Can machine learning predict the phase behavior of surfactants?

20 December 2022, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

We explore the prediction of surfactant phase behavior using state-of-the-art machine- learning methods, using a data set for twenty-three non-ionic surfactants modified from Bell, Phil. Trans. R. Soc. A 2016, 374, 20150137. We recover Bell’s observation that most machine learning methods are capable to some degree of filling in missing data in partially-complete phase diagrams. However, strong data bias and a lack of chemical space information generally lead to poor results for de novo phase diagram prediction. Although some machine learning methods perform better than others, these observations are largely robust to the particular choice of algorithm. For the gap-filling challenge we additionally examine how to sample state points effectively in the context of typical experimental protocols, to make the most of machine-learning interpolation. Our results indicate what factors should be considered when preparing for machine- learning prediction of surfactant phase behavior in future studies.

Keywords

surfactant
machine learning

Supplementary materials

Title
Description
Actions
Title
Data to support the main article
Description
• Machine learning performance using unaltered phase state labels (corresponding to Section 3.2). • Gap filling predictions for the full set of surfactants (corresponding to Section 4.1). • Full phase diagram prediction for full set of surfactants (corresponding to Section 4.2). • Confusion plots for all studied surfactants (corresponding to Section 4.4.1). • Correlation between regression metrics and maximum similarity (corresponding to Section 4.4.2). • Further laboratory sampling examples (corresponding to Section 4.5).
Actions
Title
Data file containing information used to train the models in the main article
Description
We make available a machine readable format data set (machine-readable- data.txt) comprising the surfactants studied along with their phase behaviour at specific temperature and composition (weight fraction) points. For each surfactant the calculated tail length (Å), tail volume (Å3) and head group area (Å2 at 25°C) are presented.
Actions

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.