Influence of sample preparation methods on FTIR spectra for taxonomic identification of tropical trees in the Atlantic forest

Abstract

The Atlantic forest is one of the world's major tropical biomes due to its rich biodiversity. Its vast diversity of plant species poses challenges in floristic surveys. Fourier transform infrared spectroscopy (FTIR) enables rapid and residue-free data collection, providing diverse applications in organic sample analysis. FTIR spectra quality depends on the sample preparation methodology. However, no research on FTIR spectroscopy methodology for taxonomy has been conducted with tropical tree species. Hence, this study addresses the sample preparation influence on FTIR spectra for the taxonomic classification of 12 tree species collected in the Serra do Mar State Park (PESM) - Cunha Nucleus - São Paulo State, Brazil. Spectra were obtained from intact fresh (FL), intact dried (DL), and heat-dried ground (GL) leaves. The spectra were evaluated through chemometrics using Principal Component Analysis (PCA), Hierarchical Cluster Analysis (HCA), and Linear Discriminant Analysis (LDA) with validation by LDA-PCA. The results demonstrate that sample preparation directly influences tropical species FTIR spectra categorization capability. The best taxonomic classification result for all techniques, validated by LDA-PCA, was obtained from GL. FTIR spectra evaluation through PCA, HCA, and LDA allow for the observation of phylogenetic relationships among the species. FTIR spectroscopy proves to be a viable technique for taxonomic evaluation of tree species in floristic exploration of tropical biomes which can complement traditional tools used for taxonomic studies.

Keywords: Atlantic forest; FTIR; Multivariate analysis; Plant taxonomy; Tropical trees.

Graphical abstract

Fig. 1

Average FTIR spectra of plant samples fingerprint region (1770 cm⁻¹ – 700 cm⁻¹): A = FL; B = DL and C = GL.

Fig. 2

Score plot and loadings from PCA with 95% confidence ellipse and HCA graph plot of the fingerprint region (1770 cm⁻¹ – 700 cm⁻¹) of FL (A, B, C), DL (D, E, F) and GL (G, H, I).

Fig. 3

Score plot graph LDA-PCA with 95% confidence ellipse and LDA-PCA prediction confusion matrixes (B, D, F) - Fingerprint Region (1770 cm⁻¹ – 700 cm⁻¹): FL (A, B); DL (C, D); GL (E, F).

Fig. 4

LDA-PCA classification quality parameters for the three different sampling methods (A) and for each species: FL (B); DL (C) and GL (D) – 18 spectra for each species on the dataset cross-validation. Caption:Araucaria angustifolia (Aa); Campomanesia guaviroba (Cb); Guapira opposita (Go); Inga sessilis (Is); Myrsine gardneriana (Mg); Myrsine lineata (Ml); Myrsine umbellata (Mu); Nectandra lanceolata (Nl); Psychotria suterella (Ps); Schinus terebinthifolia (St); Senna multijuga (Sm); Sapium glandulosum (Sg).

figs1