Dielectric tensor of perovskite oxides at finite temperature using equivariant graph neural network potentials

TL;DR

This paper uses equivariant graph neural network potentials to efficiently simulate finite temperature properties of perovskite oxides, accurately capturing dielectric behavior and phase transitions with minimal training data.

Contribution

It introduces a machine learning force field based on equivariant graph neural networks for finite temperature simulations of perovskite oxides, demonstrating high accuracy with limited data.

Findings

Successfully modeled temperature-dependent dielectric tensor

Captured structural phase transitions in calcium titanate

Achieved efficient learning from small datasets

Abstract

Atomistic simulations of properties of materials at finite temperatures are computationally demanding and require models that are more efficient than the ab initio approaches. Machine learning (ML) and artificial intelligence (AI) address this issue by enabling accurate models with close to ab initio accuracy. Here, we demonstrate the utility of ML models in capturing properties of realistic materials by performing finite temperature molecular dynamics simulations of perovskite oxides using a force field based on equivariant graph neural networks. The models demonstrate efficient learning from a small training dataset of energies, forces, stresses, and tensors of Born effective charges. We qualitatively capture the temperature dependence of the dielectric tensor and structural phase transitions in calcium titanate.