Application of neural networks to predict volume in eucalyptus

dc.contributor.authorBhering, Leonardo Lopes
dc.contributor.authorCruz, Cosme Damião
dc.contributor.authorPeixoto, Leonardo de Azevedo
dc.contributor.authorRosado, Antônio Marcos
dc.contributor.authorNascimento, Moysés
dc.contributor.authorLaviola, Bruno Galveas
dc.date.accessioned2018-02-07T12:19:22Z
dc.date.available2018-02-07T12:19:22Z
dc.date.issued2015-03-16
dc.description.abstractThe aim of this study was to evaluate the methodology of Artificial Neural Networks (ANN) in order to predict wood volume in eucalyptus and its impacts on the selection of superior families, and to compare artificial neural network with regression models. Data used were obtained in a random block design with 140 half-sib families with five replications at three years of age, and four replications at six years of age, both with five plants per plot. The volume was estimated using ANN and regression models. It was used 2000 and 1500 data to train ANN, and 1500 and 1300 to validate ANN for 3 and 6 years of age, respectively. It is concluded that ANN can help improving the accuracy to measure the volume in eucalyptus trees, and to automate the process of forestry inventory and were more accurate in predicting wood volume than almost all regression models.en
dc.description.abstractO objetivo deste trabalho foi avaliar a metodologia das redes neurais artificiais (RNA) para predizer o volume de madeira nos programas de melhoramento de eucalipto e na seleção de famílias comparando as RNA com modelos de regressão. O delineamento foi em blocos casualizados com 140 famílias de meios-irmãos, 5 e 4 repetições para 3 e 6 anos respectivamente, ambos com 5 plantas por parcela. Para o treinamento da rede, foi utilizado 2000 e 1500 indivíduos, e para validação foram utilizados 1500 e 1300 indivíduos, respectivamente, para 3 e 6 anos. Foi concluído que as RNA pode ajudar a melhorar a acurácia na medição do volume em árvores de eucalipto e automatizar o processo do inventário florestal. As RNA foram mais acuradas na predição do volume de madeira que quase todos os modelos de regressão.pt-BR
dc.formatpdfpt-BR
dc.identifier.issn1984-7033
dc.identifier.urihttp://dx.doi.org/10.1590/1984-70332015v15n3a23
dc.identifier.urihttp://www.locus.ufv.br/handle/123456789/17415
dc.language.isoengpt-BR
dc.publisherCrop Breeding and Applied Biotechnologypt-BR
dc.relation.ispartofseriesv .15, n. 3, p. 125-131, July/Sept. 2015pt-BR
dc.rightsOpen Accesspt-BR
dc.subjectGenetic parameterspt-BR
dc.subjectGain with selectionpt-BR
dc.subjectPlant breedingpt-BR
dc.titleApplication of neural networks to predict volume in eucalyptusen
dc.typeArtigopt-BR

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
artigo.pdf
Size:
323.42 KB
Format:
Adobe Portable Document Format
Description:
Texto completo

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections