ML-IAPs_iron

This repo is associated with the publicaiton Efficiency, Accuracy, and Transferability of Machine Learning Potentials: Application to Dislocations and Cracks in Iron: The repo contains two parts:

1. Training scripts of multiple machine learning interatomic potentials, including

   • moment tensor potential (MTP)
   • gaussian approximation potential (GAP)
   • neural network potential (NNP)
   • atomic cluster expansion (PACE)

   The training procedures are described in the readme file under each folder. The training scripts are also explained in the readme file.

2. The corresponding potential files ready-to-use for LAMMPS.

3. Jupyter notebooks for reproducing the Figures in publication.