Analyzing the Stability of Non-coplanar Circumbinary Planets using Machine Learning

TL;DR

This paper investigates the orbital stability of non-coplanar circumbinary exoplanets using numerical simulations and machine learning, revealing key factors influencing stability and demonstrating the effectiveness of deep neural networks.

Contribution

It introduces a machine learning approach, especially deep neural networks, to predict the stability of circumbinary planets, improving speed and accuracy over traditional methods.

Findings

Larger orbital inclinations tend to increase stability.

Planet mass between Earth and Jupiter has little effect on stability.

Deep neural networks outperform other machine learning algorithms.

Abstract

Exoplanet detection in the past decade by efforts including NASA's Kepler and TESS missions has discovered many worlds that differ substantially from planets in our own Solar system, including more than 400 exoplanets orbiting binary or multi-star systems. This not only broadens our understanding of the diversity of exoplanets, but also promotes our study of exoplanets in the complex binary and multi-star systems and provides motivation to explore their habitability. In this study, we analyze orbital stability of exoplanets in non-coplanar circumbinary systems using a numerical simulation method, with which a large number of circumbinary planet samples are generated in order to quantify the effects of various orbital parameters on orbital stability. We also train a machine learning model that can quickly determine the stability of the circumbinary planetary systems. Our results indicate that larger inclinations of the planet tend to increase the stability of its orbit, but change in the planet's mass range between Earth and Jupiter has little effect on the stability of the system. In addition, we find that Deep Neural Networks (DNNs) have higher accuracy and precision than other machine learning algorithms.