Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações do UFSM |
Texto Completo: | http://repositorio.ufsm.br/handle/1/19024 |
Resumo: | The aim was to estimate the volume (VT) and biomass (BA) of Paricá plantations with machine learning from the images of MSI/SENTINEL-2A, in Ulianópolis, Pará. In three productive areas (PO2, CAP2, and PO) of the species, 56 sample units (UAs) were installed for the forest inventory. The productive capacity was evaluated by the site index (IS) based on ANATRO of 28 dominant trees. Covariance analysis was applied on the IS model. Soil samples were collected from 0-20cm (chemical) and 20-40cm (physical). Three UAs per area were randomized for the harvesting and cubic scaling of the trees. BA was performed by the direct method, considering 10 trees Dg per stand. The T22MHA scene was downloaded from 26/07/2016. In Qgis, a 1A product was generated consisting of stack of bands B2 to B12. In 47 UAs, the reflectance of pixel/band was extracted for the calculation of the vegetation index (IV). GLM was applied to model VT. The estimation of BA was done from the FEBmean. The prediction of VT and BA by the sensor considered 50 IVs and 12 bands, where by cross-validation, the most accurate algorithm was defined among the tested ones (Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN)). The pre-selection of the 10 most important variables for the spatialization of VTpredicted and BApredicted was performed by the RF. The analysis was done by RStudio 3.5.2. The precision of the inventory was <10% in CAP2 and PO areas, and in PO2 was 13.50%. For the IS, sample errors occurred of 15%, 9%, and 11% for PO2, CAP2, and PO areas, respectively. The model height-age of Schumacher, =3,4531 , was adjusted for GLM from the Gama-Identity distribution. The sites were divided into high (21 to 25m), medium (19 to 21m), and low (15 to 19m) productivity. The high productivity was registered in 80% of the UAs of CAP2, 50% of PO2, and 8% of PO. From the 36º month-old, different growth rate was verified. The covariance analysis differentiates the sites more (PO2 and CAP2) and less (PO) productive. The topographic characteristics, the presence of more clay and moderate soil acidity were relevant to turn CAP2 more conducive to the productivity of the species. The function for the estimation of VT in PO2 (88.96m³.ha-1 ± 14.50) and CAP2 (152.35 m³.ha-1 ± 16.45) was in Naslund – Gaussian. The function for VT in PO (139.37m³.ha-1 ± 28.41) was Meyer – Gaussian. The stem contributed with 86.54% of BA, branches and leaves participated with 8.28% and 5.18%. The BA registered for PO2, CAP2, and PO were 34,53ton.ha-1 ± 5,63; 56,54ton.ha-1 ± 7,75; and 51,93ton.ha-1 ± 11,95, respectively. The comparisons between VTobserved and VTpredicted, defined by ANN showed similarities in CAP2 and in PO. The comparisons between BAobserved and BApredicited calculated by RF showed proportionality in CAP2. The most precise estimation of VT and BA occurred to CAP2. The differences in PO2 and PO do not reflect a statistical problem, but rather spectral mixtures. |
id |
UFSM_53090911e4dbf1e7ebe7f056a10f2f7d |
---|---|
oai_identifier_str |
oai:repositorio.ufsm.br:1/19024 |
network_acronym_str |
UFSM |
network_name_str |
Biblioteca Digital de Teses e Dissertações do UFSM |
repository_id_str |
|
spelling |
2019-11-22T16:14:12Z2019-11-22T16:14:12Z2019-03-01http://repositorio.ufsm.br/handle/1/19024The aim was to estimate the volume (VT) and biomass (BA) of Paricá plantations with machine learning from the images of MSI/SENTINEL-2A, in Ulianópolis, Pará. In three productive areas (PO2, CAP2, and PO) of the species, 56 sample units (UAs) were installed for the forest inventory. The productive capacity was evaluated by the site index (IS) based on ANATRO of 28 dominant trees. Covariance analysis was applied on the IS model. Soil samples were collected from 0-20cm (chemical) and 20-40cm (physical). Three UAs per area were randomized for the harvesting and cubic scaling of the trees. BA was