Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil

Detalhes bibliográficos
Autor(a) principal: Magalhães,Ivo Augusto Lopes
Data de Publicação: 2023
Outros Autores: Carvalho Junior,Osmar Abilio de, Sano,Edson Eyji
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://scielo.pt/scielo.php?script=sci_arttext&pid=S0430-50272023000200087
Resumo: Abstract Delimitation of areas subject to flooding is crucial to understand water dynamics and fluvial changes. This study analyzed the potential of C-band Synthetic Aperture Radar (SAR) images acquired by the Sentinel-1 satellite in 2017, 2018, and 2019 to delineate flooded areas in the Central Amazon. The images were processed by the Artificial Neural Network Multi-Layer Perceptron (ANN-MLP) and two K-Nearest Neighbor (KNN-7 and KNN-11) machine learning (ML) classifiers. Pre-processing of Single Look Complex (SLC) SAR images involved the following methodological steps: orbit-file application; radiometric calibration (σ0); Range-Doppler terrain correction; speckle noise filtering; and conversion of linear data to backscattering coefficients (units in dB). We applied the Lee filter, with a window size of 3x3, for speckle filtering. A set of 6000 randomly distributed samples for training (70%), validation (20%), and test (10%) was obtained based on visual interpretation of Sentinel-2 optical satellite image acquired in the same years of SAR images. We found the largest flooded areas in 2019 in the study area (municipality of Parintins and Urucará, Amazonas River, Brazil): 6244km2 by the ANN-MLP classifier; 6268km2 by KNN-7; and 6290km2 by KNN-11, while the smallest flooded areas were found in 2018: 5364km2 by ANN-MLP; 5412km2 by KNN-7; and 5535km2 by KNN-11. The three classifiers presented Kappa coefficients between 0.77 and 0.91. ANN-MLP showed the best accuracy. The presence of shadow effects in the SAR images increased the commission errors.
id RCAP_2bf08501357811e3fcb51661be563155
oai_identifier_str oai:scielo:S0430-50272023000200087
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, BrazilRemote sensingwater resourcesimage classifiersinundationAbstract Delimitation of areas subject to flooding is crucial to understand water dynamics and fluvial changes. This study analyzed the potential of C-band Synthetic Aperture Radar (SAR) images acquired by the Sentinel-1 satellite in 2017, 2018, and 2019 to delineate flooded areas in the Central Amazon. The images were processed by the Artificial Neural Network Multi-Layer Perceptron (ANN-MLP) and two K-Nearest Neighbor (KNN-7 and KNN-11) machine learning (ML) classifiers. Pre-processing of Single Look Complex (SLC) SAR images involved the following methodological steps: orbit-file application; radiometric calibration (σ0); Range-Doppler terrain correction; speckle noise filtering; and conversion of linear data to backscattering coefficients (units in dB). We applied the Lee filter, with a window size of 3x3, for speckle filtering. A set of 6000 randomly distributed samples for training (70%), validation (20%), and test (10%) was obtained based on visual interpretation of Sentinel-2 optical satellite image acquired in the same years of SAR images. We found the largest flooded areas in 2019 in the study area (municipality of Parintins and Urucará, Amazonas River, Brazil): 6244km2 by the ANN-MLP classifier; 6268km2 by KNN-7; and 6290km2 by KNN-11, while the smallest flooded areas were found in 2018: 5364km2 by ANN-MLP; 5412km2 by KNN-7; and 5535km2 by KNN-11. The three classifiers presented Kappa coefficients between 0.77 and 0.91. ANN-MLP showed the best accuracy. The presence of shadow effects in the SAR images increased the commission errors.Centro de Estudos Geográficos2023-08-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articletext/htmlhttp://scielo.pt/scielo.php?script=sci_arttext&pid=S0430-50272023000200087Finisterra - Revista Portuguesa de Geografia n.123 2023reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAPenghttp://scielo.pt/scielo.php?script=sci_arttext&pid=S0430-50272023000200087Magalhães,Ivo Augusto LopesCarvalho Junior,Osmar Abilio deSano,Edson Eyjiinfo:eu-repo/semantics/openAccess2024-02-06T16:58:24Zoai:scielo:S0430-50272023000200087Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T02:15:09.846500Repositório 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 Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil
title Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil
spellingShingle Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil
Magalhães,Ivo Augusto Lopes
Remote sensing
water resources
image classifiers
inundation
title_short Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil
title_full Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil
title_fullStr Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil
title_full_unstemmed Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil
title_sort Delimitation of flooded areas based on sentinel-1 sar data processed through machine learning: a study case from central amazon, Brazil
author Magalhães,Ivo Augusto Lopes
author_facet Magalhães,Ivo Augusto Lopes
Carvalho Junior,Osmar Abilio de
Sano,Edson Eyji
author_role author
author2 Carvalho Junior,Osmar Abilio de
Sano,Edson Eyji
author2_role author
author
dc.contributor.author.fl_str_mv Magalhães,Ivo Augusto Lopes
Carvalho Junior,Osmar Abilio de
Sano,Edson Eyji
dc.subject.por.fl_str_mv Remote sensing
water resources
image classifiers
inundation
topic Remote sensing
water resources
image classifiers
inundation
description Abstract Delimitation of areas subject to flooding is crucial to understand water dynamics and fluvial changes. This study analyzed the potential of C-band Synthetic Aperture Radar (SAR) images acquired by the Sentinel-1 satellite in 2017, 2018, and 2019 to delineate flooded areas in the Central Amazon. The images were processed by the Artificial Neural Network Multi-Layer Perceptron (ANN-MLP) and two K-Nearest Neighbor (KNN-7 and KNN-11) machine learning (ML) classifiers. Pre-processing of Single Look Complex (SLC) SAR images involved the following methodological steps: orbit-file application; radiometric calibration (σ0); Range-Doppler terrain correction; speckle noise filtering; and conversion of linear data to backscattering coefficients (units in dB). We applied the Lee filter, with a window size of 3x3, for speckle filtering. A set of 6000 randomly distributed samples for training (70%), validation (20%), and test (10%) was obtained based on visual interpretation of Sentinel-2 optical satellite image acquired in the same years of SAR images. We found the largest flooded areas in 2019 in the study area (municipality of Parintins and Urucará, Amazonas River, Brazil): 6244km2 by the ANN-MLP classifier; 6268km2 by KNN-7; and 6290km2 by KNN-11, while the smallest flooded areas were found in 2018: 5364km2 by ANN-MLP; 5412km2 by KNN-7; and 5535km2 by KNN-11. The three classifiers presented Kappa coefficients between 0.77 and 0.91. ANN-MLP showed the best accuracy. The presence of shadow effects in the SAR images increased the commission errors.
publishDate 2023
dc.date.none.fl_str_mv 2023-08-01
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://scielo.pt/scielo.php?script=sci_arttext&pid=S0430-50272023000200087
url http://scielo.pt/scielo.php?script=sci_arttext&pid=S0430-50272023000200087
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv http://scielo.pt/scielo.php?script=sci_arttext&pid=S0430-50272023000200087
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
dc.publisher.none.fl_str_mv Centro de Estudos Geográficos
publisher.none.fl_str_mv Centro de Estudos Geográficos
dc.source.none.fl_str_mv Finisterra - Revista Portuguesa de Geografia n.123 2023
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_ 1799137252281942016