How to Get the Most Out of U-Net for Glacier Calving Front Segmentation
The melting of ice sheets and glaciers is one of the main contributors to global sea-level rise. Hence, continuous monitoring of glacier changes and in particular the mapping of positional changes of their calving front is of significant importance. This delineation process, in general, has been car...
Published in: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1109/JSTARS.2022.3148033 https://doaj.org/article/d20a2bb1fc334860ac5916f8a86cbb13 |
id |
ftdoajarticles:oai:doaj.org/article:d20a2bb1fc334860ac5916f8a86cbb13 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:d20a2bb1fc334860ac5916f8a86cbb13 2023-05-15T14:01:49+02:00 How to Get the Most Out of U-Net for Glacier Calving Front Segmentation Maniraman Periyasamy Amirabbas Davari Thorsten Seehaus Matthias Braun Andreas Maier Vincent Christlein 2022-01-01T00:00:00Z https://doi.org/10.1109/JSTARS.2022.3148033 https://doaj.org/article/d20a2bb1fc334860ac5916f8a86cbb13 EN eng IEEE https://ieeexplore.ieee.org/document/9699423/ https://doaj.org/toc/2151-1535 2151-1535 doi:10.1109/JSTARS.2022.3148033 https://doaj.org/article/d20a2bb1fc334860ac5916f8a86cbb13 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 15, Pp 1712-1723 (2022) Glacier calving front segmentation optimized U-Net semantic segmentation Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 article 2022 ftdoajarticles https://doi.org/10.1109/JSTARS.2022.3148033 2022-12-31T11:23:16Z The melting of ice sheets and glaciers is one of the main contributors to global sea-level rise. Hence, continuous monitoring of glacier changes and in particular the mapping of positional changes of their calving front is of significant importance. This delineation process, in general, has been carried out manually, which is time-consuming and not feasible for the abundance of available data within the past decade. Automatic delineation of the glacier fronts in synthetic aperture radar (SAR) images can be performed using deep learning-based U-Net models. This article aims to study and survey the components of a U-Net model and optimize the model to get the most out of U-Net for glacier (calving front) segmentation. We trained the U-Net to segment the SAR images of Sjogren-Inlet and Dinsmoore–Bombardier–Edgworth glacier systems on the Antarctica Peninsula region taken by ERS-1/2, Envisat, RadarSAT-1, ALOS, TerraSAR-X, and TanDEM-X missions. The U-Net model was optimized in six aspects. The first two aspects, namely data preprocessing and data augmentation, enhanced the representation of information in the image. The remaining four aspects optimized the feature extraction of U-Net by finding the best-suited loss function, bottleneck, normalization technique, and dropouts for the glacier segmentation task. The optimized U-Net model achieves a dice coefficient score of 0.9378 with a 20% improvement over the baseline U-Net model, which achieved a score of 0.7377. This segmentation result is further postprocessed to delineate the calving front. The optimized U-Net model shows 23% improvement in the glacier front delineation compared to the baseline model. Article in Journal/Newspaper Antarc* Antarctica Directory of Open Access Journals: DOAJ Articles Sjogren ENVELOPE(-58.867,-58.867,-64.233,-64.233) IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 15 1712 1723 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Glacier calving front segmentation optimized U-Net semantic segmentation Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 |
spellingShingle |
Glacier calving front segmentation optimized U-Net semantic segmentation Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Maniraman Periyasamy Amirabbas Davari Thorsten Seehaus Matthias Braun Andreas Maier Vincent Christlein How to Get the Most Out of U-Net for Glacier Calving Front Segmentation |
topic_facet |
Glacier calving front segmentation optimized U-Net semantic segmentation Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 |
description |
The melting of ice sheets and glaciers is one of the main contributors to global sea-level rise. Hence, continuous monitoring of glacier changes and in particular the mapping of positional changes of their calving front is of significant importance. This delineation process, in general, has been carried out manually, which is time-consuming and not feasible for the abundance of available data within the past decade. Automatic delineation of the glacier fronts in synthetic aperture radar (SAR) images can be performed using deep learning-based U-Net models. This article aims to study and survey the components of a U-Net model and optimize the model to get the most out of U-Net for glacier (calving front) segmentation. We trained the U-Net to segment the SAR images of Sjogren-Inlet and Dinsmoore–Bombardier–Edgworth glacier systems on the Antarctica Peninsula region taken by ERS-1/2, Envisat, RadarSAT-1, ALOS, TerraSAR-X, and TanDEM-X missions. The U-Net model was optimized in six aspects. The first two aspects, namely data preprocessing and data augmentation, enhanced the representation of information in the image. The remaining four aspects optimized the feature extraction of U-Net by finding the best-suited loss function, bottleneck, normalization technique, and dropouts for the glacier segmentation task. The optimized U-Net model achieves a dice coefficient score of 0.9378 with a 20% improvement over the baseline U-Net model, which achieved a score of 0.7377. This segmentation result is further postprocessed to delineate the calving front. The optimized U-Net model shows 23% improvement in the glacier front delineation compared to the baseline model. |
format |
Article in Journal/Newspaper |
author |
Maniraman Periyasamy Amirabbas Davari Thorsten Seehaus Matthias Braun Andreas Maier Vincent Christlein |
author_facet |
Maniraman Periyasamy Amirabbas Davari Thorsten Seehaus Matthias Braun Andreas Maier Vincent Christlein |
author_sort |
Maniraman Periyasamy |
title |
How to Get the Most Out of U-Net for Glacier Calving Front Segmentation |
title_short |
How to Get the Most Out of U-Net for Glacier Calving Front Segmentation |
title_full |
How to Get the Most Out of U-Net for Glacier Calving Front Segmentation |
title_fullStr |
How to Get the Most Out of U-Net for Glacier Calving Front Segmentation |
title_full_unstemmed |
How to Get the Most Out of U-Net for Glacier Calving Front Segmentation |
title_sort |
how to get the most out of u-net for glacier calving front segmentation |
publisher |
IEEE |
publishDate |
2022 |
url |
https://doi.org/10.1109/JSTARS.2022.3148033 https://doaj.org/article/d20a2bb1fc334860ac5916f8a86cbb13 |
long_lat |
ENVELOPE(-58.867,-58.867,-64.233,-64.233) |
geographic |
Sjogren |
geographic_facet |
Sjogren |
genre |
Antarc* Antarctica |
genre_facet |
Antarc* Antarctica |
op_source |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 15, Pp 1712-1723 (2022) |
op_relation |
https://ieeexplore.ieee.org/document/9699423/ https://doaj.org/toc/2151-1535 2151-1535 doi:10.1109/JSTARS.2022.3148033 https://doaj.org/article/d20a2bb1fc334860ac5916f8a86cbb13 |
op_doi |
https://doi.org/10.1109/JSTARS.2022.3148033 |
container_title |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
container_volume |
15 |
container_start_page |
1712 |
op_container_end_page |
1723 |
_version_ |
1766271855280259072 |