Midinfrared Spectroscopic Analysis of Aqueous Mixtures Using Artificial-Intelligence-Enhanced Metamaterial Waveguide Sensing Platform

Abstract

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.

Recent Progress in Silicon‐Based Photonic Integrated Circuits and Emerging Applications

“…Figure 6h‐i demonstrates an AI‐powered metamaterial waveguide sensing platform for analyzing aqueous mixtures in the MIR. [ 264 ] The waveguide geometry, as shown in Figure 6h‐ii, is carefully designed on the SOI platform, utilizing subwavelength grating metamaterials to enhance the sensitivity of the waveguide sensor in a compact footprint. A PDMS microfluidic channel is then bonded to the chip surface and defines the sensing area.…”

“…h-iii) Machine learning for CNN and MLP regressor. Adapted with permission [264]. Copyright 2022, American Chemical Society.…”

A shadow enabled non-invasive probe for multi-feature intelligent liquid surveillance system

“…Optoelectronic detection strategies that obtain information via the uniqueness of the absorption spectrum of liquids have shown great promise because of their fast response, high accuracy, and excellent stability. [20][21][22][23][24] However, many of the optoelectronic probes have limitations due to complex fabrication steps, the requirement of essential light emitters, and energy consumption. 25,26 Therefore, developing non-invasive liquid probes with self-powered capabilities under ambient light conditions puts forward urgent requirements.…”

A Natural Gradient Biological-Enabled Multimodal Triboelectric Nanogenerator for Driving Safety Monitoring

“…Therefore, the self-powered sensing devices that contribute to braking performance monitoring still play an important role in improving driving safety. Since TENG was reported in 2012, , TENG has been seen as a milestone discovery in the field of self-powered sensing. – Certainly, TENGs also have great advantages in an intelligent transportation system, including driving behavior and vehicle operation monitoring. – More and more TENGs were integrated into facilities such as steering wheels, tires, wind barrier, and speed bump to harvest the wasted mechanical energy. – On the one hand, they can harvest the mechanical energy of vehicle vibration, and on the other hand, they serve as self-powered sensors to monitor real-time traffic information. Nevertheless, almost no TENG-enabled vehicle braking performance monitoring was identified, but numerous traffic accidents are directly related to braking and hydroplaning during emergency braking.…”