Predicting the Stability of Hierarchical Triple Systems with Convolutional Neural Networks

Abstract

The dynamical stability of hierarchical triple systems is a long-standing question in celestial mechanics and dynamical astronomy. Assessing the long-term stability of triples is challenging because it requires computationally expensive simulations. Here we propose a convolutional neural network model to predict the stability of equal-mass hierarchical triples by looking at their evolution during the first 5 × 105 inner binary orbits. We employ the regularized few-body code tsunami to simulate 5 × 106 hierarchical triples, from which we generate a large training and test data set. We develop 12 different network configurations that use different combinations of the triples’ orbital elements and compare their performances. Our best model uses six time series, namely, the semimajor axes ratio, the inner and outer eccentricities, the mutual inclination, and the arguments of pericenter. This model achieves excellent performance, with an area under the ROC curve score of over 95% and informs of the relevant parameters to study triple systems stability. All trained models are made publicly available, which allows predicting the stability of hierarchical triple systems 200 times faster than pure N-body methods.