A Deep Learning Architecture for Semantic Segmentation of Radar Sounder Data
During the last decades, radar sounders provided direct measurements (radargrams) of the Earth’s polar caps’ subsurface. Radargrams are of critical importance for a better understanding of glaciologic structures and processes of the ice sheet in the framework of climate change. This article aims to...
Published in: | IEEE Transactions on Geoscience and Remote Sensing |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | http://hdl.handle.net/11572/331172 https://doi.org/10.1109/TGRS.2021.3125773 https://ieeexplore.ieee.org/document/9605569 |
id |
ftutrentoiris:oai:iris.unitn.it:11572/331172 |
---|---|
record_format |
openpolar |
spelling |
ftutrentoiris:oai:iris.unitn.it:11572/331172 2024-02-11T09:58:25+01:00 A Deep Learning Architecture for Semantic Segmentation of Radar Sounder Data Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo 2022 STAMPA http://hdl.handle.net/11572/331172 https://doi.org/10.1109/TGRS.2021.3125773 https://ieeexplore.ieee.org/document/9605569 eng eng info:eu-repo/semantics/altIdentifier/wos/WOS:000756892900036 volume:2022/60 firstpage:450651401 lastpage:450651414 numberofpages:14 journal:IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING http://hdl.handle.net/11572/331172 doi:10.1109/TGRS.2021.3125773 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85125462306 https://ieeexplore.ieee.org/document/9605569 info:eu-repo/semantics/closedAccess Basal boundary conditions basal units convolutional neural network cryosphere deep learning radar sounder (RS) remote sensing info:eu-repo/semantics/article 2022 ftutrentoiris https://doi.org/10.1109/TGRS.2021.3125773 2024-01-23T23:12:20Z During the last decades, radar sounders provided direct measurements (radargrams) of the Earth’s polar caps’ subsurface. Radargrams are of critical importance for a better understanding of glaciologic structures and processes of the ice sheet in the framework of climate change. This article aims to automatically extract information on basal boundary conditions given their substantial relevance for modeling the ice-sheet processes, such as the sliding. We introduce a novel automatic method based on deep learning to detect the basal layer and basal units in radargrams acquired in the inland of icy areas. Radargrams are segmented into englacial layers, bedrock, basal units, and noise-limited regions; the latter includes the echo-free zone (EFZ), thermal noise, and signal perturbation. The network is a U-Net with attention gates and the Atrous Spatial Pyramid Pooling (ASPP) module that automatically extract semantically meaningful features at different scales. Experimental results on two datasets acquired in north Greenland and west Antarctica by the Multichannel Coherent Radar Depth Sounder (MCoRDS3) indicate a high overall segmentation accuracy. The accuracy of basal ice and signal perturbation detection is high, and that of the other classes is comparable with the literature techniques based on handcrafted features. The results show the effectiveness of the proposed method in automatically extracting semantically meaningful features to segment radargrams and map the basal layer and basal units. Article in Journal/Newspaper Antarc* Antarctica Greenland Ice Sheet North Greenland West Antarctica Università degli Studi di Trento: CINECA IRIS Greenland Pyramid ENVELOPE(157.300,157.300,-81.333,-81.333) West Antarctica IEEE Transactions on Geoscience and Remote Sensing 60 1 14 |
institution |
Open Polar |
collection |
Università degli Studi di Trento: CINECA IRIS |
op_collection_id |
ftutrentoiris |
language |
English |
topic |
Basal boundary conditions basal units convolutional neural network cryosphere deep learning radar sounder (RS) remote sensing |
spellingShingle |
Basal boundary conditions basal units convolutional neural network cryosphere deep learning radar sounder (RS) remote sensing Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo A Deep Learning Architecture for Semantic Segmentation of Radar Sounder Data |
topic_facet |
Basal boundary conditions basal units convolutional neural network cryosphere deep learning radar sounder (RS) remote sensing |
description |
During the last decades, radar sounders provided direct measurements (radargrams) of the Earth’s polar caps’ subsurface. Radargrams are of critical importance for a better understanding of glaciologic structures and processes of the ice sheet in the framework of climate change. This article aims to automatically extract information on basal boundary conditions given their substantial relevance for modeling the ice-sheet processes, such as the sliding. We introduce a novel automatic method based on deep learning to detect the basal layer and basal units in radargrams acquired in the inland of icy areas. Radargrams are segmented into englacial layers, bedrock, basal units, and noise-limited regions; the latter includes the echo-free zone (EFZ), thermal noise, and signal perturbation. The network is a U-Net with attention gates and the Atrous Spatial Pyramid Pooling (ASPP) module that automatically extract semantically meaningful features at different scales. Experimental results on two datasets acquired in north Greenland and west Antarctica by the Multichannel Coherent Radar Depth Sounder (MCoRDS3) indicate a high overall segmentation accuracy. The accuracy of basal ice and signal perturbation detection is high, and that of the other classes is comparable with the literature techniques based on handcrafted features. The results show the effectiveness of the proposed method in automatically extracting semantically meaningful features to segment radargrams and map the basal layer and basal units. |
author2 |
Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo |
format |
Article in Journal/Newspaper |
author |
Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo |
author_facet |
Donini, Elena Bovolo, Francesca Bruzzone, Lorenzo |
author_sort |
Donini, Elena |
title |
A Deep Learning Architecture for Semantic Segmentation of Radar Sounder Data |
title_short |
A Deep Learning Architecture for Semantic Segmentation of Radar Sounder Data |
title_full |
A Deep Learning Architecture for Semantic Segmentation of Radar Sounder Data |
title_fullStr |
A Deep Learning Architecture for Semantic Segmentation of Radar Sounder Data |
title_full_unstemmed |
A Deep Learning Architecture for Semantic Segmentation of Radar Sounder Data |
title_sort |
deep learning architecture for semantic segmentation of radar sounder data |
publishDate |
2022 |
url |
http://hdl.handle.net/11572/331172 https://doi.org/10.1109/TGRS.2021.3125773 https://ieeexplore.ieee.org/document/9605569 |
long_lat |
ENVELOPE(157.300,157.300,-81.333,-81.333) |
geographic |
Greenland Pyramid West Antarctica |
geographic_facet |
Greenland Pyramid West Antarctica |
genre |
Antarc* Antarctica Greenland Ice Sheet North Greenland West Antarctica |
genre_facet |
Antarc* Antarctica Greenland Ice Sheet North Greenland West Antarctica |
op_relation |
info:eu-repo/semantics/altIdentifier/wos/WOS:000756892900036 volume:2022/60 firstpage:450651401 lastpage:450651414 numberofpages:14 journal:IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING http://hdl.handle.net/11572/331172 doi:10.1109/TGRS.2021.3125773 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85125462306 https://ieeexplore.ieee.org/document/9605569 |
op_rights |
info:eu-repo/semantics/closedAccess |
op_doi |
https://doi.org/10.1109/TGRS.2021.3125773 |
container_title |
IEEE Transactions on Geoscience and Remote Sensing |
container_volume |
60 |
container_start_page |
1 |
op_container_end_page |
14 |
_version_ |
1790594052646764544 |