Requests for technical support from the VASP group should be posted in the VASP-forum.

Difference between revisions of "Category:Machine Learning"

From Vaspwiki
Jump to navigationJump to search
Line 1: Line 1:
 +
This section describes the methodology used for force-field generation using machine learning.
 +
 +
*Besides the usual input files ({{TAG|INCAR}}, {{TAG|POSCAR}}, etc.) the machine learning force field method requires the following input files:
 +
 +
{{TAG|ABCAR}} Ab initio data used to create the training data.
 +
 +
{{TAG|FFCAR}} File containing force field parameters.
 +
 +
*The machine learning force field method generates the following output files:
 +
 +
{{TAG|ML_LOGFILE}} Main output file for the machine learning force field method.
 +
 +
{{TAG|ABNCAR}} New abinitio data (used as {{TAG|ABCAR}} in the next run).
 +
 +
{{TAG|REGCAR}} Output file summarizing regression results.
 +
 +
{{TAG|HISCAR}} Output file summarizing the histogram data.
 +
 +
{{TAG|FFNCAR}} File containing new force field parameters (used as {{TAG|FFCAR}} in the next run).
 +
 +
{{TAG|ML_EATOM}} Output file containing local atomic energies
 +
 +
{{TAG|ML_HEAT}} Output file including local heat flux
 +
 +
 
All {{TAG|INCAR}} tags belonging to the machine learning force field method start with the prefix ''ML_FF_''. Input tags that are related to the many-body term end with ''_MB''.
 
All {{TAG|INCAR}} tags belonging to the machine learning force field method start with the prefix ''ML_FF_''. Input tags that are related to the many-body term end with ''_MB''.
  
Line 4: Line 29:
 
*{{TAG|On-the-fly machine learning force field generation using Bayesian linear regression}}
 
*{{TAG|On-the-fly machine learning force field generation using Bayesian linear regression}}
  
{{TAG|ABCAR}}
+
 
{{TAG|ABNCAR}}
+
 
{{TAG|REGCAR}}
+
 
{{TAG|HISCAR}}
+
 
{{TAG|FFCAR}}
 
{{TAG|FFNCAR}}
 
{{TAG|ML_LOGFILE}}
 
{{TAG|ML_EATOM}}
 
{{TAG|ML_HEAT}}
 
 
----
 
----
 
[[Category:VASP|Machine Learning]][[Category:VASP6]]
 
[[Category:VASP|Machine Learning]][[Category:VASP6]]

Revision as of 16:59, 23 May 2019

This section describes the methodology used for force-field generation using machine learning.

  • Besides the usual input files (INCAR, POSCAR, etc.) the machine learning force field method requires the following input files:

ABCAR Ab initio data used to create the training data.

FFCAR File containing force field parameters.

  • The machine learning force field method generates the following output files:

ML_LOGFILE Main output file for the machine learning force field method.

ABNCAR New abinitio data (used as ABCAR in the next run).

REGCAR Output file summarizing regression results.

HISCAR Output file summarizing the histogram data.

FFNCAR File containing new force field parameters (used as FFCAR in the next run).

ML_EATOM Output file containing local atomic energies

ML_HEAT Output file including local heat flux


All INCAR tags belonging to the machine learning force field method start with the prefix ML_FF_. Input tags that are related to the many-body term end with _MB.

Theoretical Background