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 such investigations allow us to better understand the final configuration and geochemistry of the terrestrial planets, as well as to place our solar system in the context of other exosolar systems. These simulations, however, classically prescribe collisions to result in perfect mergers, but 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, streamlining simulations into a classifier of collision outcomes and a regressor of accretion efficiency. The classifier maps a 4-Dimensional 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 provides insights about the outcome regimes. The regressor is a neural network which is trained to closely mimic the functional relationship between the 4-D 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, 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.

arXiv comment18 pages, 7 figures, 3 tables. Accepted for publication on ApJ

References in corpus (26)

• Deep Learning in Neural Networks: An Overview
• Catastrophic disruptions revisited
• Identifying Mislabeled Training Data
• Building the Terrestrial Planets: Constrained Accretion in the Inner Solar System
• Collisions between Gravity-Dominated Bodies: 2. The Diversity of Impact Outcomes during the End Stage of Planet Formation
• Collisions Between Gravity-Dominated Bodies: 1. Outcome Regimes and Scaling Laws
• Scaling forces to asteroid surfaces: The role of cohesion
• A hit-and-run Giant Impact scenario
• Minimum Radii of Super-Earths: Constraints from Giant Impacts
• Formation of Terrestrial Planets from Protoplanets under a Realistic Accretion Condition
• Collisional Stripping and Disruption of Super-Earths
• SPH calculations of asteroid disruptions: The role of pressure dependent failure models
• The Formation of the Collisional Family around the Dwarf Planet Haumea
• Giant Impact: An Efficient Mechanism for the Devolatilization of Super-Earths
• Water/Icy Super-Earths: Giant Impacts and Maximum Water Content
• On the Impact Origin of Phobos and Deimos I: Thermodynamic and Physical Aspects
• Warm Debris Disks Produced by Giant Impacts During Terrestrial Planet Formation
• Forming Mercury by Giant Impacts
• Formation of bi-lobed shapes by sub-catastrophic collisions: A late origin of comet 67P/C-G's structure
• Consequences of Giant Impacts on Early Uranus for Rotation, Internal Structure, Debris, and Atmospheric Erosion
• SPH calculations of Mars-scale collisions: the role of the Equation of State, material rheologies, and numerical effects
• Numerical Simulations of Collisional Disruption of Rotating Gravitational Aggregates: Dependence on Material Properties
• Constraints on the pre-impact orbits of Solar System giant impactors
• Toward Understanding the Origin of Asteroid Geometries: Variety in Shapes Produced by Equal-Mass Impacts
• Constraining the Thermal Properties of Planetary Surfaces using Machine Learning: Application to Airless Bodies
• Small-body deflection techniques using spacecraft: techniques in simulating the fate of ejecta

Cited by in corpus (20)

• ExoMDN: Rapid characterization of exoplanet interior structures with Mixture Density Networks
• Realistic On-the-fly Outcomes of Planetary Collisions II: Bringing Machine Learning to N-body Simulations
• Realistic collisional water transport during terrestrial planet formation: Self-consistent modeling by an N-body--SPH hybrid code
• Towards a population synthesis of discs and planets. II. Confronting disc models and observations at the population level
• Collision Chains among the Terrestrial Planets. III. Formation of the Moon
• The Effect of Inefficient Accretion on Planetary Differentiation
• Fate of the runner in hit-and-run collisions
• Investigating the Feasibility of an Impact-Induced Martian Dichotomy
• The Role of Giant Impacts in Planet Formation
• Machine learning applied to simulations of collisions between rotating, differentiated planets
• Collision Chains among the Terrestrial Planets. II. An Asymmetry between Earth and Venus
• Could Uranus and Neptune form by collisions of planetary embryos?
• Can a machine learn the outcome of planetary collisions?
• Residual Neural Networks for the Prediction of Planetary Collision Outcomes
• Can metal-rich worlds form by giant impacts?
• Exploring the catastrophic regime: thermodynamics and disintegration in head-on planetary collisions
• Metal-silicate mixing in planetesimal collisions
• Water worlds in N-body simulations with fragmentation in systems without gaseous giants
• Merging Criteria for Planetesimal Collisions
• Re-accretion of Giant Impact Ejecta Can Drive Significant Atmospheric Erosion on Terrestrial Planets