Discovery of highly anisotropic dielectric crystals with equivariant graph neural networks

TL;DR

This paper introduces an equivariant graph neural network model that accurately predicts the full dielectric tensor of crystals, capturing anisotropic properties crucial for advanced material design.

Contribution

The study develops a novel equivariant graph neural network that predicts complete dielectric tensors, surpassing previous scalar-only prediction methods.

Findings

Achieves state-of-the-art accuracy in dielectric tensor prediction.

Discovers crystals with isotropic structures but anisotropic dielectric responses.

Broadens understanding of structure-property relationships in dielectric materials.

Abstract

Anisotropy in crystals plays a pivotal role in many technological applications. For example, anisotropic electronic and thermal transport are thought to be beneficial for thermoelectric applications, while anisotropic mechanical properties are of interest for emerging metamaterials, and anisotropic dielectric materials have been suggested as a novel platform for dark matter detection. Understanding and tailoring anisotropy in crystals is therefore essential for the design of next-generation functional materials. To date, however, most data-driven approaches have focused on the prediction of scalar crystal properties, such as the spherically averaged dielectric tensor or the bulk and shear elastic moduli. Here, we adopt the latest approaches in equivariant graph neural networks to develop a model that can predict the full dielectric tensor of crystals. Our model, trained on the Materials Project dataset of c.a. 6,700 dielectric tensors, achieves state-of-the-art accuracy in scalar dielectric prediction in addition to capturing the directional response. We showcase the performance of the model by discovering crystals with almost isotropic connectivity but highly anisotropic dielectric tensors, thereby broadening our knowledge of the structure-property relationships in dielectric crystals.