Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Trabalho de conclusão de curso |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFSCAR |
Texto Completo: | https://repositorio.ufscar.br/handle/ufscar/15450 |
Resumo: | In Brazil, Pinus sp. is a very common invasive plant and has an excellent adaptation to edaphoclimatic conditions in the Southeast and South regions of the country, especially in wet field areas. As an invasive plant, it can cause the exclusion of native species through competition, causing a loss of biodiversity and even changes in the structure of the ecosystem. Therefore, having tools that help in planning the mitigation of environmental impacts caused by these species is very important. Among these tools is Remote Sensing, which can identify and locate exotic and invasive plant individuals. Thus, the present work aimed to use very high resolution multispectral images to test and compare the MAXVER and Random Forest (RF) classifiers through a confusion matrix, more specifically, the Kappa Index, to understand which one has the best performance in the identification of isolated individuals of Pinus sp. in wet field areas. To do that, 5 classes were created, "Pinus" (Pinus sp.), "Nao_Pinus" (indicating all the remaining components of the landscape that do not fit into the other classes), "Agua" (indicating places with water, such as lakes, for example), “Solo” (indicating exposed soil) and “Sombra” (indicating shady locations), with which the two classifiers were performed using a 4-band image composition (NIR, Red Edge, Red and Green). Then, 500 random points were created, divided equally by each class, carrying the information of its classification performed by the classifiers and the one performed manually, this one taken as real. From this information, the Confusion Matrix was constructed, obtaining the Kappa Index. Both were classified as having moderate agreement, being MAXVER with an index of 0.5023 and RF with an index of 0.5264. Observing these values, noticed that RF showed greater agreement than MAXVER and, consequently, among these two classifiers, RF is suggested being better for the presented purpose, under the methodology used. It is noteworthy that, in addition to MAXVER and Random Forest, other classifiers can be used to identify individuals of Pinus sp. and other species, which may even show better performance for this purpose. |
id |
SCAR_2d83105c00cfdb04fc437a124694a8ed |
---|---|
oai_identifier_str |
oai:repositorio.ufscar.br:ufscar/15450 |
network_acronym_str |
SCAR |
network_name_str |
Repositório Institucional da UFSCAR |
repository_id_str |
4322 |
spelling |
Moreira, Mateus GomesMolin, Paulo Guilhermehttp://lattes.cnpq.br/1529819650942373http://lattes.cnpq.br/377493034527627568f63fd4-77cb-449c-851d-62f371c1a7802022-01-07T21:21:16Z2022-01-07T21:21:16Z2021-11-11MOREIRA, Mateus Gomes. Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido. 2021. Trabalho de Conclusão de Curso (Graduação em Engenharia Ambiental) – Universidade Federal de São Carlos, Lagoa do Sino, 2021. Disponível em: https://repositorio.ufscar.br/handle/ufscar/15450.https://repositorio.ufscar.br/handle/ufscar/15450In Brazil, Pinus sp. is a very common invasive plant and has an excellent adaptation to edaphoclimatic conditions in the Southeast and South regions of the country, especially in wet field areas. As an invasive plant, it can cause the exclusion of native species through competition, causing a loss of biodiversity and even changes in the structure of the ecosystem. Therefore, having tools that help in planning the mitigation of environmental impacts caused by these species is very important. Among these tools is Remote Sensing, which can identify and locate exotic and invasive plant individuals. Thus, the present work aimed to use very high resolution multispectral images to test and compare the MAXVER and Random Forest (RF) classifiers through a confusion matrix, more specifically, the Kappa Index, to understand which one has the best performance in the identification of isolated individuals of Pinus sp. in wet field areas. To do that, 5 classes were created, "Pinus" (Pinus sp.), "Nao_Pinus" (indicating all the remaining components of the landscape that do not fit into the other classes), "Agua" (indicating places with water, such as lakes, for example), “Solo” (indicating exposed soil) and “Sombra” (indicating shady locations), with which the two classifiers