A temperature-dependent quantum mechanical/neural net model for vapor pressure

We present a temperature-dependent model for vapor pressure based on a feed -forward neural net and descriptors calculated using AM1 semiempirical MO-t heory. This model is based on a set of 7681 measurements at various tempera tures performed on 2349 molecules. We employ a 10-fold cross-validation sch eme that allows us to estimate errors for individual predictions. For the t raining set we find a standard deviation of the error s = 0.322 and a corre lation coefficient (R-2) of 0.976. The corresponding values for the validat ion set are s = 0.326 and R-2 = 0.976. We thoroughly investigate the temper ature-dependence of our predictions to ensure that our model behaves in a p hysically reasonable manner. As a further test of temperature-dependence, w e also examine the accuracy of our vapor pressure model in predicting the r elated physical properties, the boiling point, and the enthalpy of vaporiza tion.