Artificial neural networks for classifying the productive capacity of a forest stand in the Jari region, western Pará

Abstract

Listen

Translate article

The growth and production of a forest stand depend on indicators such as the site's productive capacity, which can be defined as the site's potential to produce wood, or another product in each location, for a given species or clone. This study compared traditional methods and artificial neural networks in the classification of the productive capacity of sites in Eucalyptus urograndis plantations located in the Jari region, western Pará state. For this, 593 permanent circular plots of 500 m² each were randomized, where 38,072 trees were monitored annually from 2013 to 2017. In each plot, the diameter at the height of 1.30 from the ground (DBH, in cm) and the total height (Ht, in meters) of nine trees were measured. Three traditional methods were evaluated: guide-curve method (GC), difference equation method (DE), and parameter prediction method (PP). The statistical criteria used to assess the quality of the classification were: BIAS (%), mean squared error (RMSE (%)), and Pearson correlation coefficient (r). Artificial neural networks were superior to traditional methods, indicating the potential of the algorithm to model the productive capacity of a site for forest stands.