MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Caminhos de Geografia |
Texto Completo: | https://seer.ufu.br/index.php/caminhosdegeografia/article/view/65520 |
Resumo: | This article aims to evaluate the use of orbital images from the MSI sensor, Sentinel 2A satellite, to map the vegetation in the area corresponding to the Maringá sheet (PR), chart SF-22-Y-D-II-3. The NDVI index was the spectral variable selected, and nine images were processed using Google Earth Engine between February 2021 and January 2022. The classifications were based on the statistical images of mean and standard deviation, instead of individual images. Two classification methods were tested, one by simple slicing, and the other method was the decision tree (algorithm J48), in which 413 reference points were used. The results showed that the decision tree classifier presented slightly better results than the simple slicing, with Kappa indexes equal to 0.893 and 0.877, respectively. The decision tree used the mean as the main variable, but when it was between 0.6678 and 0.7504 the pixels were also classified using the standard deviation. Simple slicing classified more areas as vegetation, while the decision tree classified less areas. While the first classifier would be more suitable for mapping conservation areas, regardless of the size of the vegetation, the second would be more suitable for mapping forest cover. |
id |
UFU-16_dce8aee2f1f674acfe224e5ddb31c4c0 |
---|---|
oai_identifier_str |
oai:ojs.www.seer.ufu.br:article/65520 |
network_acronym_str |
UFU-16 |
network_name_str |
Caminhos de Geografia |
repository_id_str |
|
spelling |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREEMAPEAMENTO DA COBERTURA VEGETAL PARA ATUALIZAÇÃO CARTOGRÁFICA EM MARINGÁ/PR COM USO DE ABORDAGEM ESTATÍSTICA DO NDVI E ÁRVORE DE DECISÃOGEEClassificaçãoEscalaUso do soloSentinel 2AGEEClassificationScaleUse of the soilSentinel 2AThis article aims to evaluate the use of orbital images from the MSI sensor, Sentinel 2A satellite, to map the vegetation in the area corresponding to the Maringá sheet (PR), chart SF-22-Y-D-II-3. The NDVI index was the spectral variable selected, and nine images were processed using Google Earth Engine between February 2021 and January 2022. The classifications were based on the statistical images of mean and standard deviation, instead of individual images. Two classification methods were tested, one by simple slicing, and the other method was the decision tree (algorithm J48), in which 413 reference points were used. The results showed that the decision tree classifier presented slightly better results than the simple slicing, with Kappa indexes equal to 0.893 and 0.877, respectively. The decision tree used the mean as the main variable, but when it was between 0.6678 and 0.7504 the pixels were also classified using the standard deviation. Simple slicing classified more areas as vegetation, while the decision tree classified less areas. While the first classifier would be more suitable for mapping conservation areas, regardless of the size of the vegetation, the second would be more suitable for mapping forest cover.Este artigo tem como objetivo avaliar o uso de imagens orbitais do sensor MSI, satélite Sentinel 2A, para o mapeamento da vegetação na área correspondente à carta topográfica de Maringá (PR), folha SF-22-Y-D-II-3. O índice NDVI foi a variável espectral selecionada, e com uso do Google Earth Engine foram processadas nove imagens entre fev/2021 e jan/2022. As classificações se pautaram nas imagens-estatísticas de média e desvio-padrão, ao invés das imagens individuais. Foram testados dois métodos de classificação, um por fatiamento simples, e o outro método foi a árvore de decisão (algoritmo J48), em que foram usados 413 pontos de referência. Os resultados mostraram que o classificador por árvore de decisão apresentou resultados ligeiramente melhores do que o fatiamento simples, com índices Kappa iguais a 0,893 e 0,877, respectivamente. A árvore de decisão utilizou a média como principal variável, mas quando ela esteve entre 0,6678 e 0,7504 os pixels foram classificados também com o uso do desvio-padrão. O fatiamento simples classificou mais áreas como vegetação, enquanto a árvore de decisão classificou menos áreas. Enquanto o primeiro classificador seria mais indicado para o mapeamento de áreas de preservação, independentemente do porte da vegetação, o segundo seria mais indicado para o mapeamento de coberturas florestais.EDUFU - Editora da Universidade Federal de Uberlândia2023-06-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionAvaliado pelos paresapplication/pdfhttps://seer.ufu.br/index.php/caminhosdegeografia/article/view/6552010.14393/RCG249365520Caminhos de Geografia; Vol. 24 No. 93 (2023): Junho; 65-76Caminhos de Geografia; Vol. 24 Núm. 93 (2023): Junho; 65-76Caminhos de Geografia; v. 24 n. 93 (2023): Junho; 65-761678-6343reponame:Caminhos de Geografiainstname:Universidade Federal de Uberlândia (UFU)instacron:UFUporhttps://seer.ufu.br/index.php/caminhosdegeografia/article/view/65520/36152Copyright (c) 2023 Américo José Marques, Otávio Cristiano Montanherhttp://creativecommons.org/licenses/by-nc-nd/4.0info:eu-repo/semantics/openAccessMarques, Américo JoséMontanher, Otávio Cristiano2023-06-12T12:29:01Zoai:ojs.www.seer.ufu.br:article/65520Revistahttps://seer.ufu.br/index.php/caminhosdegeografia/indexPUBhttp://www.seer.ufu.br/index.php/caminhosdegeografia/oaiflaviasantosgeo@gmail.com1678-63431678-6343opendoar:2023-06-12T12:29:01Caminhos de Geografia - Universidade Federal de Uberlândia (UFU)false |
