Olfaction is an evolutionary old sensory system, which provides sophisticated access to information
about our surroundings. Inspired by the biological example, gas sensors in combination with efficient
machine learning algorithms aim to achieve similar performance and thus to digitize the sense of
smell. Despite the significant progress of e-noses, their compactness still remains challenging due to
the complex layout design of sensor arrays with a multitude of receptor types or sensor materials, and
the high working temperature. In this work, we present the development of machine learning-enabled
graphene-based single-channel electronic olfaction (e-olfaction) sensors and propose a methodology
to evaluate their olfactory performance. We selected four VOC-based odors, namely eucalyptol, 2-
nonanone, eugenol, and 2-phenylethanol, which are widely used in human olfactory performance
assessment. We achieved a low odor detection limit of 4.4 ppm (for 2Phe) and high odor
discrimination (83.3%) and identification (97.5%) accuracies. Both molecular dynamics simulations
(MDS) and density functional theory (DFT) were employed to elucidate the adsorption interaction
between odorant molecules and sensing materials. Our work demonstrates that the developed e-
olfaction exhibits excellent olfactory performance in sniffing out VOC-based odors. This work may
facilitate miniaturization of e-noses, digitization of odors, and distinction of volatile organic compounds
(VOCs) in various emerging applications.
Key words: Biomimetic olfaction, gas sensors, machine learning, odor discrimination, odor
identification
Olfaction is an evolutionary old sensory system, which provides sophisticated access to information
about our surroundings. Inspired by the biological example, gas sensors in combination with efficient
machine learning algorithms aim to achieve similar performance and thus to digitize the sense of
smell. Despite the significant progress of e-noses, their compactness still remains challenging due to
the complex layout design of sensor arrays with a multitude of receptor types or sensor materials, and
the high working temperature. In this work, we present the development of machine learning-enabled
graphene-based single-channel electronic olfaction (e-olfaction) sensors and propose a methodology
to evaluate their olfactory performance. We selected four VOC-based odors, namely eucalyptol, 2-
nonanone, eugenol, and 2-phenylethanol, which are widely used in human olfactory performance
assessment. We achieved a low odor detection limit of 4.4 ppm (for 2Phe) and high odor
discrimination (83.3%) and identification (97.5%) accuracies. Both molecular dynamics simulations
(MDS) and density functional theory (DFT) were employed to elucidate the adsorption interaction
between odorant molecules and sensing materials. Our work demonstrates that the developed e-
olfaction exhibits excellent olfactory performance in sniffing out VOC-based odors. This work may
facilitate miniaturization of e-noses, digitization of odors, and distinction of volatile organic compounds
(VOCs) in various emerging applications.
Key words: Biomimetic olfaction, gas sensors, machine learning, odor discrimination, odor
identification