were performed using a 4-band image composition (NIR, Red Edge, Red and Green). Then, 500 random points were created, divided equally by each class, carrying the information of its classification performed by the classifiers and the one performed manually, this one taken as real. From this information, the Confusion Matrix was constructed, obtaining the Kappa Index. Both were classified as having moderate agreement, being MAXVER with an index of 0.5023 and RF with an index of 0.5264. Observing these values, noticed that RF showed greater agreement than MAXVER and, consequently, among these two classifiers, RF is suggested being better for the presented purpose, under the methodology used. It is noteworthy that, in addition to MAXVER and Random Forest, other classifiers can be used to identify individuals of Pinus sp. and other species, which may even show better performance for this purpose.No Brasil, o Pinus sp. é uma planta invasora muito comum, uma vez que apresenta excelente adaptação às condições edafoclimáticas das regiões Sudeste e Sul do país, com destaque para áreas de campo úmido. Sendo uma planta invasora, ela pode implicar na exclusão de espécies nativas através da competição, ocasionando em perda de biodiversidade e até modificações na estrutura do ecossistema. Logo, é importante dispor de ferramentas que auxiliem no planejamento de mitigação de impactos ambientais causados por estas espécies. Entre estas ferramentas está o Sensoriamento Remoto, o qual pode identificar e localizar indivíduos de plantas exóticas e invasoras. Nesse contexto, o presente trabalho teve por objetivo utilizar imagens multiespectrais de altíssima resolução para testar e comparar os classificadores MAXVER e Random Forest (RF) através de uma matriz de confusão, mais especificamente, o Índice Kappa, a fim de se compreender qual possui melhor desempenho na identificação de indivíduos isolados de Pinus sp. em uma área de campo úmido. Para isso, foram criadas 5 classes, “Pinus” (indicando indivíduos de Pinus), “Nao_Pinus” (indicando todos os componentes restantes da paisagem que não se enquadram nas demais classes), “Agua” (indicando locais com água, como lagos, por exemplo), “Solo” (indicando solo exposto) e “Sombra” (indicando locais com sombra), com os quais executou-se os dois classificadores utilizando uma composição de imagens de 4 bandas (NIR, Red Edge, Red e Green). Com isso, criou-se 500 pontos aleatórios divididos igualmente por cada classe carregando a informação de sua classificação realizada pelos classificadores e a realizada manualmente, esta tomada como real. A partir destas informações, construiu-se então a Matriz de Confusão, obtendo-se o Índice Kappa. Ambos foram classificados como com concordância moderada, sendo MAXVER com índice de 0,5023 e RF com índice de 0,5264. Observando estes valores, percebeu-se que RF apresentou maior concordância que MAXVER e, portanto, dentre estes dois classificadores, sugere-se que seja melhor para a finalidade apresentada, diante da metodologia utilizada. Destaca-se ainda que, além de MAXVER e Random Forest, outros classificadores podem ser utilizados para identificação de indivíduos de Pinus sp. e outras espécies, os quais podem inclusive apresentar melhor desempenho para esta finalidade.Não recebi financiamentoporUniversidade Federal de São CarlosCâmpus Lagoa do SinoEngenharia Ambiental - EAm-LSUFSCarAttribution-NonCommercial-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nc-nd/3.0/br/info:eu-repo/semantics/openAccessPinus sp.Plantas invasorasCampo úmidoSensoriamento remotoImagens multiespectraisMAXVERÍndice KappaRandom ForestCIENCIAS AGRARIAS::RECURSOS FLORESTAIS E ENGENHARIA FLORESTALComparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmidoComparison between the MAXVER and Random Forest method to identify Pinus sp. in wet field areasinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bachelorThesis600600b9fc33b3-9a64-46cd-8473-cdd2ec208ec5reponame:Repositório Institucional da UFSCARinstname:Universidade Federal de São Carlos (UFSCAR)instacron:UFSCARORIGINAL[TCC - Rev] Comparação entre o método de MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido.pdf[TCC - Rev] Comparação entre o método de MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido.pdfTCCapplication/pdf11733015https://repositorio.ufscar.br/bitstream/ufscar/15450/1/%5bTCC%20-%20Rev%5d%20Compara%c3%a7%c3%a3o%20entre%20o%20m%c3%a9todo%20de%20MAXVER%20e%20Random%20Forest%20na%20identifica%c3%a7%c3%a3o%20de%20Pinus%20sp.