dc.title.none.fl_str_mv |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE MAPEAMENTO DA COBERTURA VEGETAL PARA ATUALIZAÇÃO CARTOGRÁFICA EM MARINGÁ/PR COM USO DE ABORDAGEM ESTATÍSTICA DO NDVI E ÁRVORE DE DECISÃO |
title |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE |
spellingShingle |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE Marques, Américo José GEE Classificação Escala Uso do solo Sentinel 2A GEE Classification Scale Use of the soil Sentinel 2A |
title_short |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE |
title_full |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE |
title_fullStr |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE |
title_full_unstemmed |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE |
title_sort |
MAPPING OF VEGETABLE COVERAGE FOR CARTOGRAPHIC UPDATE IN MARINGÁ/PR USING THE NDVI STATISTICAL APPROACH AND DECISION TREE |
author |
Marques, Américo José |
author_facet |
Marques, Américo José Montanher, Otávio Cristiano |
author_role |
author |
author2 |
Montanher, Otávio Cristiano |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Marques, Américo José Montanher, Otávio Cristiano |
dc.subject.por.fl_str_mv |
GEE Classificação Escala Uso do solo Sentinel 2A GEE Classification Scale Use of the soil Sentinel 2A |
topic |
GEE Classificação Escala Uso do solo Sentinel 2A GEE Classification Scale Use of the soil Sentinel 2A |
description |
This article aims to evaluate the use of orbital images from the MSI sensor, Sentinel 2A satellite, to map the vegetation in the area corresponding to the Maringá sheet (PR), chart SF-22-Y-D-II-3. The NDVI index was the spectral variable selected, and nine images were processed using Google Earth Engine between February 2021 and January 2022. The classifications were based on the statistical images of mean and standard deviation, instead of individual images. Two classification methods were tested, one by simple slicing, and the other method was the decision tree (algorithm J48), in which 413 reference points were used. The results showed that the decision tree classifier presented slightly better results than the simple slicing, with Kappa indexes equal to 0.893 and 0.877, respectively. The decision tree used the mean as the main variable, but when it was between 0.6678 and 0.7504 the pixels were also classified using the standard deviation. Simple slicing classified more areas as vegetation, while the decision tree classified less areas. While the first classifier would be more suitable for mapping conservation areas, regardless of the size of the vegetation, the second would be more suitable for mapping forest cover. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-06-12 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Avaliado pelos pares |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://seer.ufu.br/index.php/caminhosdegeografia/article/view/65520 10.14393/RCG249365520 |
url |
https://seer.ufu.br/index.php/caminhosdegeografia/article/view/65520 |
identifier_str_mv |
10.14393/RCG249365520 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://seer.ufu.br/index.php/caminhosdegeografia/article/view/65520/36152 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2023 Américo José Marques, Otávio Cristiano Montanher http://creativecommons.org/licenses/by-nc-nd/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2023 Américo José Marques, Otávio Cristiano Montanher http://creativecommons.org/licenses/by-nc-nd/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
EDUFU - Editora da Universidade Federal de Uberlândia |
publisher.none.fl_str_mv |
EDUFU - Editora da Universidade Federal de Uberlândia |
dc.source.none.fl_str_mv |
Caminhos de Geografia; Vol. 24 No. 93 (2023): Junho; 65-76 Caminhos de Geografia; Vol. 24 Núm. 93 (2023): Junho; 65-76 Caminhos de Geografia; v. 24 n. 93 (2023): Junho; 65-76 1678-6343 reponame:Caminhos de Geografia instname:Universidade Federal de Uberlândia (UFU) instacron:UFU |
instname_str |
Universidade Federal de Uberlândia (UFU) |
instacron_str |
UFU |
institution |
UFU |
reponame_str |
Caminhos de Geografia |
collection |
Caminhos de Geografia |
repository.name.fl_str_mv |
Caminhos de Geografia - Universidade Federal de Uberlândia (UFU) |
repository.mail.fl_str_mv |
flaviasantosgeo@gmail.com |
_version_ |
1797067010534801408 |