Data-Driven Prediction of Dielectric Anisotropy in Nematic Liquid Crystals

TL;DR

This paper presents a machine learning approach to accurately predict dielectric anisotropy in nematic liquid crystals, outperforming traditional estimation methods by leveraging a curated large-scale dataset.

Contribution

It introduces a curated dataset and demonstrates that supervised machine learning models significantly improve dielectric anisotropy predictions over traditional methods.

Findings

Machine learning models achieve RMSE of 2.6 in predictions.

Traditional methods have higher RMSEs of 9.7 and 11.2.

Curated data and reporting standards are essential for progress.

Abstract

We curate a large-scale dataset of low frequency dielectric anisotropy values for low molecular weight liquid crystals. Using this dataset, we demonstrate that supervised machine-learning models can predict dielectric anisotropy with substantially improved accuracy (RMSE 2.6) compared to estimates obtained from the Maier-Meier relations using molecular properties from both the widely used semiempirical AM1 method (RMSE 9.7) and the modern r2scan-3c composite method (RMSE 11.2). Realising the potential of machine learning techniques for liquid crystalline materials requires carefully curated data to be accessible, and on this basis we propose a simple and standard template for reporting data.