In ACS nano ; h5-index 203.0
As miniaturized solutions, mid-infrared (MIR) waveguide sensors are promising for label-free compositional detection of mixtures leveraging plentiful absorption fingerprints. However, the quantitative analysis of liquid mixtures is still challenging using MIR waveguide sensors, as the absorption spectrum overlaps for multiple organic components accompanied by strong water absorption background. Here, we present an artificial-intelligence-enhanced metamaterial waveguide sensing platform (AIMWSP) for aqueous mixture analysis in the MIR. With the sensitivity-improved metamaterial waveguide and assistance of machine learning, the MIR absorption spectra of a ternary mixture in water can be successfully distinguished and decomposed to single-component spectra for predicting concentration. A classification accuracy of 98.88% for 64 mixing ratios and 92.86% for four concentrations below the limit of detection (972 ppm, based on 3σ) with steps of 300 ppm are realized. Besides, the mixture concentration prediction with root-mean-squared error varying from 0.107 vol % to 1.436 vol % is also achieved. Our work indicates the potential of further extending this sensing platform to MIR spectrometer-on-chip aiming for the data analytics of multiple organic components in aqueous environments.
Zhou Jingkai, Zhang Zixuan, Dong Bowei, Ren Zhihao, Liu Weixin, Lee Chengkuo
2022-Dec-28
artificial intelligence, metamaterial, mid-infrared spectroscopy, mixture analysis, waveguide sensors
