ChemVise: Maximizing Out-of-Distribution Chemical Detection with a Novel Application of Transfer Learning

Accurate chemical sensors are vital in medical, military, and home safety applications. Training machine learning models to be accurate on real world chemical sensor data requires performing many diverse, costly experiments in controlled laboratory settings to create a data set. In practice, even large data sets of laboratory experiments may be insufficient for generalization of a trained model to a real-world testing distribution. Rather than perform greater numbers of experiments requiring exhaustive mixtures of chemical analytes, this research proposes learning approximations of complex exposures from training sets of simple ones by using single-analyte exposure signals as building blocks of a multiple-analyte space. Furthermore, we pair these synthetic signals to targets in an information-dense representation space utilizing a large corpus of chemistry knowledge. Through utilization of a semantically meaningful analyte representation spaces along with synthetic targets we achieve rapid analyte classification in the presence of obscurants without corresponding obscured-analyte training data. Transfer learning for supervised learning with molecular representations makes assumptions about the input data. Instead, we borrow from the natural language and natural image processing literature for a novel approach to chemical sensor signal classification using molecular semantics for arbitrary chemical sensor hardware designs.