Making Thermodynamic Models of Mixtures Predictive by Machine Learning: Matrix Completion of Pair Interactions

TL;DR

This paper introduces a hybrid machine learning approach that combines matrix completion with classical thermodynamic models to predict mixture properties more accurately and comprehensively, including for multicomponent systems.

Contribution

It develops a novel hybrid model embedding matrix completion into UNIQUAC, enabling complete parameter prediction for all binary systems and improved activity coefficient predictions.

Findings

Outperforms existing physical models like modified UNIFAC in activity coefficient prediction.

Provides a complete set of UNIQUAC parameters for 1146 binary systems.

Enables activity coefficient predictions at arbitrary temperatures and compositions.

Abstract

Predictive models of thermodynamic properties of mixtures are paramount in chemical engineering and chemistry. Classical thermodynamic models are successful in generalizing over (continuous) conditions like temperature and concentration. On the other hand, matrix completion methods (MCMs) from machine learning successfully generalize over (discrete) binary systems; these MCMs can make predictions without any data for a given binary system by implicitly learning commonalities across systems. In the present work, we combine the strengths of both worlds in a hybrid approach. The underlying idea is to predict the pair-interaction energies, as they are used in basically all physical models of liquid mixtures, by an MCM. As an example, we embed an MCM into UNIQUAC, a widely-used physical model for the Gibbs excess energy. We train the resulting hybrid model in a Bayesian machine-learning framework on experimental data for activity coefficients in binary systems of 1146 components from the Dortmund Data Bank. We thereby obtain, for the first time, a complete set of UNIQUAC parameters for all binary systems of these components, which allows us to predict, in principle, activity coefficients at arbitrary temperature and composition for any combination of these components, not only for binary but also for multicomponent systems. The hybrid model even outperforms the best available physical model for predicting activity coefficients, the modified UNIFAC (Dortmund) model.