Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements
Retrieval of sea ice types using Synthetic Aperture Radar (SAR) has the potential for near real-time and high resolution monitoring of the polar regions throughout the year. The core challenge of the idea has, since its inception, been the unavailability of in-situ measurements of the ice. Not only...
Main Authors: | , , , , , , , |
---|---|
Format: | Conference Object |
Language: | unknown |
Published: |
2023
|
Subjects: | |
Online Access: | https://elib.dlr.de/192994/ https://mosaic.colorado.edu/sites/default/files/Abstract_Assignments_Conference_2022.pdf |
id |
ftdlr:oai:elib.dlr.de:192994 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:192994 2024-05-19T07:48:19+00:00 Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements Kortum, Karl Singha, Suman Spreen, Gunnar Jutila, Arttu Hutter, Nils Birnbaum, Gerit Ricker, Robert von Albedyll, Luisa 2023-02-14 https://elib.dlr.de/192994/ https://mosaic.colorado.edu/sites/default/files/Abstract_Assignments_Conference_2022.pdf unknown Kortum, Karl und Singha, Suman und Spreen, Gunnar und Jutila, Arttu und Hutter, Nils und Birnbaum, Gerit und Ricker, Robert und von Albedyll, Luisa (2023) Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements. 2nd MOSAiC Science Conference, 2023-02-13 - 2023-02-17, Boulder Colorado, USA. SAR-Signalverarbeitung Konferenzbeitrag NonPeerReviewed 2023 ftdlr 2024-04-25T01:05:25Z Retrieval of sea ice types using Synthetic Aperture Radar (SAR) has the potential for near real-time and high resolution monitoring of the polar regions throughout the year. The core challenge of the idea has, since its inception, been the unavailability of in-situ measurements of the ice. Not only does this impede the rate at which progress can be made, progress itself becomes hard to recognise as we do not have extensive in-situ data to validate the results. Using helicopter-borne Airborne Laser Scanner (ALS) data and near coincident SAR acquisitions from the MOSAiC mission we can alleviate this problem with twenty matched product pairs. We compare five different deep learning classifiers and can establish their performances for ice types directly derived from the ALS measurement. We find a clear discrepancy between methods which are able to learn from the class distributions (segmentation) and those that cannot (classification). These findings infer a limit of the validity of classifiers trained from e.g. ice-charts, where the spatial class distributions are not covered well by the data. For the first time we can compute accuracies of modern classifiers for SAR-based retrieval, which are truly representative of their real-world performance. Conference Object Sea ice German Aerospace Center: elib - DLR electronic library |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
unknown |
topic |
SAR-Signalverarbeitung |
spellingShingle |
SAR-Signalverarbeitung Kortum, Karl Singha, Suman Spreen, Gunnar Jutila, Arttu Hutter, Nils Birnbaum, Gerit Ricker, Robert von Albedyll, Luisa Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements |
topic_facet |
SAR-Signalverarbeitung |
description |
Retrieval of sea ice types using Synthetic Aperture Radar (SAR) has the potential for near real-time and high resolution monitoring of the polar regions throughout the year. The core challenge of the idea has, since its inception, been the unavailability of in-situ measurements of the ice. Not only does this impede the rate at which progress can be made, progress itself becomes hard to recognise as we do not have extensive in-situ data to validate the results. Using helicopter-borne Airborne Laser Scanner (ALS) data and near coincident SAR acquisitions from the MOSAiC mission we can alleviate this problem with twenty matched product pairs. We compare five different deep learning classifiers and can establish their performances for ice types directly derived from the ALS measurement. We find a clear discrepancy between methods which are able to learn from the class distributions (segmentation) and those that cannot (classification). These findings infer a limit of the validity of classifiers trained from e.g. ice-charts, where the spatial class distributions are not covered well by the data. For the first time we can compute accuracies of modern classifiers for SAR-based retrieval, which are truly representative of their real-world performance. |
format |
Conference Object |
author |
Kortum, Karl Singha, Suman Spreen, Gunnar Jutila, Arttu Hutter, Nils Birnbaum, Gerit Ricker, Robert von Albedyll, Luisa |
author_facet |
Kortum, Karl Singha, Suman Spreen, Gunnar Jutila, Arttu Hutter, Nils Birnbaum, Gerit Ricker, Robert von Albedyll, Luisa |
author_sort |
Kortum, Karl |
title |
Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements |
title_short |
Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements |
title_full |
Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements |
title_fullStr |
Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements |
title_full_unstemmed |
Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements |
title_sort |
extrapolating airborne laser scanner derived sea ice classes to synthetic aperture radar measurements |
publishDate |
2023 |
url |
https://elib.dlr.de/192994/ https://mosaic.colorado.edu/sites/default/files/Abstract_Assignments_Conference_2022.pdf |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
Kortum, Karl und Singha, Suman und Spreen, Gunnar und Jutila, Arttu und Hutter, Nils und Birnbaum, Gerit und Ricker, Robert und von Albedyll, Luisa (2023) Extrapolating Airborne Laser Scanner derived Sea Ice Classes to Synthetic Aperture Radar Measurements. 2nd MOSAiC Science Conference, 2023-02-13 - 2023-02-17, Boulder Colorado, USA. |
_version_ |
1799488871234273280 |