Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.rsase.2023.100965 http://hdl.handle.net/11449/247144 |
Resumo: | This paper presents the mangrove mapping carried out in the Rio de Janeiro City, Brazil, using two remote sensing data processing approaches in order to evaluate their potentialities as a complementary tool for oil spill sensitivity mapping. Ten vegetation indices were computed using the Landsat 8 imagery available in Google Earth Engine, and subsequently their spectral patterns were classified through three supervised and five unsupervised methods. Additionally, one pre-processed Landsat 8 OLI bands composition were classified by these eight classification algorithms. To role as a ground-truth for the comparison of 88 automatically produced maps, a mangrove map was prepared based on the methodological guidelines of Oceanic Atmospheric Administration of United States of America for Environmental Sensitivity Index. The best results were presented by Cobweb unsupervised classification of Mangrove Vegetation Index, properly identifying a great mangrove habitats diversity, such as inland brackish, riverine fringe and seaward forests. |
id |
UNSP_b75c137ea10a0a1350b3345b5a33a9b8 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/247144 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, BrazilGoogle earth engineImage classificationMangroveVegetation indexThis paper presents the mangrove mapping carried out in the Rio de Janeiro City, Brazil, using two remote sensing data processing approaches in order to evaluate their potentialities as a complementary tool for oil spill sensitivity mapping. Ten vegetation indices were computed using the Landsat 8 imagery available in Google Earth Engine, and subsequently their spectral patterns were classified through three supervised and five unsupervised methods. Additionally, one pre-processed Landsat 8 OLI bands composition were classified by these eight classification algorithms. To role as a ground-truth for the comparison of 88 automatically produced maps, a mangrove map was prepared based on the methodological guidelines of Oceanic Atmospheric Administration of United States of America for Environmental Sensitivity Index. The best results were presented by Cobweb unsupervised classification of Mangrove Vegetation Index, properly identifying a great mangrove habitats diversity, such as inland brackish, riverine fringe and seaward forests.Department of Geology and Natural Resources Geosciences Institute University of Campinas, PO Box 6152, SPDepartment of Geology Institute of Geosciences and Exact Sciences São Paulo State University, SPDepartment of Geology Institute of Geosciences and Exact Sciences São Paulo State University, SPUniversidade Estadual de Campinas (UNICAMP)Universidade Estadual Paulista (UNESP)Rodrigues, Flávio Henrique [UNESP]Cerri, Rodrigo Irineu [UNESP]de Andrade Kolya, André [UNESP]Veiga, Vinícius Mendes [UNESP]Gomes Vieira Reis, Fábio Augusto [UNESP]2023-07-29T13:07:31Z2023-07-29T13:07:31Z2023-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.rsase.2023.100965Remote Sensing Applications: Society and Environment, v. 30.2352-9385http://hdl.handle.net/11449/24714410.1016/j.rsase.2023.1009652-s2.0-85152145149Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengRemote Sensing Applications: Society and Environmentinfo:eu-repo/semantics/openAccess2023-07-29T13:07:31Zoai:repositorio.unesp.br:11449/247144Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T18:23:36.779707Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil |
title |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil |
spellingShingle |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil Rodrigues, Flávio Henrique [UNESP] Google earth engine Image classification Mangrove Vegetation index |
title_short |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil |
title_full |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil |
title_fullStr |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil |
title_full_unstemmed |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil |
title_sort |
Comparison of vegetation indices and image classification methods for mangrove mapping at semi-detailed scale in southwest of Rio de Janeiro, Brazil |
author |
Rodrigues, Flávio Henrique [UNESP] |
author_facet |
Rodrigues, Flávio Henrique [UNESP] Cerri, Rodrigo Irineu [UNESP] de Andrade Kolya, André [UNESP] Veiga, Vinícius Mendes [UNESP] Gomes Vieira Reis, Fábio Augusto [UNESP] |
author_role |
author |
author2 |
Cerri, Rodrigo Irineu [UNESP] de Andrade Kolya, André [UNESP] Veiga, Vinícius Mendes [UNESP] Gomes Vieira Reis, Fábio Augusto [UNESP] |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual de Campinas (UNICAMP) Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Rodrigues, Flávio Henrique [UNESP] Cerri, Rodrigo Irineu [UNESP] de Andrade Kolya, André [UNESP] Veiga, Vinícius Mendes [UNESP] Gomes Vieira Reis, Fábio Augusto [UNESP] |
dc.subject.por.fl_str_mv |
Google earth engine Image classification Mangrove Vegetation index |
topic |
Google earth engine Image classification Mangrove Vegetation index |
description |
This paper presents the mangrove mapping carried out in the Rio de Janeiro City, Brazil, using two remote sensing data processing approaches in order to evaluate their potentialities as a complementary tool for oil spill sensitivity mapping. Ten vegetation indices were computed using the Landsat 8 imagery available in Google Earth Engine, and subsequently their spectral patterns were classified through three supervised and five unsupervised methods. Additionally, one pre-processed Landsat 8 OLI bands composition were classified by these eight classification algorithms. To role as a ground-truth for the comparison of 88 automatically produced maps, a mangrove map was prepared based on the methodological guidelines of Oceanic Atmospheric Administration of United States of America for Environmental Sensitivity Index. The best results were presented by Cobweb unsupervised classification of Mangrove Vegetation Index, properly identifying a great mangrove habitats diversity, such as inland brackish, riverine fringe and seaward forests. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T13:07:31Z 2023-07-29T13:07:31Z 2023-04-01 |
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://dx.doi.org/10.1016/j.rsase.2023.100965 Remote Sensing Applications: Society and Environment, v. 30. 2352-9385 http://hdl.handle.net/11449/247144 10.1016/j.rsase.2023.100965 2-s2.0-85152145149 |
url |
http://dx.doi.org/10.1016/j.rsase.2023.100965 http://hdl.handle.net/11449/247144 |
identifier_str_mv |
Remote Sensing Applications: Society and Environment, v. 30. 2352-9385 10.1016/j.rsase.2023.100965 2-s2.0-85152145149 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Remote Sensing Applications: Society and Environment |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128926301552640 |