# Zinc (Zn) Moment Tensor Potential Training Set: DFT Energies, Forces and Stresses (Mei et al. 2024), ColabFit Conversion

## Facts

- Provider: Haojie Mei, Luyao Cheng, Liang Chen, Feifei Wang, Jinfu Li, Lingti Kong (Shanghai Jiao Tong University); ColabFit conversion
- License: CC-BY-4.0 (https://github.com/meihaojie/Zn_system)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/Zn_MTP_CMS2023
- Access: public, readable without an account
- Category: Chemistry & Materials
- Source: https://doi.org/10.1016/j.commatsci.2023.112723
- Page: https://scigantic.com/archive/a6177bd3-c8aa-58da-8305-d830560e170e
- Keywords: Chemistry & Materials, DFT, interatomic potentials, Parquet, Hugging Face

## About

DFT training data for a machine-learning interatomic potential for zinc metal: atomic configurations spanning solid and liquid aggregation states, several crystal structures, point and extended defects and a range of cell sizes, chosen so that one potential describes a broad spectrum of local atomic environments in Zn. The authors fitted a Moment Tensor Potential (MTP) to it; the repository holds the fitting data and the Zn.mtp potential. ColabFit's card counts 13,299 configurations and 276,240 atoms, labelled with energy, atomic forces and stress; the repository is about 27 MB. Files are the ColabFit Exchange conversion: Parquet files under co/ hold one row per configuration (atomic numbers, positions, cell, computed properties and metadata), ds.parquet holds dataset-level information, and cs/ groups configurations into named sets where defined; read them with pyarrow, pandas, polars or Hugging Face datasets. The authors' GitHub repository states that each file is licensed under CC BY 4.0; cite Mei et al., Computational Materials Science 233, 112723 (2024).

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/Zn_MTP_CMS2023")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `co/co_0.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/a6177bd3-c8aa-58da-8305-d830560e170e
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/a6177bd3-c8aa-58da-8305-d830560e170e
- Over MCP: `get_schema_card` with id `a6177bd3-c8aa-58da-8305-d830560e170e` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Chemistry & Materials datasets](https://scigantic.com/topics/chemistry-and-materials)
- [DFT datasets](https://scigantic.com/topics/dft)
- [Interatomic potentials datasets](https://scigantic.com/topics/interatomic-potentials)
