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.
 
This section describes the methodology used for force-field generation using machine learning.
 +
 +
== Input ==
  
 
*Besides the usual input files ({{TAG|INCAR}}, {{TAG|POSCAR}}, etc.) the machine learning force field method requires the following input files:
 
*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|ABCAR}} Ab initio data used to create the training data.
 
**{{TAG|FFCAR}} File containing force field parameters.
 
**{{TAG|FFCAR}} File containing force field parameters.
 +
 +
== Output ==
  
 
*The machine learning force field method generates the following output files:
 
*The machine learning force field method generates the following output files:
Line 20: Line 24:
 
*{{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}}
  
 
+
== How to ==
 +
*{{TAG|Executing machine learning force field generation}}
  
  

Revision as of 08:09, 27 May 2019

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

Input

  • 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.

Output

  • 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

How to