common edge detection techniques, and can be used to continuously map out calving-ice fronts with a variety of data products. |
format |
Text |
author |
Yara Mohajerani Michael Wood Isabella Velicogna Eric Rignot |
author_facet |
Yara Mohajerani Michael Wood Isabella Velicogna Eric Rignot |
author_sort |
Yara Mohajerani |
title |
Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study |
title_short |
Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study |
title_full |
Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study |
title_fullStr |
Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study |
title_full_unstemmed |
Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study |
title_sort |
detection of glacier calving margins with convolutional neural networks: a case study |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2019 |
url |
https://doi.org/10.3390/rs11010074 |
op_coverage |
agris |
long_lat |
ENVELOPE(-55.633,-55.633,72.633,72.633) |
geographic |
Greenland Kangerlussuaq |
geographic_facet |
Greenland Kangerlussuaq |
genre |
Antarc* Antarctica glacier Greenland Jakobshavn Kangerlussuaq |
genre_facet |
Antarc* Antarctica glacier Greenland Jakobshavn Kangerlussuaq |
op_source |
Remote Sensing; Volume 11; Issue 1; Pages: 74 |
op_relation |
https://dx.doi.org/10.3390/rs11010074 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs11010074 |
container_title |
Remote Sensing |
container_volume |
11 |
container_issue |
1 |
container_start_page |
74 |
_version_ |
1774712361352953856 |