English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The requirement that planetary systems be dynamically stable is often used tovet new discoveries or set limits on unconstrained masses or orbital elements.This is typically carried out via computationally expensive N-body simulations.We show that characterizing the complicated and multi-dimensional stabilityboundary of tightly packed systems is amenable to machine learning methods. Wefind that training an XGBoost machine learning algorithm on physicallymotivated features yields an accurate classifier of stability in packedsystems. On the stability timescale investigated ($10^7$ orbits), it is 3orders of magnitude faster than direct N-body simulations. Optimized machinelearning classifiers for dynamical stability may thus prove useful across thediscipline, e.g., to characterize the exoplanet sample discovered by theupcoming Transiting Exoplanet Survey Satellite (TESS). This proof of conceptmotivates investing computational resources to train algorithms capable ofpredicting stability over longer timescales and over broader regions of phasespace.

A Machine Learns to Predict the Stability of Tightly Packed Planetary Systems