ML_MODE

ML_MODE = [string]
Default: ML_MODE = NONE

Description: String based tag selecting operation mode for machine learning force fields.

Warning: The description of this tag is currently under construction!

This tag acts as a "supertag" and selects the operation mode by selecting the defaults for all other tags. Every tag that is affected by this "supertag" can be overwritten by the user by simply specifying the value for that tag. The following options are available for this tag:

ML_MODE = TRAIN or train: On-the-fly training is executed. If no ML_AB file is detected in the calculation folder the training is executed from scratch (ML_ISTART=0). Otherwise if an ML_AB exists a continuation run is executed (ML_ISTART=1).
ML_MODE = SELECT or select: Reselection of the local reference configurations is done for an existing ML_AB file (ML_ISTART=3). Furthermore the following tags are set: NSW=1 ; ML_CDOUB = 4 ; ML_EPS_LOW = 1E-11
ML_MODE = REFIT or refit: Refitting of the force field from an existing ML_AB file using the fast version (ML_ISTART=4 together with ML_LFAST=.TRUE.). Furthermore the following tags are set: NSW=1 ; ML_IALGO_LINREG=4 ; ML_SIGW0 = 1E-7 ; ML_SIGV0 = 1 ; ML_EPS_LOW = 1E-11.
ML_MODE = REFITBAYESIAN or refitbayesian (deprecated); Refitting of the force field from an existing ML_AB file using the Bayesian regression (ML_ISTART=4). Furthermore the following tags are set: NSW=1 ; ML_IALGO_LINREG=1 ; ML_LFAST=.FALSE. . This results in lower accuracy and much slower force fields then using ML_MODE = REFIT and should be used with caution. On the other hand, this mode allows to generate ML_FFN files that can calculate Bayesian error estimates.
ML_MODE = RUN or run: Force field only mode is executed (ML_ISTART=2). This mode requires an ML_FF file.
ML_MODE = NONE or none: This tag is not used.

If any option other than the above is chosen or any of them is misspelled (be careful to write everything in upper case or lower case letters) the code will exit with an error.

The user may overwrite the default by specifying any of the machine learning tags in the INCAR file.

Related tags and articles