Search

Comparative wood anatomy is the most accepted (traditional) method for wood identification. However, there is an ongoing search for an effective method where traditional methods may be insufficient in distinguishing on the species level. Near-infrared spectroscopy (NIRS) is one of the developing methods for wood identification. Near-infrared data of Scots pine, black pine, sessile oak and Hungarian oak were collected and examined in the spectral range of 12,000–4000 cm−1 with a resolution of 4 cm−1. Data were analyzed by partial least squares discriminate analysis (PLS-DA), decision trees (DT), artificial neural networks (ANN) and support vector machines (SVM). Raw data were subjected to multiple scatter correction (MSC), standard normal variate (SNV), Savitzky–Golay for derivatives (first [FD], second [SD]) and smoothing (Sm) and combinations of these preprocessing methods (Sm + FD, Sm + SD, FD + MSC, FD + SNV). Model performance compared through test accuracies. Accuracies varied between 99–100%, 76–98% and 73–96%, for genus level, oak and pine species, respectively. PLS-DA and SVM were found the most successful models. This study revealed that it is possible to discriminate Scots pine from black pine, and sessile oak from Hungarian oak by near-infrared spectroscopy and multivariate data analysis. [ABSTRACT FROM AUTHOR]

Identification of wood species with fast, reliable and non-destructive methods is highly important for forestry and wood-related industries. Near-infrared spectra of anatomically similar pine species (Pinus sylvestris L. and Pinus nigra J.F. Arnold) were taken and analysed by partial least squared discriminant analysis (PLS-DA) for comparing the efficiency of preprocessing methods. Raw data were subjected to multiple scatter correction (MSC), standard normal variate (SNV), Savitzky–Golay for derivatives (1st and 2nd Dr) and smoothing (Sm) and combination of these preprocessing methods (1st Dr, 1st Dr + SNV, 1st Dr + MSC, Sm + 1st Dr and Sm + 2nd Dr). The success of the models was determined by the accuracies of test sets that did not participate in the calibration phase. In this study, it was determined that not all the preprocessing methods improve the model performance. Smoothing with 1st derivatives (Sm + 1st Dr) enhanced 14.3% improvement and have the best performance (95%) for classification of pine species. For understanding modelled relationship, mean spectra and selectivity ratio were used. It was found that discrimination was held by the differences at their absorption, and the most important variables for wood classification were noted around 4000–7000 cm−1. [ABSTRACT FROM AUTHOR]