EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY

Detalhes bibliográficos
Autor(a) principal: Silva Oliveira, Helena
Data de Publicação: 2020
Outros Autores: Marchesan, Juliana, Alba, Elisiane, Honnef, Dionatas Henrique, Frigo Wolfer, Matheus, Soares Pereira, Rudiney
Tipo de documento: Artigo
Idioma: por
Título da fonte: Geo UERJ
Texto Completo: https://www.e-publicacoes.uerj.br/geouerj/article/view/43259
Resumo: Analyzing classification algorithms of land use and land cover as well as images from sensors on satellites with different spatial resolutions are essential to determine the most suitable for each location. The objective of this study was to evaluate the efficiency of supervised classification algorithms, Maximum Likelihood (MLE) and Bhattacharyya, using medium spatial resolution (OLI/Landsat 8) and high (REIS/RapidEye) images in localized municipalities in the central of Rio Grande do Sul state. For this were used OLI/Landsat 8 and REIS/RapidEye sensor images with spatial resolution of 30 and 5 m, respectively. The classification of both images was performed by the MLE and Bhattacharyya algorithms with the definition of six classes of land use and land cover, these being Native Forest, Planted Forest, Exposed Soil, Agriculture, Field and Water. To evaluate the efficiency of the classification were used 120 points distributed randomly stratified in each municipality, 20 points in each class of land use and land cover. The quality of the classification was analyzed by Kappa and global accuracy indices, and the error of omission and commission was calculated. According to the results, the kappa index was higher for the classifications using the REIS/RapidEye sensor images for both algorithms, totaling 85.33% (MLE) and 83.67% (Bhattacharyya). In this context, it was possible to conclude that the REIS/RapidEye images and the MLE algorithm stand out for the best results, which are more adequate for the study area.
id UERJ-21_2b3bc341cd3632e5c2e4a203f450c3fc
oai_identifier_str oai:ojs.www.e-publicacoes.uerj.br:article/43259
network_acronym_str UERJ-21
network_name_str Geo UERJ
repository_id_str
spelling EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERYAVALIAÇÃO DE ALGORITMOS PARA CLASSIFICAÇÃO DE USO E COBERTURA DA TERRA NA PORÇÃO CENTRAL DO RIO GRANDE DO SUL A PARTIR DE IMAGENS DE ALTA E MÉDIA RESOLUÇÃO ESPACIALLandsat 8. RapidEye. MLE. Bhattacharyya. Kappa.Landsat 8. RapidEye. MaxVer. Bhattacharyya. Kappa.Analyzing classification algorithms of land use and land cover as well as images from sensors on satellites with different spatial resolutions are essential to determine the most suitable for each location. The objective of this study was to evaluate the efficiency of supervised classification algorithms, Maximum Likelihood (MLE) and Bhattacharyya, using medium spatial resolution (OLI/Landsat 8) and high (REIS/RapidEye) images in localized municipalities in the central of Rio Grande do Sul state. For this were used OLI/Landsat 8 and REIS/RapidEye sensor images with spatial resolution of 30 and 5 m, respectively. The classification of both images was performed by the MLE and Bhattacharyya algorithms with the definition of six classes of land use and land cover, these being Native Forest, Planted Forest, Exposed Soil, Agriculture, Field and Water. To evaluate the efficiency of the classification were used 120 points distributed randomly stratified in each municipality, 20 points in each class of land use and land cover. The quality of the classification was analyzed by Kappa and global accuracy indices, and the error of omission