Realistic On-the-fly Outcomes of Planetary Collisions: Machine Learning Applied to Simulations of Giant Impacts

Abstract

Planet formation simulations are capable of directly integrating the evolution of hundreds to thousands of planetary embryos and planetesimals as they accrete pairwise to become planets. In principle, these investigations allow us to better understand the final configuration and geochemistry of the terrestrial planets, and also to place our solar system in the context of other exosolar systems. While these simulations classically prescribe collisions to result in perfect mergers, recent computational advances have begun to allow for more complex outcomes to be implemented. Here we apply machine learning to a large but sparse database of giant impact studies, which allows us to streamline the simulations into a classifier of collision outcomes and a regressor of accretion efficiency. The classifier maps a four-dimensional (4D) parameter space (target mass, projectile-to-target mass ratio, impact velocity, impact angle) into the four major collision types: merger, graze-and-merge, hit-and-run, and disruption. The definition of the four regimes and their boundary is fully data-driven. The results do not suffer from any model assumption in the fitting. The classifier maps the structure of the parameter space and it provides insights into the outcome regimes. The regressor is a neural network that is trained to closely mimic the functional relationship between the 4D space of collision parameters, and a real-variable outcome, the mass of the largest remnant. This work is a prototype of a more complete surrogate model, that will be based on extended sets of simulations (big data), that will quickly and reliably predict specific collision outcomes for use in realistic N-body dynamical studies of planetary formation.