# Copper FHI-aims DFT Training Set for the Atomic Cluster Expansion (PACE), ColabFit Conversion

## Facts

- Provider: Yury Lysogorskiy, Ralf Drautz and coauthors; ColabFit conversion
- License: CC-BY-4.0 (https://zenodo.org/records/4734035)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/Cu_FHI-aims_NPJCM_2021
- Access: public, readable without an account
- DOI: https://doi.org/10.60732/c712b78a
- Category: Chemistry & Materials
- Source: https://doi.org/10.1038/s41524-021-00559-9
- Page: https://scigantic.com/archive/05195656-285d-574b-98d8-3f91548c6b50
- Keywords: Chemistry & Materials, DFT, Parquet, Hugging Face

## About

The copper training data from Lysogorskiy, Drautz and coworkers' performant implementation of the atomic cluster expansion (PACE) (npj Computational Materials 2021). About 46,000 copper configurations, computed with the FHI-aims code, cover small clusters and bulk structures, surfaces, interfaces, point defects and randomly modified variants with displaced or missing atoms, labeled with energies and atomic forces. The ColabFit card counts 46,327 configurations and about 307,000 atoms; the repository is about 81 MB (measured 2026-11-19). This is the ColabFit Exchange conversion: configurations are Parquet files under co/ (structure, positions, cell, computed properties and metadata per row) with dataset-level information in ds.parquet; read them with pyarrow, pandas, polars or Hugging Face datasets, following the ColabFit configuration schema at materials.colabfit.org/docs. The original Zenodo record is CC-BY-4.0; cite Lysogorskiy et al., npj Computational Materials 2021.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/Cu_FHI-aims_NPJCM_2021")
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/05195656-285d-574b-98d8-3f91548c6b50
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/05195656-285d-574b-98d8-3f91548c6b50
- Over MCP: `get_schema_card` with id `05195656-285d-574b-98d8-3f91548c6b50` 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)