and commission was calculated. According to the results, the kappa index was higher for the classifications using the REIS/RapidEye sensor images for both algorithms, totaling 85.33% (MLE) and 83.67% (Bhattacharyya). In this context, it was possible to conclude that the REIS/RapidEye images and the MLE algorithm stand out for the best results, which are more adequate for the study area.Analisar algoritmos de classificação do uso e cobertura da terra bem como imagens provenientes de sensores a bordo de satélites com diferentes resoluções espaciais são essenciais para determinar os mais adequados para cada local. Assim, o presente estudo tem por objetivo avaliar a eficiência de algoritmos de classificação supervisionada, Máxima Verossimilhança (MaxVer) e Bhattacharyya, utilizando imagens de resolução espacial média (OLI/Landsat 8) e alta (REIS/RapidEye), em municípios localizados na porção central do estado do Rio Grande do Sul. Foram utilizadas para a classificação imagens do sensor OLI/Landsat 8 e REIS/RapidEye, com resolução espacial de 30 e 5 m, respectivamente. A classificação de ambas as imagens foi realizada pelos algoritmos MaxVer e Bhattacharyya com a definição de seis classes de uso e cobertura da terra, sendo estas Floresta nativa, Floresta plantada, Solo exposto, Agricultura, Campo e Água. Para avaliar a eficiência da classificação foram utilizados 120 pontos distribuídos de forma aleatória estratificada em cada município, sendo 20 pontos em cada classe de uso e cobertura da terra. A qualidade da classificação foi analisada pelos índices Kappa e exatidão global, ainda, calculou-se o erro de omissão e comissão. De acordo com os resultados obtidos o índice kappa foi maior para as classificações utilizando as imagens do sensor REIS/RapidEye para ambos os algoritmos, totalizando 85,33% (MaxVer) e 83,67% (Bhattacharyya). Neste contexto, foi possível concluir que as imagens REIS/RapidEye e o algoritmo MaxVer destacaram-se obtendo os melhores resultados, sendo estes mais adequados para a área de estudo.Universidade do Estado do Rio de Janeiro2020-12-31info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://www.e-publicacoes.uerj.br/geouerj/article/view/4325910.12957/geouerj.2020.43259Geo UERJ; n. 37 (2020): Jul/Dez - Olhares Geográficos sobre o Moçambique; e432591981-90211415-7543reponame:Geo UERJinstname:Universidade do Estado do Rio de Janeiro (UERJ)instacron:UERJporhttps://www.e-publicacoes.uerj.br/geouerj/article/view/43259/36672Copyright (c) 2020 Helena Silva Oliveira, Juliana Marchesan, Elisiane Alba, Dionatas Henrique Honnef, Rudiney Soares Pereirainfo:eu-repo/semantics/openAccessSilva Oliveira, HelenaMarchesan, JulianaAlba, ElisianeHonnef, Dionatas HenriqueFrigo Wolfer, MatheusSoares Pereira, Rudiney2022-02-20T22:23:21Zoai:ojs.www.e-publicacoes.uerj.br:article/43259Revistahttps://www.e-publicacoes.uerj.br/index.php/geouerjPUBhttps://www.e-publicacoes.uerj.br/index.php/geouerj/oaitunesregina@gmail.com || ppeuerj@eduerj.uerj.br || geouerj.revista@gmail.com || glauciomarafon@hotmail.com1981-90211415-7543opendoar:2022-02-20T22:23:21Geo UERJ - Universidade do Estado do Rio de Janeiro (UERJ)false
dc.title.none.fl_str_mv EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY
AVALIAÇÃO DE ALGORITMOS PARA CLASSIFICAÇÃO DE USO E COBERTURA DA TERRA NA PORÇÃO CENTRAL DO RIO GRANDE DO SUL A PARTIR DE IMAGENS DE ALTA E MÉDIA RESOLUÇÃO ESPACIAL
title EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY
spellingShingle EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY
Silva Oliveira, Helena
Landsat 8. RapidEye. MLE. Bhattacharyya. Kappa.
