Clapeyron Neural Networks for Single-Species Vapor-Liquid Equilibria
This work addresses data scarcity and thermodynamic consistency in chemical engineering property prediction, though it is incremental as it adapts an existing thermodynamics-informed approach to a different equation.
The paper tackled the problem of predicting pure component vapor-liquid equilibrium properties with scarce data and thermodynamic inconsistency by incorporating the Clapeyron equation into graph neural networks, resulting in improved accuracy, especially for data-scarce properties.
Machine learning (ML) approaches have shown promising results for predicting molecular properties relevant for chemical process design. However, they are often limited by scarce experimental property data and lack thermodynamic consistency. As such, thermodynamics-informed ML, i.e., incorporating thermodynamic relations into the loss function as regularization term for training, has been proposed. We herein transfer the concept of thermodynamics-informed graph neural networks (GNNs) from the Gibbs-Duhem to the Clapeyron equation, predicting several pure component properties in a multi-task manner, namely: vapor pressure, liquid molar volume, vapor molar volume and enthalpy of vaporization. We find improved prediction accuracy of the Clapeyron-GNN compared to the single-task learning setting, and improved approximation of the Clapeyron equation compared to the purely data-driven multi-task learning setting. In fact, we observe the largest improvement in prediction accuracy for the properties with the lowest availability of data, making our model promising for practical application in data scarce scenarios of chemical engineering practice.