Predicting second virial coefficients of organic and inorganic compounds using Gaussian Process Regression

TL;DR

This paper demonstrates that Gaussian process regression, using simple molecular features, can accurately predict the temperature-dependent second virial coefficients of diverse compounds, including unseen molecules, with high precision.

Contribution

The study introduces a robust, extensible Gaussian process regression model that predicts second virial coefficients from intuitive molecular features, applicable to both organic and inorganic compounds.

Findings

Achieved less than 1% relative error within the training temperature range.

Extended accurate predictions to temperatures outside the training data with 2.14% error.

Successfully predicted virial coefficients for unseen organic molecules with 2.66% error.

Abstract

We show that by using intuitive and accessible molecular features it is possible to predict the temperature-dependent second virial coefficient of organic and inorganic compounds using Gaussian process regression. In particular, we built a low dimensional representation of features based on intrinsic molecular properties, topology and physical properties relevant for the characterization of molecule-molecule interactions. The featurization was used to predict second virial coefficients in the interpolative regime with a relative error $\lesssim 1\% $ and to extrapolate the prediction to temperatures outside of the training range for each compound in the dataset with a relative error of 2.14\%. Additionally, the model's predictive abilities were extended to organic molecules unseen in the training process, yielding a prediction with a relative error of 2.66\%. Therefore, apart from being robust, the present Gaussian process regression model is extensible to a variety of organic and inorganic compounds.