Loading...
Loading...
Contributors:
Dataset URI:
10.5281/zenodo.22756145This repository contains the data and models supporting the publication “Multi-fidelity Machine Learning Interatomic Potentials for Charged Point Defects” (DOI: 10.1103/tzwd-cl3y). The repository is organised as follows: 1_FM_benchmark/ contains the DFT-PBE reference calculations used to benchmark foundation machine learning interatomic potentials for the VSb(1) defect across different charge states. 2_global_embedding/ contains the training and test datasets, trained MACE model and training script for the charge-embedded MACE model, together with the HSE06 DFT reference calculations for VSe(1) across five charge states. 3_MF/ contains the datasets, trained models and training scripts for the multi-fidelity MACE models, together with the corresponding DFT training data and calculation settings. Further methodological details and computational settings are provided in the main article and Supplemental Material.
Keyword(s):
charged defects; MACE; machine learning interatomic potentials; multi-fidelity learning; point defects.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)