Abstract

A new computational task has been defined and solved over the past 15 years for extended material systems: the analytic fitting of the Born-Oppenheimer potential energy surface as a function of nuclear coordinates under the assumption of medium-range interactions, 5 ~ 10 Å. The resulting potentials are reactive, many-body, with evaluation costs that are on the order of 0.1-10 ms/atom/cpucore (or about 1ms on a GPU for system sizes that fit into memory), and reach accuracies of a few meV/atom when trained specifically for a given system using iterative/active learning methods. Perhaps the most surprising aspect has been the stability of models trained on very diverse training sets across the periodic table. I will show the recently published MACE -MP-0 model that was trained on just 150,000 real and hypothetical inorganic crystals (90% of training set < 70 atoms), but is capable of stable molecular dynamics on any system tested so far without any extra data – including crystals, liquids, surfaces, clusters, molecules, and combinations of all of these.