Machine learning potentials for extended systems: a perspective

In the past two and a half decades machine learning potentials have evolved from a special purpose solution to a broadly applicable tool for large-scale atomistic simulations. By combining the efficiency of empirical potentials and force fields with an accuracy close to first-principles calculations they now enable computer simulations of a wide range of molecules and materials. In this perspective, we summarize the present status of these new types of models for extended systems, which are increasingly used for materials modelling. There are several approaches, but they all have in common that they exploit the locality of atomic properties in some form. Long-range interactions, most prominently electrostatic interactions, can also be included even for systems in which non-local charge transfer leads to an electronic structure that depends globally on all atomic positions. Remaining challenges and limitations of current approaches are discussed.

Automated summary

In the past two and a half decades, machine learning potentials have evolved to become a broadly applicable tool for large-scale atomistic simulations, combining efficiency and accuracy. These models exploit the locality of atomic properties and can include long-range interactions, even for systems with non-local charge transfer. Challenges and limitations of current approaches are also discussed.