JARVIS ALIGNN-FF Training Set: OptB88vdW Energies, Forces and Stresses for 89 Elements, ColabFit Conversion
- Provider
- Kamal Choudhary, Brian DeCost and coauthors (NIST JARVIS); ColabFit conversion
- License
- CC-BY-4.0 (source)
- Size
- 4 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/colabfit/JARVIS_ALIGNN_FF)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Chemistry & Materials
- Source
- https://doi.org/10.1039/D2DD00096B
About this dataset
The training data behind ALIGNN-FF, NIST's atomistic line graph neural network force field for the whole periodic table. It is drawn from JARVIS-DFT relaxation runs (VASP, OptB88vdW functional), keeping the first, last, middle, highest-energy and lowest-energy snapshots of each calculation and filtering for unique, defect-free structures. ColabFit counts 304,146 configurations (about 3.2 million atoms) over 89 elements, labelled with energies, atomic forces and stress. It is a compact universal-potential training set for comparison with MPtrj, MatPES or OMat24. 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. The ALIGNN-FF data file is published by the authors on figshare under CC-BY-4.0; cite Choudhary et al., Digital Discovery 2, 346 (2023).
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("colabfit/JARVIS_ALIGNN_FF")
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, JARVIS ALIGNN-FF Training Set: OptB88vdW Energies, Forces and Stresses for 89 Elements, 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
- Flat Bands in Graphene Superlattices with Transition-Metal Adatoms: DFT Structures (Skurativska et al. 2021, Materials Cloud), ColabFit Conversion
- Open Catalyst 2025 (OC25) Train
- MetaboLights: EMBL-EBI's open repository for metabolomics studies
- NASA Physical Sciences Informatics (PSI)
- ANI-2x at wB97X/def2-TZVPP: 8.5 Million Organic Molecule DFT Energies, ColabFit Conversion
- Transition1x Training Split: Reaction Pathway DFT Energies and Forces, ColabFit Conversion
- Liquid Water and Ice Ih/Ic at Hybrid DFT (revPBE0-D3): Neural Network Training Set for Ab Initio Thermodynamics (Cheng et al. 2019, Materials Cloud), ColabFit Conversion
- UNEP-v1: 16-Element Metal and Alloy DFT Training Set for a Unified NeuroEvolution Potential, ColabFit Conversion