Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts

Detalhes bibliográficos
Autor(a) principal: Clark, Andrew
Data de Publicação: 2022
Outros Autores: Moorman, Brian, Whalen, Dustin, Vieira, Gonçalo
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10451/53980
Resumo: Permafrost coasts are experiencing accelerated erosion in response to above average warming in the Arctic resulting in local, regional, and global consequences. However, Arctic coasts are expansive in scale, constituting 30–34% of Earth’s coastline, and represent a particular challenge for wide-scale, high temporal measurement and monitoring. This study addresses the potential strengths and limitations of an object-based approach to integrate with an automated workflow by assessing the accuracy of coastal classifications and subsequent feature extraction of coastal indicator features. We tested three object-based classifications; thresholding, supervised, and a deep learning model using convolutional neural networks, focusing on a Pleaides satellite scene in the Western Canadian Arctic. Multiple spatial resolutions (0.6, 1, 2.5, 5, 10, and 30 m/pixel) and segmentation scales (100, 200, 300, 400, 500, 600, 700, and 800) were tested to understand the wider applicability across imaging platforms. We achieved classification accuracies greater than 85% for the higher image resolution scenarios using all classification methods. Coastal features, waterline and tundra, or vegetation, line, generated from image classifications were found to be within the image uncertainty 60% of the time when compared to reference features. Further, for very high resolution scenarios, segmentation scale did not affect classification accuracy; however, a smaller segmentation scale (i.e., smaller image objects) led to improved feature extraction. Similar results were generated across classification approaches with a slight improvement observed when using deep learning CNN, which we also suggest has wider applicability. Overall, our study provides a promising contribution towards broad scale monitoring of Arctic coastal erosion.
id RCAP_adc3425101386d118eefb32eb477ec86
oai_identifier_str oai:repositorio.ul.pt:10451/53980
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Multiscale Object-Based Classification and Feature Extraction along Arctic CoastsArctic coastal erosionCoastal feature extractionCoastal classificationObject-based image analysisGEOBIAPermafrost coasts are experiencing accelerated erosion in response to above average warming in the Arctic resulting in local, regional, and global consequences. However, Arctic coasts are expansive in scale, constituting 30–34% of Earth’s coastline, and represent a particular challenge for wide-scale, high temporal measurement and monitoring. This study addresses the potential strengths and limitations of an object-based approach to integrate with an automated workflow by assessing the accuracy of coastal classifications and subsequent feature extraction of coastal indicator features. We tested three object-based classifications; thresholding, supervised, and a deep learning model using convolutional neural networks, focusing on a Pleaides satellite scene in the Western Canadian Arctic. Multiple spatial resolutions (0.6, 1, 2.5, 5, 10, and 30 m/pixel) and segmentation scales (100, 200, 300, 400, 500, 600, 700, and 800) were tested to understand the wider applicability across imaging platforms. We achieved classification accuracies greater than 85% for the higher image resolution scenarios using all classification methods. Coastal features, waterline and tundra, or vegetation, line, generated from image classifications were found to be within the image uncertainty 60% of the time when compared to reference features. Further, for very high resolution scenarios, segmentation scale did not affect classification accuracy; however, a smaller segmentation scale (i.e., smaller image objects) led to improved feature extraction. Similar results were generated across classification approaches with a slight improvement observed when using deep learning CNN, which we also suggest has wider applicability. Overall, our study provides a promising contribution towards broad scale monitoring of Arctic coastal erosion.MDPIRepositório da Universidade de LisboaClark, AndrewMoorman, BrianWhalen, DustinVieira, Gonçalo2022-07-27T13:47:57Z20222022-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10451/53980engClark, A., Moorman, B., Whalen, D. & Vieira, G. (2022). Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts. Remote Sensing, 14(13), 2982. http://dx.doi.org/10.3390/rs1413298210.3390/rs141329822072-4292info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-08T17:00:19Zoai:repositorio.ul.pt:10451/53980Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:04:58.510704Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts
title Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts
spellingShingle Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts
Clark, Andrew
Arctic coastal erosion
Coastal feature extraction
Coastal classification
Object-based image analysis
GEOBIA
title_short Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts
title_full Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts
title_fullStr Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts
title_full_unstemmed Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts
title_sort Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts
author Clark, Andrew
author_facet Clark, Andrew
Moorman, Brian
Whalen, Dustin
Vieira, Gonçalo
author_role author
author2 Moorman, Brian
Whalen, Dustin
Vieira, Gonçalo
author2_role author
author
author
dc.contributor.none.fl_str_mv Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Clark, Andrew
Moorman, Brian
Whalen, Dustin
Vieira, Gonçalo
dc.subject.por.fl_str_mv Arctic coastal erosion
Coastal feature extraction
Coastal classification
Object-based image analysis
GEOBIA
topic Arctic coastal erosion
Coastal feature extraction
Coastal classification
Object-based image analysis
GEOBIA
description Permafrost coasts are experiencing accelerated erosion in response to above average warming in the Arctic resulting in local, regional, and global consequences. However, Arctic coasts are expansive in scale, constituting 30–34% of Earth’s coastline, and represent a particular challenge for wide-scale, high temporal measurement and monitoring. This study addresses the potential strengths and limitations of an object-based approach to integrate with an automated workflow by assessing the accuracy of coastal classifications and subsequent feature extraction of coastal indicator features. We tested three object-based classifications; thresholding, supervised, and a deep learning model using convolutional neural networks, focusing on a Pleaides satellite scene in the Western Canadian Arctic. Multiple spatial resolutions (0.6, 1, 2.5, 5, 10, and 30 m/pixel) and segmentation scales (100, 200, 300, 400, 500, 600, 700, and 800) were tested to understand the wider applicability across imaging platforms. We achieved classification accuracies greater than 85% for the higher image resolution scenarios using all classification methods. Coastal features, waterline and tundra, or vegetation, line, generated from image classifications were found to be within the image uncertainty 60% of the time when compared to reference features. Further, for very high resolution scenarios, segmentation scale did not affect classification accuracy; however, a smaller segmentation scale (i.e., smaller image objects) led to improved feature extraction. Similar results were generated across classification approaches with a slight improvement observed when using deep learning CNN, which we also suggest has wider applicability. Overall, our study provides a promising contribution towards broad scale monitoring of Arctic coastal erosion.
publishDate 2022
dc.date.none.fl_str_mv 2022-07-27T13:47:57Z
2022
2022-01-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10451/53980
url http://hdl.handle.net/10451/53980
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Clark, A., Moorman, B., Whalen, D. & Vieira, G. (2022). Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts. Remote Sensing, 14(13), 2982. http://dx.doi.org/10.3390/rs14132982
10.3390/rs14132982
2072-4292
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134601390587904