performed by the direct method, considering 10 trees Dg per stand. The T22MHA scene was downloaded from 26/07/2016. In Qgis, a 1A product was generated consisting of stack of bands B2 to B12. In 47 UAs, the reflectance of pixel/band was extracted for the calculation of the vegetation index (IV). GLM was applied to model VT. The estimation of BA was done from the FEBmean. The prediction of VT and BA by the sensor considered 50 IVs and 12 bands, where by cross-validation, the most accurate algorithm was defined among the tested ones (Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN)). The pre-selection of the 10 most important variables for the spatialization of VTpredicted and BApredicted was performed by the RF. The analysis was done by RStudio 3.5.2. The precision of the inventory was <10% in CAP2 and PO areas, and in PO2 was 13.50%. For the IS, sample errors occurred of 15%, 9%, and 11% for PO2, CAP2, and PO areas, respectively. The model height-age of Schumacher, =3,4531 , was adjusted for GLM from the Gama-Identity distribution. The sites were divided into high (21 to 25m), medium (19 to 21m), and low (15 to 19m) productivity. The high productivity was registered in 80% of the UAs of CAP2, 50% of PO2, and 8% of PO. From the 36º month-old, different growth rate was verified. The covariance analysis differentiates the sites more (PO2 and CAP2) and less (PO) productive. The topographic characteristics, the presence of more clay and moderate soil acidity were relevant to turn CAP2 more conducive to the productivity of the species. The function for the estimation of VT in PO2 (88.96m³.ha-1 ± 14.50) and CAP2 (152.35 m³.ha-1 ± 16.45) was in Naslund – Gaussian. The function for VT in PO (139.37m³.ha-1 ± 28.41) was Meyer – Gaussian. The stem contributed with 86.54% of BA, branches and leaves participated with 8.28% and 5.18%. The BA registered for PO2, CAP2, and PO were 34,53ton.ha-1 ± 5,63; 56,54ton.ha-1 ± 7,75; and 51,93ton.ha-1 ± 11,95, respectively. The comparisons between VTobserved and VTpredicted, defined by ANN showed similarities in CAP2 and in PO. The comparisons between BAobserved and BApredicited calculated by RF showed proportionality in CAP2. The most precise estimation of VT and BA occurred to CAP2. The differences in PO2 and PO do not reflect a statistical problem, but rather spectral mixtures.Objetivou-se a estimativa do volume (VT) e da biomassa (BA) de plantações de Paricá, com uso de aprendizado de máquinas, a partir de imagens MSI/SENTINEL-2A, Ulianópolis, Pará. Em três áreas (PO2, CAP2 e PO) produtoras da espécie foram instaladas 56 unidades de amostras (UA’s) para o inventário. A capacidade produtiva foi avaliada pelo índice de sítio (IS), com base na ANATRO de 28 árvores dominantes. Sobre o modelo de IS foi aplicada a análise de covariância. As amostras de solo foram coletadas de 0-20cm (química) e 20-40cm (física). Foram aleatorizadas três UA’s por área para a realização do abate e cubagem rigorosa das árvores. A BA foi realizada pelo método direto, considerando 10 árvores Dg por povoamento. Foi realizado download da cena T22MHA, de 26/07/2016. No Qgis foi gerado um produto 1A composto pela pilha de bandas B2 a B12. Em 47 UA’s foram extraídos a reflectância do pixel/banda, para o cálculo dos índices de vegetação (IV). Para modelagem do VT foi aplicada a GLM. A estimação da BA foi feita a partir do FEBmédio. A predição do VT e da BA pelo sensor considerou 50 IV’s e 12 bandas, onde por validação cruzada, definiu-se o algoritmo mais apropriado dentre os testados (Random Forest (RF), Suport Vector Machine (SVM) e Artificial Neural Network (ANN)). Pelo RF ocorreu a pré-seleção das 10 variáveis mais importantes para a espacialização do VTestimado e BAestimada. As análises foram feitas no RStudio 3.5.2. A precisão do inventário foi < 10% nas áreas CAP2 e PO, e em PO2 foi de 13,50%. Para o IS ocorreram erros de amostragem de 15%, 9% e 11% para as áreas PO2, CAP2 e PO, respectivamente. O modelo alturaidade de Schumacher, = 3,4531 , , foi ajustado