Newton vs the machine: solving the chaotic three-body problem using deep neural networks

TL;DR

This paper demonstrates that deep neural networks can be trained to solve the chaotic three-body problem efficiently, providing accurate solutions much faster than traditional numerical methods, and enabling scalable simulations of complex astrophysical phenomena.

Contribution

The authors introduce a neural network approach trained on ensemble solutions to replace iterative numerical solvers for the three-body problem, achieving significant speedups.

Findings

Neural networks can accurately predict three-body dynamics within bounded time intervals.

The method is up to 100 million times faster than traditional solvers.

This approach enables scalable simulations for astrophysical research.

Abstract

Since its formulation by Sir Isaac Newton, the problem of solving the equations of motion for three bodies under their own gravitational force has remained practically unsolved. Currently, the solution for a given initialization can only be found by performing laborious iterative calculations that have unpredictable and potentially infinite computational cost, due to the system's chaotic nature. We show that an ensemble of solutions obtained using an arbitrarily precise numerical integrator can be used to train a deep artificial neural network (ANN) that, over a bounded time interval, provides accurate solutions at fixed computational cost and up to 100 million times faster than a state-of-the-art solver. Our results provide evidence that, for computationally challenging regions of phase-space, a trained ANN can replace existing numerical solvers, enabling fast and scalable simulations of many-body systems to shed light on outstanding phenomena such as the formation of black-hole binary systems or the origin of the core collapse in dense star clusters.