Landsat 8. RapidEye. MaxVer. Bhattacharyya. Kappa.
title_short EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY
title_full EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY
title_fullStr EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY
title_full_unstemmed EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY
title_sort EVALUATION OF ALGORITHMS FOR LAND USE AND LAND COVER CLASSIFICATION IN THE CENTRAL PORTION OF RIO GRANDE DO SUL STATE FROM HIGH AND MEDIUM SPATIAL RESOLUTION IMAGERY
author Silva Oliveira, Helena
author_facet Silva Oliveira, Helena
Marchesan, Juliana
Alba, Elisiane
Honnef, Dionatas Henrique
Frigo Wolfer, Matheus
Soares Pereira, Rudiney
author_role author
author2 Marchesan, Juliana
Alba, Elisiane
Honnef, Dionatas Henrique
Frigo Wolfer, Matheus
Soares Pereira, Rudiney
author2_role author
author
author
author
author
dc.contributor.author.fl_str_mv Silva Oliveira, Helena
Marchesan, Juliana
Alba, Elisiane
Honnef, Dionatas Henrique
Frigo Wolfer, Matheus
Soares Pereira, Rudiney
dc.subject.por.fl_str_mv Landsat 8. RapidEye. MLE. Bhattacharyya. Kappa.
Landsat 8. RapidEye. MaxVer. Bhattacharyya. Kappa.
topic Landsat 8. RapidEye. MLE. Bhattacharyya. Kappa.
Landsat 8. RapidEye. MaxVer. Bhattacharyya. Kappa.
description Analyzing classification algorithms of land use and land cover as well as images from sensors on satellites with different spatial resolutions are essential to determine the most suitable for each location. The objective of this study was to evaluate the efficiency of supervised classification algorithms, Maximum Likelihood (MLE) and Bhattacharyya, using medium spatial resolution (OLI/Landsat 8) and high (REIS/RapidEye) images in localized municipalities in the central of Rio Grande do Sul state. For this were used OLI/Landsat 8 and REIS/RapidEye sensor images with spatial resolution of 30 and 5 m, respectively. The classification of both images was performed by the MLE and Bhattacharyya algorithms with the definition of six classes of land use and land cover, these being Native Forest, Planted Forest, Exposed Soil, Agriculture, Field and Water. To evaluate the efficiency of the classification were used 120 points distributed randomly stratified in each municipality, 20 points in each class of land use and land cover. The quality of the classification was analyzed by Kappa and global accuracy indices, and the error of omission and commission was calculated. According to the results, the kappa index was higher for the classifications using the REIS/RapidEye sensor images for both algorithms, totaling 85.33% (MLE) and 83.67% (Bhattacharyya). In this context, it was possible to conclude that the REIS/RapidEye images and the MLE algorithm stand out for the best results, which are more adequate for the study area.
publishDate 2020
dc.date.none.fl_str_mv 2020-12-31
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://www.e-publicacoes.uerj.br/geouerj/article/view/43259
10.12957/geouerj.2020.43259
url https://www.e-publicacoes.uerj.br/geouerj/article/view/43259
identifier_str_mv 10.12957/geouerj.2020.43259
dc.language.iso.fl_str_mv por
language por
dc.relation.none.fl_str_mv https://www.e-publicacoes.uerj.br/geouerj/article/view/43259/36672
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 Universidade do Estado do Rio de Janeiro
publisher.none.fl_str_mv Universidade do Estado do Rio de Janeiro
dc.source.none.fl_str_mv Geo UERJ; n. 37 (2020): Jul/Dez - Olhares Geográficos sobre o Moçambique; e43259
1981-9021
1415-7543
reponame:Geo UERJ
instname:Universidade do Estado do Rio de Janeiro (UERJ)
instacron:UERJ
instname_str Universidade do Estado do Rio de Janeiro (UERJ)
instacron_str UERJ
institution UERJ
reponame_str Geo UERJ
collection Geo UERJ
repository.name.fl_str_mv Geo UERJ - Universidade do Estado do Rio de Janeiro (UERJ)
repository.mail.fl_str_mv tunesregina@gmail.com || ppeuerj@eduerj.uerj.br || geouerj.revista@gmail.com || glauciomarafon@hotmail.com
_version_ 1799317529633488896