Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches

Detalhes bibliográficos
Autor(a) principal: Della-Silva, João Lucas
Data de Publicação: 2022
Outros Autores: Silva Junior, Carlos Antonio da, Lima, Mendelson, Ribeiro, Ricardo da Silva, Shiratsuchi, Luciano Shozo, Rossi, Fernando Saragosa [UNESP], Teodoro, Larissa Pereira Ribeiro, Teodoro, Paulo Eduardo
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1016/j.rsase.2022.100742
http://hdl.handle.net/11449/223718
Resumo: Sampling trees in natural environment can be used in studies ranging from floristic composition and phytogeography to management and growth modelling, and accurate inventories are based on highly labor-intensive methods. Relying on hyperspectral approach, this study aimed to differentiate spectral libraries of four Amazon tree species. We first prepared the spectroradiometer data on representative bands on foliar biochemistry, followed by reflectance inflection difference and finally, we applied vegetation indices. Next, the discriminant analysis was reasoned on multivariate approach, were successfully discriminated the spectral curves related to each of evaluated tree species. By visual analysis, some regions of the electromagnetic spectrum with higher differentiation in reflectance responses can be seen, in portions of the visible spectrum (0.5–0.65 μm), near-infrared (0.913–1.25 μm) and short-wave infrared 2 (2.1–2.5 μm). There was a higher contribution in distinguishing between species based on specific RID (Reflectance Inflection Difference) heights, such as seen on specific representative bands, where RID approach reached 99.87% of data variability related to principal component 1 (PC1) and 99.72% for leaf structure-based bands in PC1. Principal component analysis applied to the vegetation indices brought satisfactory results, with PC1 highly related to the variability of the vegetation indices results (99.37%). Adopting this approach in hyperspectral data at the leaf level and well-defined classes results in good responses. We emphasize the importance of using combined vegetation indices, with greater contributions by indices developed for quantization or absorption of electromagnetic radiation by chlorophyll, which are based in the visible region. These results can improve further research by using remote sensing techniques, as create brand-new data for Amazonian tree species policymaking, conservation and research.
id UNSP_17a4ae6baa3d6dfd26569ee18960e5ea
oai_identifier_str oai:repositorio.unesp.br:11449/223718
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approachesAmazonian treesForest managementHyperspectral dataMultivariate analysisVegetation indicesSampling trees in natural environment can be used in studies ranging from floristic composition and phytogeography to management and growth modelling, and accurate inventories are based on highly labor-intensive methods. Relying on hyperspectral approach, this study aimed to differentiate spectral libraries of four Amazon tree species. We first prepared the spectroradiometer data on representative bands on foliar biochemistry, followed by reflectance inflection difference and finally, we applied vegetation indices. Next, the discriminant analysis was reasoned on multivariate approach, were successfully discriminated the spectral curves related to each of evaluated tree species. By visual analysis, some regions of the electromagnetic spectrum with higher differentiation in reflectance responses can be seen, in portions of the visible spectrum (0.5–0.65 μm), near-infrared (0.913–1.25 μm) and short-wave infrared 2 (2.1–2.5 μm). There was a higher contribution in distinguishing between species based on specific RID (Reflectance Inflection Difference) heights, such as seen on specific representative bands, where RID approach reached 99.87% of data variability related to principal component 1 (PC1) and 99.72% for leaf structure-based bands in PC1. Principal component analysis applied to the vegetation indices brought satisfactory results, with PC1 highly related to the variability of the vegetation indices results (99.37%). Adopting this approach in hyperspectral data at the leaf level and well-defined classes results in good responses. We emphasize the importance of using combined vegetation indices, with greater contributions by indices developed for quantization or absorption of electromagnetic radiation by chlorophyll, which are based in the visible region. These results can improve further research by using remote sensing techniques, as create brand-new data for Amazonian tree species policymaking, conservation and research.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Federal University of Mato Grosso (UFMT) Post-Graduate Program in Environmental Sciences (PPGCAM), Mato GrossoState University of Mato Grosso (UNEMAT), Mato GrossoState University of Mato Grosso (UNEMAT), Alta Floresta, Mato GrossoUniversity of São Paulo (USP) Institute of Biosciences Department of BotanyLouisiana State University (LSU) AgCenter School of Plant Environmental and Soil SciencesState University of São Paulo (UNESP) JaboticabalFederal University of Mato Grosso do Sul (UFMS), Chapadão do Sul, Mato Grosso do SulState University of São Paulo (UNESP) JaboticabalCAPES: 001CNPq: 303767/2020-0CNPq: 309250/2021-8Post-Graduate Program in Environmental Sciences (PPGCAM)State University of Mato Grosso (UNEMAT)Universidade de São Paulo (USP)and Soil