Tailored group contribution methods designed using machine learning to predict enthalpies in carboxylic acids and anhydrides

Abstract

This research details a methodology to obtain the enthalpy of formation in gas and crystalline phase, as well as the enthalpy of combustion and sublimation for 4methylphthalic acid (4MPAc) and 4-methylphthalic anhydride (4MPAn), using Machine Learning (ML), the prediction of these properties was achieved by Ridge Regression. The predicted values of 4MPAc were compared to the experimental data obtained from differential scanning calorimetry (DSC), thermogravimetric analysis (TGA) and combustion calorimetry. The aforementioned properties were used to determine the equilibrium constant of the interconversion reaction between 4MPAc and its corresponding anhydride.