Prediction of Crystal Lattice Energy Using Enthalpy of Sublimation: A Group Contribution-Based Model

Abstract

In this study, a new group contribution-based model is presented to predict the enthalpy of sublimation of pure compounds. This model can also be used to predict the lattice crystal energy of such compounds. The model is a neural network using the number of occurrences of 172 chemical groups on the chemical structures of pure compounds to predict the enthalpy of sublimation. This comprehensive model is generated using a large data set of pure compounds (1384 pure compounds). The squared correlation coefficient, average percent error, and root-mean-square error of the model over all investigated compounds are 0.9854, 3.54%, and 4.21, respectively.