Dataset

Matbench_mp_e_form



Download Dataset XYZ file

Name Matbench_mp_e_form
Extended ID Matbench_mp_e_form_DunnWangGanoseDoppJain__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
Elements Bi (0.57%)
Mg (2.62%)
O (35.82%)
Rb (0.49%)
In (0.4%)
Sn (0.63%)
C (2.32%)
Fe (1.59%)
K (0.93%)
N (2.21%)
F (3.66%)
Mn (1.34%)
Ca (0.77%)
S (2.99%)
Lu (0.16%)
Re (0.16%)
Co (1.15%)
Cu (0.97%)
Zn (0.7%)
Rh (0.27%)
Si (1.87%)
Sm (0.26%)
Dy (0.22%)
Cl (1.75%)
H (5.93%)
Mo (0.66%)
Ni (1.02%)
Ge (0.77%)
Na (1.17%)
V (0.95%)
Al (1.23%)
As (0.55%)
Sr (0.65%)
Ga (0.6%)
Y (0.4%)
Li (2.91%)
Ti (0.71%)
Ta (0.29%)
U (0.24%)
Nb (0.47%)
Se (1.44%)
P (2.79%)
I (0.75%)
Cs (0.4%)
Tm (0.16%)
W (0.41%)
Zr (0.36%)
Ba (0.79%)
Ru (0.22%)
Ce (0.32%)
Tl (0.26%)
Ir (0.18%)
Yb (0.21%)
Pb (0.33%)
Sb (0.63%)
B (1.52%)
Hf (0.19%)
Cd (0.37%)
Pd (0.31%)
Sc (0.22%)
Ag (0.37%)
La (0.56%)
Nd (0.32%)
Au (0.21%)
Ho (0.22%)
Er (0.23%)
Be (0.17%)
Pr (0.29%)
Br (0.72%)
Te (0.69%)
Pm (0.02%)
Cr (0.59%)
Pt (0.24%)
Tb (0.21%)
Tc (0.04%)
Gd (0.14%)
Hg (0.27%)
Np (0.03%)
Th (0.09%)
Os (0.1%)
Ac (0.02%)
Eu (0.15%)
Pu (0.04%)
Pa (0.01%)
Number of Data Objects 132,752
Number of Configurations 132,752
Number of Atoms 3,869,658
Links https://doi.org/10.1038/s41524-020-00406-3
https://matbench.materialsproject.org/
https://doi.org/10.1016/j.commatsci.2014.10.037
Configuration Sets by Name (None)
Configuration Sets by ID (None)
Data Objects Too many to display
ColabFit ID DS_5drebe4tktiu_0
Files colabfitspec.json

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.