ML SION2: Difference between revisions

From VASP Wiki
No edit summary
No edit summary
Line 1: Line 1:
{{TAGDEF|ML_FF_SION2_MB|[real]}}
{{TAGDEF|ML_FF_SION2_MB|[real]|1.5*{{TAG|ML_FF_SION1_MB}}}}
{{DEF|ML_FF_SION2_MB|none|if {{TAG|ML_FF_IBROAD2_MB}}{{=}}1|0.5|otherwise}}


Description: This tag specifies the width of the Gaussian functions used for broadening the atomic distributions of the angular descriptor within the machine learning force field method.
Description: This tag specifies the width of the Gaussian functions used for broadening the atomic distributions of the angular descriptor within the machine learning force field method.

Revision as of 10:21, 16 November 2020

ML_FF_SION2_MB = [real]
Default: ML_FF_SION2_MB = 1.5*ML_FF_SION1_MB 

Description: This tag specifies the width of the Gaussian functions used for broadening the atomic distributions of the angular descriptor within the machine learning force field method.


The unit of ML_FF_SION2_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. This tag is not used if ML_FF_IBROAD1_MB=1 (which is not the default).


Related Tags and Sections

ML_FF_LMLFF, ML_FF_SION1_MB, ML_FF_RCUT1_MB, ML_FF_RCUT2_MB, ML_FF_MRB1_MB, ML_FF_MRB2_MB

Examples that use this tag