A GEP based model for prediction of densities of ionic liquids

One of the most important properties of ionic liquids (ILs) is their densities. Accurate knowledge of this property is required in engineering and scientific purposes including equipment design, liquid metering calculations, and other applications. As a result, it is important to develop accurate and effective models for prediction of this property. The present work aims to develop a model based on Gene Expression Programming (GEP) technique for prediction of experimental density values of 146 different ionic liquids at different temperatures. A databank containing 602 data gathered from the literature was utilized to develop the model. The input parameters of the model are temperature, molecular weight of IL, normal boiling point temperature of IL, critical pressure of IL, critical volume of IL, and acentric factor of IL. The outcomes of this work indicate that the developed model is capable of estimating target density data with an acceptable accuracy. The effectiveness and accuracy of the model were checked by utilizing different statistical and graphical techniques. Moreover, results of the proposed model are compared with predictions of literature correlations and it is shown that the GEP model is effectively superior to other correlations and exhibits higher accuracy and reliability.