Representation/Prediction of Solubilities of Pure Compounds in Water Using Artificial Neural Network−Group Contribution Method

Abstract

In this work, the artificial neural network−group contribution (ANN−GC) method has been applied to represent/predict the solubilities of pure chemical compounds in water over the (293 to 298) K temperature range at atmospheric pressure. A set of 3585 pure compounds from various chemical families has been investigated to propose a comprehensive and predictive method. The obtained results show a squared correlation coefficient (R2) value of 0.96 and a root-mean-square error of 0.4 for the calculated/predicted properties with respect to existing experimental values, demonstrating the reliability of the proposed model.