Predicting the Stability of Hierarchical Triple Systems with Convolutional Neural Networks

TL;DR

This paper introduces a convolutional neural network model that predicts the stability of hierarchical triple systems from early orbital data, significantly reducing computational costs compared to traditional simulations.

Contribution

The study develops and compares twelve CNN configurations using orbital elements, achieving high accuracy and providing a fast, data-driven method for stability prediction of triple systems.

Findings

Best model achieves over 95% AUC.

Model predicts stability 200 times faster than N-body simulations.

Identifies key orbital parameters influencing stability.

Abstract

Understanding the long-term evolution of hierarchical triple systems is challenging due to its inherent chaotic nature, and it requires computationally expensive simulations. Here we propose a convolutional neural network model to predict the stability of hierarchical triples by looking at their evolution during the first $5 \times 10^5$ inner binary orbits. We employ the regularized few-body code TSUNAMI to simulate $5\times 10^6$ hierarchical triples, from which we generate a large training and test dataset. We develop twelve different network configurations that use different combinations of the triples' orbital elements and compare their performances. Our best model uses 6 time-series, namely, the semimajor axes ratio, the inner and outer eccentricities, the mutual inclination and the arguments of pericenter. This model achieves an area under the curve of over $95\%$ and informs of the relevant parameters to study triple systems stability. All trained models are made publicly available, allowing to predict the stability of hierarchical triple systems $200$ times faster than pure $N$-body methods.