Prediction of Vapor Pressures of Hydrocarbons and Halohydrocarbons from Molecular Structure with a Computational Neural Network Model
Eric S. Goll, Peter C. Jurs · Journal of Chemical Information and Computer Sciences · 1999
Computational methods are used to link the molecular structures of 352 hydrocarbons and halohydrocarbons to their vapor pressures at 25 °C. The data are from the Design Institute for Physical Property Data (DIPPR) database. Vapor pressures of the compounds range from −1.016 log(VP) to +6.65 log(VP) with VP in pascals. Multiple linear regression was used to develop linear statistical models. A 7:3:1 computational neural network (CNN) was used to create a nonlinear model best suited for prediction of vapor pressure. The root-mean-square errors associated with the training, cross-validation, and prediction set compounds used for this CNN model were 0.163, 0.163, and 0.209 log units.