This study presents a new approach to wood species identification using laser-induced breakdown spectroscopy (LIBS) combined with stacked machine learning techniques. The research analyzed 700 samples comprising nine Dalbergia species and nine additional tropical timber species, utilizing a handheld LIBS analyzer. A stacking methodology was developed by integrating three support vector machine (SVM) models with different kernel functions (linear, polynomial, and radial) in a one-versus-all (OVA) configuration. These SVM outputs were then combined using a partial least squares discriminant analysis (PLS-DA) meta-learner. Through PCA-based variable selection, the dimensionality was reduced from 23 401 to wavelengths while maintaining classification accuracy. The stacking approach achieved a Cohen's kappa value of 0.8671 in the validation set, significantly outperforming traditional flat classifiers. Variable importance analysis revealed calcium, magnesium, and barium as crucial elements for species differentiation, with their concentrations reflecting environmental conditions and geographical origins. This research demonstrates the potential of combining LIBS spectroscopy with advanced machine learning techniques for rapid, non-invasive timber identification, which can support efforts against illegal logging and enforcement of international trade regulations.
