Three-body problem -- from Newton to supercomputer plus machine learning

Abstract

The famous three-body problem can be traced back to Newton in 1687, but quite few families of periodic orbits were found in 300 years thereafter. In this paper, we propose an effective approach and roadmap to numerically gain planar periodic orbits of three-body systems with arbitrary masses by means of machine learning based on an artificial neural network (ANN) model. Given any a known periodic orbit as a starting point, this approach can provide more and more periodic orbits (of the same family name) with variable masses, while the mass domain having periodic orbits becomes larger and larger, and the ANN model becomes wiser and wiser. Finally we have an ANN model trained by means of all obtained periodic orbits of the same family, which provides a convenient way to give accurate enough predictions of periodic orbits with arbitrary masses for physicists and astronomers. It suggests that the high-performance computer and artificial intelligence (including machine learning) should be the key to gain periodic orbits of the famous three-body problem.

arXiv comment17 pages, 9 figures, 6 tables, accepted by New Astronomy in May 2022. See also https://www.researchsquare.com/article/rs-395522/v1

References in corpus (20)

• On the Convergence of Adam and Beyond
• Three Classes of Newtonian Three-Body Planar Periodic Orbits
• A Statistical Solution to the Chaotic, Non-Hierarchical Three-Body Problem
• On the mathematically reliable long-term simulation of chaos of Lorenz equation in the interval [0,10000]
• On the reliability of computed chaotic solutions of nonlinear differential equations
• More than six hundreds new families of Newtonian periodic planar collisionless three-body orbits
• The 1223 new periodic orbits of planar three-body problem with unequal mass and zero angular momentum
• On the risks of using double precision in numerical simulations of spatio-temporal chaos
• Chaotic motion of three-body problem : an origin of macroscopic randomness of the universe
• Physical limit of prediction for chaotic motion of three-body problem
• Collisionless periodic orbits in the free-fall three-body problem
• Gravitational wave forms, polarizations, response functions and energy losses of triple systems in Einstein-Aether theory
• On the probability of finding a nonphysical solution through shadowing
• Ultra-chaos: an insurmountable objective obstacle of reproducibility and replicability
• Angular momentum and topological dependence of Kepler's Third Law in the Broucke-Hadjidemetriou-Hénon family of periodic three-body orbits
• A comment on "Computational periodicity as observed in a simple system," by Edward N. Lorenz (2006a)
• Kepler's third law of n-body periodic orbits in a Newtonian gravitation field
• On the inherent self-excited macroscopic randomness of chaotic three-body system
• One family of 13315 stable periodic orbits of the non-hierarchical unequal-mass triple system
• Chaotic dynamics in the planar gravitational many-body problem with rigid body rotations

Cited by in corpus (10)

• Large-scale influence of numerical noises as artificial stochastic disturbances on a sustained turbulence
• Is a direct numerical simulation (DNS) of Navier-Stokes equations with small enough grid spacing and time-step definitely reliable/correct?
• Noise-expansion cascade: an origin of randomness of turbulence
• Modeling the Time Evolution of Compact Binary Systems with Machine Learning
• Clean numerical simulation (CNS) of three-dimensional turbulent Kolmogorov flow
• A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
• Quantum implicit representation of vortex filaments in turbulence
• An adaptive symplectic integrator for gravitational dynamics
• Rydberg excitons in cuprous oxide: A two-particle system with classical chaos
• LieDetect: Detection of representation orbits of compact Lie groups from point clouds