%20em%20%c3%a1reas%20de%20campo%20%c3%bamido.pdf456c5a49b918e48c539d05f268308762MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufscar.br/bitstream/ufscar/15450/2/license_rdfe39d27027a6cc9cb039ad269a5db8e34MD52TEXT[TCC - Rev] Comparação entre o método de MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido.pdf.txt[TCC - Rev] Comparação entre o método de MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido.pdf.txtExtracted texttext/plain45084https://repositorio.ufscar.br/bitstream/ufscar/15450/3/%5bTCC%20-%20Rev%5d%20Compara%c3%a7%c3%a3o%20entre%20o%20m%c3%a9todo%20de%20MAXVER%20e%20Random%20Forest%20na%20identifica%c3%a7%c3%a3o%20de%20Pinus%20sp.%20em%20%c3%a1reas%20de%20campo%20%c3%bamido.pdf.txt53e77add536627ee7e695f051c276c1bMD53THUMBNAIL[TCC - Rev] Comparação entre o método de MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido.pdf.jpg[TCC - Rev] Comparação entre o método de MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido.pdf.jpgIM Thumbnailimage/jpeg5402https://repositorio.ufscar.br/bitstream/ufscar/15450/4/%5bTCC%20-%20Rev%5d%20Compara%c3%a7%c3%a3o%20entre%20o%20m%c3%a9todo%20de%20MAXVER%20e%20Random%20Forest%20na%20identifica%c3%a7%c3%a3o%20de%20Pinus%20sp.%20em%20%c3%a1reas%20de%20campo%20%c3%bamido.pdf.jpgfd18b925d046b5fbf8d9f7be40e4c995MD54ufscar/154502023-09-18 18:32:27.64oai:repositorio.ufscar.br:ufscar/15450Repositório InstitucionalPUBhttps://repositorio.ufscar.br/oai/requestopendoar:43222023-09-18T18:32:27Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR)false |
dc.title.por.fl_str_mv |
Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido |
dc.title.alternative.eng.fl_str_mv |
Comparison between the MAXVER and Random Forest method to identify Pinus sp. in wet field areas |
title |
Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido |
spellingShingle |
Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido Moreira, Mateus Gomes Pinus sp. Plantas invasoras Campo úmido Sensoriamento remoto Imagens multiespectrais MAXVER Índice Kappa Random Forest CIENCIAS AGRARIAS::RECURSOS FLORESTAIS E ENGENHARIA FLORESTAL |
title_short |
Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido |
title_full |
Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido |
title_fullStr |
Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido |
title_full_unstemmed |
Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido |
title_sort |
Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido |
author |
Moreira, Mateus Gomes |
author_facet |
Moreira, Mateus Gomes |
author_role |
author |
dc.contributor.authorlattes.por.fl_str_mv |
http://lattes.cnpq.br/3774930345276275 |
dc.contributor.author.fl_str_mv |
Moreira, Mateus Gomes |
dc.contributor.advisor1.fl_str_mv |
Molin, Paulo Guilherme |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/1529819650942373 |
dc.contributor.authorID.fl_str_mv |
68f63fd4-77cb-449c-851d-62f371c1a780 |
contributor_str_mv |
Molin, Paulo Guilherme |
dc.subject.por.fl_str_mv |
Pinus sp. Plantas invasoras Campo úmido Sensoriamento remoto Imagens multiespectrais MAXVER Índice Kappa |
topic |
Pinus sp. Plantas invasoras Campo úmido Sensoriamento remoto Imagens multiespectrais MAXVER Índice Kappa Random Forest CIENCIAS AGRARIAS::RECURSOS FLORESTAIS E ENGENHARIA FLORESTAL |
dc.subject.eng.fl_str_mv |
Random Forest |
dc.subject.cnpq.fl_str_mv |
CIENCIAS AGRARIAS::RECURSOS FLORESTAIS E ENGENHARIA FLORESTAL |
description |
In Brazil, Pinus sp. is a very common invasive plant and has an excellent adaptation to edaphoclimatic conditions in the Southeast and South regions of the country, especially in wet field areas. As an invasive plant, it can cause the exclusion of native species through competition, causing a loss of biodiversity and even changes in the structure of the ecosystem. Therefore, having tools that help in planning the mitigation of environmental impacts caused by these species is very important. Among these tools is Remote Sensing, which can identify and locate exotic and invasive plant individuals. Thus, the present work aimed to use very high resolution multispectral images to test and compare the MAXVER and Random Forest (RF) classifiers through a confusion matrix, more specifically, the Kappa Index, to understand which one has the best performance in the identification of isolated individuals of Pinus sp. in wet field areas. To do that, 5 classes