作者: Fabrízzio Alphonsus A.M.N. Soares , Edna Lúcia Flôres , Christian Dias Cabacinha , Gilberto Arantes Carrijo , Antônio Cláudio Paschoarelli Veiga
DOI: 10.1016/J.ASOC.2012.02.018
关键词: Artificial neural network 、 Forest inventory 、 Volume (thermodynamics) 、 Multilayer perceptron 、 Mathematical optimization 、 Tree (data structure) 、 Statistics 、 Eucalyptus 、 Computer science
摘要: In this work, diameters of Eucalyptus trees are predicted by means Multilayer Perceptron and Radial Basis Function artificial neural networks. By taking only three diameter measures at the base tree, recursively until they reach value minimum merchantable diameter, with no previous knowledge total tree height. It was considered top 4cm outside bark as diameter. The training conducted 10% from planted site. Smalian method utilizes to calculate volumes. performance proposed model satisfactory when volumes compared actual ones.