Predicting the morphological characteristics and basic density of Eucalyptus wood using the NIRS technique

Abstract

This work aimed to apply the near infrared spectroscopy technique (NIRS) for fast prediction of basic density and morphological characteristics of wood fibers in Eucalyptus clones. Six Eucalyptus clones aged three years were used, obtained from plantations in Cocais, Guanhães, Rio Doce and Santa Bárbara, in Minas Gerais state. The morphological characteristics of the fibers and basic density of the wood were determined by conventional methods and correlated with near infrared spectra using partial least square regression (PLS regression). Best calibration correlations were obtained in basic density prediction, with values 0.95 for correlation coefficient of cross validation (Rcv) and 3.4 for ratio performance deviation (RPD), in clone 57. Fiber length can be predicted by models with Rcv ranging from 0.61 to 0.89 and standard error (SECV) ranging from 0.037 to 0.079 mm. The prediction model for wood fiber width presented higher Rcv (0.82) and RPD (1.9) values in clone 1046. Best fits to estimate lumen diameter and fiber wall thickness were obtained with information from clone 1046. In some clones, the NIRS technique proved efficient to predict the anatomical properties and basic density of wood in Eucalyptus clones.