Estimation of the Heat Capacity of Ionic Liquids: A Quantitative Structure–Property Relationship Approach

In this paper, a quantitative structure–property relationship model is developed using genetic function approximation (GFA) to predict the liquid heat capacity at constant pressure (<i>C</i>_pL) for ionic liquids at atmospheric pressure. The NIST Standard Reference Database was used to prepare a data set of <i>C</i>_pL data consisting of 3726 experimental data points comprised of 82 ionic liquids. The data set was split into two subsets, with 80% of the data used as a training set and 20% as a test set. Instead of using nonlinear modeling like artificial neural networks and a support vector machine, the GFA method was used to determine a model by a binary combination of descriptors rather than using single ones. Statistical analysis of the model shows that it has an overall AARD % of 1.70%, a coefficient of determination (<i>R</i>²) of 0.993, and a root mean square of error of 15.11 J mol^–1 K<sup>–1