Predicting the formulation and stability of deep eutectic solvents (DES) has almost exclusively been empirically driven, limiting the development because it is time-consuming, labor-intensive, and expensive. Machine learning has recently been used as an auxiliary tool to predict physicochemical features of solvents, improving the required computations associated with creating the DES. The research will focus on enhancing and optimizing these machine-learning modules, enabling more efficient improvements of the computational algorithms without needing costly and energy-inefficient computational resources. Austin will be working with Dr. Jorge Barroso and Dr. Garcia.