Identification of Ammonia and Phosphine Gas Using Graphene Nanosensor with Machine Learning Techniques

Abstract

Both ammonia (NH₃) and phosphine (PH₃) are widely used in industrial processes, and yet they are noxious and exhibit detrimental effects on human health. A variety of gas sensors have been developed to detect and monitor them in an industrial environment. Despite the remarkable progress on sensor development, there are still some limitations, for instance, the requirement of high operating temperatures, and that most sensors are solely dedicated to individual gas monitoring. Here we develop an ultrasensitive, highly discriminative platform for the detection and identification of NH₃ and PH₃ at room temperature using graphene nanosensors. Graphene is exfoliated and successfully functionalized by copper phthalocyanine derivate (CuPc). In combination with highly efficient machine learning techniques, the developed graphene nanosensor demonstrates an excellent gas identification performance even at ultralow concentrations, 100 ppb NH₃ (accuracy-100.0%, sensitivity-100.0%, specificity-100.0%), 100 ppb PH₃ (accuracy-77.8%, sensitivity-75.0%, and specificity-78.6%). Molecular dynamics simulation results reveal that the CuPc molecules attached on the graphene surface facilitates the adsorption of NH₃ on graphene owing to hydrogen bonding interactions. This smart sensor prototype paves a path to design highly selective, highly sensitive, miniaturized, non-dedicated gas sensors towards a wide spectrum of industrious gases.

Keywords: Graphene, gas sensing, ammonia and phosphine, gas identification, machine learning, molecular dynamic simulations