Gibbs–Helmholtz graph neural network: capturing the temperature dependency of activity coefficients at infinite dilution

Abstract

The accurate prediction of physicochemical properties of chemical compounds in mixtures (such as the activity coefficient at infinite dilution γ_ij^∞) is essential for developing novel and more sustainable chemical processes. In this work, we analyze the performance of previously-proposed GNN-based models for the prediction of γ_ij^∞, and compare them with several mechanistic models in a series of 9 isothermal studies. Moreover, we develop the Gibbs–Helmholtz Graph Neural Network (GH-GNN) model for predicting ln γ_ij^∞ of molecular systems at different temperatures. Our method combines the simplicity of a Gibbs–Helmholtz-derived expression with a series of graph neural networks that incorporate explicit molecular and intermolecular descriptors for capturing dispersion and hydrogen bonding effects. We have trained this model using experimentally determined ln γ_ij^∞ data of 40 219 binary-systems involving 1032 solutes and 866 solvents, overall showing superior performance compared to the popular UNIFAC-Dortmund model. We analyze the performance of GH-GNN for continuous and discrete inter/extrapolation and give indications for the model's applicability domain and expected accuracy. In general, GH-GNN is able to produce predictions with a mean absolute error below 0.3 for extrapolated binary-systems if at least 25 systems with the same combination of solute–solvent chemical classes are contained in the training set and a Tanimoto similarity indicator above 0.35 is also present. This model and its applicability domain recommendations have been made open-source at https://github.com/edgarsmdn/GH-GNN.