Enhanced thermophysical property prediction with uncertainty quantification using group contribution-Gaussian process regression

Abstract

Group contribution (GC) models are powerful, simple, and popular methods for property prediction. However, the most accessible and computationally efficient GC methods, like the Joback and Reid (JR) GC models, often exhibit severe systematic bias. Furthermore, most GC methods do not have uncertainty estimates associated with their predictions. The present work develops a hybrid method for property prediction that integrates GC models with Gaussian process (GP) regression. Predictions from the JR GC method, along with the molecular weight, are used as input features to the GP models, which learn and correct the systematic biases in the GC predictions, resulting in highly accurate property predictions with reliable uncertainty estimates. The method was applied to six properties: normal boiling temperature (T_b), enthalpy of vaporization at T_b (ΔH_vap), normal melting temperature (T_m), critical pressure (P_c), critical molar volume (V_c), and critical temperature (T_c). The CRC Handbook of Chemistry and Physics was used as the primary source of experimental data. The final collected experimental data ranged from 485 molecules for ΔH_vap to 5640 for T_m. The proposed GCGP method significantly improved property prediction accuracy compared to the GC-only method. The coefficient of determination (R²) values of the testing set predictions are ≥0.85 for five out of six and ≥0.90 for four out of six properties modeled, and compare favorably with other methods in the literature. T_m was used to demonstrate one way the GCGP method can be tuned for even better predictive accuracy. The GCGP method provides reliable uncertainty estimates and computational efficiency for making new predictions. The GCGP method proved robust to variations in GP model architecture and kernel choice.