Dataset
MP-ALOE
Species content of dataset
Name :
MP-ALOE
Authors :
Matthew C. Kuner, Aaron D. Kaplan, Kristin A. Persson, Mark Asta, Daryl C. Chrzan
Description :
MP-ALOE is a dataset of nearly 1 million DFT calculations computed with the r2SCAN meta-generalized gradient approximation, covering 89 elements. The dataset was constructed using active learning via Query by Committee (QBC) and downsampling via the DIRECT method, and primarily consists of off-equilibrium structures. Initial structures were generated by elemental substitution into prototype structures from the ICSD and Materials Project databases (restricted to 2-8 atoms and up to ternary compositions). QBC used an ensemble of interatomic potentials (initially MACE-MP-0, CHGNet, and M3GNet, followed by iteratively trained MACE models) to select structures with energy uncertainty exceeding 100 meV/atom, force uncertainty exceeding 100 meV/Å, or stress uncertainty exceeding 100 meV/ų. DIRECT downsampling reduced approximately 500,000 selected structures to approximately 125,000 for DFT calculation. Near-equilibrium structures from the Materials Project (up to 3 elements, up to 32 atoms, approximately 30,000 structures) were recalculated with identical DFT settings. A two-stage VASP workflow was applied: an initial static calculation using PBE, followed by r2SCAN relaxation for three ionic steps. In total, 909,792 frames from 303,264 structure relaxations are included. DFT calculations used projector-augmented wave (PAW) potentials, a 680 eV plane-wave cutoff, and KSPACING=0.2, with additional parameters from the MP24RelaxSet in pymatgen. Calculations were managed by the atomate2 workflow package.
Cite As :
Kuner, M. C., Kaplan, A. D., Persson, K. A., Asta, M., and Chrzan, D. C. "MP-ALOE." ColabFit, 2025. https://doi.org/None.
ColabFit ID :
Date Added :
2026-04-13
License :
CC-BY-4.0
Downloads :
0
Num. Configurations :
909,789
Num. Atoms :
5,891,262
Calculated Property Types :
atomic_forces
cauchy_stress
electronic_band_gap
energy
Elements :
Ac (0.07%)
Ag (0.51%)
Al (1.56%)
Ar (0.01%)
As (1.24%)
Au (0.68%)
B (2.44%)
Ba (0.58%)
Be (1.59%)
Bi (0.95%)
Br (1.64%)
C (2.57%)
Ca (0.78%)
Cd (0.49%)
Ce (0.16%)
Cl (2.51%)
Co (1.1%)
Cr (1.6%)
Cs (0.39%)
Cu (0.83%)
Dy (0.02%)
Er (0.02%)
Eu (0.07%)
F (4.72%)
Fe (1.12%)
Ga (0.9%)
Gd (0.06%)
Ge (0.97%)
H (2.42%)
He (0.01%)
Hf (1.75%)
Hg (0.53%)
Ho (0.02%)
I (1.54%)
In (0.7%)
Ir (1.32%)
K (0.43%)
Kr (0.02%)
La (0.28%)
Li (1.58%)
Lu (0.2%)
Mg (1.78%)
Mn (1.51%)
Mo (1.64%)
N (4.03%)
Na (0.52%)
Nb (1.71%)
Nd (0.04%)
Ne (0.01%)
Ni (0.98%)
Np (0.05%)
O (11.53%)
Os (1.5%)
P (2.01%)
Pa (0.08%)
Pb (0.41%)
Pd (0.73%)
Pm (0.02%)
Pr (0.04%)
Pt (1.01%)
Pu (0.06%)
Rb (0.41%)
Re (1.82%)
Rh (0.94%)
Ru (1.77%)
S (2.84%)
Sb (1.01%)
Sc (1.15%)
Se (1.94%)
Si (1.88%)
Sm (0.01%)
Sn (0.89%)
Sr (0.67%)
Ta (2.09%)
Tb (0.01%)
Tc (0.93%)
Te (1.29%)
Th (0.12%)
Ti (1.95%)
Tl (0.31%)
Tm (0.0%)
U (0.1%)
V (2.01%)
W (2.29%)
Xe (0.0%)
Y (0.97%)
Yb (0.01%)
Zn (0.78%)
Zr (1.75%)
Methods :
DFT-R2SCAN
Software :
VASP
Publication Link :
Data Source Link :
Other Links :
Spec File :
Configuration Sets by Name :
Configuration Sets by ID :
Name: MP-ALOE
