Be-2024-06-05¶
The current structure dataset comprises 13855 structures. Procedures to generate structures and estimate MLPs are found in A. Seko, J. Appl. Phys. 133, 011101 (2023).
Predictions using Pareto optimal MLPs
These properties are calculated for MLP equilibrium structures obtained by performing local structure optimizations from the DFT equilibrium structures. These DFT equilibrium structures are obtained by optimizing prototype structures that are included in ICSD. As a result, the structure type of the converged structure may sometimes differ from the one shown in the legend.
The other properties predicted using each Pareto optimal MLP are available from column Predictions in the following table.
Be-2024-06-05 shows large prediction errors. Distributed MLPs should be carefully used. MLPs are often accurate for reasonable structures, but it is sometimes inaccurate for unrealistic structures.
Name |
Time |
RMSE |
Predictions |
Files |
|---|---|---|---|---|
polymlp-00002 |
0.029 / 0.003 |
21.733 / 0.2087 |
– |
– |
polymlp-00004 |
0.032 / 0.003 |
20.414 / 0.1998 |
– |
– |
polymlp-00010 |
0.058 / 0.005 |
16.711 / 0.1993 |
– |
– |
polymlp-00035 |
0.125 / 0.014 |
9.703 / 0.0973 |
– |
– |
polymlp-00064 |
0.158 / 0.016 |
7.072 / 0.0803 |
– |
– |
polymlp-00093 |
0.195 / 0.020 |
5.764 / 0.0762 |
– |
– |
polymlp-00096 |
0.234 / 0.022 |
5.238 / 0.0701 |
– |
– |
polymlp-00073 |
0.472 / 0.034 |
4.122 / 0.0644 |
||
polymlp-00097 |
0.586 / 0.043 |
3.686 / 0.0622 |
||
polymlp-00102 |
0.618 / 0.044 |
3.585 / 0.0607 |
||
polymlp-00103 |
1.067 / 0.060 |
3.233 / 0.0579 |
||
polymlp-00105 |
1.766 / 0.086 |
2.978 / 0.0559 |
||
polymlp-00284 |
9.954 / 0.682 |
2.177 / 0.0513 |
Units:
Time: [ms] (1core/36cores)
RMSE: [meV/atom]/[eV/ang.]
Column “Time” shows the time required to compute the energy and forces for 1 MD step and 1 atom, which is estimated from 10 runs for a large structure using a workstation with Intel(R) Xeon(R) CPU E5-2695 v4 @ 2.10GHz. Note that these MLPs should be carefully used for extreme structures. The MLPs often return meaningless values for them.
All Pareto optimal MLPs are available
here.