SciencesUniversidade Estadual Paulista (UNESP)Universidade Federal de Mato Grosso do Sul (UFMS)Della-Silva, João LucasSilva Junior, Carlos Antonio daLima, MendelsonRibeiro, Ricardo da SilvaShiratsuchi, Luciano ShozoRossi, Fernando Saragosa [UNESP]Teodoro, Larissa Pereira RibeiroTeodoro, Paulo Eduardo2022-04-28T19:52:41Z2022-04-28T19:52:41Z2022-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.rsase.2022.100742Remote Sensing Applications: Society and Environment, v. 26.2352-9385http://hdl.handle.net/11449/22371810.1016/j.rsase.2022.1007422-s2.0-85127098921Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengRemote Sensing Applications: Society and Environmentinfo:eu-repo/semantics/openAccess2022-04-28T19:52:41Zoai:repositorio.unesp.br:11449/223718Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T23:40:16.336411Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches
title Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches
spellingShingle Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches
Della-Silva, João Lucas
Amazonian trees
Forest management
Hyperspectral data
Multivariate analysis
Vegetation indices
title_short Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches
title_full Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches
title_fullStr Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches
title_full_unstemmed Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches
title_sort Amazonian species evaluation using leaf-based spectroscopy data and dimensionality reduction approaches
author Della-Silva, João Lucas
author_facet Della-Silva, João Lucas
Silva Junior, Carlos Antonio da
Lima, Mendelson
Ribeiro, Ricardo da Silva
Shiratsuchi, Luciano Shozo
Rossi, Fernando Saragosa [UNESP]
Teodoro, Larissa Pereira Ribeiro
Teodoro, Paulo Eduardo
author_role author
author2 Silva Junior, Carlos Antonio da
Lima, Mendelson
Ribeiro, Ricardo da Silva
Shiratsuchi, Luciano Shozo
Rossi, Fernando Saragosa [UNESP]
Teodoro, Larissa Pereira Ribeiro
Teodoro, Paulo Eduardo
author2_role author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Post-Graduate Program in Environmental Sciences (PPGCAM)
State University of Mato Grosso (UNEMAT)
Universidade de São Paulo (USP)
and Soil Sciences
Universidade Estadual Paulista (UNESP)
Universidade Federal de Mato Grosso do Sul (UFMS)
dc.contributor.author.fl_str_mv Della-Silva, João Lucas
Silva Junior, Carlos Antonio da
Lima, Mendelson
Ribeiro, Ricardo da Silva
Shiratsuchi, Luciano Shozo
Rossi, Fernando Saragosa [UNESP]
Teodoro, Larissa Pereira Ribeiro
Teodoro, Paulo Eduardo
dc.subject.por.fl_str_mv Amazonian trees
Forest management
Hyperspectral data
Multivariate analysis
Vegetation indices
topic Amazonian trees
Forest management
Hyperspectral data
Multivariate analysis
Vegetation indices
description Sampling trees in natural environment can be used in studies ranging from floristic composition and phytogeography to management and growth modelling, and accurate inventories are based on highly labor-intensive methods. Relying on hyperspectral approach, this study aimed to differentiate spectral libraries of four Amazon tree species. We first prepared the spectroradiometer data on representative bands on foliar biochemistry, followed by reflectance inflection difference and finally, we applied vegetation indices. Next, the discriminant analysis was reasoned on multivariate approach, were successfully discriminated the spectral curves related to each of evaluated tree species. By visual analysis, some regions of the electromagnetic spectrum with higher differentiation in reflectance responses can be seen, in portions of the visible spectrum (0.5–0.65 μm), near-infrared (0.913–1.25 μm) and short-wave infrared 2 (2.1–2.5 μm). There was a higher contribution in distinguishing between species based on specific RID (Reflectance Inflection Difference) heights, such as seen on specific representative bands, where RID approach reached 99.87% of data variability related to principal component 1 (PC1) and 99.72% for leaf structure-based bands in PC1. Principal component analysis applied to the vegetation indices brought satisfactory results, with PC1 highly related to the variability of the vegetation indices results (99.37%). Adopting this approach in hyperspectral data at the leaf level and well-defined classes results in good responses. We emphasize the importance of using combined vegetation indices, with greater contributions by indices developed for quantization or absorption of electromagnetic radiation by chlorophyll, which are based in the visible region. These results can improve further research by using remote sensing techniques, as create brand-new data for Amazonian tree species policymaking, conservation and research.
publishDate 2022
dc.date.none.fl_str_mv 2022-04-28T19:52:41Z
2022-04-28T19:52:41Z
2022-04-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1016/j.rsase.2022.100742
Remote Sensing Applications: Society and Environment, v. 26.
2352-9385
http://hdl.handle.net/11449/223718
10.1016/j.rsase.2022.100742
2-s2.0-85127098921
url http://dx.doi.org/10.1016/j.rsase.2022.100742
http://hdl.handle.net/11449/223718
identifier_str_mv Remote Sensing Applications: Society and Environment, v. 26.
2352-9385
10.1016/j.rsase.2022.100742
2-s2.0-85127098921
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Remote Sensing Applications: Society and Environment
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808129541705564160