Ana Paula Marques Martins

Estimativa do Afilamento do Fuste de Araucária Utilizando Técnicas de Inteligência Artificial

ABSTRACT The aim of this study was to compare the performance of artificial intelligence techniques with taper functions and evaluate the effect of age on this estimate. The data set was comprised of 135 observations covering the ages 6, 12, 18, 24 and 43 years of age of a stand of Araucaria angustifolia. Adjusted taper functions were Kozak Schoepfer, Hradetzky and Garay modified. The artificial intelligence models used were: ANN and tree model. The input vectors are the same variables used in taper equations and also the same arrangement with the addition of age. 70% of the data was used for adjustment and 30% for validation. The taper function Hradetzky provided the best fit. Among the models evaluated, the ANN provided the best estimates, highlighting the ANN by adding the age variable. The performance of M5P was satisfactory, however, less effective than the other techniques. Keywords: taper function, M5P, multi layer perceptron . 1. INTRODUCAO Tendo em vista a tendencia do setor florestal brasileiro em manejar as florestas visando multiprodutos para maximizacao da renda, se faz necessaria a adocao de tecnicas que possibilitem a quantificacao e qualificacao desses produtos ( Mendonca et al., 2015 ). Nesse contexto, as funcoes de afilamento tem se mostrado como

Relação hipsométrica para Pinus elliottii Engelm em diferentes posições sociológicas em Dois Vizinhos (PR)

This study aims to model the hypsometric relation to Pinus elliottii Engelm in the city of Dois Vizinhos, Parana State, Brazil, and to investigate the difference of the relationship between the different sociological positions. For this study was conducted a census on a plot of 0.25 ha located on the Campus of the Federal Technological University of Parana, being measured diameter at breast height (dbh), total height (h) and sociological position of three strata: PS1 - dominant trees; PS2 - codominant trees; and PS3 - controlled or suppressed trees. Seven models of hypsometric relation determined by STEPWISE procedure were adjusted. The parameters used for selection of the models were the adjusted coefficient of determination (R 2 aj. ), coefficient of variation (CV), calculated F value and the examination of residue. The analysis of covariance (ANACOVA) was used to verify the difference in level and trend of the equations selected among the different sociological positions. The model selected to describe the hypsometric relation was: ln h = 2.7654 to 15.62751 * 1 / √dap 3 with R 2 aj. values equal to 0.53, CV 4.57% and F value equal to 331.47. Analysis of covariance indicated significant differences in level and slope model that describes the hypsometric relationship between the different sociological positions, fitting with this data again, generating equations for each sociological position, these being: PS1: ln h = 2.7905 to 15.6652 * 1 / √dap 3 ; PS2: ln h = 2.6206 to 7.3158 * 1 / √dap 3 ; and PS3: ln h = 2.7537 to 15.9753 * 1 / √dap 3 .