Arctic Sea Ice property retrieval from synthetic aperture radar with deep learning methods
Current climate models are not capturing the feedback mechanisms driving the accelerated warming of the Arctic. A central challenge is the sparsity of observations. Satellite-borne synthetic aperture radar (SAR) instruments have the capability of monitoring Earth's sea ice masses at high resolu...
Main Author: | |
---|---|
Other Authors: | , , |
Format: | Doctoral or Postdoctoral Thesis |
Language: | English |
Published: |
Universität Bremen
2024
|
Subjects: | |
Online Access: | https://media.suub.uni-bremen.de/handle/elib/7803 https://doi.org/10.26092/elib/2885 https://nbn-resolving.org/urn:nbn:de:gbv:46-elib78032 |
id |
ftsubbremen:oai:media.suub.uni-bremen.de:Publications/elib/7803 |
---|---|
record_format |
openpolar |
spelling |
ftsubbremen:oai:media.suub.uni-bremen.de:Publications/elib/7803 2024-06-23T07:49:50+00:00 Arctic Sea Ice property retrieval from synthetic aperture radar with deep learning methods Kortum, Karl Spreen, Gunnar Singha, Suman Haas, Christian 2024-02-08 application/pdf https://media.suub.uni-bremen.de/handle/elib/7803 https://doi.org/10.26092/elib/2885 https://nbn-resolving.org/urn:nbn:de:gbv:46-elib78032 eng eng Universität Bremen Fachbereich 01: Physik/Elektrotechnik (FB 01) https://media.suub.uni-bremen.de/handle/elib/7803 https://doi.org/10.26092/elib/2885 doi:10.26092/elib/2885 urn:nbn:de:gbv:46-elib78032 info:eu-repo/semantics/openAccess CC BY 4.0 (Attribution) https://creativecommons.org/licenses/by/4.0/ Sea Ice Machine Learning Deep Learning Synthetic Aperture Radar Physics-informed Neural Networks Altimetry 530 530 Physics ddc:530 Dissertation doctoralThesis 2024 ftsubbremen https://doi.org/10.26092/elib/2885 2024-05-29T06:29:28Z Current climate models are not capturing the feedback mechanisms driving the accelerated warming of the Arctic. A central challenge is the sparsity of observations. Satellite-borne synthetic aperture radar (SAR) instruments have the capability of monitoring Earth's sea ice masses at high resolution, unhampered by cloud coverage or the Arctic night. The measurements are made at scales of 10's of metres whilst still covering the Arctic in a matter of days. However, interpreting the radar signal to retrieve relevant sea ice information is difficult because of the complex interactions of the ice with the electromagnetic radar signal. Conventional neural network algorithms leverage contextual image data to make accurate predictions of surface ice properties comparable to those made by human experts. They are, however, dependent on large amounts of high-quality ground truth that is rare in these regions. Thus, the full potential of the SAR data is yet to be unlocked. With the advent of the MOSAiC mission, large timeseries of SAR data and near-coincident ground measurements were acquired for the first time. This thesis uses the unique opportunity provided by these data to analyse the behaviour of deep learning models. Seven months of data from the campaign is classified and analysed, using newly developed techniques to enable robust predictions across the timeseries. Core features are identified to facilitate robust and high-resolution classification. The final challenge of ground truth sparsity is then overcome using innovative network configurations that enable the training of 99.99%$ of the model parameters without any ground truth data. The techniques open up sea ice property retrieval to big data technologies, relying only on the abundantly available SAR data. These techniques enable the extrapolation of sparse reference data to a large space of sea ice conditions and enable high resolution mapping of the Earth's region most affected by human-made climate change. Doctoral or Postdoctoral Thesis Arctic Climate change Sea ice Media SuUB Bremen (Staats- und Universitätsbibliothek Bremen) Arctic |
institution |
Open Polar |
collection |
Media SuUB Bremen (Staats- und Universitätsbibliothek Bremen) |
op_collection_id |
ftsubbremen |
language |
English |
topic |
Sea Ice Machine Learning Deep Learning Synthetic Aperture Radar Physics-informed Neural Networks Altimetry 530 530 Physics ddc:530 |
spellingShingle |
Sea Ice Machine Learning Deep Learning Synthetic Aperture Radar Physics-informed Neural Networks Altimetry 530 530 Physics ddc:530 Kortum, Karl Arctic Sea Ice property retrieval from synthetic aperture radar with deep learning methods |
topic_facet |
Sea Ice Machine Learning Deep Learning Synthetic Aperture Radar Physics-informed Neural Networks Altimetry 530 530 Physics ddc:530 |
description |
Current climate models are not capturing the feedback mechanisms driving the accelerated warming of the Arctic. A central challenge is the sparsity of observations. Satellite-borne synthetic aperture radar (SAR) instruments have the capability of monitoring Earth's sea ice masses at high resolution, unhampered by cloud coverage or the Arctic night. The measurements are made at scales of 10's of metres whilst still covering the Arctic in a matter of days. However, interpreting the radar signal to retrieve relevant sea ice information is difficult because of the complex interactions of the ice with the electromagnetic radar signal. Conventional neural network algorithms leverage contextual image data to make accurate predictions of surface ice properties comparable to those made by human experts. They are, however, dependent on large amounts of high-quality ground truth that is rare in these regions. Thus, the full potential of the SAR data is yet to be unlocked. With the advent of the MOSAiC mission, large timeseries of SAR data and near-coincident ground measurements were acquired for the first time. This thesis uses the unique opportunity provided by these data to analyse the behaviour of deep learning models. Seven months of data from the campaign is classified and analysed, using newly developed techniques to enable robust predictions across the timeseries. Core features are identified to facilitate robust and high-resolution classification. The final challenge of ground truth sparsity is then overcome using innovative network configurations that enable the training of 99.99%$ of the model parameters without any ground truth data. The techniques open up sea ice property retrieval to big data technologies, relying only on the abundantly available SAR data. These techniques enable the extrapolation of sparse reference data to a large space of sea ice conditions and enable high resolution mapping of the Earth's region most affected by human-made climate change. |
author2 |
Spreen, Gunnar Singha, Suman Haas, Christian |
format |
Doctoral or Postdoctoral Thesis |
author |
Kortum, Karl |
author_facet |
Kortum, Karl |
author_sort |
Kortum, Karl |
title |
Arctic Sea Ice property retrieval from synthetic aperture radar with deep learning methods |
title_short |
Arctic Sea Ice property retrieval from synthetic aperture radar with deep learning methods |
title_full |
Arctic Sea Ice property retrieval from synthetic aperture radar with deep learning methods |
title_fullStr |
Arctic Sea Ice property retrieval from synthetic aperture radar with deep learning methods |
title_full_unstemmed |
Arctic Sea Ice property retrieval from synthetic aperture radar with deep learning methods |
title_sort |
arctic sea ice property retrieval from synthetic aperture radar with deep learning methods |
publisher |
Universität Bremen |
publishDate |
2024 |
url |
https://media.suub.uni-bremen.de/handle/elib/7803 https://doi.org/10.26092/elib/2885 https://nbn-resolving.org/urn:nbn:de:gbv:46-elib78032 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change Sea ice |
genre_facet |
Arctic Climate change Sea ice |
op_relation |
https://media.suub.uni-bremen.de/handle/elib/7803 https://doi.org/10.26092/elib/2885 doi:10.26092/elib/2885 urn:nbn:de:gbv:46-elib78032 |
op_rights |
info:eu-repo/semantics/openAccess CC BY 4.0 (Attribution) https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.26092/elib/2885 |
_version_ |
1802640521617735680 |