Machine learning force field calculations: Basics - Revision history

Singraber at 13:19, 24 January 2025

2025-01-24T13:19:22Z

← Older revision		Revision as of 13:19, 24 January 2025
Line 27:		Line 27:
	Leave <code>{{TAG\|ML_MODE}} = train</code> unchanged and restart {{VASP}}. The log file will contain a section describing the existing data set and after initial generation of a force field the regular on-the-fly procedure continues. In the end, the resulting {{FILE\|ML_ABN}} will contain the training structures from both on-the-fly runs. Similarly, the {{FILE\|ML_FFN}} file is a combined force field. In the presence of an {{FILE\|ML_AB}} file the <code>train</code> mode will always perform a continuation run. If you would like to start from scratch just remove the {{FILE\|ML_AB}} file from the execution directory. {{NB\|tip\|Apply this strategy repeatedly in order to systematically improve your MLFF, e.g., first train on water only, then on sodium chloride and finally, train on the combination of both.}}		Leave <code>{{TAG\|ML_MODE}} = train</code> unchanged and restart {{VASP}}. The log file will contain a section describing the existing data set and after initial generation of a force field the regular on-the-fly procedure continues. In the end, the resulting {{FILE\|ML_ABN}} will contain the training structures from both on-the-fly runs. Similarly, the {{FILE\|ML_FFN}} file is a combined force field. In the presence of an {{FILE\|ML_AB}} file the <code>train</code> mode will always perform a continuation run. If you would like to start from scratch just remove the {{FILE\|ML_AB}} file from the execution directory. {{NB\|tip\|Apply this strategy repeatedly in order to systematically improve your MLFF, e.g., first train on water only, then on sodium chloride and finally, train on the combination of both.}}

	''' Step 4: Refit for fast prediction mode '''		''' Step 4: Refit for fast prediction mode ''' (available as of {{VASP}}.6.4.0)

	When on-the-fly training succeeded and the result matches your expectations with respect to applicability and residual errors there is one final step required before the force field should be applied in prediction-only MD runs: refitting for fast prediction mode. Copy once again the final data set to {{FILE\|ML_AB}}:		When on-the-fly training succeeded and the result matches your expectations with respect to applicability and residual errors there is one final step required before the force field should be applied in prediction-only MD runs: refitting for fast prediction mode. Copy once again the final data set to {{FILE\|ML_AB}}:

Singraber: /* Step-by-step instructions */

2023-05-17T13:18:01Z

Step-by-step instructions

← Older revision		Revision as of 13:18, 17 May 2023
Line 41:		Line 41:
	In the {{FILE\|INCAR}} file set		In the {{FILE\|INCAR}} file set
	{{TAGBL\|ML_MODE}} = run		{{TAGBL\|ML_MODE}} = run
	With this choice {{VASP}} will only use the predictions from the MLFF, no ab-initio calculations are performed. The execution time per time step will be orders of magnitude lower if compared with corresponding ab-initio runs. {{NB\|tip\|The MLFF can be transferred to larger system sizes, i.e., you may duplicate your simulation box to benefit from improved statistics. Because the method scales linearly with the number of atoms you can easily estimate the impact on computational demand.}}		With this choice {{VASP}} will only use the predictions from the MLFF, no ab-initio calculations are performed. The execution time per time step will be orders of magnitude lower if compared with corresponding ab-initio runs. {{NB\|tip\|The MLFF can be transferred to larger system sizes, i.e., you may duplicate your simulation box to benefit from improved statistics. Because the method scales linearly with the number of atoms you can easily estimate the impact on computational demand.}} {{NB\|warning\|Please have a look at a [[Known issues\|known issue]] (from date 2023-05-17) if you intend to use triclinic geometries with small or large lattice angles.}}

	== Advice ==		== Advice ==

Singraber at 14:36, 5 May 2023

2023-05-05T14:36:10Z

Show changes

Huebsch: Huebsch moved page Construction:Machine learning force field calculations: Basics to Machine learning force field calculations: Basics without leaving a redirect

2023-05-05T14:01:43Z

Huebsch moved page Construction:Machine learning force field calculations: Basics to Machine learning force field calculations: Basics without leaving a redirect

← Older revision	Revision as of 14:01, 5 May 2023
(No difference)

