A Bayesian neural network predicts the dissolution of compact planetary systems

01/11/2021
by   Miles Cranmer, et al.
271

Despite over three hundred years of effort, no solutions exist for predicting when a general planetary configuration will become unstable. We introduce a deep learning architecture to push forward this problem for compact systems. While current machine learning algorithms in this area rely on scientist-derived instability metrics, our new technique learns its own metrics from scratch, enabled by a novel internal structure inspired from dynamics theory. Our Bayesian neural network model can accurately predict not only if, but also when a compact planetary system with three or more planets will go unstable. Our model, trained directly from short N-body time series of raw orbital 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. Despite being trained on compact resonant and near-resonant three-planet configurations, the model demonstrates robust generalization to both non-resonant and higher multiplicity configurations, in the latter case outperforming models fit to that specific set of integrations. 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. Our inference model is publicly available in the SPOCK package, with training code open-sourced.

READ FULL TEXT
research
11/25/2014

Efficient Algorithms for Bayesian Network Parameter Learning from Incomplete Data

We propose an efficient family of algorithms to learn the parameters of ...
research
06/24/2022

Predicting the Stability of Hierarchical Triple Systems with Convolutional Neural Networks

Understanding the long-term evolution of hierarchical triple systems is ...
research
12/31/2020

Neural Network Approximations for Calabi-Yau Metrics

Ricci flat metrics for Calabi-Yau threefolds are not known analytically....
research
11/16/2021

Deep Distilling: automated code generation using explainable deep learning

Human reasoning can distill principles from observed patterns and genera...
research
07/05/2022

Machine Learning Model Sizes and the Parameter Gap

We study trends in model size of notable machine learning systems over t...
research
10/18/2019

Machine learning Calabi-Yau metrics

We apply machine learning to the problem of finding numerical Calabi-Yau...
research
05/20/2021

On planetary systems as ordered sequences

A planetary system consists of a host star and one or more planets, arra...

Please sign up or login with your details

Forgot password? Click here to reset