Predicting Ionic Liquids Properties with Machine-Learning

Since the last decade, there has been a dramatic increase in the number of ionic liquids (ILs) synthesized, tested and utilized in various applications (e.g. energy storage, CO₂ capture, catalysis, lubricant additives, etc.). The intense interest has been due to the various novel properties that can be found in ionic liquids, such as tunable ionic conductivity, negligible vapor pressure, liquid phase within a wide temperature range, non-flammability at ambient condition, etc. Among these properties, the melting point (T_m) of ionic liquids (IL) are very important in various applications. However, the T_m can change considerably depending on the molecular structures of the anions and cations. In this study, we will explore the use of various machine learning methods to predict the melting points of various ILs that consists of several different cation and anion classes. In addition to melting point prediction, some of the related structures-properties studies of ILs will be discussed.