por GLM, a partir da distribuição Gama – Identidade. Os sítios foram divididos em alta (21 a 25m), média (19 a 21m) e baixa (15 a 19m) produtividade. A alta produtividade foi registrada em 80% das UA’s de CAP2, 50% de PO2 e 8% de PO. A partir do 36º mês de idade, verificou-se diferentes taxas de crescimento. A análise de covariâncias distinguiu os sítios mais (PO2 e CAP2) e menos (PO) produtivos. As características topográficas, a presença de mais argila e a moderada acidez do solo foram relevantes para tornar CAP2 mais propício à produtividade da espécie. A função para estimação do VT em PO2 (88,96m3.ha-1 ± 14,50) e CAP2 (152,35m3.ha-1 ± 16,45) foi de Naslund – gaussiana. A função para VT em PO (139,37m3.ha-1 ± 28,41) foi de Meyer – gaussiana. O fuste contribuiu com 86,54% da BA, os galhos e folhas participaram com 8,28% e 5,18%. A BA registrada para PO2, CAP2 e PO foi de 34,53ton.ha-1 ± 5,63; 56,54ton.ha-1 ± 7,75; e 51,93ton.ha-1 ± 11,95, respectivamente. As comparações entre os VTobservado e VTestimado, definido pela ANN, demonstraram semelhanças em CAP2 e em PO. As comparações entre BAobservada e BAestimada, calculada pela RF, revelou proporcionalidade apenas em CAP2. As estimações mais precisas de VT e BA ocorreram para CAP2. As diferenças em PO2 e PO, não refletem um problema de ordem estatística, mas sim de misturas espectrais.Fundação Amazônia de Amaparo a Estudos e Pesquisas, FAPESPAporUniversidade Federal de Santa MariaCentro de Ciências RuraisPrograma de Pós-Graduação em Engenharia FlorestalUFSMBrasilRecursos Florestais e Engenharia FlorestalAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessAlgoritmo de aprendizado de máquinasÍndice de vegetaçãoParicáVolume de madeiraUlianópolisMachine learning algorithmVegetation indexVolume of timberCNPQ::CIENCIAS AGRARIAS::RECURSOS FLORESTAIS E ENGENHARIA FLORESTALCapacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2Productive capacity, estimation of volume and biomass in Schizolobium parahyba var. amazonicum plantations using sentinel 2 imagesinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisPereira, Rudiney Soareshttp://lattes.cnpq.br/9479801378014588Dalla Corte, Ana Paulahttp://lattes.cnpq.br/9528175326712747Silva, Emanuel Araújohttp://lattes.cnpq.br/2765651276275384Sanquetta, Carlos Robertohttp://lattes.cnpq.br/9641517111540508Amaral, Lúcio de Paulahttp://lattes.cnpq.br/6612592358172016http://lattes.cnpq.br/9934744665863266Batista, Fábio de Jesus500200000003600a7274a7d-8dcd-466b-9a0d-c2b629e2ca88ce0631ac-dda3-4952-850d-0565ff5f6409b8681ceb-750b-4829-ae08-e40c03e518499215eedd-f015-4c70-bf7f-3c4727227d87685262ea-5f0d-4d07-bada-e23eb17b133c0dc06b07-acdf-4c76-9b58-6a68ee610e29reponame:Biblioteca Digital de Teses e Dissertações do UFSMinstname:Universidade Federal de Santa Maria (UFSM)instacron:UFSMORIGINALTES_PPGEF_2019_BATISTA_FABIO.pdfTES_PPGEF_2019_BATISTA_FABIO.pdfTese de Doutoradoapplication/pdf9833531http://repositorio.ufsm.br/bitstream/1/19024/1/TES_PPGEF_2019_BATISTA_FABIO.pdf85dbbfd196e4c4b5a969388aeb1610e2MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805http://repositorio.ufsm.br/bitstream/1/19024/2/license_rdf4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-81956http://repositorio.ufsm.br/bitstream/1/19024/3/license.txt2f0571ecee68693bd5cd3f17c1e075dfMD53TEXTTES_PPGEF_2019_BATISTA_FABIO.pdf.txtTES_PPGEF_2019_BATISTA_FABIO.pdf.txtExtracted texttext/plain379389http://repositorio.ufsm.br/bitstream/1/19024/4/TES_PPGEF_2019_BATISTA_FABIO.pdf.txtc571b81462d703600133269c1d9e37ffMD54THUMBNAILTES_PPGEF_2019_BATISTA_FABIO.pdf.jpgTES_PPGEF_2019_BATISTA_FABIO.pdf.jpgIM Thumbnailimage/jpeg4424http://repositorio.ufsm.br/bitstream/1/19024/5/TES_PPGEF_2019_BATISTA_FABIO.pdf.jpg3d60c8e150e02adf10479523401fcf5aMD551/190242019-11-23 03:02:46.121oai:repositorio.ufsm.br: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 Digital de Teses e Dissertaçõeshttps://repositorio.ufsm.br/ONGhttps://repositorio.ufsm.br/oai/requestatendimento.sib@ufsm.br||tedebc@gmail.comopendoar:2019-11-23T06:02:46Biblioteca Digital de Teses e Dissertações do UFSM - Universidade Federal de Santa Maria (UFSM)false |
