A Bayesian neural network predicts the dissolution of compact planetary systems

TL;DR

This paper introduces a Bayesian neural network that accurately predicts the timing of instability in compact planetary systems, outperforming existing methods and generalizing well across different configurations, with fast computation and confidence intervals.

Contribution

A novel deep learning architecture that learns instability metrics from raw data, providing accurate, fast, and generalizable predictions with uncertainty estimates.

Findings

Predicts planetary system instability times more accurately than analytical methods.

Generalizes well to non-resonant and higher multiplicity systems.

Computes predictions up to five orders of magnitude faster than numerical simulations.

Abstract

Despite over three hundred years of effort, no solutions exist for predicting when a general planetary configuration will become unstable. We introduce a deep learning architecture to push forward this problem for compact systems. While current machine learning algorithms in this area rely on scientist-derived instability metrics, our new technique learns its own metrics from scratch, enabled by a novel internal structure inspired from dynamics theory. Our Bayesian neural network model can accurately predict not only if, but also when a compact planetary system with three or more planets will go unstable. Our model, trained directly from short N-body time series of raw orbital elements, is more than two orders of magnitude more accurate at predicting instability times than analytical estimators, while also reducing the bias of existing machine learning algorithms by nearly a factor of three. Despite being trained on compact resonant and near-resonant three-planet configurations, the model demonstrates robust generalization to both non-resonant and higher multiplicity configurations, in the latter case outperforming models fit to that specific set of integrations. The model computes instability estimates up to five orders of magnitude faster than a numerical integrator, and unlike previous efforts provides confidence intervals on its predictions. Our inference model is publicly available in the SPOCK package, with training code open-sourced.