Predicting physical properties of alkanes with neural networks

The physical properties of many alkanes are unknown, which prevents engineers from optimally deploying them in base oil lubricants. In order to address this issue, we train neural networks that can work with fragmented data, enabling us to exploit the property-property correlations and increase the accuracy of our models. We encode molecular structure into five nonnegative integers, which enables us to exploit the structure-property correlations. We establish correlations between branching and the boiling point, heat capacity and vapor pressure as a function of temperature. Furthermore, we explore the connection between the symmetry and the melting point and identify erroneous data entries in the flash point of linear alkanes. Finally, we predict linear alkanes’ kinematic viscosity by exploiting the temperature and pressure dependence of shear viscosity and density.