Ajuste do modelo de Schumacher e Hall e aplicação de redes neurais artificiais para estimar volume de árvores de eucalipto

Silva, Mayra Luiza Marques da; Binoti, Daniel Henrique Breda; Gleriani, José Marinaldo; Leite, Hélio Garcia

doi:10.1590/s0100-67622009000600015

Cited by 66 publications

(72 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As observed in the frequency histogram of percentage errors of ANN2 estimates, 73% of the data were wrong in the range of -10 to 10% when submitted to training, while in the validation process for the same interval the data missed 63% (Figure 3). Considering the results found in the present work, it can be verified that the artificial neural networks are efficient to estimate the individual volume variable in Eucalyptus forest stands, also corroborated by the studies developed by Silva et al (2009 and Miguel et al (2016).…”

Section: Volume Estimatessupporting

confidence: 90%

“…In the last years, ANN have gained prominence in the forest environment, with applications in the estimation of the trees volume (Binoti et al, 2014;Miguel et al, 2016;Silva et al, 2009) growth and production , taper (Diamantopoulou, 2005;Leite et al, 2010), individual tree volume (Castro et al, 2013), total tree height (Binoti et al, 2013), and diametric distribution (Binoti et al, 2012), however further studies are still needed on the subject.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial neural networks in whole-stand level modeling of Eucalyptus plants

Lima¹,

Lustosa²,

Oliveira³

et al. 2017

Afr. J. Agric. Res.

View full text Add to dashboard Cite

Forestry production is traditionally predicted using mathematical modelling, where whole-stand models are prominent for providing estimates of growth and production per unit area. However, there is a need to perform research that adopts innovative tools, such as artificial Intelligence techniques. The objective of this study was to train and evaluate the efficiency of Artificial Neural Networks (ANN) in the modeling process of growth and production of Whole-Stand Level, in "equineanean" forests of the Eucalyptus genus clones. For the training of the networks, the supervised method was adopted. There were 100 networks trained, of which, for each output variable, 5 networks were selected. The criteria used to verify the quality of the training and validation of the networks were: Student's test "T", graphical analysis of the dispersion of residues, standard error of the relative estimate (Syx%), Pearson's correlation coefficient (r) between the observed and estimated values, and aggregate difference (AD). The ANN selected in the training process, which estimated the volume variables, site index and future production, when validated did not differ statistically by the Test "T" and presented adequate statistical accuracy values to the modeling process, with satisfactory correlation values (r) between the observed and estimated values, low values of standard error of the relative estimate (Syx%) and aggregate difference (AD). Artificial neural networks of the multilayer perceptron type are precise and efficient in the entire modeling process for whole-stand level of Eucalyptus plantations, therefore its use is recommended.

show abstract

Section: Volume Estimatessupporting

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Artificial neural networks in whole-stand level modeling of Eucalyptus plants

Lima¹,

Lustosa²,

Oliveira³

et al. 2017

Afr. J. Agric. Res.

View full text Add to dashboard Cite

show abstract

“…The use of neural networks to estimate height and volume of trees has been already reported (Silva et al 2009(Silva et al , Özçelik et al 2010(Silva et al , Özçelik et al 2013). The information on height and DBH was used as inputs in the configuration of the adopted network in those studies.…”

Section: Resultsmentioning

confidence: 98%

Application of neural networks to predict volume in eucalyptus

Bhering

Cruz

Rosado

et al. 2015

Crop Breed. Appl. Biotechnol.

View full text Add to dashboard Cite

-The 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. Keywords

show abstract

“…O modelo de Schumacher-Hall é particularmente difícil de ser superado, porque a conformação logarítmica e a combinação das variáveis independentes dap e altura lhe confere propriedades estatísticas muito favoráveis na estimativa volumétrica (SILVA et al, 2009). Ademais, sua simplicidade e praticidade facilitam o seu emprego no dia-adia.…”

Section: Ajuste De Equações Volumétricasunclassified

Contribuição de um segundo diâmetro na estimação de volume individual de plantios jovens de Tectona grandis L.f.

Sanquetta

Corte

et al. 2016

AGRO@MBIENTE

View full text Add to dashboard Cite

Resumo: Estimar o volume individual das árvores com precisão e sem viés é um pré-requisito para um inventário florestal de qualidade. Para tanto, os métodos mais comuns se baseiam na aplicação do fator de forma médio ou em equações de simples ou dupla entrada. O presente estudo propõe modelos com dois diâmetros como variáveis independentes para estimar o volume comercial de Tectona grandis, visando melhorar sua precisão e reduzir o viés. Trinta e cinco árvores de plantios comerciais de 4 a 5 anos de idade, localizados no município de Redenção, Pará, foram cubadas rigorosamente pelo método de Smalian. Diâmetros a diferentes alturas foram correlacionados com o volume real. Três novos modelos volumétricos baseados em dois diâmetros foram propostos, sem a adição da variável altura da árvore. Compararam-se esses modelos com outros tradicionalmente empregados em inventários florestais. O modelo de melhor ajuste usa o diâmetro à altura do peito (dap) e o diâmetro a 4,0 m de altura (d4,0) como variáveis independentes. Dificuldades operacionais do uso de d4,0 foram discutidas. Os modelos que utilizam o dap e o diâmetro a 2,0 m (d2,0) foram considerados os mais satisfatórios, pois são mais precisos e práticos que os clássicos, além de serem operacionalmente mais factíveis que o modelo com d4,0. Portanto, existem outros diâmetros que são mais correlacionados com o volume do que o dap, e que a introdução de um segundo diâmetro melhora as estimativas de volume, mesmo sem a inclusão da variável altura.Palavras-chave: Correlação. Predição. Modelagem. Regressão. Abstract:Estimating the individual volume of trees with precision and without bias is a prerequisite of a quality forest inventory. The most common methods are based on application of the average form factor, or on single or double entry equations. This study proposes models with two diameters as independent variables to estimate the commercial volume of Tectona grandis, with a view to improving precision and reducing bias. Thirty-five trees from commercial plantation of 4-5 years old, in the town of Redenção, in the State of Pará, were rigorously cubed using the Smalian method of scaling. Diameters at different heights were correlated with actual volume. Three new volumetric models based on two diameters were proposed, without the addition of tree height as a variable. These models were compared with others, which are traditionally used in forest inventories. The model with the best fit uses the diameter at breast height (dap) and at a height of 4.0 m (d4.0) as independent variables. The operational difficulties of using d4.0 are discussed. Models that use the dap and the diameter at 2.0 m (d2.0) were considered the most satisfactory, as they are more accurate and practical than classic models, and operationally more feasible than the model using d4,0. The conclusion was that there are other diameters that are more correlated with volume than dap, and that the introduction of a second diameter improves volume estimates, even without the inclusion of height as a variable.

show abstract

Ajuste do modelo de Schumacher e Hall e aplicação de redes neurais artificiais para estimar volume de árvores de eucalipto

Cited by 66 publications

References 6 publications

Artificial neural networks in whole-stand level modeling of Eucalyptus plants

Artificial neural networks in whole-stand level modeling of Eucalyptus plants

Application of neural networks to predict volume in eucalyptus

Contribuição de um segundo diâmetro na estimação de volume individual de plantios jovens de Tectona grandis L.f.

Contact Info

Product

Resources

About