Novel molecular descriptors for prediction of H 2 S solubility in ionic liquids

Abstract Molecular descriptors are very important input parameters for establishing properties prediction models of materials, such as ionic liquids (ILs). In this work, as a new class of molecular descriptors, namely, electrostatic potential surface ( S EP ) is proposed to predict one of the important representative properties of ILs, i.e. the H 2 S solubility in ILs. 1318 experimental data points of 28 ILs, including 7 cations and 12 anions covering diverse temperatures and pressures, have been gathered from 15 references. According to the qualitative analyses, it is found that anions play a more important role than cations for the H 2 S solubility in ILs, besides the anions with stronger hydrogen-bond basicity have higher capacities to absorb H 2 S. Combining the S EP descriptors with the extreme learning machine (ELM) algorithm, two new quantitative models (ELM 1 based on the isolated ions and ELM 2 based on the ion pairs) for predicting H 2 S solubility are established. The average absolute relative deviation (AARD%) for the total set of ELM 1 and ELM 2 models are 5.87% and 3.84%, respectively. The results indicate that the S EP descriptors can extensively be employed to predict properties of ILs due to their rich information at electron level.