|
|
Registro Completo
|
Biblioteca(s): |
Embrapa Unidades Centrais. |
|
Data corrente: |
28/05/2019 |
|
Data da última atualização: |
25/11/2019 |
|
Autoria: |
ARAÚJO JÚNIOR, C. A.; SOUZA, P. D. de; ASSIS, A. L. de; CABACINHA, C. D.; LEITE, H. G.; SOARES, C. P. B.; SILVA, A. A. L. da; CASTRO, R. V. O. |
|
Afiliação: |
Carlos Alberto Araújo Júnior, Universidade Federal de Minas Gerais - UFMG/Instituto de Ciências Agrárias; Pábulo Diogo de Souza, Universidade Federal de Santa Maria - UFSM/Centro de Ciências Rurais/Departamento de Ciências Florestais; Adriana Leandra de Assis, Universidade Federal de Minas Gerais - UFMG/Instituto de Ciências Agrárias; Christian Dias Cabacinha, Universidade Federal de Minas Gerais - UFMG/Instituto de Ciências Agrárias; Helio Garcia Leite, Universidade Federal de Viçosa - UFV/Departamento de Engenharia Florestal; Carlos Pedro Boechat Soares, Universidade Federal de Viçosa - UFV/Departamento de Engenharia Florestal; Antonilmar Araújo Lopes da Silva, Celulose Nipo-Brasileira S.A.; Renato Vinícius Oliveira Castro, Universidade Federal de São João Del- Rei - UFSJ/Departamento de Ciências Agrárias. |
|
Título: |
Artificial neural networks, quantile regression, and linear regression for site index prediction in the presence of outliers. |
|
Ano de publicação: |
2019 |
|
Fonte/Imprenta: |
Pesquisa Agropecuária Brasileira, v. 54, e00078, 2019. |
|
Idioma: |
Inglês |
|
Notas: |
Título em português: Redes neurais artificiais, regressão quantílica e regressão linear para predição do índice de sítio na presença de ?outliers?. |
|
Conteúdo: |
The objective of this work was to compare methods of obtaining the site index for eucalyptus (Eucalyptus spp.) stands, as well as to evaluate their impact on the stability of this index in databases with and without outliers. Three methods were tested, using linear regression, quantile regression, and artificial neural network. Twenty-two permanent plots from a continuous forest inventory were used, measured in trees with ages from 23 to 83 months. The outliers were identified using a boxplot graphic. The artificial neural network showed better results than the linear and quantile regressions, both for dominant height and site index estimates. The stability obtained for the site index classification by the artificial neural network was also better than the one obtained by the other methods, regardless of the presence or the absence of outliers in the database. This shows that the artificial neural network is a solid modelling technique in the presence of outliers. When the cause of the presence of outliers in the database is not known, they can be kept in it if techniques as artificial neural networks or quantile regression are used. |
|
Palavras-Chave: |
Dominant height; Erros não amostrais; Forest modelling; Inteligência artificial; Modelagem florestal; Non-sampling errors. |
|
Thesagro: |
Inventário Florestal. |
|
Thesaurus NAL: |
Artificial intelligence; Eucalyptus; Forest inventory. |
|
Categoria do assunto: |
-- |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/205475/1/Artificial-neural-networks-quantile.pdf
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/197787/1/Artificial-neural-networks.pdf
|
|
Marc: |
LEADER 02341naa a2200337 a 4500
001 2115117
005 2019-11-25
008 2019 bl uuuu u00u1 u #d
100 1 $aARAÚJO JÚNIOR, C. A.
245 $aArtificial neural networks, quantile regression, and linear regression for site index prediction in the presence of outliers.$h[electronic resource]
260 $c2019
500 $aTítulo em português: Redes neurais artificiais, regressão quantílica e regressão linear para predição do índice de sítio na presença de ?outliers?.
520 $aThe objective of this work was to compare methods of obtaining the site index for eucalyptus (Eucalyptus spp.) stands, as well as to evaluate their impact on the stability of this index in databases with and without outliers. Three methods were tested, using linear regression, quantile regression, and artificial neural network. Twenty-two permanent plots from a continuous forest inventory were used, measured in trees with ages from 23 to 83 months. The outliers were identified using a boxplot graphic. The artificial neural network showed better results than the linear and quantile regressions, both for dominant height and site index estimates. The stability obtained for the site index classification by the artificial neural network was also better than the one obtained by the other methods, regardless of the presence or the absence of outliers in the database. This shows that the artificial neural network is a solid modelling technique in the presence of outliers. When the cause of the presence of outliers in the database is not known, they can be kept in it if techniques as artificial neural networks or quantile regression are used.
650 $aArtificial intelligence
650 $aEucalyptus
650 $aForest inventory
650 $aInventário Florestal
653 $aDominant height
653 $aErros não amostrais
653 $aForest modelling
653 $aInteligência artificial
653 $aModelagem florestal
653 $aNon-sampling errors
700 1 $aSOUZA, P. D. de
700 1 $aASSIS, A. L. de
700 1 $aCABACINHA, C. D.
700 1 $aLEITE, H. G.
700 1 $aSOARES, C. P. B.
700 1 $aSILVA, A. A. L. da
700 1 $aCASTRO, R. V. O.
773 $tPesquisa Agropecuária Brasileira$gv. 54, e00078, 2019.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Unidades Centrais (AI-SEDE) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
