Prediction of Activity Coefficients by Similarity-Based Imputation using Quantum-Chemical Descriptors

TL;DR

This paper presents a similarity-based imputation method using quantum-chemical descriptors to predict thermodynamic properties of binary mixtures, outperforming traditional physical models especially with limited data.

Contribution

Introduces a novel similarity-based method (SBM) leveraging quantum-chemical descriptors for predicting mixture properties, applicable with sparse data.

Findings

SBM outperforms modified UNIFAC and COSMO-SAC-dsp in predicting activity coefficients.

The method remains effective with limited available data.

SBM can be applied to various mixture properties.

Abstract

In this work, we introduce a novel approach for predicting thermodynamic properties of binary mixtures, which we call the similarity-based method (SBM). The method is based on quantifying the pairwise similarity of components, which we achieve by comparing quantum-chemical descriptors of the components, namely $\sigma$-profiles. The basic idea behind the approach is that mixtures with similar pairs of components will have similar thermodynamic properties. The SBM is trained on a matrix that contains some data for a given property for different binary mixtures; the missing entries are then predicted by the SBM. As an example, we consider the prediction of isothermal activity coefficients at infinite dilution ($\gamma^\infty_{ij}$) and show that the SBM outperforms the well-established physical methods modified UNIFAC (Dortmund) and COSMO-SAC-dsp. In this case, the matrix is only sparsely occupied, and it is shown that the SBM works also if only a limited number of data for similar mixtures is available. The SBM idea can be transferred to any mixture property and is a powerful tool for generating essential data for many applications.