# H2 on Pt(111): Active-Learned Reactive Bayesian Force Field Training Data, ColabFit Conversion

## Facts

- Provider: Jonathan Vandermause, Yu Xie, Jin Soo Lim, Cameron J. Owen, Boris Kozinsky (Harvard); ColabFit conversion
- License: CC-BY-4.0 (https://archive.materialscloud.org/api/records/at71v-gdh04)
- Size: 6 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/HPt_NC_2022
- Access: public, readable without an account
- DOI: https://doi.org/10.24435/materialscloud:r0-84
- Category: Chemistry & Materials
- Source: https://doi.org/10.1038/s41467-022-32294-0
- Page: https://scigantic.com/archive/878ad7e9-1b1e-5d3f-bbe1-b57ca51144fb
- Keywords: Chemistry & Materials, DFT, interatomic potentials, Parquet, Hugging Face

## About

Training frames gathered on the fly by the FLARE Bayesian active learning framework while simulating heterogeneous hydrogen turnover (H2 adsorption, dissociation and recombination) on the Pt(111) catalyst surface. A sparse Gaussian process decided at each MD step whether new DFT (VASP) calculations were needed; the resulting model was mapped to a fast polynomial form and ran two-phase gas/surface simulations at twice the speed of ReaxFF. ColabFit counts 90,731 configurations of H and Pt (about 5.7 million atoms) with energies, atomic forces and stress. 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 Vandermause et al., Nature Communications 13, 5183 (2022).

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/HPt_NC_2022")
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/878ad7e9-1b1e-5d3f-bbe1-b57ca51144fb
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/878ad7e9-1b1e-5d3f-bbe1-b57ca51144fb
- Over MCP: `get_schema_card` with id `878ad7e9-1b1e-5d3f-bbe1-b57ca51144fb` 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)