Singraber: /* Important general remarks */

2023-05-05T13:59:42Z

Important general remarks

← Older revision		Revision as of 13:59, 5 May 2023
Line 43:		Line 43:
	With this choice {{VASP}} will only use the predictions from the machine-learned force field, no ab-initio calculations are performed. The execution time per time step will be orders of magnitude lower if compared with corresponding ab-initio runs. {{NB\|tip\|The MLFF can be transferred to larger system sizes, i.e., you may duplicate your simulation box to benefit from improved statistics. Because the method scales linearly with the number of atoms you can easily estimate the impact on computational demand.}}		With this choice {{VASP}} will only use the predictions from the machine-learned force field, no ab-initio calculations are performed. The execution time per time step will be orders of magnitude lower if compared with corresponding ab-initio runs. {{NB\|tip\|The MLFF can be transferred to larger system sizes, i.e., you may duplicate your simulation box to benefit from improved statistics. Because the method scales linearly with the number of atoms you can easily estimate the impact on computational demand.}}

	== ~~Important general remarks~~ ==		== Advice ==

	On-the-fly learning can be significantly more involved than, e.g., a single-point electronic calculation, because it combines multiple features of {{VASP}}. Each part requires a proper setup via the available {{FILE\|INCAR}} tags. A misconfiguration corresponding to one part of the calculation may have severe effects on the quality of the resulting machine-learned force field. In the worst case, successful training may even be impossible. To be more specific, on-the-fly learning requires control over the following aspects:		On-the-fly learning can be significantly more involved than, e.g., a single-point electronic calculation, because it combines multiple features of {{VASP}}. Each part requires a proper setup via the available {{FILE\|INCAR}} tags. A misconfiguration corresponding to one part of the calculation may have severe effects on the quality of the resulting machine-learned force field. In the worst case, successful training may even be impossible. To be more specific, on-the-fly learning requires control over the following aspects:

Singraber: /* Step-by-step instructions */

2023-05-05T13:58:41Z

Step-by-step instructions

← Older revision		Revision as of 13:58, 5 May 2023
Line 3:		Line 3:
	== Step-by-step instructions ==		== Step-by-step instructions ==

	On-the-fly training is based on molecular-dynamics simulations to sample training structures. Piece by piece a data set is automatically assembled and used to generate a machine-learned force field whenever feasible. Conversely, at each time step the current force field predicts energy, forces and the corresponding Bayesian error estimations. Simply put, if the error is above a certain threshold another ab-initio calculation is performed and the reference energy and forces are added to the training data set. In the opposite case, the ab initio step is omitted and the system is propagated via MLFF predictions. As the force field gets better along the trajectory many ab-initio steps can be avoided and the MD simulation is significantly accelerated. Ultimately, the on-the-fly training results in an MLFF which is ready for production, i.e., running an MD simulation in prediction-only mode. The following steps outline the path from start to production run:		On-the-fly training is based on molecular-dynamics simulations (MD) to sample training structures. Piece by piece a data set is automatically assembled and used to generate a machine-learned force field whenever feasible. Conversely, at each time step the current force field predicts energy, forces and the corresponding Bayesian error estimations. Simply put, if the error is above a certain threshold another ab-initio calculation is performed and the reference energy and forces are added to the training data set. In the opposite case, the ab initio step is omitted and the system is propagated via MLFF predictions. As the force field gets better along the trajectory many ab-initio steps can be avoided and the MD simulation is significantly accelerated. Ultimately, the on-the-fly training results in an MLFF which is ready for production, i.e., running an MD simulation in prediction-only mode. The following steps outline the path from start to production run:

	''' Step 1: Prepare an MD run '''		''' Step 1: Prepare an MD run '''

Singraber: /* Step-by-step instructions */

2023-05-05T13:57:36Z

Step-by-step instructions

← Older revision		Revision as of 13:57, 5 May 2023
Line 3:		Line 3:
	== Step-by-step instructions ==		== Step-by-step instructions ==

	~~The on~~-the-fly training ~~{{VASP}} features~~ is based on molecular-dynamics simulations to sample training structures. Piece by piece a data set is automatically assembled and used to generate a machine-learned force field whenever feasible. Conversely, at each time step the current force field predicts energy, forces and the corresponding Bayesian error estimations. Simply put, if the error is above a certain threshold another ab-initio calculation is performed and the reference energy and forces are added to the training data set. In the opposite case, the ab initio step is omitted and the system is propagated via MLFF predictions. As the force field gets better along the trajectory many ab-initio steps can be avoided and the MD simulation is significantly accelerated. Ultimately, the on-the-fly training results in an MLFF which is ready for production, i.e., running an MD simulation in prediction-only mode. The following steps outline the path from start to production run:		On-the-fly training is based on molecular-dynamics simulations to sample training structures. Piece by piece a data set is automatically assembled and used to generate a machine-learned force field whenever feasible. Conversely, at each time step the current force field predicts energy, forces and the corresponding Bayesian error estimations. Simply put, if the error is above a certain threshold another ab-initio calculation is performed and the reference energy and forces are added to the training data set. In the opposite case, the ab initio step is omitted and the system is propagated via MLFF predictions. As the force field gets better along the trajectory many ab-initio steps can be avoided and the MD simulation is significantly accelerated. Ultimately, the on-the-fly training results in an MLFF which is ready for production, i.e., running an MD simulation in prediction-only mode. The following steps outline the path from start to production run:

