Classification of Amazonian fast-growing tree species and wood chemical determination by FTIR and multivariate analysis (PLS-DA, PLS)

Abstract

Fast-growing trees like Capirona, Bolaina, and Pashaco have the potential to reduce forest degradation because of their ecological features, the economic importance in the Amazon Forest, and an industry based on wood-polymer composites. Therefore, a practical method to discriminate specie (to avoid illegal logging) and determine chemical composition (tree breeding programs) is needed. This study aimed to validate a model for the classification of wood species and a universal model for the rapid determination of cellulose, hemicellulose, and lignin using FTIR spectroscopy coupled with chemometrics. Our results showed that PLS-DA models for the classification of wood species (0.84 ≤ R2 ≤ 0.91, 0.12 ≤ RMSEP ≤ 0.20, accuracy, specificity, and sensibility between 95.2 and 100%) were satisfied with the full spectra and the differentiation among these species based on IR peaks related to cellulose, lignin, and hemicellulose. Besides, the full spectra helped build a three-species universal PLS model to quantify the principal wood chemical components. Lignin (RPD = 2.27, $${R}_{c}^{2}$$ R c 2 = 0.84) and hemicellulose (RPD = 2.46, $${R}_{c}^{2}$$ R c 2 = 0.83) models showed a good prediction, while cellulose model (RPD = 3.43, $${R}_{c}^{2}$$ R c 2 = 0.91) classified as efficient. This study showed that FTIR-ATR, together with chemometrics, is a reliable method to discriminate wood species and to determine the wood chemical composition in juvenile trees of Pashaco, Capirona, and Bolaina.

Making wood inspection easier: FTIR spectroscopy and machine learning for Brazilian native commercial wood species identification

“…11,14,15 The diverse molecular composition found in wood presents an exciting prospect for creating a rapid and precise technique to detect and categorize wood samples using molecular spectroscopy. In the literature, we can nd a few examples that support our hypothesis: (i) three fast-growing tree species from the Amazonian forest (Pashco, Capirona, and Bolaina) were successfully discriminated by using Fourier transform infrared spectroscopy (FTIR) associated with partial least square discrimination analysis (PLS-DA), by using cellulose, lignin, and hemicellulose peaks with accuracy above 91%; 16 (ii) FTIR and PLS-DA were also able to differentiate between compression and non-compression wood by analyzing lignin bands from Pinus radiata species; 17 (iii) the growing location of wood samples was identied by FTIR spectrafrom 24 wood samples (16 hardwood and 8 sowood)and hierarchical clustering analysis (HCA), followed by principal component analysis (PCA) and linear discriminant analysis (LDA); 18 (iv) two Pine woods species and growing location was also determined by using ATR-FTIR (attenuated total reectance -Fourier transform infrared spectroscopy) and PCA with DA in the lignin and polysaccharide bands range. 19 Recently, our group demonstrated the potential use of FTIR associated with PCA and Support Vector Machine (SVM) to classify Eucalyptus species.…”