ML MRB2: Difference between revisions

From VASP Wiki
VisualWikitext
m (Karsai moved page ML FF MRB2 MB to ML MRB2)
No edit summary
Line 1: Line 1:
{{TAGDEF|ML_FF_MRB2_MB|[integer]|{{TAG|ML_FF_MRB1_MB}}/1.5}}
{{TAGDEF|ML_MRB2|[integer]|{{TAG|ML_MRB1}}/1.5}}


Description: This tag sets the number of radial basis sets used to expand the atomic distribution for the angular descriptor within the machine learning force field method.  
Description: This tag sets the number of radial basis sets used to expand the atomic distribution for the angular descriptor within the machine learning force field method.  
----
----
The values for {{TAG|ML_FF_MRB1_MB}} and {{TAG|ML_FF_MRB2_MB}} are automatically set by the code (empirically) and usually need not to be set by the user. Only in very few cases if the error in the radial expansion (see later in the text) is not sufficiently low these values need to be adjusted manually.
The values for {{TAG|ML_MRB1}} and {{TAG|ML_MRB2}} are automatically set by the code (empirically) and usually need not to be set by the user. Only in very few cases if the error in the radial expansion (see later in the text) is not sufficiently low these values need to be adjusted manually.


The tags {{TAG|ML_FF_MRB1_MB}} and {{TAG|ML_FF_MRB2_MB}} set the number of radial basis sets used to expand the atomic distribution of the radial and angular density. These tags depend very sensitively on the cut-off radius of the descriptor ({{TAG|ML_FF_RCUT1_MB}} and {{TAG|ML_FF_RCUT2_MB}}) and the width of the Gaussian functions used in the broadening of the atomic distributions ({{TAG|ML_FF_SION1_MB}} and {{TAG|ML_FF_SION2_MB}}). The error occuring due to the expansion of the radial basis functions is monitored in the {{TAG|ML_LOGFILE}} file by searching for the following line "''Error in radial expansion: ...''". A typical reasonable value for the error threshold that was empirically determined (by us and in reference {{cite|szlachta:prb:2014}}) is <math>\pm 0.02</math>. Hence, the number of basis functions should be adjusted until the error written in the {{TAG|ML_LOGFILE}} is smaller than this value. A more detailed description of the basis sets is given in appendix A of reference {{cite|jinnouchi2:arx:2019}}.
The tags {{TAG|ML_MRB1}} and {{TAG|ML_MRB2}} set the number of radial basis sets used to expand the atomic distribution of the radial and angular density. These tags depend very sensitively on the cut-off radius of the descriptor ({{TAG|ML_RCUT1}} and {{TAG|ML_RCUT2}}) and the width of the Gaussian functions used in the broadening of the atomic distributions ({{TAG|ML_SION1}} and {{TAG|ML_SION2}}). The error occuring due to the expansion of the radial basis functions is monitored in the {{TAG|ML_LOGFILE}} file by searching for the following line "''Error in radial expansion: ...''". A typical reasonable value for the error threshold that was empirically determined (by us and in reference {{cite|szlachta:prb:2014}}) is <math>\pm 0.02</math>. Hence, the number of basis functions should be adjusted until the error written in the {{TAG|ML_LOGFILE}} is smaller than this value. A more detailed description of the basis sets is given in appendix A of reference {{cite|jinnouchi2:arx:2019}}.




Line 14: Line 14:
<noinclude>
<noinclude>
== Related Tags and Sections ==
== Related Tags and Sections ==
{{TAG|ML_FF_LMLFF}}, {{TAG|ML_FF_MRB1_MB}}, {{TAG|ML_FF_W1_MB}}, {{TAG|ML_FF_W1_MB}}, {{TAG|ML_FF_RCUT1_MB}}, {{TAG|ML_FF_RCUT2_MB}}, {{TAG|ML_FF_SION1_MB}}, {{TAG|ML_FF_SION2_MB}}
{{TAG|ML_LMLFF}}, {{TAG|ML_MRB1}}, {{TAG|ML_W1}}, {{TAG|ML_RCUT1}}, {{TAG|ML_RCUT2}}, {{TAG|ML_SION1}}, {{TAG|ML_SION2}}


{{sc|ML_FF_MRB2_MB|Examples|Examples that use this tag}}
{{sc|ML_MRB2|Examples|Examples that use this tag}}
----
----


[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]
[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]

Revision as of 09:05, 23 August 2021

ML_MRB2 = [integer]
Default: ML_MRB2 = ML_MRB1/1.5 

Description: This tag sets the number of radial basis sets used to expand the atomic distribution for the angular descriptor within the machine learning force field method.

The values for ML_MRB1 and ML_MRB2 are automatically set by the code (empirically) and usually need not to be set by the user. Only in very few cases if the error in the radial expansion (see later in the text) is not sufficiently low these values need to be adjusted manually.

The tags ML_MRB1 and ML_MRB2 set the number of radial basis sets used to expand the atomic distribution of the radial and angular density. These tags depend very sensitively on the cut-off radius of the descriptor (ML_RCUT1 and ML_RCUT2) and the width of the Gaussian functions used in the broadening of the atomic distributions (ML_SION1 and ML_SION2). The error occuring due to the expansion of the radial basis functions is monitored in the ML_LOGFILE file by searching for the following line "Error in radial expansion: ...". A typical reasonable value for the error threshold that was empirically determined (by us and in reference [1]) is . Hence, the number of basis functions should be adjusted until the error written in the ML_LOGFILE is smaller than this value. A more detailed description of the basis sets is given in appendix A of reference [2].


References

  1. ↑ W. J. Szlachta, A. P. Bartók, and G. Csányi, Phys. Rev. B 90, 104108 (2014).
  2. ↑ R. Jinnouchi, F. Karsai, and G. Kresse, Phys. Rev. B 100, 014105 (2019).


Related Tags and Sections

ML_LMLFF, ML_MRB1, ML_W1, ML_RCUT1, ML_RCUT2, ML_SION1, ML_SION2

Examples that use this tag

Retrieved from "https://www.vasp.at/wiki/index.php?title=ML_MRB2&oldid=12789"