	''' Step 1: Prepare an MD run '''		''' Step 1: Prepare an MD run '''

Singraber: /* Step-by-step instructions */

2023-05-05T13:54:38Z

Step-by-step instructions

Singraber: /* Parallelization */

2023-05-05T13:48:13Z

Parallelization

Show changes

Singraber: /* Parallelization and memory usage */

2023-05-05T08:25:19Z

Parallelization and memory usage

← Older revision		Revision as of 08:25, 5 May 2023
Line 58:		Line 58:
	{{NB\|tip\|Begin by thoroughly familiarizing yourself with pure ab initio calculations for your system before attempting to generate a machine-learned force field from scratch. Once you are confident in controlling the convergence, proceed to run a brief MD simulation without machine learning assistance. Validate whether the results align with expected values regarding conservation principles and so forth. Only then, move forward with the machine learning aspects of the calculation.}}		{{NB\|tip\|Begin by thoroughly familiarizing yourself with pure ab initio calculations for your system before attempting to generate a machine-learned force field from scratch. Once you are confident in controlling the convergence, proceed to run a brief MD simulation without machine learning assistance. Validate whether the results align with expected values regarding conservation principles and so forth. Only then, move forward with the machine learning aspects of the calculation.}}

	== Parallelization ~~and memory usage~~ ==		== Parallelization ==

	At present, {{VASP}} provides only MPI-based parallelization for the MLFF feature. Therefore, any operational mode relying exclusively on MLFF code - such as predictive MD simulations ({{TAG\|ML_MODE}} = run) and local reference configuration selection ({{TAG\|ML_MODE}} = select) - cannot leverage alternative forms of parallelization like [[OpenACC GPU port of VASP\|OpenACC offloading to GPUs]] or [[Combining MPI and OpenMP\|an MPI/OpenMP hybrid approach]]. Conversely, a usual on-the-fly training involves both MLFF generation and ab initio computations. When the latter component predominates in terms of computational demand, utilizing non-MPI parallelization remains practical.		At present, {{VASP}} provides only MPI-based parallelization for the MLFF feature. Therefore, any operational mode relying exclusively on MLFF code - such as predictive MD simulations ({{TAG\|ML_MODE}} = run) and local reference configuration selection ({{TAG\|ML_MODE}} = select) - cannot leverage alternative forms of parallelization like [[OpenACC GPU port of VASP\|OpenACC offloading to GPUs]] or [[Combining MPI and OpenMP\|an MPI/OpenMP hybrid approach]]. Conversely, a usual on-the-fly training involves both MLFF generation and ab initio computations. When the latter component predominates in terms of computational demand, utilizing non-MPI parallelization remains practical.

← Older revision		Revision as of 13:54, 5 May 2023
Line 3:		Line 3:
	== Step-by-step instructions ==		== Step-by-step instructions ==

	The on-the-fly training {{VASP}} features is based on molecular dynamics simulations to sample training structures. Piece by piece a data set is automatically assembled and used to generate a machine-learned force field whenever feasible. Conversely, at each time step the current force field predicts energy, forces and the corresponding Bayesian error estimations. Simply put, if the error is above a certain threshold another ab initio calculation is performed and the reference energy and forces are added to the training data set. In the opposite case, the ab initio step is omitted and the system is propagated via MLFF predictions. As the force field gets better along the trajectory many ab initio steps can be avoided and the MD simulation is significantly accelerated. Ultimately, the on-the-fly training results in an MLFF which is ready for production, i.e., running an MD simulation in prediction-only mode. The following steps outline the path from start to production run:		The on-the-fly training {{VASP}} features is based on molecular-dynamics simulations to sample training structures. Piece by piece a data set is automatically assembled and used to generate a machine-learned force field whenever feasible. Conversely, at each time step the current force field predicts energy, forces and the corresponding Bayesian error estimations. Simply put, if the error is above a certain threshold another ab-initio calculation is performed and the reference energy and forces are added to the training data set. In the opposite case, the ab initio step is omitted and the system is propagated via MLFF predictions. As the force field gets better along the trajectory many ab-initio steps can be avoided and the MD simulation is significantly accelerated. Ultimately, the on-the-fly training results in an MLFF which is ready for production, i.e., running an MD simulation in prediction-only mode. The following steps outline the path from start to production run:

