Scalable Dielectric Tensor Predictions for Inorganic Materials using Equivariant Graph Neural Networks

TL;DR

This paper introduces GoeCTP, a novel equivariant graph neural network framework that predicts dielectric tensors of inorganic materials more accurately and efficiently, enabling large-scale virtual screening for new dielectric materials.

Contribution

GoeCTP is a flexible, frame-averaging-based equivariant model that removes structural restrictions of previous models, improving dielectric tensor prediction accuracy.

Findings

GoeCTP outperforms state-of-the-art models in dielectric tensor prediction.

Successfully identified promising dielectric material candidates from large databases.

Demonstrated efficiency in large-scale virtual screening for inorganic dielectrics.

Abstract

Accurate prediction of dielectric tensors is essential for accelerating the discovery of next-generation inorganic dielectric materials. Existing machine learning approaches, such as equivariant graph neural networks, typically rely on specially-designed network architectures to enforce O(3) equivariance. However, to preserve equivariance, these specially-designed models restrict the update of equivariant features during message passing to linear transformations or gated equivariant nonlinearities. The inability to implicitly characterize more complex nonlinear structures may reduce the predictive accuracy of the model. In this study, we introduce a frame-averaging-based approach to achieve equivariant dielectric tensor prediction. We propose GoeCTP, an O(3)-equivariant framework that predicts dielectric tensors without imposing any structural restrictions on the backbone network. We benchmark its performance against several state-of-the-art models and further employ it for large-scale virtual screening of thermodynamically stable materials from the Materials Project database. GoeCTP successfully identifies various promising candidates, such as Zr(InBr$_3$)$_2$ (band gap $E_g = 2.41$ eV, dielectric constant $\overline{\varepsilon} = 194.72$) and SeI$_2$ (anisotropy ratio $\alpha_r = 96.763$), demonstrating its accuracy and efficiency in accelerating the discovery of advanced inorganic dielectric materials.