Machine learning-enabled graphene-based electronic olfaction sensors and their olfactory performance assessment

Abstract

Olfaction is an evolutionary old sensory system, which provides sophisticated access to information about our surroundings. In particular, detecting the volatile organic compounds (VOCs) emitted during natural and artificial processes can be used as characteristic fingerprints and help to identify their source. Inspired by the biological example, artificial olfaction aims at achieving similar performance and thus digitizing the sense of smell. Here, we present the development of machine learning-enabled graphene-based electronic olfaction sensors and propose an approach to assess their olfactory performance toward VOCs. Eleven transient kinetic features extracted from the sensing response profile are utilized as their fingerprint information. By mimicking the Sniffin' Sticks test, electronic olfaction sensors exhibit high olfactory performance toward four VOC odors (clove, eucalyptus, lemon, and rose scent) in terms of odor detection threshold, odor discrimination, and identification performance. Upon exposure to binary odor mixtures, response features of electronic olfaction sensors behave more similarly to that of an individual odor, with a tendency that correlates with their ratio, resembling the overshadowing effect in human olfactory perception. Molecular dynamics simulations and density functional theory calculations results reveal competing adsorption mechanisms between odorant molecules and sensing materials. This may facilitate electronic olfaction sensor applications in some emerging fields, such as environmental monitoring or public security.