	''' Step 1: Prepare an MD run '''		''' Step 1: Prepare an MD run '''

	Prepare an [[#Category:Calculation setup\|ab initio]] [[#Category:Molecular dynamics\|molecular dynamics]] run with your desired {{FILE\|POSCAR}} starting configuration and an appropriate setup in {{FILE\|INCAR}}, {{FILE\|KPOINTS}} and {{FILE\|POTCAR}} files.		Prepare an [[#Category:Calculation setup\|ab-initio]] [[#Category:Molecular dynamics\|molecular-dynamics]] run with your desired {{FILE\|POSCAR}} starting configuration and an appropriate setup in {{FILE\|INCAR}}, {{FILE\|KPOINTS}} and {{FILE\|POTCAR}} files.

	''' Step 2: Start on-the-fly training from scratch '''		''' Step 2: Start on-the-fly training from scratch '''
Line 13:		Line 13:
	The machine-learned force field method can be configured with a lot of [[#Category:Machine-learned force fields\|INCAR tags]] which are easily recognized from their prefix <code>ML_</code>. In general, to enable any MLFF feature the following {{FILE\|INCAR}} tag needs to be set:		The machine-learned force field method can be configured with a lot of [[#Category:Machine-learned force fields\|INCAR tags]] which are easily recognized from their prefix <code>ML_</code>. In general, to enable any MLFF feature the following {{FILE\|INCAR}} tag needs to be set:
	{{TAGBL\|ML_LMLFF}} = .TRUE.		{{TAGBL\|ML_LMLFF}} = .TRUE.
	If this tag is not set to <code>.TRUE.</code> other MLFF-related {{FILE\|INCAR}} tags are completely ignored and {{VASP}} will perform regular ab initio calculations. Furthermore, to start on-the-fly training we additionally need to set the {{TAG\|ML_MODE}} "super"-tag:		If this tag is not set to <code>.TRUE.</code> other MLFF-related {{FILE\|INCAR}} tags are completely ignored and {{VASP}} will perform regular ab-initio calculations. Furthermore, to start on-the-fly training we additionally need to set the {{TAG\|ML_MODE}} "super"-tag:
	{{TAGBL\|ML_MODE}} = train		{{TAGBL\|ML_MODE}} = train
	When executed in this <code>train</code> mode {{VASP}} will automatically perform ab initio calculation whenever necessary and otherwise rely on the predictions of the machine-learned force field. The usual output files, e.g., {{FILE\|OUTCAR}}, {{FILE\|XDATCAR}}, will be created along the MD trajectory. In addition, MLFF-related files will be written to disk, the most important ones being:		When executed in this <code>train</code> mode {{VASP}} will automatically perform ab-initio calculation whenever necessary and otherwise rely on the predictions of the machine-learned force field. The usual output files, e.g., {{FILE\|OUTCAR}}, {{FILE\|XDATCAR}}, will be created along the MD trajectory. In addition, MLFF-related files will be written to disk, the most important ones being:
	* {{FILE\|ML_LOGFILE}} The log file for all MLFF-related details; training status, current errors and other important quantities can be extracted from here.		* {{FILE\|ML_LOGFILE}} The log file for all MLFF-related details; training status, current errors and other important quantities can be extracted from here.
	* {{FILE\|ML_ABN}} This file contains the collected training structures and a list of selected local reference configurations.		* {{FILE\|ML_ABN}} This file contains the collected training structures and a list of selected local reference configurations.
Line 41:		Line 41:
	In the {{FILE\|INCAR}} file set		In the {{FILE\|INCAR}} file set
	{{TAGBL\|ML_MODE}} = run		{{TAGBL\|ML_MODE}} = run
	With this choice {{VASP}} will only use the predictions from the machine-learned force field, no ab initio calculations are performed. The execution time per time step will be orders of magnitude lower if compared with corresponding ab initio runs. {{NB\|tip\|The MLFF can be transferred to larger system sizes, i.e., you may duplicate your simulation box to benefit from improved statistics. Because the method scales linearly with the number of atoms you can easily estimate the impact on computational demand.}}		With this choice {{VASP}} will only use the predictions from the machine-learned force field, no ab-initio calculations are performed. The execution time per time step will be orders of magnitude lower if compared with corresponding ab-initio runs. {{NB\|tip\|The MLFF can be transferred to larger system sizes, i.e., you may duplicate your simulation box to benefit from improved statistics. Because the method scales linearly with the number of atoms you can easily estimate the impact on computational demand.}}

	== Important general remarks ==		== Important general remarks ==