The utilization of an olfactory machine in wood identification demonstrates a promising prospect: discerning disparities in emission profiles of volatile organic compounds between Picea abies and Pinus sylvestris

Abstract

In order to identify wood species for various purposes using the traditional method based on macro- and microscopic wood anatomy and physical characteristics, a comprehensive technical understanding of wood anatomy is crucial. However, in recent years, there has been growing interest in alternative wood identification methods. The use of intelligent systems that are able to identify species through the analysis of emitted odors can be a possible alternative to this task. As the capabilities of odor monitoring sensors continue to advance while their associated expenses concurrently decrease, it appears that the opportune moment has arrived for the implementation of automated, non-anthropogenic systems and methodologies for identifying wood. In this study, Picea abies L. and Pinus sylvestris L. were used to produce a set of odor fingerprints. An olfactory machine consisting of six metal oxide semiconductors was used to produce the specific odor profile of each species. Samples with a fresh planed surface were prepared. Overall, the odor characteristics obtained through the olfactory system using principal component analysis (PCA), support vector machine (SVM), and linear discriminant analysis (LDA) correctly distinguished two conifer species with 100% accuracy.