Effective modeling methods to accurately predict the miscibility of CO2 in ionic liquids

Abstract

CO2 solubility in ionic liquids (ILs) over wide temperature and pressure ranges of (283.15–373.35 K) and (99.8–85800.0 kPa), respectively, has been predicted using three models; a group method of data handling correlation (model I), a radial basis function network (model II), and an empirical relation (model III). The Nelder–Mead simplex and Levenberg–Marquardt algorithms were used to find the constants of the suggested functionality relations for models I and III, respectively. Model I with R2, RMSE and AARD% of 0.9650, 4.2727 and 8.46, respectively; model II with R2, RMSE and AARD% of 0.9942, 1.7172, and 4.23, respectively and model III with R2, RMSE and AARD% of 0.9886, 2.4248 and 4.25, respectively, were highly accurate in the prediction of experimental values. All the models proposed are vigorous and possess satisfactory error trends based on a comprehensive statistical assessment. To confirm the validity of the database, the dataset was subjected to a statistical outlier diagnostic test.