Bayesian Unsupervised Machine Learning Approach to Segment Arctic Sea Ice Using SMOS Data
Microwave radiometry at L-band is sensitive to sea ice thickness (SIT) up to ∼ 60 cm. Current methods to infer SIT depend on ice-physical properties and data provided by the ESA’s Soil Moisture and Ocean Salinity (SMOS) mission. However, retrieval accuracy is limited due to seasonally and regionally...
Published in: | Geophysical Research Letters |
---|---|
Main Authors: | , , , |
Other Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
American Geophysical Union
2021
|
Subjects: | |
Online Access: | http://hdl.handle.net/10261/252549 https://doi.org/10.1029/2020GL091285 https://doi.org/10.13039/501100000780 |
id |
ftcsic:oai:digital.csic.es:10261/252549 |
---|---|
record_format |
openpolar |
spelling |
ftcsic:oai:digital.csic.es:10261/252549 2024-02-11T10:01:04+01:00 Bayesian Unsupervised Machine Learning Approach to Segment Arctic Sea Ice Using SMOS Data Herbert, Christoph Camps, Adriano Wellmann, Florian Vall-llossera, Mercè La Caixa European Commission Ministerio de Ciencia, Innovación y Universidades (España) 2021-03-25 http://hdl.handle.net/10261/252549 https://doi.org/10.1029/2020GL091285 https://doi.org/10.13039/501100000780 unknown American Geophysical Union #PLACEHOLDER_PARENT_METADATA_VALUE# info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/ESP2017-89463-C3-2-R info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-099008-B-C21 info:eu-repo/grantAgreement/EC/H2020/713673 Publisher's version http://dx.doi.org/10.1029/2020GL091285 Sí doi:10.1029/2020GL091285 issn: 1944-8007 Geophysical Research Letters 48 (2021) http://hdl.handle.net/10261/252549 http://dx.doi.org/10.13039/501100000780 open artículo http://purl.org/coar/resource_type/c_6501 2021 ftcsic https://doi.org/10.1029/2020GL09128510.13039/501100000780 2024-01-16T11:14:37Z Microwave radiometry at L-band is sensitive to sea ice thickness (SIT) up to ∼ 60 cm. Current methods to infer SIT depend on ice-physical properties and data provided by the ESA’s Soil Moisture and Ocean Salinity (SMOS) mission. However, retrieval accuracy is limited due to seasonally and regionally variable surface conditions during the formation and melting of sea ice. In this work, Arctic sea ice is segmented using a Bayesian unsupervised learning algorithm aiming to recognize spatial patterns by harnessing multi-incidence angle brightness temperature observations. The approach considers both statistical characteristics and spatial correlations of the observations. The temporal stability and separability of classes are analyzed to distinguish ambiguous from well-determined regions. Model uncertainty is quantified from class membership probabilities using information entropy. The presented approach opens up a new scope to improve current SIT retrieval algorithms, and can be particularly beneficial to investigate merged satellite products. There are no perceived conicts of inter-est for the lead author or coauthors. The lead author received the support of a fellowship from “la Caixa” Foundation (ID 100010434). The fellowship code is LCF/BQ/DI18/11660050. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 713673. It was also funded through the award “Unidad de Excelencia María de Maeztu” MDM-2016-0600, by the Spanish Ministry of Science and Innovation through the project “L-band” ESP2017-89463-C3-2-R, and the project “Sensing with Pioneering Opportunistic Techniques (SPOT)” RTI2018-099008-B-C21/AEI/10.13039/501100011033 Article in Journal/Newspaper Arctic Sea ice Digital.CSIC (Spanish National Research Council) Arctic Geophysical Research Letters 48 6 |
institution |
Open Polar |
collection |
Digital.CSIC (Spanish National Research Council) |
op_collection_id |
ftcsic |
language |
unknown |
description |
Microwave radiometry at L-band is sensitive to sea ice thickness (SIT) up to ∼ 60 cm. Current methods to infer SIT depend on ice-physical properties and data provided by the ESA’s Soil Moisture and Ocean Salinity (SMOS) mission. However, retrieval accuracy is limited due to seasonally and regionally variable surface conditions during the formation and melting of sea ice. In this work, Arctic sea ice is segmented using a Bayesian unsupervised learning algorithm aiming to recognize spatial patterns by harnessing multi-incidence angle brightness temperature observations. The approach considers both statistical characteristics and spatial correlations of the observations. The temporal stability and separability of classes are analyzed to distinguish ambiguous from well-determined regions. Model uncertainty is quantified from class membership probabilities using information entropy. The presented approach opens up a new scope to improve current SIT retrieval algorithms, and can be particularly beneficial to investigate merged satellite products. There are no perceived conicts of inter-est for the lead author or coauthors. The lead author received the support of a fellowship from “la Caixa” Foundation (ID 100010434). The fellowship code is LCF/BQ/DI18/11660050. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 713673. It was also funded through the award “Unidad de Excelencia María de Maeztu” MDM-2016-0600, by the Spanish Ministry of Science and Innovation through the project “L-band” ESP2017-89463-C3-2-R, and the project “Sensing with Pioneering Opportunistic Techniques (SPOT)” RTI2018-099008-B-C21/AEI/10.13039/501100011033 |
author2 |
La Caixa European Commission Ministerio de Ciencia, Innovación y Universidades (España) |
format |
Article in Journal/Newspaper |
author |
Herbert, Christoph Camps, Adriano Wellmann, Florian Vall-llossera, Mercè |
spellingShingle |
Herbert, Christoph Camps, Adriano Wellmann, Florian Vall-llossera, Mercè Bayesian Unsupervised Machine Learning Approach to Segment Arctic Sea Ice Using SMOS Data |
author_facet |
Herbert, Christoph Camps, Adriano Wellmann, Florian Vall-llossera, Mercè |
author_sort |
Herbert, Christoph |
title |
Bayesian Unsupervised Machine Learning Approach to Segment Arctic Sea Ice Using SMOS Data |
title_short |
Bayesian Unsupervised Machine Learning Approach to Segment Arctic Sea Ice Using SMOS Data |
title_full |
Bayesian Unsupervised Machine Learning Approach to Segment Arctic Sea Ice Using SMOS Data |
title_fullStr |
Bayesian Unsupervised Machine Learning Approach to Segment Arctic Sea Ice Using SMOS Data |
title_full_unstemmed |
Bayesian Unsupervised Machine Learning Approach to Segment Arctic Sea Ice Using SMOS Data |
title_sort |
bayesian unsupervised machine learning approach to segment arctic sea ice using smos data |
publisher |
American Geophysical Union |
publishDate |
2021 |
url |
http://hdl.handle.net/10261/252549 https://doi.org/10.1029/2020GL091285 https://doi.org/10.13039/501100000780 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_relation |
#PLACEHOLDER_PARENT_METADATA_VALUE# info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/ESP2017-89463-C3-2-R info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-099008-B-C21 info:eu-repo/grantAgreement/EC/H2020/713673 Publisher's version http://dx.doi.org/10.1029/2020GL091285 Sí doi:10.1029/2020GL091285 issn: 1944-8007 Geophysical Research Letters 48 (2021) http://hdl.handle.net/10261/252549 http://dx.doi.org/10.13039/501100000780 |
op_rights |
open |
op_doi |
https://doi.org/10.1029/2020GL09128510.13039/501100000780 |
container_title |
Geophysical Research Letters |
container_volume |
48 |
container_issue |
6 |
_version_ |
1790596805549883392 |