Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI

Detalhes bibliográficos
Autor(a) principal: Oliveira, Evando Natal Fernandes de
Data de Publicação: 2020
Tipo de documento: Dissertação
Idioma: por
Título da fonte: Repositório Institucional da UFG
dARK ID: ark:/38995/001300000bjxp
Texto Completo: http://repositorio.bc.ufg.br/tede/handle/tede/10380
Resumo: The knowledge and the management of land cover and land use are fundamental in a scenario of food production increasing, due to growth of the world population and change in its eating habits, especially the increase in animal protein consumption, what demands an increase in the herd of cattle and, consequently, in the pasture areas. Remote sensing has been an ally of public managers and the community for a long time, with its abundant data production about the terrestrial surface in different spatial, spectral and temporal resolutions, with particular emphasis on vegetation indices. One of these indices, the NDVI, is calculated and made available from the data generated by the MODIS satellite sensor as a time series, which is one of the most used sources of information for the classification of the most varied types of vegetation. n this work, we present a methodology for classifying pastures that comprises, in a first step, the use of the Linear Temporal Mixture Model -- LTMM, with the final members being obtained from an unsupervised classification method. Secondly, the data are labeled from a pasture map produced by the Processing of Images and Geoprocessing Laboratory of the Federal University of Goi\'as (LAPIG - UFG), which has better spatial resolution than the data generated by MODIS. Then, a classification model is constructed to be applied to the classifying data and its quality is measured by comparison with another pasture map, also produced by LAPIG, with the same spatial resolution than the classified data. The methodology used here presented results with quality compatible with other studies that had purely supervised training approaches for the classification of pastures, using the same data base.
id UFG-2_3401ecb71adc4284f71f0dc64b6cedd4
oai_identifier_str oai:repositorio.bc.ufg.br:tede/10380
network_acronym_str UFG-2
network_name_str Repositório Institucional da UFG
repository_id_str
spelling Laureano, Gustavo Teodorohttp://lattes.cnpq.br/4418446095942420Soares, Anderson da SilvaParente, Leandro LealLaureano, Gustavo Teodorohttp://lattes.cnpq.br/9247638598083574Oliveira, Evando Natal Fernandes de2020-02-27T11:09:02Z2020-01-28OLIVEIRA, Evando Natal Fernandes de. Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI. 2020.87 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2020.http://repositorio.bc.ufg.br/tede/handle/tede/10380ark:/38995/001300000bjxpThe knowledge and the management of land cover and land use are fundamental in a scenario of food production increasing, due to growth of the world population and change in its eating habits, especially the increase in animal protein consumption, what demands an increase in the herd of cattle and, consequently, in the pasture areas. Remote sensing has been an ally of public managers and the community for a long time, with its abundant data production about the terrestrial surface in different spatial, spectral and temporal resolutions, with particular emphasis on vegetation indices. One of these indices, the NDVI, is calculated and made available from the data generated by the MODIS satellite sensor as a time series, which is one of the most used sources of information for the classification of the most varied types of vegetation. n this work, we present a methodology for classifying pastures that comprises, in a first step, the use of the Linear Temporal Mixture Model -- LTMM, with the final members being obtained from an unsupervised classification method. Secondly, the data are labeled from a pasture map produced by the Processing of Images and Geoprocessing Laboratory of the Federal University of Goi\'as (LAPIG - UFG), which has better spatial resolution than the data generated by MODIS. Then, a classification model is constructed to be applied to the classifying data and its quality is measured by comparison with another pasture map, also produced by LAPIG, with the same spatial resolution than the classified data. The methodology used here presented results with quality compatible with other studies that had purely supervised training approaches for the classification of pastures, using the same data base.O conhecimento e o gerenciamento da cobertura e do uso do solo são fundamentais num cenário de aumento na produção de alimentos, devido ao crescimento da população mundial e à mudança de seus hábitos alimentares, com destaque para o incremento no consumo de proteína animal, o que demanda um aumento no rebanho bovino e, consequentemente, nas áreas de pastagens. Um aliado dos gestores e da comunidade tem sido, já há um bom tempo, o sensoriamento remoto, com sua produção de dados abundantes sobre a superfície terrestre em variadas resoluções espaciais, espectrais e temporais, com particular destaque para os índices de vegetação. Um destes índices, o NDVI, é calculado e disponibilizado com dados gerados pelo sensor MODIS em forma de uma série temporal, que é uma das fontes de informação mais usadas