dc.title.por.fl_str_mv |
Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2 |
dc.title.alternative.eng.fl_str_mv |
Productive capacity, estimation of volume and biomass in Schizolobium parahyba var. amazonicum plantations using sentinel 2 images |
title |
Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2 |
spellingShingle |
Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2 Batista, Fábio de Jesus Algoritmo de aprendizado de máquinas Índice de vegetação Paricá Volume de madeira Ulianópolis Machine learning algorithm Vegetation index Volume of timber CNPQ::CIENCIAS AGRARIAS::RECURSOS FLORESTAIS E ENGENHARIA FLORESTAL |
title_short |
Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2 |
title_full |
Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2 |
title_fullStr |
Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2 |
title_full_unstemmed |
Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2 |
title_sort |
Capacidade produtiva, estimativa de volume e biomassa em plantações de Schizolobium parahyba var. amazonicum com o uso de imagens sentinel 2 |
author |
Batista, Fábio de Jesus |
author_facet |
Batista, Fábio de Jesus |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Pereira, Rudiney Soares |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/9479801378014588 |
dc.contributor.referee1.fl_str_mv |
Dalla Corte, Ana Paula |
dc.contributor.referee1Lattes.fl_str_mv |
http://lattes.cnpq.br/9528175326712747 |
dc.contributor.referee2.fl_str_mv |
Silva, Emanuel Araújo |
dc.contributor.referee2Lattes.fl_str_mv |
http://lattes.cnpq.br/2765651276275384 |
dc.contributor.referee3.fl_str_mv |
Sanquetta, Carlos Roberto |
dc.contributor.referee3Lattes.fl_str_mv |
http://lattes.cnpq.br/9641517111540508 |
dc.contributor.referee4.fl_str_mv |
Amaral, Lúcio de Paula |
dc.contributor.referee4Lattes.fl_str_mv |
http://lattes.cnpq.br/6612592358172016 |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/9934744665863266 |
dc.contributor.author.fl_str_mv |
Batista, Fábio de Jesus |
contributor_str_mv |
Pereira, Rudiney Soares Dalla Corte, Ana Paula Silva, Emanuel Araújo Sanquetta, Carlos Roberto Amaral, Lúcio de Paula |
dc.subject.por.fl_str_mv |
Algoritmo de aprendizado de máquinas Índice de vegetação Paricá Volume de madeira Ulianópolis |
topic |
Algoritmo de aprendizado de máquinas Índice de vegetação Paricá Volume de madeira Ulianópolis Machine learning algorithm Vegetation index Volume of timber CNPQ::CIENCIAS AGRARIAS::RECURSOS FLORESTAIS E ENGENHARIA FLORESTAL |
dc.subject.eng.fl_str_mv |
Machine learning algorithm Vegetation index Volume of timber |
dc.subject.cnpq.fl_str_mv |
CNPQ::CIENCIAS AGRARIAS::RECURSOS FLORESTAIS E ENGENHARIA FLORESTAL |
description |
The aim was to estimate the volume (VT) and biomass (BA) of Paricá plantations with machine learning from the images of MSI/SENTINEL-2A, in Ulianópolis, Pará. In three productive areas (PO2, CAP2, and PO) of the species, 56 sample units (UAs) were installed for the forest inventory. The productive capacity was evaluated by the site index (IS) based on ANATRO of 28 dominant trees. Covariance analysis was applied on the IS model. Soil samples were collected from 0-20cm (chemical) and 20-40cm (physical). Three UAs per area were randomized for the harvesting and cubic scaling of the trees. BA was performed by the direct method, considering 10 trees Dg per stand. The T22MHA scene was downloaded from 26/07/2016. In Qgis, a 1A product was generated consisting of stack of bands B2 to B12. In 47 UAs, the reflectance of pixel/band was extracted for the calculation of the vegetation index (IV). GLM was applied to model VT. The estimation of BA was done from the FEBmean. The prediction of VT and BA by the sensor considered 50 IVs and 12 bands, where by cross-validation, the most accurate algorithm was defined among the tested ones (Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN)). The pre-selection