IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Revista Geographia (Niterói. Online) |
Texto Completo: | https://periodicos.uff.br/geographia/article/view/56659 |
Resumo: | This article aims to address the study carried out for the identification and cartography of water bodies in the state of Rio de Janeiro, using multitemporal remote sensing techniques in Radar images. It’s aims to contribute methodologically to the mapping of water bodies and wetlands, very specific targets that require detailed criteria for their correct classification, due to their dynamics. As a research methodology, machine learning algorithms were used on the Google Earth Engine platform, adopting Sentinel 1 – C-band images to identify these objects. A monthly time series of radar images was used, making it possible to test their potential in identifying these objects. As a result, the classification and quantification of the natural coverage of the state of Rio de Janeiro was obtained, considering the 12 months of the year 2018. The result allowed identifying the spatiality of the water bodies, in the different periods of the year, without atmospheric interference, which corresponds to a methodological difference in the attempt to map the annual flood dynamics. Mapping validation showed an excellent Kappa index (0,93), highlighting the potential of using radar images for mapping water bodies. |
id |
UFF-21_fef4cb52dcce533b104a2ab0bb761044 |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/56659 |
network_acronym_str |
UFF-21 |
network_name_str |
Revista Geographia (Niterói. Online) |
repository_id_str |
|
spelling |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIESIDENTIFICACIÓN DE MASAS DE AGUA EN SERIE TEMPORAL DE RADAR SENTINEL-1IDENTIFICAÇÃO DE CORPOS HÍDRICOS EM SÉRIE TEMPORAL DE RADAR SENTINEL-1Imagem de RadarSensoriamento RemotoAprendizado de MáquinaGoogle Earth EngineÁguaRadar ImageRemote sensingMachine learningGoogle Earth EngineWaterImagen RadarDetección remotaAprendizaje automáticoGoogle Earth EngineÁguaThis article aims to address the study carried out for the identification and cartography of water bodies in the state of Rio de Janeiro, using multitemporal remote sensing techniques in Radar images. It’s aims to contribute methodologically to the mapping of water bodies and wetlands, very specific targets that require detailed criteria for their correct classification, due to their dynamics. As a research methodology, machine learning algorithms were used on the Google Earth Engine platform, adopting Sentinel 1 – C-band images to identify these objects. A monthly time series of radar images was used, making it possible to test their potential in identifying these objects. As a result, the classification and quantification of the natural coverage of the state of Rio de Janeiro was obtained, considering the 12 months of the year 2018. The result allowed identifying the spatiality of the water bodies, in the different periods of the year, without atmospheric interference, which corresponds to a methodological difference in the attempt to map the annual flood dynamics. Mapping validation showed an excellent Kappa index (0,93), highlighting the potential of using radar images for mapping water bodies.Este artículo tiene como objetivo abordar el estudio realizado para la identificación y cartografía de cuerpos hídricos en el estado de Río de Janeiro, utilizando técnicas de teledetección multitemporal en imágenes Radar. Esta investigación pretende contribuir metodológicamente al mapeo de cuerpos de agua y humedales, que constituyen coberturas muy específicas y que requieren criterios detallados para su correcta clasificación, debido a su dinámica. Como metodología de investigación se utilizaron algoritmos de aprendizaje de maquina en la plataforma Google Earth Engine, en imágenes Sentinel 1 – banda C para identificar estos objetos. Se utilizó una serie temporal mensual de imágenes de radar, lo que permitió probar su potencial en la identificación de estas coberturas. Como resultado, se obtuvo la clasificación y cuantificación de la cobertura natural del estado de Río de Janeiro, considerando los 12 meses del año 2018. El resultado permitió identificar la espacialidad de los cuerpos de agua, en los diferentes períodos del año, sin interferencia atmosférica, lo que corresponde a un avance metodológico en el intento de mapear la dinámica de crecidas anuales. La validación del mapeo mostró un excelente índice Kappa (0,93), lo que destaca el potencial del uso de imágenes de radar para mapear cuerpos de agua.O presente artigo tem o objetivo de contribuir metodologicamente para o mapeamento de corpos hídricos e wetlands, alvos bastante específicos que demandam critérios minuciosos para sua correta classificação, devido a sua dinâmica. Assim, o estudo se concentra na identificação e cartografia de corpos hídricos no estado do Rio de Janeiro, utilizando técnicas de sensoriamento remoto multitemporal em imagens de Radar. Como metodologia de pesquisa foi utilizado algoritmo de aprendizado de máquina na plataforma Google Earth Engine, em imagens de Sentinel 1 – banda C, para a identificação dos alvos. Foi utilizada uma série temporal mensal de imagens de radar, sendo possível testar suas potencialidades na identificação desses objetos. Como resultados obteve-se a classificação e quantificação das coberturas de água do estado do Rio de Janeiro, considerando os 12 meses do ano de 2018. O resultado permitiu identificar a espacialidade dos corpos hídricos, nos diferentes períodos do ano, sem a interferência atmosférica, o que corresponde a um diferencial metodológico na tentativa de mapear a dinâmica anual da inundação. A validação do mapeamento apontou um excelente Índice Kappa (0,93), destacando