were created, "Pinus" (Pinus sp.), "Nao_Pinus" (indicating all the remaining components of the landscape that do not fit into the other classes), "Agua" (indicating places with water, such as lakes, for example), “Solo” (indicating exposed soil) and “Sombra” (indicating shady locations), with which the two classifiers were performed using a 4-band image composition (NIR, Red Edge, Red and Green). Then, 500 random points were created, divided equally by each class, carrying the information of its classification performed by the classifiers and the one performed manually, this one taken as real. From this information, the Confusion Matrix was constructed, obtaining the Kappa Index. Both were classified as having moderate agreement, being MAXVER with an index of 0.5023 and RF with an index of 0.5264. Observing these values, noticed that RF showed greater agreement than MAXVER and, consequently, among these two classifiers, RF is suggested being better for the presented purpose, under the methodology used. It is noteworthy that, in addition to MAXVER and Random Forest, other classifiers can be used to identify individuals of Pinus sp. and other species, which may even show better performance for this purpose. |
publishDate |
2021 |
dc.date.issued.fl_str_mv |
2021-11-11 |
dc.date.accessioned.fl_str_mv |
2022-01-07T21:21:16Z |
dc.date.available.fl_str_mv |
2022-01-07T21:21:16Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
format |
bachelorThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
MOREIRA, Mateus Gomes. Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido. 2021. Trabalho de Conclusão de Curso (Graduação em Engenharia Ambiental) – Universidade Federal de São Carlos, Lagoa do Sino, 2021. Disponível em: https://repositorio.ufscar.br/handle/ufscar/15450. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufscar.br/handle/ufscar/15450 |
identifier_str_mv |
MOREIRA, Mateus Gomes. Comparação entre o método MAXVER e Random Forest na identificação de Pinus sp. em áreas de campo úmido. 2021. Trabalho de Conclusão de Curso (Graduação em Engenharia Ambiental) – Universidade Federal de São Carlos, Lagoa do Sino, 2021. Disponível em: https://repositorio.ufscar.br/handle/ufscar/15450. |
url |
https://repositorio.ufscar.br/handle/ufscar/15450 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.confidence.fl_str_mv |
600 600 |
dc.relation.authority.fl_str_mv |
b9fc33b3-9a64-46cd-8473-cdd2ec208ec5 |
dc.rights.driver.fl_str_mv |
Attribution-NonCommercial-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nc-nd/3.0/br/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nc-nd/3.0/br/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de São Carlos Câmpus Lagoa do Sino Engenharia Ambiental - EAm-LS |
dc.publisher.initials.fl_str_mv |
UFSCar |
publisher.none.fl_str_mv |
Universidade Federal de São Carlos Câmpus Lagoa do Sino Engenharia Ambiental - EAm-LS |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFSCAR instname:Universidade Federal de São Carlos (UFSCAR) instacron:UFSCAR |
instname_str |
Universidade Federal de São Carlos (UFSCAR) |
instacron_str |
UFSCAR |
institution |
UFSCAR |
reponame_str |
Repositório Institucional da UFSCAR |
collection |
Repositório Institucional da UFSCAR |
bitstream.url.fl_str_mv |
https://repositorio.ufscar.br/bitstream/ufscar/15450/1/%5bTCC%20-%20Rev%5d%20Compara%c3%a7%c3%a3o%20entre%20o%20m%c3%a9todo%20de%20MAXVER%20e%20Random%20Forest%20na%20identifica%c3%a7%c3%a3o%20de%20Pinus%20sp.%20em%20%c3%a1reas%20de%20campo%20%c3%bamido.pdf https://repositorio.ufscar.br/bitstream/ufscar/15450/2/license_rdf https://repositorio.ufscar.br/bitstream/ufscar/15450/3/%5bTCC%20-%20Rev%5d%20Compara%c3%a7%c3%a3o%20entre%20o%20m%c3%a9todo%20de%20MAXVER%20e%20Random%20Forest%20na%20identifica%c3%a7%c3%a3o%20de%20Pinus%20sp.%20em%20%c3%a1reas%20de%20campo%20%c3%bamido.pdf.txt https://repositorio.ufscar.br/bitstream/ufscar/15450/4/%5bTCC%20-%20Rev%5d%20Compara%c3%a7%c3%a3o%20entre%20o%20m%c3%a9todo%20de%20MAXVER%20e%20Random%20Forest%20na%20identifica%c3%a7%c3%a3o%20de%20Pinus%20sp.%20em%20%c3%a1reas%20de%20campo%20%c3%bamido.pdf.jpg |
bitstream.checksum.fl_str_mv |
456c5a49b918e48c539d05f268308762 e39d27027a6cc9cb039ad269a5db8e34 53e77add536627ee7e695f051c276c1b fd18b925d046b5fbf8d9f7be40e4c995 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFSCAR - Universidade Federal de São Carlos (UFSCAR) |
repository.mail.fl_str_mv |
|
_version_ |
1802136399774744576 |