Machine learning models for the density and heat capacity of ionic liquid-water binary mixtures

Abstract

Ionic liquids (ILs), because of the advantages of low volatility, good thermal stability, high gas solubility and easy recovery, can be regarded as the green substitute for traditional solvent. However, the high viscosity and synthesis cost limits their application, the hybrid solvent which combining ILs together with others especially water can solve this problem. Compared with the pure IL systems, the study of the ILs-H2O binary system is rare, and the experimental data of corresponding thermodynamic properties (such as density, heat capacity, etc.) are less. Moreover, it is also difficult to obtain all the data through experiments. Therefore, this work establishes a predicted model on ILs-water binary systems based on the group contribution method (GC). Three different machine learning algorithms (ANN, XGBoost, LightBGM) are applied to fit the density and heat capacity of ILs-water binary systems. And then the three models are compared by two index of MAE and R2. The results show that the ANN-GC model has the best prediction effect on the density and heat capacity of ionic liquid-water mixed system. Furthermore, the Shapley Additive Explanations (SHAP) method is harnessed to scrutinize the significance of each structure and parameter within the ANN-GC model in relation to prediction outcomes. The results reveal that system components (XIL) within the ILs-H2O binary system exert the most substantial influence on density, while for the heat capacity, the substituents on the cation exhibit the greatest impact. This study not only introduces a robust prediction model for the density and heat capacity properties of IL-H2O binary mixtures but also provides insight into the influence of mixture features on its density and heat capacity.