a potencialidade do uso de imagens de radar para mapeamentos de corpos hídricos.UFF2023-12-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.uff.br/geographia/article/view/5665910.22409/GEOgraphia2023.v25i55.a56659GEOgraphia; Vol. 25 No. 55 (2023): jul./dez.GEOgraphia; Vol. 25 Núm. 55 (2023): jul./dez.GEOgraphia; v. 25 n. 55 (2023): jul./dez.2674-81261517-779310.22409/GEOgraphia2023.v25i55reponame:Revista Geographia (Niterói. Online)instname:Universidade Federal Fluminense (UFF)instacron:UFFporhttps://periodicos.uff.br/geographia/article/view/56659/35448https://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccess de Castro Porto Costa, EvelynPereira dos Santos, Mikaella Thomaz de Aquino Ribeiro, Eduardo Garcia Rosa, MiltonMaria Moura de Almeida, Paula Sanchez Vicens, Raúl 2023-07-19T17:27:23Zoai:ojs.pkp.sfu.ca:article/56659Revistahttps://periodicos.uff.br/geographia/indexPUBhttps://periodicos.uff.br/geographia/oaiperiodicos@proppi.uff.br ; revistageographia@gmail.com2674-81261517-7793opendoar:2023-07-19T17:27:23Revista Geographia (Niterói. Online) - Universidade Federal Fluminense (UFF)false |
dc.title.none.fl_str_mv |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES IDENTIFICACIÓN DE MASAS DE AGUA EN SERIE TEMPORAL DE RADAR SENTINEL-1 IDENTIFICAÇÃO DE CORPOS HÍDRICOS EM SÉRIE TEMPORAL DE RADAR SENTINEL-1 |
title |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES |
spellingShingle |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES de Castro Porto Costa, Evelyn Imagem de Radar Sensoriamento Remoto Aprendizado de Máquina Google Earth Engine Água Radar Image Remote sensing Machine learning Google Earth Engine Water Imagen Radar Detección remota Aprendizaje automático Google Earth Engine Água |
title_short |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES |
title_full |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES |
title_fullStr |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES |
title_full_unstemmed |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES |
title_sort |
IDENTIFICATION OF WATER BODIES IN SENTINEL-1 RADAR TIME SERIES |
author |
de Castro Porto Costa, Evelyn |
author_facet |
de Castro Porto Costa, Evelyn Pereira dos Santos, Mikaella Thomaz de Aquino Ribeiro, Eduardo Garcia Rosa, Milton Maria Moura de Almeida, Paula Sanchez Vicens, Raúl |
author_role |
author |
author2 |
Pereira dos Santos, Mikaella Thomaz de Aquino Ribeiro, Eduardo Garcia Rosa, Milton Maria Moura de Almeida, Paula Sanchez Vicens, Raúl |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
de Castro Porto Costa, Evelyn Pereira dos Santos, Mikaella Thomaz de Aquino Ribeiro, Eduardo Garcia Rosa, Milton Maria Moura de Almeida, Paula Sanchez Vicens, Raúl |
dc.subject.por.fl_str_mv |
Imagem de Radar Sensoriamento Remoto Aprendizado de Máquina Google Earth Engine Água Radar Image Remote sensing Machine learning Google Earth Engine Water Imagen Radar Detección remota Aprendizaje automático Google Earth Engine Água |
topic |
Imagem de Radar Sensoriamento Remoto Aprendizado de Máquina Google Earth Engine Água Radar Image Remote sensing Machine learning Google Earth Engine Water Imagen Radar Detección remota Aprendizaje automático Google Earth Engine Água |
description |
This article aims to address the study carried out for the identification and cartography of water bodies in the state of Rio de Janeiro, using multitemporal remote sensing techniques in Radar images. It’s aims to contribute methodologically to the mapping of water bodies and wetlands, very specific targets that require detailed criteria for their correct classification, due to their dynamics. As a research methodology, machine learning algorithms were used on the Google Earth Engine platform, adopting Sentinel 1 – C-band images to identify these objects. A monthly time series of radar images was used, making it possible to test their potential in identifying these objects. As a result, the classification and quantification of the natural coverage of the state of Rio de Janeiro was obtained, considering the 12 months of the year 2018. The result allowed identifying the spatiality of the water bodies, in the different periods of the year, without atmospheric interference, which corresponds to a methodological difference in the attempt to map the annual flood dynamics. Mapping validation showed an excellent Kappa index (0,93), highlighting the potential of using radar images for mapping water bodies. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-12-06 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://periodicos.uff.br/geographia/article/view/56659 10.22409/GEOgraphia2023.v25i55.a56659 |
url |
https://periodicos.uff.br/geographia/article/view/56659 |
identifier_str_mv |
10.22409/GEOgraphia2023.v25i55.a56659 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://periodicos.uff.br/geographia/article/view/56659/35448 |
dc.rights.driver.fl_str_mv |
https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
UFF |
publisher.none.fl_str_mv |
UFF |
dc.source.none.fl_str_mv |
GEOgraphia; Vol. 25 No. 55 (2023): jul./dez. GEOgraphia; Vol. 25 Núm. 55 (2023): jul./dez. GEOgraphia; v. 25 n. 55 (2023): jul./dez. 2674-8126 1517-7793 10.22409/GEOgraphia2023.v25i55 reponame:Revista Geographia (Niterói. Online) instname:Universidade Federal Fluminense (UFF) instacron:UFF |
instname_str |
Universidade Federal Fluminense (UFF) |
instacron_str |
UFF |
institution |
UFF |
reponame_str |
Revista Geographia (Niterói. Online) |
collection |
Revista Geographia (Niterói. Online) |
repository.name.fl_str_mv |
Revista Geographia (Niterói. Online) - Universidade Federal Fluminense (UFF) |
repository.mail.fl_str_mv |
periodicos@proppi.uff.br ; revistageographia@gmail.com |
_version_ |
1797051585406173184 |