ML SION1: Difference between revisions
No edit summary |
No edit summary |
||
| Line 7: | Line 7: | ||
Test calculations showed that a 1.5 smaller value for the broadening of the radial descriptor compared to the angular descriptor (see {{TAG|ML_FF_SION2_MB}}) gives optimal results. | Test calculations showed that a 1.5 smaller value for the broadening of the radial descriptor compared to the angular descriptor (see {{TAG|ML_FF_SION2_MB}}) gives optimal results. | ||
The default value for {{TAG|ML_FF_SION1_MB}} is chosen such that {{TAG|ML_FF_SION2_MB}} becomes 0.5. | The default value for {{TAG|ML_FF_SION1_MB}} is chosen such that {{TAG|ML_FF_SION2_MB}} becomes 0.5. | ||
== Related Tags and Sections == | == Related Tags and Sections == | ||
Revision as of 11:42, 7 June 2021
ML_FF_SION1_MB = [real]
Default: ML_FF_SION1_MB = 0.333333
Description: This tag specifies the width of the Gaussian functions used for broadening the atomic distributions for the radial descriptor within the machine learning force field method.
The unit of ML_FF_SION1_MB is in . Test calculations showed that a 1.5 smaller value for the broadening of the radial descriptor compared to the angular descriptor (see ML_FF_SION2_MB) gives optimal results. The default value for ML_FF_SION1_MB is chosen such that ML_FF_SION2_MB becomes 0.5.
Related Tags and Sections
ML_FF_LMLFF, ML_FF_SION2_MB, ML_FF_RCUT1_MB, ML_FF_RCUT2_MB, ML_FF_MRB1_MB, ML_FF_MRB2_MB