Prediction of activity coefficients at infinite dilution for organic solutes in ionic liquids by artificial neural network

Abstract

To our knowledge, this work illustrates for the first time the ability of artificial neural network (ANN) to predict activity coefficients at infinite dilution for organic solutes in ionic liquids (ILs). Activity coefficient at infinite dilution ( γ ∞) is a useful parameter which can be used for the selection of effective solvent in the separation processes. Using a multi-layer feed-forward network with Levenberg–Marquardt optimization algorithm, the resulting ANN model generated activity coefficient at infinite dilution data over a temperature range of 298 to 363 K. The unavailable input data concerning softness ( S) of organic compounds (solutes) and dipole moment ( μ) of ionic liquids were calculated using GAMESS suites of quantum chemistry programs. The resulting ANN model and its validation are based on the investigation of up to 24 structurally different organic compounds (alkanes, alkenes, alkynes, cycloalkanes, aromatics, and alcohols) in 16 common imidazolium-based ionic liquids, at different temperatures within the range of 298 to 363 K ( i.e. a total number of 914 γ Solute ∞ for each IL data point). The results show a satisfactory agreement between the predicted ANN and experimental data, where, the root mean square error (RMSE) and the determination coefficient ( R 2) of the designed neural network were found to be 0.103, 0.996 for training data and 0.128, 0.994 for testing data, respectively.