Dielectric Tensor Prediction for Inorganic Materials Using Latent Information from Preferred Potential

TL;DR

This paper introduces a neural network model that accurately predicts dielectric tensors of inorganic materials, enabling better material design and discovery of high-performance dielectrics.

Contribution

It develops an equivariant neural network approach to predict dielectric tensors, capturing their directional properties, which was not addressed by previous scalar-focused models.

Findings

Model achieves high accuracy in dielectric tensor prediction.

Successfully identifies promising high-dielectric and anisotropic materials.

Demonstrates potential for accelerating dielectric material discovery.

Abstract

Dielectrics are crucial for technologies like flash memory, CPUs, photovoltaics, and capacitors, but public data on these materials are scarce, restricting research and development. Existing machine learning models have focused on predicting scalar polycrystalline dielectric constants, neglecting the directional nature of dielectric tensors essential for material design. This study leverages multi-rank equivariant structural embeddings from a universal neural network potential to enhance predictions of dielectric tensors. We develop an equivariant readout decoder to predict total, electronic, and ionic dielectric tensors while preserving O(3) equivariance, and benchmark its performance against state-of-the-art algorithms. Virtual screening of thermodynamically stable materials from Materials Project for two discovery tasks, high-dielectric and highly anisotropic materials, identifies promising candidates including Cs2Ti(WO4)3 (band gap $E_g=2.93 \mathrm{eV}$, dielectric constant $\varepsilon=180.90$) and CsZrCuSe3 (anisotropic ratio $\alpha_r = 121.89$). The results demonstrate our model's accuracy in predicting dielectric tensors and its potential for discovering novel dielectric materials.