Extended ID: MP-ALOE__Kuner-Kaplan-Persson-Asta-Chrzan__DS_k14lrwu6r2mo_0
Description: MP-ALOE is a dataset of nearly 1 million DFT calculations computed with the r2SCAN meta-generalized gradient approximation, covering 89 elements. The dataset was constructed using active learning via Query by Committee (QBC) and downsampling via the DIRECT method, and primarily consists of off-equilibrium structures. Initial structures were generated by elemental substitution into prototype structures from the ICSD and Materials Project databases (restricted to 2-8 atoms and up to ternary compositions). QBC used an ensemble of interatomic potentials (initially MACE-MP-0, CHGNet, and M3GNet, followed by iteratively trained MACE models) to select structures with energy uncertainty exceeding 100 meV/atom, force uncertainty exceeding 100 meV/Å, or stress uncertainty exceeding 100 meV/ų. DIRECT downsampling reduced approximately 500,000 selected structures to approximately 125,000 for DFT calculation. Near-equilibrium structures from the Materials Project (up to 3 elements, up to 32 atoms, approximately 30,000 structures) were recalculated with identical DFT settings. A two-stage VASP workflow was applied: an initial static calculation using PBE, followed by r2SCAN relaxation for three ionic steps. In total, 909,792 frames from 303,264 structure relaxations are included. DFT calculations used projector-augmented wave (PAW) potentials, a 680 eV plane-wave cutoff, and KSPACING=0.2, with additional parameters from the MP24RelaxSet in pymatgen. Calculations were managed by the atomate2 workflow package.
Authors:
Matthew C. Kuner
Aaron D. Kaplan
Kristin A. Persson
Mark Asta
Daryl C. Chrzan
DOI: None
Calculated Property Types:
atomic_forces
cauchy_stress
electronic_band_gap
energy
Elements:
Ac (0.07%)
Ag (0.51%)
Al (1.56%)
Ar (0.01%)
As (1.24%)
Au (0.68%)
B (2.44%)
Ba (0.58%)
Be (1.59%)
Bi (0.95%)
Br (1.64%)
C (2.57%)
Ca (0.78%)
Cd (0.49%)
Ce (0.16%)
Cl (2.51%)
Co (1.1%)
Cr (1.6%)
Cs (0.39%)
Cu (0.83%)
Dy (0.02%)
Er (0.02%)
Eu (0.07%)
F (4.72%)
Fe (1.12%)
Ga (0.9%)
Gd (0.06%)
Ge (0.97%)
H (2.42%)
He (0.01%)
Hf (1.75%)
Hg (0.53%)
Ho (0.02%)
I (1.54%)
In (0.7%)
Ir (1.32%)
K (0.43%)
Kr (0.02%)
La (0.28%)
Li (1.58%)
Lu (0.2%)
Mg (1.78%)
Mn (1.51%)
Mo (1.64%)
N (4.03%)
Na (0.52%)
Nb (1.71%)
Nd (0.04%)
Ne (0.01%)
Ni (0.98%)
Np (0.05%)
O (11.53%)
Os (1.5%)
P (2.01%)
Pa (0.08%)
Pb (0.41%)
Pd (0.73%)
Pm (0.02%)
Pr (0.04%)
Pt (1.01%)
Pu (0.06%)
Rb (0.41%)
Re (1.82%)
Rh (0.94%)
Ru (1.77%)
S (2.84%)
Sb (1.01%)
Sc (1.15%)
Se (1.94%)
Si (1.88%)
Sm (0.01%)
Sn (0.89%)
Sr (0.67%)
Ta (2.09%)
Tb (0.01%)
Tc (0.93%)
Te (1.29%)
Th (0.12%)
Ti (1.95%)
Tl (0.31%)
Tm (0.0%)
U (0.1%)
V (2.01%)
W (2.29%)
Xe (0.0%)
Y (0.97%)
Yb (0.01%)
Zn (0.78%)
Zr (1.75%)
Methods:
DFT-R2SCAN
Software:
VASP
Number of Configurations: 909,789
Number of Atoms: 5,891,262
Publication Link: https://doi.org/10.1038/s41524-025-01834-9
Data Source Link: https://figshare.com/articles/dataset/MP_ALOE_An_r2SCAN_dataset_for_universal_machine_learning_interatomic_potentials/29452190
Other Links:
https://arxiv.org/abs/2507.05559
Dataset viewer powered by Hugging Face
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.