Modified UNIFAC 2.0-A Group-Contribution Method Completed with Machine Learning
Nicolas Hayer, Hans Hasse, Fabian Jirasek
Abstract
Predicting thermodynamic properties of mixtures is a cornerstone of chemical engineering, yet conventional group-contribution (GC) methods like modified UNIFAC (Dortmund) remain limited by incomplete parameter tables. To address this, we present modified UNIFAC 2.0, a hybrid model that integrates a matrix completion method from machine learning into the GC framework, allowing for the simultaneous training of all pair-interaction parameters, including those that cannot be fitted directly due to missing data. By training on more than 500,000 experimental data points for activity coefficients and excess enthalpies from the Dortmund Data Bank, modified UNIFAC 2.0 achieves improved accuracy, while significantly expanding the predictive scope compared to the latest published modified UNIFAC (Dortmund) version, which covers only 39% of all possible interactions. Its flexible design allows updates with new experimental data or customizations for specific applications. The new model can easily be implemented in established simulation software with complete parameter tables readily available.