Mapping of Glaciers on Horseshoe Island, Antarctic Peninsula, with Deep Learning Based on High-Resolution Orthophoto
Antarctica plays a key role in the hydrological cycle of the Earth’s climate system, with an ice sheet that is the largest block of ice that reserves Earth’s 90% of total ice volume and 70% of fresh water. Furthermore, the sustainability of the region is an important concern due to the challenges po...
Published in: | Drones |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/drones7020072 |
id |
ftmdpi:oai:mdpi.com:/2504-446X/7/2/72/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2504-446X/7/2/72/ 2023-08-20T04:01:28+02:00 Mapping of Glaciers on Horseshoe Island, Antarctic Peninsula, with Deep Learning Based on High-Resolution Orthophoto Mahmut Oğuz Selbesoğlu Tolga Bakirman Oleg Vassilev Burcu Ozsoy 2023-01-18 application/pdf https://doi.org/10.3390/drones7020072 EN eng Multidisciplinary Digital Publishing Institute Drones in Ecology https://dx.doi.org/10.3390/drones7020072 https://creativecommons.org/licenses/by/4.0/ Drones; Volume 7; Issue 2; Pages: 72 Antarctica deep learning Horseshoe glacier orthophoto Text 2023 ftmdpi https://doi.org/10.3390/drones7020072 2023-08-01T08:22:42Z Antarctica plays a key role in the hydrological cycle of the Earth’s climate system, with an ice sheet that is the largest block of ice that reserves Earth’s 90% of total ice volume and 70% of fresh water. Furthermore, the sustainability of the region is an important concern due to the challenges posed by melting glaciers that preserve the Earth’s heat balance by interacting with the Southern Ocean. Therefore, the monitoring of glaciers based on advanced deep learning approaches offers vital outcomes that are of great importance in revealing the effects of global warming. In this study, recent deep learning approaches were investigated in terms of their accuracy for the segmentation of glacier landforms in the Antarctic Peninsula. For this purpose, high-resolution orthophotos were generated based on UAV photogrammetry within the Sixth Turkish Antarctic Expedition in 2022. Segformer, DeepLabv3+ and K-Net deep learning methods were comparatively analyzed in terms of their accuracy. The results showed that K-Net provided efficient results with 99.62% accuracy, 99.58% intersection over union, 99.82% precision, 99.76% recall and 99.79% F1-score. Visual inspections also revealed that K-Net was able to preserve the fine details around the edges of the glaciers. Our proposed deep-learning-based method provides an accurate and sustainable solution for automatic glacier segmentation and monitoring. Text Antarc* Antarctic Antarctic Peninsula Antarctica Horseshoe Island Ice Sheet Southern Ocean MDPI Open Access Publishing Antarctic Southern Ocean The Antarctic Antarctic Peninsula Horseshoe Island ENVELOPE(-67.189,-67.189,-67.836,-67.836) Drones 7 2 72 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
Antarctica deep learning Horseshoe glacier orthophoto |
spellingShingle |
Antarctica deep learning Horseshoe glacier orthophoto Mahmut Oğuz Selbesoğlu Tolga Bakirman Oleg Vassilev Burcu Ozsoy Mapping of Glaciers on Horseshoe Island, Antarctic Peninsula, with Deep Learning Based on High-Resolution Orthophoto |
topic_facet |
Antarctica deep learning Horseshoe glacier orthophoto |
description |
Antarctica plays a key role in the hydrological cycle of the Earth’s climate system, with an ice sheet that is the largest block of ice that reserves Earth’s 90% of total ice volume and 70% of fresh water. Furthermore, the sustainability of the region is an important concern due to the challenges posed by melting glaciers that preserve the Earth’s heat balance by interacting with the Southern Ocean. Therefore, the monitoring of glaciers based on advanced deep learning approaches offers vital outcomes that are of great importance in revealing the effects of global warming. In this study, recent deep learning approaches were investigated in terms of their accuracy for the segmentation of glacier landforms in the Antarctic Peninsula. For this purpose, high-resolution orthophotos were generated based on UAV photogrammetry within the Sixth Turkish Antarctic Expedition in 2022. Segformer, DeepLabv3+ and K-Net deep learning methods were comparatively analyzed in terms of their accuracy. The results showed that K-Net provided efficient results with 99.62% accuracy, 99.58% intersection over union, 99.82% precision, 99.76% recall and 99.79% F1-score. Visual inspections also revealed that K-Net was able to preserve the fine details around the edges of the glaciers. Our proposed deep-learning-based method provides an accurate and sustainable solution for automatic glacier segmentation and monitoring. |
format |
Text |
author |
Mahmut Oğuz Selbesoğlu Tolga Bakirman Oleg Vassilev Burcu Ozsoy |
author_facet |
Mahmut Oğuz Selbesoğlu Tolga Bakirman Oleg Vassilev Burcu Ozsoy |
author_sort |
Mahmut Oğuz Selbesoğlu |
title |
Mapping of Glaciers on Horseshoe Island, Antarctic Peninsula, with Deep Learning Based on High-Resolution Orthophoto |
title_short |
Mapping of Glaciers on Horseshoe Island, Antarctic Peninsula, with Deep Learning Based on High-Resolution Orthophoto |
title_full |
Mapping of Glaciers on Horseshoe Island, Antarctic Peninsula, with Deep Learning Based on High-Resolution Orthophoto |
title_fullStr |
Mapping of Glaciers on Horseshoe Island, Antarctic Peninsula, with Deep Learning Based on High-Resolution Orthophoto |
title_full_unstemmed |
Mapping of Glaciers on Horseshoe Island, Antarctic Peninsula, with Deep Learning Based on High-Resolution Orthophoto |
title_sort |
mapping of glaciers on horseshoe island, antarctic peninsula, with deep learning based on high-resolution orthophoto |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2023 |
url |
https://doi.org/10.3390/drones7020072 |
long_lat |
ENVELOPE(-67.189,-67.189,-67.836,-67.836) |
geographic |
Antarctic Southern Ocean The Antarctic Antarctic Peninsula Horseshoe Island |
geographic_facet |
Antarctic Southern Ocean The Antarctic Antarctic Peninsula Horseshoe Island |
genre |
Antarc* Antarctic Antarctic Peninsula Antarctica Horseshoe Island Ice Sheet Southern Ocean |
genre_facet |
Antarc* Antarctic Antarctic Peninsula Antarctica Horseshoe Island Ice Sheet Southern Ocean |
op_source |
Drones; Volume 7; Issue 2; Pages: 72 |
op_relation |
Drones in Ecology https://dx.doi.org/10.3390/drones7020072 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/drones7020072 |
container_title |
Drones |
container_volume |
7 |
container_issue |
2 |
container_start_page |
72 |
_version_ |
1774724731435483136 |