Machine learning benchmarks predict chaotic three-body system behavior

Benchmarking Machine Learning for Chaotic Three-Body Dynamics in Astrophysics

Machine Learning

Summary

Predicting how three objects move under gravity is very hard because their paths can change unpredictably. The authors tested different machine learning methods to see how well they can guess whether three objects will stay stable or fly apart, and how well they can predict their paths over time. They found that machine learning can predict if the system will stay stable early on, but accurately forecasting the exact paths far into the future remains a challenge. They also compared their machine learning results to traditional astrophysics methods.

What this means in practice

  • For space mission planners: Assess stability of triple orbital systems early on to inform mission trajectory safety decisions using machine learning models.
  • For game physics developers: Improve predictive models for chaotic multi-body interactions to enhance realism in space simulation games and training environments.

Authors

Sheng Wan, Pavan Vynatheya, Duo Xu, Li Kevin Wenliang, Ye Zhu

Abstract

Machine learning (ML) and generative AI have recently made impressive progress in understanding physics. We explore a hierarchy of prediction problems stemming from chaotic three-body systems and benchmark existing ML approaches, including general-purpose prediction algorithms and those that build on top of foundational physics models. We first simulate the trajectories of triple systems near the critical boundary of stable/unstable initial conditions. We then design a hierarchy of learning tasks, focusing mainly on two broad problems: stability prediction and trajectory prediction. The former classifies whether a given triple system has diverged or not up to a specific horizon, while the latter predicts the exact trajectory, both given suitable input features. We benchmark a range of ML approaches, from simple regression methods to state-of-the-art foundational physics models, across these tasks, and compare them against astrophysical methods such as the Mardling-Aarseth stability criterion. Our experiments reveal a clear order of task difficulties in chaotic three-body dynamics: early dynamics enable strong stability prediction, while precise long-horizon trajectory forecasting remains difficult. Code and dataset are publicly available at https://github.com/Simonwan03/ThreeBodyMLBench.