Novel Data Science Driven Chemical and Biological Agent Sensors: Towards Better Discrimination in Complex Environments

Abstract

Chemical and biological agents remain a persistent threat to both Warfighters and civilian personnel in both combat and non-combat environments. While many useful detection technologies exist to provide early warning, many of them suffer from similar drawbacks. Most common are unacceptable false positive response rates and inability to discriminate target analytes in complex or obscurant-laden environments. A typical approach to this problem is to develop material solutions for more specific and sensitive sensors. While useful, these solutions are often too expensive, not practical, or non-deployable. Our approach fuses both material and data science to extend the power of multiplexed sensor arrays towards more accurate and faster detection and discrimination.This presentation will discuss our approach towards both vapor and liquid analytes using two different multiplex array systems. For vapor phase detection, sorptive and conductive graphene-based nanocomposite films are used for semi-selective affinity towards chemical agent simulants in binary mixtures with common obscurants. For the liquid phase, graphene arrays functionalized with antimicrobial peptides are encapsulated with a 3D printed self-supporting microfluidic cell, creating a multiplexed sensing platform for electrochemical detection towards the discrimination of bacterial species and strains. For both systems, response data are pre-processed using a novel algorithm called the Autoencoder Kalman Filter and the entire response dataset is used to train neural networks for analyte discrimination. Robust machine learning is enabled via response curve simulations, providing more accurate response training. Ultimately, both more accurate and faster responses are provided, leading to much lower false positive rates and quicker decision times. Using our approach, we first show that the chemical agent vapor simulant, dimethyl methylphosphonate (DMMP) can be identified from a mixture with JP8/kerosene, a common battle field contaminant. Next, we show that bacteria samples of the same species but different strains can be identified in complex media.