Predicting Planetary Instability

A Bayesian neural network predicts the dissolution of compact planetary systems

We introduce a deep learning architecture to predict when a compact planetary system with three or more planets will become unstable.Our model, trained directly from short n-body time series of raworbital 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.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.