Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms
Accurate identification of grounding lines is of immense importance for estimating the mass budgets of ocean-terminating ice sheets and glaciers of Antarctica and Greenland. In Differential Interferometric SAR (DInSAR) interferograms, human experts still largely manually digitize grounding lines. Th...
Published in: | IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium |
---|---|
Main Authors: | , , , |
Format: | Conference Object |
Language: | English |
Published: |
IEEE
2023
|
Subjects: | |
Online Access: | https://elib.dlr.de/199052/ https://elib.dlr.de/199052/1/Deep_Neural_Network_Based_Automatic_Grounding_Line_Delineation_In_Dinsar_Interferograms.pdf https://ieeexplore.ieee.org/document/10282372 |
id |
ftdlr:oai:elib.dlr.de:199052 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:199052 2024-05-19T07:29:37+00:00 Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms Ramanath Tarekere, Sindhu Krieger, Lukas Heidler, Konrad Floricioiu, Dana 2023-10-20 application/pdf https://elib.dlr.de/199052/ https://elib.dlr.de/199052/1/Deep_Neural_Network_Based_Automatic_Grounding_Line_Delineation_In_Dinsar_Interferograms.pdf https://ieeexplore.ieee.org/document/10282372 en eng IEEE https://elib.dlr.de/199052/1/Deep_Neural_Network_Based_Automatic_Grounding_Line_Delineation_In_Dinsar_Interferograms.pdf Ramanath Tarekere, Sindhu und Krieger, Lukas und Heidler, Konrad und Floricioiu, Dana (2023) Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms. In: International Geoscience and Remote Sensing Symposium (IGARSS), Seiten 183-186. IEEE. IGARSS 2023, 2023-07-16 - 2023-07-21, Pasadena, California, USA. doi:10.1109/IGARSS52108.2023.10282372 <https://doi.org/10.1109/IGARSS52108.2023.10282372>. ISBN 979-8-3503-2010-7. ISSN 2153-7003. SAR-Signalverarbeitung Konferenzbeitrag PeerReviewed 2023 ftdlr https://doi.org/10.1109/IGARSS52108.2023.10282372 2024-04-25T01:09:13Z Accurate identification of grounding lines is of immense importance for estimating the mass budgets of ocean-terminating ice sheets and glaciers of Antarctica and Greenland. In Differential Interferometric SAR (DInSAR) interferograms, human experts still largely manually digitize grounding lines. The time-consuming nature of this task makes it infeasible to produce timely, continent-wide grounding line mappings. This study employed a Deep Neural Network (DNN) to automate delineation. The Holistically-Nested Edge Detection (HED) network was trained in a supervised manner on features derived from interferometric phase, elevation data, ice velocity, tidal amplitude, atmospheric pressure and corresponding manual delineations. HED-generated lines achieved a median deviation of 209 m with a median absolute deviation of 153 m from manual delineations. The developed automatic pipeline demonstrates the potential for generating spatially and temporally dense mappings of the grounding line. Conference Object Antarc* Antarctica Greenland German Aerospace Center: elib - DLR electronic library IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium 183 186 |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
English |
topic |
SAR-Signalverarbeitung |
spellingShingle |
SAR-Signalverarbeitung Ramanath Tarekere, Sindhu Krieger, Lukas Heidler, Konrad Floricioiu, Dana Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms |
topic_facet |
SAR-Signalverarbeitung |
description |
Accurate identification of grounding lines is of immense importance for estimating the mass budgets of ocean-terminating ice sheets and glaciers of Antarctica and Greenland. In Differential Interferometric SAR (DInSAR) interferograms, human experts still largely manually digitize grounding lines. The time-consuming nature of this task makes it infeasible to produce timely, continent-wide grounding line mappings. This study employed a Deep Neural Network (DNN) to automate delineation. The Holistically-Nested Edge Detection (HED) network was trained in a supervised manner on features derived from interferometric phase, elevation data, ice velocity, tidal amplitude, atmospheric pressure and corresponding manual delineations. HED-generated lines achieved a median deviation of 209 m with a median absolute deviation of 153 m from manual delineations. The developed automatic pipeline demonstrates the potential for generating spatially and temporally dense mappings of the grounding line. |
format |
Conference Object |
author |
Ramanath Tarekere, Sindhu Krieger, Lukas Heidler, Konrad Floricioiu, Dana |
author_facet |
Ramanath Tarekere, Sindhu Krieger, Lukas Heidler, Konrad Floricioiu, Dana |
author_sort |
Ramanath Tarekere, Sindhu |
title |
Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms |
title_short |
Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms |
title_full |
Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms |
title_fullStr |
Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms |
title_full_unstemmed |
Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms |
title_sort |
deep neural network based automatic grounding line delineation in dinsar interferograms |
publisher |
IEEE |
publishDate |
2023 |
url |
https://elib.dlr.de/199052/ https://elib.dlr.de/199052/1/Deep_Neural_Network_Based_Automatic_Grounding_Line_Delineation_In_Dinsar_Interferograms.pdf https://ieeexplore.ieee.org/document/10282372 |
genre |
Antarc* Antarctica Greenland |
genre_facet |
Antarc* Antarctica Greenland |
op_relation |
https://elib.dlr.de/199052/1/Deep_Neural_Network_Based_Automatic_Grounding_Line_Delineation_In_Dinsar_Interferograms.pdf Ramanath Tarekere, Sindhu und Krieger, Lukas und Heidler, Konrad und Floricioiu, Dana (2023) Deep Neural Network Based Automatic Grounding Line Delineation In DInsar Interferograms. In: International Geoscience and Remote Sensing Symposium (IGARSS), Seiten 183-186. IEEE. IGARSS 2023, 2023-07-16 - 2023-07-21, Pasadena, California, USA. doi:10.1109/IGARSS52108.2023.10282372 <https://doi.org/10.1109/IGARSS52108.2023.10282372>. ISBN 979-8-3503-2010-7. ISSN 2153-7003. |
op_doi |
https://doi.org/10.1109/IGARSS52108.2023.10282372 |
container_title |
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium |
container_start_page |
183 |
op_container_end_page |
186 |
_version_ |
1799480311153688576 |