Instability prediction in diverse planetary systems with machine learning

Machine learning has proven to be an invaluable tool for characterizing the stability of planets in planetary systems. In this work, we investigate the performance of a machine learning classifier on tightly-packed systems containing a rich diversity of planets, from Earths to Jupiters. Using information derived from short numerical simulations about a planet’s early orbital evolution and its relationship with the most massive planets in the system, we train a random forest classifier to predict instability with a > 88% accuracy. Our classifier relies on relative planet masses and the standard deviation of eccentricity for much of its predictive power. Most misclassified planets lie along a multi-dimensional boundary between stable and unstable planets, indicating that their early orbital evolution is ambiguous. The major reason for misclassification in this work is time-scale: because our classifier uses information from the very beginning of the simulations, it is blind to late time interactions that cause or prevent instability. Machine learning methods like those utilized in this work provide powerful tools to complement numerical simulations across a wide range of planetary architectures.