Dataset

OMat24_train_rattled_1000

Download Original Data Files 19.2 GB

Download Dataset Parquet Files 11.7 GB

Species content of dataset

Name :

OMat24_train_rattled_1000

Extended ID :

OMat24_train_rattled_1000__Barroso-Luque-Shuaibi-Fu-Wood-Dzamba-Gao-Rizvi-Zitnick-Ulissi__DS_opcbnu5xs3pe_0

ColabFit ID :

DS_opcbnu5xs3pe_0

Files :

colabfitspec.json

Description :

The rattled-1000 training split of OMat24 (Open Materials 2024). OMat24 is a large-scale open dataset of density functional theory (DFT) calculations. The dataset is available in sub-datasets and subsampled sub-datasets based on the structure generation strategy used. There are two main splits in OMat24: train and validation, each divided into the aforementioned subsampling and sub-datasets.

Authors :

Luis Barroso-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, C. Lawrence Zitnick, Zachary W. Ulissi

DOI :

10.60732/6994f9f0 https://commons.datacite.org/doi.org/10.60732/6994f9f0 https://doi.datacite.org/dois/10.60732%2F6994f9f0 https://doi.org/10.60732/6994f9f0 Cite as: Barroso-Luque, L., Shuaibi, M., Fu, X., Wood, B. M., Dzamba, M., Gao, M., Rizvi, A., Zitnick, C. L., and Ulissi, Z. W. "OMat24 train rattled 1000." ColabFit, 2025. https://doi.org/10.60732/6994f9f0.
For other citation formats, see the DataCite Fabrica page for this dataset.

Num. Configurations :

11,388,475

Num. Atoms :

161,511,768

Downloads :

Calculated Property Types :

atomic_forces cauchy_stress energy

Elements :

Ac (1.4%) Ag (1.78%) Al (1.74%) Ar (0.0%) As (1.35%) Au (1.82%) B (0.61%) Ba (0.99%) Be (1.05%) Bi (0.96%) Br (1.74%) C (0.75%) Ca (1.73%) Cd (1.83%) Ce (0.63%) Cl (1.78%) Co (1.32%) Cr (0.93%) Cs (0.91%) Cu (1.64%) Dy (1.38%) Er (1.23%) Eu (0.11%) F (1.36%) Fe (1.05%) Ga (1.39%) Gd (0.09%) Ge (1.13%) H (1.32%) He (0.0%) Hf (0.76%) Hg (1.86%) Ho (1.21%) I (1.23%) In (1.81%) Ir (1.31%) K (1.66%) Kr (0.0%) La (2.22%) Li (2.23%) Lu (0.27%) Mg (2.1%) Mn (1.23%) Mo (0.9%) N (1.31%) Na (1.4%) Nb (0.65%) Nd (1.51%) Ne (0.0%) Ni (1.6%) Np (0.24%) O (3.68%) Os (1.01%) P (1.46%) Pa (0.52%) Pb (1.45%) Pd (1.7%) Pm (1.74%) Pr (1.53%) Pt (1.7%) Pu (0.56%) Rb (1.11%) Re (1.0%) Rh (1.63%) Ru (1.21%) S (1.82%) Sb (1.41%) Sc (1.45%) Se (2.12%) Si (1.24%) Sm (1.04%) Sn (1.07%) Sr (0.31%) Ta (0.39%) Tb (0.29%) Tc (0.79%) Te (1.71%) Th (0.39%) Ti (0.31%) Tl (1.22%) Tm (0.71%) U (0.12%) V (0.33%) W (0.88%) Xe (0.0%) Y (0.85%) Yb (0.0%) Zn (1.21%) Zr (0.48%)

Methods :

DFT-PBE+U

Software :

VASP

Publication Link :

https://doi.org/10.48550/arXiv.2410.12771

Data Source Link :

https://fair-chem.github.io/inorganic_materials/datasets/omat24.html

Other Links :

https://doi.org/10.1002/adma.202210788 https://huggingface.co/datasets/fairchem/OMAT24

Configuration Sets by Name :

Configuration Sets by ID :

Name: OMat24_train_rattled_1000 Extended ID: OMat24_train_rattled_1000__Barroso-Luque-Shuaibi-Fu-Wood-Dzamba-Gao-Rizvi-Zitnick-Ulissi__DS_opcbnu5xs3pe_0 Description: The rattled-1000 training split of OMat24 (Open Materials 2024). OMat24 is a large-scale open dataset of density functional theory (DFT) calculations. The dataset is available in sub-datasets and subsampled sub-datasets based on the structure generation strategy used. There are two main splits in OMat24: train and validation, each divided into the aforementioned subsampling and sub-datasets. Authors: Luis Barroso-Luque Muhammed Shuaibi Xiang Fu Brandon M. Wood Misko Dzamba Meng Gao Ammar Rizvi C. Lawrence Zitnick Zachary W. Ulissi DOI: 10.60732/6994f9f0 Calculated Property Types: atomic_forces cauchy_stress energy Elements: Ac (1.4%) Ag (1.78%) Al (1.74%) Ar (0.0%) As (1.35%) Au (1.82%) B (0.61%) Ba (0.99%) Be (1.05%) Bi (0.96%) Br (1.74%) C (0.75%) Ca (1.73%) Cd (1.83%) Ce (0.63%) Cl (1.78%) Co (1.32%) Cr (0.93%) Cs (0.91%) Cu (1.64%) Dy (1.38%) Er (1.23%) Eu (0.11%) F (1.36%) Fe (1.05%) Ga (1.39%) Gd (0.09%) Ge (1.13%) H (1.32%) He (0.0%) Hf (0.76%) Hg (1.86%) Ho (1.21%) I (1.23%) In (1.81%) Ir (1.31%) K (1.66%) Kr (0.0%) La (2.22%) Li (2.23%) Lu (0.27%) Mg (2.1%) Mn (1.23%) Mo (0.9%) N (1.31%) Na (1.4%) Nb (0.65%) Nd (1.51%) Ne (0.0%) Ni (1.6%) Np (0.24%) O (3.68%) Os (1.01%) P (1.46%) Pa (0.52%) Pb (1.45%) Pd (1.7%) Pm (1.74%) Pr (1.53%) Pt (1.7%) Pu (0.56%) Rb (1.11%) Re (1.0%) Rh (1.63%) Ru (1.21%) S (1.82%) Sb (1.41%) Sc (1.45%) Se (2.12%) Si (1.24%) Sm (1.04%) Sn (1.07%) Sr (0.31%) Ta (0.39%) Tb (0.29%) Tc (0.79%) Te (1.71%) Th (0.39%) Ti (0.31%) Tl (1.22%) Tm (0.71%) U (0.12%) V (0.33%) W (0.88%) Xe (0.0%) Y (0.85%) Yb (0.0%) Zn (1.21%) Zr (0.48%) Methods: DFT-PBE+U Software: VASP Number of Configurations: 11,388,475 Number of Atoms: 161,511,768 Publication Link: https://doi.org/10.48550/arXiv.2410.12771 Data Source Link: https://fair-chem.github.io/inorganic_materials/datasets/omat24.html Other Links: https://doi.org/10.1002/adma.202210788 https://huggingface.co/datasets/fairchem/OMAT24

Report an issue with this dataset

No uploaded content is transferred in ownership from the original creators to ColabFit. All content is distributed under the license specified by its contributor who has stated that he or she has the authority to share it under the specified license.