Download file (1.38 MB)
Download as zip (1.28 MB)

Collection

Citation

Description:

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.

Rights:

• Creative Commons BY Attribution 4.0 International
  

Keyword: Graph neural network, machine learning, dielectrics, perovskite oxides, phase transitions

Date published:

Publisher: Taylor & Francis

Journal:

• Science and Technology of Advanced Material (ISSN: 14686996) vol. 5 2497254

Funding:

Manuscript type: Author's version (Accepted manuscript)

MDR DOI: https://doi.org/10.48505/nims.5451

First published URL: https://doi.org/10.1080/27660400.2025.2497254

Related item:

Other identifier(s):

Contact agent:

Updated at: 2025-04-24 11:19:42 +0900

Published on MDR: 2025-04-24 12:26:37 +0900