Machine-learned interatomic potentials for elastic property calculation

In this repository, you can find the data required to reproduce the results obtained in our work "On-the-Fly Machine Learning of Interatomic Potentials for Elastic Property Modeling in Al-Mg-Zr Solid Solutions".

Datasets

• training.extxyz: Training data generated by on-the-fly learning method
• validation.extxyz: Unseen structures during training.

Models

Contains the developed ML interatomic potentials (VASP-ML and MACE-ML) used for elastic property calculation.

Elastic Properties

Additional python scripts:

• stretcher.py: generate stretched POSCARs
• moduli.py: calculation of B and G modulus
• modulisecond.py: calculation of E and $\nu$