DeepSpektra - Enhanced Explosives and Illicit Drugs Detection by Targeted Interrogation of Surfaces

The Synthetik team is uniquely placed to conduct this Phase II SBIR effort where we plan to extend and optimize our DeepSpektra high-resolution hyperspectral and deep learning-based non-contact detection technology to provide enhanced, targeted sampling for explosive and illegal drugs trace detection that was successfully demonstrated in Phase I.Synthetik's DeepSpektra technology directly addresses a significant pain point for TSA, namely optimal sample collection for effective trace detection at passenger security checkpoints. The technology will greatly enhance non-contact explosives and illicit drugs detection technologies by directing these modalities toward surfaces that have residues of interest for further interrogation.DeepSpektra technology is not intended to replace current in-service trace detectors, but rather to augment their capabilities such that they can be more effective in the field.More effective and accurate trace detection and classification is dependent on the collection of more feature rich data.This will be achieved during Phase II by: 1) determining the wavelengths that provide optimal data for detection, 2) improving machine learning (ML) model architecture, pre-processing, and training, and 3) enhancing hardware design, including increased illumination.During Phase II, we will also seek to quickly realize the immediate commercial potential in this technology by rapidly fabricating and distributing the DeepSpektra system to both federal and commercial markets in the US and globally.