▎ 摘　　要

The poor gas selectivity problem has been a long-standing issue for miniaturized chemical-resistor gas sensors. The electronic nose (e-nose) was proposed in the 1980s to tackle the selectivity issue, but it required top-down chemical functionalization processes to deposit multiple functional materials. Here, we report a novel gas-sensing scheme using a single graphene field-effect transistor (GFET) and machine learning to realize gas selectivity under particular conditions by combining the unique properties of the GFET and e-nose concept. Instead of using multiple functional materials, the gas-sensing conductivity profiles of a GFET are recorded and decoupled into four distinctive physical properties and projected onto a feature space as 4D output vectors and classified to differentiated target gases by using machine-learning analyses. Our single-GFET approach coupled with trained pattern recognition algorithms was able to classify water, methanol, and ethanol vapors with high accuracy quantitatively when they were tested individually. Furthermore, the gas-sensing patterns of methanol were qualitatively distinguished from those of water vapor in a binary mixture condition, suggesting that the proposed scheme is capable of differentiating a gas from the realistic scenario of an ambient environment with background humidity. As such, this work offers a new class of gas-sensing schemes using a single GFET without multiple functional materials toward miniaturized e-noses. Sensors: Graphene and machine learning sniff out gasesA sensor combined with machine learning algorithms makes an effective 'electronic nose' to distinguish different gases, according to research from the United States. The new approach, developed by a team led by Takeshi Hayasaka of the University of California, Berkeley, combines selectivity, low cost, and low power consumption without needing different materials to sense different gases. A graphene field effect transistor is used as a sensor, and four parameters of its conductivity profile are used as inputs to a machine learning classifier. With enough data, the classifier could identify water, methanol, and ethanol vapors. The researchers also showed that it could distinguish water and methanol in a mixture. These findings are an important step towards a miniaturized e-nose, which would be useful in areas such as environmental and safety monitoring, petrochemical processing, and other industries.