Machine Learning-Based Design of Ionic Liquids at the Atomic Scale for Highly Efficient CO2 Capture

Abstract

Ionic liquids (ILs) are considered excellent substitutes for aqueous alkanolamine solutions in CO2 capture systems. However, the smart design of ILs, facing the small sparse data set and complex ionic structures, poses a huge challenge. To address this issue, a novel machine learning method based on a syntax-directed variational autoencoder (SDVAE), deep factorization machine (DeepFM), and gradient-based particle swarm optimization (GBPSO) was proposed in this work. The SDVAE converts the molecular structure and chemical space of the ILs, and then DeepFM predicts the solubility of each coordinate in the chemical space representing an IL. Finally, GBPSO identifies the coordinates that represent ILs with ideal properties. Our main optimization objective is a high solubility difference for CO2 between its absorption and desorption conditions in commercial plant capture systems, which represents the CO2 capture ability. The best IL generated has a predicted solubility difference that is 35.3% higher than that of the best one in the data set. A synthetic novel IL [EMIM][TOS] from the generated results was experimentally evaluated; it has a sufficiently high solubility difference to be a capture solvent with low energy consumption. Our model has proved to be a high-efficiency molecular design model that can be used for sparse small data sets.