Amorphous Alumina (a-AlOx) DFT Training Data for Machine Learning Potentials, ColabFit Conversion
- Provider
- Wenwen Li, Yasunobu Ando, Satoshi Watanabe (University of Tokyo); ColabFit conversion
- License
- CC-BY-4.0 (source)
- Size
- 6 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/colabfit/a-AlOx_JCP_2020)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.24435/materialscloud:y1-zd
- Category
- Chemistry & Materials
- Source
- https://doi.org/10.1063/5.0026289
About this dataset
Reference data for a neural network interatomic potential of amorphous aluminium oxide across density and Al:O composition, used to map how structure, mechanical and electronic properties of a-AlOx (a gate dielectric and protective coating) vary in a high-dimensional composition space. Supercells of 24 to 132 atoms were computed with VASP, PAW and PBE at a 550 eV cutoff. The set has two configuration sets: the actual training data and additional reference data. ColabFit counts 123,560 configurations of Al and O (about 4.5 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 Li, Ando and Watanabe, J. Chem. Phys. 153, 164119 (2020).
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("colabfit/a-AlOx_JCP_2020")
print(ds)Data structure
File types in sampled files: Parquet
Files
Example file: co/co_0.parquet
Analyze this dataset without downloading it
On Scigantic, Amorphous Alumina (a-AlOx) DFT Training Data for Machine Learning Potentials, ColabFit Conversion opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Chemistry & Materials datasets
- MAD-1.5 Massive Atomic Diversity r2SCAN Training Split (102 Elements), ColabFit Conversion
- Pt-Ni Nanoalloy DFT Training Set for a Neural Network Potential (Han et al. 2022), ColabFit Conversion
- JARVIS QE-TB Three-Body Tight-Binding DFT Dataset (PBEsol), ColabFit Conversion
- COMP6v2 Benchmark Suite (wB97X/6-31G*), ColabFit Conversion
- WS22 Acrolein (C3H4O): Wigner-Sampled Conformations with PBE0 Energies and Forces (Pinheiro Jr et al. 2023, Zenodo), ColabFit Conversion
- Alpha-Brass (Cu-Zn) Nanoparticles, Slabs and Bulk: Neural Network Potential Training Data (Weinreich et al. 2021, Materials Cloud), ColabFit Conversion
- 3BPA Flexible Drug-Like Molecule: Mixed-Temperature MD Training Set for ACE Force Fields (Kovacs et al. 2021), ColabFit Conversion
- COD Synthetic Powder X-Ray Diffraction (XRD) Patterns: 436,196 Simulated Diffractograms from the Crystallography Open Database