para a classificação das mais variadas feições vegetais. Neste trabalho, apresentamos uma metodologia de classificação de pastagens que compreende, numa primeira etapa, o uso do Modelo Linear de Mistura Temporal -- MLMT, sendo que os membros finais foram obtidos a partir de uma classificação não supervisionada. Num segundo momento, é feita a rotulação dos dados a partir de um mapa de pastagens que tem melhor resolução espacial que os dados gerados pelo MODIS e que foi produzido pelo Laboratório de Processamento de Imagens e Geoprocessamento da Universidade Federal de Goiás (LAPIG -- UFG). Em seguida, é construído o modelo de classificação que é aplicado aos dados a serem classificados e sua qualidade é aferida por meio da comparação com outro mapa de pastagens, também produzido pelo LAPIG, com resolução espacial semelhante aos dados classificados. A metodologia aqui utilizada apresentou resultados com qualidade compatível com outros trabalhos que tiveram abordagens de treinamento puramente supervisionado para a classificação de pastagens, usando a mesma base de dados.Submitted by Marlene Santos (marlene.bc.ufg@gmail.com) on 2020-02-26T20:32:12Z No. of bitstreams: 2 Dissertação - Evando Natal Fernandes de Oliveira - 2020.pdf: 22399125 bytes, checksum: 21d3a5484ae57ce04b3711c10abf242a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2020-02-27T11:09:01Z (GMT) No. of bitstreams: 2 Dissertação - Evando Natal Fernandes de Oliveira - 2020.pdf: 22399125 bytes, checksum: 21d3a5484ae57ce04b3711c10abf242a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)Made available in DSpace on 2020-02-27T11:09:02Z (GMT). No. of bitstreams: 2 Dissertação - Evando Natal Fernandes de Oliveira - 2020.pdf: 22399125 bytes, checksum: 21d3a5484ae57ce04b3711c10abf242a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2020-01-28Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPESapplication/pdfporUniversidade Federal de GoiásPrograma de Pós-graduação em Ciência da Computação (INF)UFGBrasilInstituto de Informática - INF (RG)http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessSéries temporaisNDVIPastagensClusterizaçãoClassificação supervisionadaMLMTMLMEMODISTime seriesPastureClusteringSemisupervised classificationLTMMLSMMCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOUma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVIA semi-supervised approach for pastures classification using NDVI time seriesinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesis-3303550325223384799600600600600-771226673463364476836717112058112045092075167498588264571reponame:Repositório Institucional da UFGinstname:Universidade Federal de Goiás (UFG)instacron:UFGLICENSElicense.txtlicense.txttext/plain; charset=utf-82165http://repositorio.bc.ufg.br/tede/bitstreams/7ab2c533-2eb0-45a9-84c6-885209875503/downloadbd3efa91386c1718a7f26a329fdcb468MD51CC-LICENSElicense_urllicense_urltext/plain; charset=utf-849http://repositorio.bc.ufg.br/tede/bitstreams/0bae7050-00b5-4786-8c57-859b0f2a7442/download4afdbb8c545fd630ea7db775da747b2fMD52license_textlicense_texttext/html; charset=utf-80http://repositorio.bc.ufg.br/tede/bitstreams/1b41cc8b-e8fc-49c0-b08e-2b219e54a0b4/downloadd41d8cd98f00b204e9800998ecf8427eMD53license_rdflicense_rdfapplication/rdf+xml; charset=utf-80http://repositorio.bc.ufg.br/tede/bitstreams/899e9653-4933-4dfb-80c5-2cb73564cacf/downloadd41d8cd98f00b204e9800998ecf8427eMD54ORIGINALDissertação - Evando Natal Fernandes de Oliveira - 2020.pdfDissertação - Evando Natal Fernandes de Oliveira - 2020.pdfapplication/pdf22399125http://repositorio.bc.ufg.br/tede/bitstreams/731b0dd2-396e-4747-bf6f-82b3562a0396/download21d3a5484ae57ce04b3711c10abf242aMD55tede/103802020-02-27 08:09:02.086http://creativecommons.org/licenses/by-nc-nd/4.0/Acesso Abertoopen.accessoai:repositorio.bc.ufg.br:tede/10380http://repositorio.bc.ufg.br/tedeRepositório InstitucionalPUBhttp://repositorio.bc.ufg.br/oai/requesttasesdissertacoes.bc@ufg.bropendoar:2020-02-27T11:09:02Repositório Institucional da UFG - Universidade Federal de Goiás (UFG)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
dc.title.eng.fl_str_mv Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI
dc.title.alternative.eng.fl_str_mv A semi-supervised approach for pastures classification using NDVI time series
title Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI
spellingShingle Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI
Oliveira, Evando Natal Fernandes de
Séries temporais
NDVI
Pastagens
Clusterização
Classificação supervisionada
MLMT
MLME
MODIS
Time series
Pasture
Clustering
Semisupervised classification
LTMM
LSMM
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
title_short Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI
title_full Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI
title_fullStr Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI
title_full_unstemmed Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI
title_sort Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI
author Oliveira, Evando Natal Fernandes de
author_facet Oliveira, Evando Natal Fernandes de
author_role author
dc.contributor.advisor1.fl_str_mv Laureano, Gustavo Teodoro
dc.contributor.advisor1Lattes.fl_str_mv http://lattes.cnpq.br/4418446095942420
dc.contributor.referee1.fl_str_mv Soares, Anderson da Silva