of the 10 most important variables for the spatialization of VTpredicted and BApredicted was performed by the RF. The analysis was done by RStudio 3.5.2. The precision of the inventory was <10% in CAP2 and PO areas, and in PO2 was 13.50%. For the IS, sample errors occurred of 15%, 9%, and 11% for PO2, CAP2, and PO areas, respectively. The model height-age of Schumacher, =3,4531 , was adjusted for GLM from the Gama-Identity distribution. The sites were divided into high (21 to 25m), medium (19 to 21m), and low (15 to 19m) productivity. The high productivity was registered in 80% of the UAs of CAP2, 50% of PO2, and 8% of PO. From the 36º month-old, different growth rate was verified. The covariance analysis differentiates the sites more (PO2 and CAP2) and less (PO) productive. The topographic characteristics, the presence of more clay and moderate soil acidity were relevant to turn CAP2 more conducive to the productivity of the species. The function for the estimation of VT in PO2 (88.96m³.ha-1 ± 14.50) and CAP2 (152.35 m³.ha-1 ± 16.45) was in Naslund – Gaussian. The function for VT in PO (139.37m³.ha-1 ± 28.41) was Meyer – Gaussian. The stem contributed with 86.54% of BA, branches and leaves participated with 8.28% and 5.18%. The BA registered for PO2, CAP2, and PO were 34,53ton.ha-1 ± 5,63; 56,54ton.ha-1 ± 7,75; and 51,93ton.ha-1 ± 11,95, respectively. The comparisons between VTobserved and VTpredicted, defined by ANN showed similarities in CAP2 and in PO. The comparisons between BAobserved and BApredicited calculated by RF showed proportionality in CAP2. The most precise estimation of VT and BA occurred to CAP2. The differences in PO2 and PO do not reflect a statistical problem, but rather spectral mixtures. |
publishDate |
2019 |
dc.date.accessioned.fl_str_mv |
2019-11-22T16:14:12Z |
dc.date.available.fl_str_mv |
2019-11-22T16:14:12Z |
dc.date.issued.fl_str_mv |
2019-03-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://repositorio.ufsm.br/handle/1/19024 |
url |
http://repositorio.ufsm.br/handle/1/19024 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.cnpq.fl_str_mv |
500200000003 |
dc.relation.confidence.fl_str_mv |
600 |
dc.relation.authority.fl_str_mv |
a7274a7d-8dcd-466b-9a0d-c2b629e2ca88 ce0631ac-dda3-4952-850d-0565ff5f6409 b8681ceb-750b-4829-ae08-e40c03e51849 9215eedd-f015-4c70-bf7f-3c4727227d87 685262ea-5f0d-4d07-bada-e23eb17b133c 0dc06b07-acdf-4c76-9b58-6a68ee610e29 |
dc.rights.driver.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Santa Maria Centro de Ciências Rurais |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Engenharia Florestal |
dc.publisher.initials.fl_str_mv |
UFSM |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Recursos Florestais e Engenharia Florestal |
publisher.none.fl_str_mv |
Universidade Federal de Santa Maria Centro de Ciências Rurais |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações do UFSM instname:Universidade Federal de Santa Maria (UFSM) instacron:UFSM |
instname_str |
Universidade Federal de Santa Maria (UFSM) |
instacron_str |
UFSM |
institution |
UFSM |
reponame_str |
Biblioteca Digital de Teses e Dissertações do UFSM |
collection |
Biblioteca Digital de Teses e Dissertações do UFSM |
bitstream.url.fl_str_mv |
http://repositorio.ufsm.br/bitstream/1/19024/1/TES_PPGEF_2019_BATISTA_FABIO.pdf http://repositorio.ufsm.br/bitstream/1/19024/2/license_rdf http://repositorio.ufsm.br/bitstream/1/19024/3/license.txt http://repositorio.ufsm.br/bitstream/1/19024/4/TES_PPGEF_2019_BATISTA_FABIO.pdf.txt http://repositorio.ufsm.br/bitstream/1/19024/5/TES_PPGEF_2019_BATISTA_FABIO.pdf.jpg |
bitstream.checksum.fl_str_mv |
85dbbfd196e4c4b5a969388aeb1610e2 4460e5956bc1d1639be9ae6146a50347 2f0571ecee68693bd5cd3f17c1e075df c571b81462d703600133269c1d9e37ff 3d60c8e150e02adf10479523401fcf5a |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações do UFSM - Universidade Federal de Santa Maria (UFSM) |
repository.mail.fl_str_mv |
atendimento.sib@ufsm.br||tedebc@gmail.com |
_version_ |
1801485338450853888 |