# Amorphous Lithium-Silicon (LixSi) Anode Structures for aenet Potentials, ColabFit Conversion

## Facts

- Provider: Michael S. Chen, Tobias Morawietz, Thomas E. Markland, Nongnuch Artrith; ColabFit conversion
- License: CC-BY-4.0 (https://archive.materialscloud.org/api/records/67p3q-dch39)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/AENET_amorphous_LiSi_JCP2021
- Access: public, readable without an account
- DOI: https://doi.org/10.24435/materialscloud:dx-ct
- Category: Chemistry & Materials
- Source: https://doi.org/10.1063/5.0063880
- Page: https://scigantic.com/archive/ad1b449b-a511-5a7e-a5ff-b40c28a377f3
- Keywords: Chemistry & Materials, Parquet, Hugging Face

## About

Training data for artificial neural network potentials of amorphous lithium silicide, the alloy formed in silicon battery anodes. Structures with compositions LixSi (0 <= x <= 4.75), covering bulk, surfaces and clusters of up to 608 atoms, were generated by an evolutionary algorithm with iterative refinement and relaxed until residual forces fell below 20 meV/A. Energies and forces are PBE with PAW potentials in VASP (520 eV cutoff, at least 1000 k-points per atom). The set was released with the AENET-LAMMPS and AENET-TINKER interfaces paper. ColabFit counts 44,651 configurations of Li and Si (about 5.7 million atoms) with energies and atomic forces. This is the ColabFit Exchange conversion: configurations sit in Parquet files under co/ (positions, cell, species, 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 schema at materials.colabfit.org/docs. Published on Materials Cloud under CC-BY-4.0; cite Chen et al., J. Chem. Phys. 155, 074801 (2021) and Artrith et al., J. Chem. Phys. 148, 241711 (2018).

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/AENET_amorphous_LiSi_JCP2021")
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/ad1b449b-a511-5a7e-a5ff-b40c28a377f3
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/ad1b449b-a511-5a7e-a5ff-b40c28a377f3
- Over MCP: `get_schema_card` with id `ad1b449b-a511-5a7e-a5ff-b40c28a377f3` 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)