dc.contributor.referee2.fl_str_mv Parente, Leandro Leal
dc.contributor.referee3.fl_str_mv Laureano, Gustavo Teodoro
dc.contributor.authorLattes.fl_str_mv http://lattes.cnpq.br/9247638598083574
dc.contributor.author.fl_str_mv Oliveira, Evando Natal Fernandes de
contributor_str_mv Laureano, Gustavo Teodoro
Soares, Anderson da Silva
Parente, Leandro Leal
Laureano, Gustavo Teodoro
dc.subject.por.fl_str_mv Séries temporais
NDVI
Pastagens
Clusterização
Classificação supervisionada
MLMT
MLME
MODIS
topic Séries temporais
NDVI
Pastagens
Clusterização
Classificação supervisionada
MLMT
MLME
MODIS
Time series
Pasture
Clustering
Semisupervised classification
LTMM
LSMM
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
dc.subject.eng.fl_str_mv Time series
Pasture
Clustering
Semisupervised classification
LTMM
LSMM
dc.subject.cnpq.fl_str_mv CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
description The knowledge and the management of land cover and land use are fundamental in a scenario of food production increasing, due to growth of the world population and change in its eating habits, especially the increase in animal protein consumption, what demands an increase in the herd of cattle and, consequently, in the pasture areas. Remote sensing has been an ally of public managers and the community for a long time, with its abundant data production about the terrestrial surface in different spatial, spectral and temporal resolutions, with particular emphasis on vegetation indices. One of these indices, the NDVI, is calculated and made available from the data generated by the MODIS satellite sensor as a time series, which is one of the most used sources of information for the classification of the most varied types of vegetation. n this work, we present a methodology for classifying pastures that comprises, in a first step, the use of the Linear Temporal Mixture Model -- LTMM, with the final members being obtained from an unsupervised classification method. Secondly, the data are labeled from a pasture map produced by the Processing of Images and Geoprocessing Laboratory of the Federal University of Goi\'as (LAPIG - UFG), which has better spatial resolution than the data generated by MODIS. Then, a classification model is constructed to be applied to the classifying data and its quality is measured by comparison with another pasture map, also produced by LAPIG, with the same spatial resolution than the classified data. The methodology used here presented results with quality compatible with other studies that had purely supervised training approaches for the classification of pastures, using the same data base.
publishDate 2020
dc.date.accessioned.fl_str_mv 2020-02-27T11:09:02Z
dc.date.issued.fl_str_mv 2020-01-28
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.citation.fl_str_mv OLIVEIRA, Evando Natal Fernandes de. Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI. 2020.87 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2020.
dc.identifier.uri.fl_str_mv http://repositorio.bc.ufg.br/tede/handle/tede/10380
dc.identifier.dark.fl_str_mv ark:/38995/001300000bjxp
identifier_str_mv OLIVEIRA, Evando Natal Fernandes de. Uma abordagem semissupervisionada para classificação de pastagens usando séries temporais de NDVI. 2020.87 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2020.
ark:/38995/001300000bjxp
url http://repositorio.bc.ufg.br/tede/handle/tede/10380
dc.language.iso.fl_str_mv por
language por
dc.relation.program.fl_str_mv -3303550325223384799
dc.relation.confidence.fl_str_mv 600
600
600
600
dc.relation.department.fl_str_mv -7712266734633644768
dc.relation.cnpq.fl_str_mv 3671711205811204509
dc.relation.sponsorship.fl_str_mv 2075167498588264571
dc.rights.driver.fl_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv 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 Universidade Federal de Goiás
dc.publisher.program.fl_str_mv Programa de Pós-graduação em Ciência da Computação (INF)
dc.publisher.initials.fl_str_mv UFG
dc.publisher.country.fl_str_mv Brasil
dc.publisher.department.fl_str_mv Instituto de Informática - INF (RG)
publisher.none.fl_str_mv Universidade Federal de Goiás
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFG
instname:Universidade Federal de Goiás (UFG)
instacron:UFG
instname_str Universidade Federal de Goiás (UFG)
instacron_str UFG
institution UFG
reponame_str Repositório Institucional da UFG
collection Repositório Institucional da UFG
bitstream.url.fl_str_mv http://repositorio.bc.ufg.br/tede/bitstreams/7ab2c533-2eb0-45a9-84c6-885209875503/download
http://repositorio.bc.ufg.br/tede/bitstreams/0bae7050-00b5-4786-8c57-859b0f2a7442/download
http://repositorio.bc.ufg.br/tede/bitstreams/1b41cc8b-e8fc-49c0-b08e-2b219e54a0b4/download
http://repositorio.bc.ufg.br/tede/bitstreams/899e9653-4933-4dfb-80c5-2cb73564cacf/download
http://repositorio.bc.ufg.br/tede/bitstreams/731b0dd2-396e-4747-bf6f-82b3562a0396/download
bitstream.checksum.fl_str_mv bd3efa91386c1718a7f26a329fdcb468
4afdbb8c545fd630ea7db775da747b2f
d41d8cd98f00b204e9800998ecf8427e
d41d8cd98f00b204e9800998ecf8427e
21d3a5484ae57ce04b3711c10abf242a
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional da UFG - Universidade Federal de Goiás (UFG)
repository.mail.fl_str_mv tasesdissertacoes.bc@ufg.br
_version_ 1815172623402795008