Four generations of neural network potentials

Jörg Behler, Ruhr-Universität Bochum, Germany

A lot of progress has been made in recent years in the development of machine learning potentials (MLP) for atomistic simulations. Neural network potentials (NNPs), which have been introduced more than two decades ago, are an important class of MLPs. While the first generation of NNPs has been restricted to small molecules with only a few degrees of freedom, the second generation extended the applicability of MLPs to high-dimensional systems containing thousands of atoms by constructing the total energy as a sum of environment-dependent atomic energies.
Long-range electrostatic interactions can be included in third-generation NNPs employing environment-dependent charges, but only recently limitations of this locality approximation could be overcome by the introduction of fourth-generation NNPs, which are able to describe non-local charge transfer using a global charge equilibration step. In this talk an overview about the evolution of high-dimensional neural network potentials will be given along with typical applications in large-scale atomistic simulations.

back to MCIC 2023