Name: Matbench mp e form
License: MIT

Dataset

Matbench_mp_e_form

Download Original Data Files 137.8 MB

Download Dataset Parquet Files 128.3 MB

Download Dataset XYZ Files 76.1 MB

Find on Hugging Face 🤗

View the Matbench family of datasets

Species content of dataset

Name :

Matbench_mp_e_form

Authors :

Alexander Dunn, Qi Wang, Alex Ganose, Daniel Dopp, Anubhav Jain

Description :

Matbench v0.1 test dataset for predicting DFT formation energy from structure. Adapted from Materials Project database. Entries having formation energy more than 2.5eV and those containing noble gases are removed. Retrieved April 2, 2019. For benchmarking w/ nested cross validation, the order of the dataset must be identical to the retrieved data; refer to the Automatminer/Matbench publication for more details.Matbench is an automated leaderboard for benchmarking state of the art ML algorithms predicting a diverse range of solid materials' properties. It is hosted and maintained by the Materials Project.

DOI :

https://doi.org/10.60732/3cef7b09 https://commons.datacite.org/doi.org/10.60732/3cef7b09

Cite As :

Dunn, A., Wang, Q., Ganose, A., Dopp, D., and Jain, A. "Matbench mp e form." ColabFit, 2024. https://doi.org/10.60732/3cef7b09.

ColabFit ID :

DS_5drebe4tktiu_0

Extended ID :

Matbench_mp_e_form__Dunn-Wang-Ganose-Dopp-Jain__DS_5drebe4tktiu_0

Date Added :

2024-01-04

License :

MIT

Downloads :

166

Num. Configurations :

132,741

Num. Atoms :

3,869,238

Calculated Property Types :

formation_energy

Elements :

Ac (0.02%) Ag (0.37%) Al (1.23%) As (0.55%) Au (0.21%) B (1.51%) Ba (0.79%) Be (0.17%) Bi (0.57%) Br (0.72%) C (2.32%) Ca (0.77%) Cd (0.37%) Ce (0.32%) Cl (1.75%) Co (1.15%) Cr (0.59%) Cs (0.4%) Cu (0.97%) Dy (0.22%) Er (0.23%) Eu (0.15%) F (3.66%) Fe (1.59%) Ga (0.6%) Gd (0.14%) Ge (0.77%) H (5.93%) Hf (0.19%) Hg (0.27%) Ho (0.22%) I (0.75%) In (0.4%) Ir (0.18%) K (0.93%) La (0.56%) Li (2.91%) Lu (0.16%) Mg (2.62%) Mn (1.34%) Mo (0.66%) N (2.21%) Na (1.17%) Nb (0.47%) Nd (0.32%) Ni (1.02%) Np (0.03%) O (35.82%) Os (0.1%) P (2.79%) Pa (0.01%) Pb (0.33%) Pd (0.31%) Pm (0.02%) Pr (0.29%) Pt (0.24%) Pu (0.04%) Rb (0.49%) Re (0.16%) Rh (0.27%) Ru (0.22%) S (2.99%) Sb (0.63%) Sc (0.22%) Se (1.44%) Si (1.87%) Sm (0.26%) Sn (0.63%) Sr (0.65%) Ta (0.29%) Tb (0.21%) Tc (0.04%) Te (0.69%) Th (0.09%) Ti (0.71%) Tl (0.26%) Tm (0.16%) U (0.24%) V (0.95%) W (0.41%) Y (0.4%) Yb (0.21%) Zn (0.7%) Zr (0.36%)

Methods :

DFT-undefined

Software :

VASP

Publication Link :

https://doi.org/10.1038/s41524-020-00406-3

Data Source Link :

https://matbench.materialsproject.org/

Other Links :

https://doi.org/10.1016/j.commatsci.2014.10.037

Spec File :

colabfitspec.json

Configuration Sets by Name :

Configuration Sets by ID :

Name: Matbench_mp_e_form Extended ID: Matbench_mp_e_form__Dunn-Wang-Ganose-Dopp-Jain__DS_5drebe4tktiu_0 Description: Matbench v0.1 test dataset for predicting DFT formation energy from structure. Adapted from Materials Project database. Entries having formation energy more than 2.5eV and those containing noble gases are removed. Retrieved April 2, 2019. For benchmarking w/ nested cross validation, the order of the dataset must be identical to the retrieved data; refer to the Automatminer/Matbench publication for more details.Matbench is an automated leaderboard for benchmarking state of the art ML algorithms predicting a diverse range of solid materials' properties. It is hosted and maintained by the Materials Project. Authors: Alexander Dunn Qi Wang Alex Ganose Daniel Dopp Anubhav Jain DOI: 10.60732/3cef7b09 Calculated Property Types: formation_energy Elements: Ac (0.02%) Ag (0.37%) Al (1.23%) As (0.55%) Au (0.21%) B (1.51%) Ba (0.79%) Be (0.17%) Bi (0.57%) Br (0.72%) C (2.32%) Ca (0.77%) Cd (0.37%) Ce (0.32%) Cl (1.75%) Co (1.15%) Cr (0.59%) Cs (0.4%) Cu (0.97%) Dy (0.22%) Er (0.23%) Eu (0.15%) F (3.66%) Fe (1.59%) Ga (0.6%) Gd (0.14%) Ge (0.77%) H (5.93%) Hf (0.19%) Hg (0.27%) Ho (0.22%) I (0.75%) In (0.4%) Ir (0.18%) K (0.93%) La (0.56%) Li (2.91%) Lu (0.16%) Mg (2.62%) Mn (1.34%) Mo (0.66%) N (2.21%) Na (1.17%) Nb (0.47%) Nd (0.32%) Ni (1.02%) Np (0.03%) O (35.82%) Os (0.1%) P (2.79%) Pa (0.01%) Pb (0.33%) Pd (0.31%) Pm (0.02%) Pr (0.29%) Pt (0.24%) Pu (0.04%) Rb (0.49%) Re (0.16%) Rh (0.27%) Ru (0.22%) S (2.99%) Sb (0.63%) Sc (0.22%) Se (1.44%) Si (1.87%) Sm (0.26%) Sn (0.63%) Sr (0.65%) Ta (0.29%) Tb (0.21%) Tc (0.04%) Te (0.69%) Th (0.09%) Ti (0.71%) Tl (0.26%) Tm (0.16%) U (0.24%) V (0.95%) W (0.41%) Y (0.4%) Yb (0.21%) Zn (0.7%) Zr (0.36%) Methods: DFT-undefined Software: VASP Number of Configurations: 132,741 Number of Atoms: 3,869,238 Publication Link: https://doi.org/10.1038/s41524-020-00406-3 Data Source Link: https://matbench.materialsproject.org/ Other Links: https://doi.org/10.1016/j.commatsci.2014.10.037

Dataset viewer powered by Hugging Face

Report an issue with this dataset

Related Datasets

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.