Requests for technical support from the VASP group should be posted in the VASP-forum.
Category:Machine Learning
From Vaspwiki
Jump to navigationJump to searchThe printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.
This section describes the methodology used for force-field generation using machine learning. One first should checkout the theoretical background Machine learning force field: Theory together with the basic description how to run the machine learning calculations Machine learning force field calculations: Basics. Then gain some hands-on experience with the following tutorial: Liquid Si - MLFF.
Input
- Besides the usual input files (INCAR, POSCAR, etc.) the machine learning force field method requires the following input files:
Output
- The machine learning force field method generates the following output files:
- ML_LOGFILE Main output file for the machine learning force field method.
- ML_ABNCAR New abinitio data (used as ABCAR in the next run).
- ML_REGCAR Output file summarizing regression results.
- ML_HISCAR Output file summarizing the histogram data.
- ML_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
- Machine learning force field calculations: Basics.
- Machine learning force field calculations: Intermediate.
Tutorial
- Basic tutorial to learn how to perform on-the-fly learning and how to control the accuracy of the force field: Liquid Si - MLFF.
Pages in category "Machine Learning"
The following 71 pages are in this category, out of 71 total.
M
- Machine learning force field calculations: Basics
- Machine learning force field calculations: Intermediate
- Machine learning force field: Theory
- ML AB
- ML ABN
- ML EATOM
- ML FF
- ML FF AFILT2 MB
- ML FF CDOUB
- ML FF CSF
- ML FF CSIG
- ML FF CSLOPE
- ML FF CTIFOR
- ML FF EATOM
- ML FF EPS LOW
- ML FF IAFILT2 MB
- ML FF IBROAD1 MB
- ML FF IBROAD2 MB
- ML FF ICOUPLE MB
- ML FF ICUT1 MB
- ML FF ICUT2 MB
- ML FF IERR
- ML FF IREG MB
- ML FF ISAMPLE
- ML FF ISCALE TOTEN MB
- ML FF ISOAP1 MB
- ML FF ISOAP2 MB
- ML FF ISTART
- ML FF IWEIGHT
- ML FF LAFILT2 MB
- ML FF LBASIS DISCARD
- ML FF LCOUPLE MB
- ML FF LCRITERIA
- ML FF LEATOM MB
- ML FF LHEAT MB
- ML FF LMAX2 MB
- ML FF LMLFF
- ML FF LNORM1 MB
- ML FF LNORM2 MB
- ML FF MB MB
- ML FF MCONF
- ML FF MCONF NEW
- ML FF MHIS
- ML FF MRB1 MB
- ML FF MRB2 MB
- ML FF MSPL1 MB
- ML FF MSPL2 MB
- ML FF NATOM COUPLED MB
- ML FF NDIM SCALAPACK
- ML FF NHYP1 MB
- ML FF NHYP2 MB
- ML FF NMDINT
- ML FF NR1 MB
- ML FF NR2 MB
- ML FF NWRITE
- ML FF RCOUPLE MB
- ML FF RCUT1 MB
- ML FF RCUT2 MB
- ML FF SIGV0 MB
- ML FF SIGW0 MB
- ML FF SION1 MB
- ML FF SION2 MB
- ML FF W1 MB
- ML FF WTIFOR
- ML FF WTOTEN
- ML FF WTSIF
- ML FFN
- ML HEAT
- ML HIS
- ML LOGFILE
- ML REG
