ESTIMATION OF HEIGHT OF EUCALYPTUS TREES WITH NEUROEVOLUTION OF AUGMENTING TOPOLOGIES (NEAT)

ABSTRACT The aim of this study was to evaluate the method of neuroevolution of augmenting topologies (NEAT) to adjust the weights and the topology of artificial neural networks (ANNs) in the estimation of tree height in a clonal population of eucalyptus, and compare with estimates obtained by a hypsometric regression model. To estimate the total tree height (Ht), the RNAs and the regression model, we used as variables a diameter of 1.3 m height (dbh) and the dominant height (Hd). The RNAs were adjusted and applied to the computer system NeuroForest, varying the size of the initial population (the genetic algorithm parameter) and the density of initial connections. Estimates of the total height of the trees obtained with the use of RNA and the regression model were evaluated based on the correlation coefficient, the percentage of errors scatter plot, the percentage frequency histogram of percentage errors, and the root mean square error (root mean square error - RMSE). Various settings which resulted in superior statistics to the hypsometric regression model were found. Connections had the highest correlation and the lowest RMSE% with a population size value of 300 and an initial density of 0.1 RNA. The NEAT methodology proved effective in estimating the height of trees in clonal population of eucalyptus.