Graph Neural Networks embedded into Margules model for vapor-liquid equilibria prediction
This provides an alternative for thermodynamic modeling in chemical engineering, though it is incremental as it establishes a baseline rather than a breakthrough.
The paper tackled vapor-liquid equilibrium prediction by embedding Graph Neural Networks into the extended Margules model, finding that it achieved lower overall accuracy than UNIFAC-Dortmund but higher accuracy for some binary mixtures.
Predictive thermodynamic models are crucial for the early stages of product and process design. In this paper the performance of Graph Neural Networks (GNNs) embedded into a relatively simple excess Gibbs energy model, the extended Margules model, for predicting vapor-liquid equilibrium is analyzed. By comparing its performance against the established UNIFAC-Dortmund model it has been shown that GNNs embedded in Margules achieves an overall lower accuracy. However, higher accuracy is observed in the case of various types of binary mixtures. Moreover, since group contribution methods, like UNIFAC, are limited due to feasibility of molecular fragmentation or availability of parameters, the GNN in Margules model offers an alternative for VLE estimation. The findings establish a baseline for the predictive accuracy that simple excess Gibbs energy models combined with GNNs trained solely on infinite dilution data can achieve.