Near-infrared spectroscopy for the distinction of wood and charcoal from Fabaceae species: comparison of ANN, KNN AND SVM models

Aim of study: The objective of this work was to evaluate the potential of NIR spectroscopy to differentiate Fabaceae species native to Araucaria forest fragments. Area of study; Trees of the evaluated species were collected from an Araucaria forest stand in the state of Santa Catarina, southern Brazil, in the region to be flooded by the Sao Roque hydroelectric project. Material and methods: Discs of three species (Inga vera, Machaerium paraguariense and Muellera campestris) were collected at 1.30 meters from the ground. They were sectioned to cover radial variation of the wood (regions near bark, intermediate and near pith). After wood analysis, the same samples were carbonized. Six spectra were obtained from each specimen of wood and charcoal. The original and second derivative spectra, principal component statistics and classification models (Artificial Neural Network: ANN, Support Vector Machines with kernel radial basis function: SVM and k-Nearest Neighbors: k-NN) were investigated. Main results: Visual analysis of spectra was not efficient for species differentiation, so three NIR classification models for species discrimination were tested. The best results were obtained with the use of k-NN for both wood and charcoal and ANN for wood analysis. In all situations, second derivative NIR spectra produced better results. Research highlights: Correct discrimination of wood and charcoal species for control of illegal logging was achieved. Fabaceae species in an Araucaria forest stand were correctly identified.