Best practices for machine-learned force fields

Using the machine-learning–force-fields method, VASP can construct force fields based on ab-initio simulations. There are many aspects to carefully consider while constructing, testing, retraining, and applying a force field. Here, we list some best practices but bare in mind that the list is incomplete and the method has not been applied to a large number of systems. Therefore, we recommend using the usual rigorous checking that is necessary for any research project.

Training

• It is generally possible to train force fields on a smaller unit cell and then apply it to a larger system. However, it is important to learn the correct forces. This requires converging the forces with respect to the number of k points.
• switch of the symmetry as in MD runs
• train at a higher temperature than the force field is applied but avoid phase transitions
• When the system contains different components, train them separately first. For instance, when the system has a surface of a crystal and a molecule binding on that surface. First, train the bulk crystal, then the surface, next the isolated molecule, and finally the entire system.
• use a cubic supercell with fixed angles for liquids to avoid the cell collapsing
• For simulations without fixed lattice, restart often to reinitialize the PAW basis of the KS orbitals and avoid Pulay stress.

Testing

• Set up an independent test set of random configurations. Then, check the average errors comparing forces, stresses and energy differences of two structures based on DFT and predicted by machine-learned force fields.

• If you have both, ab-initio reference data and a calculation using force fields, check the agreement of some physical properties. For instance, you might check the relaxed lattice parameters, phonons, relative energies of different phases, the elastic constant, the formation of defects etc.

• plot blocked averages

Application

• set the ab-initio parameters to small values. VASP cannot circumvent the initialization of KS orbitals although they are not used during the MD run with MLFF

Related articles

Machine-learned force fields, Ionic minimization, Molecular dynamics