Machine Learning Classification of Kuiper Belt Populations

Abstract

In the outer solar system, the Kuiper Belt contains dynamical sub-populations sculpted by a combination of planet formation and migration and gravitational perturbations from the present-day giant planet configuration. The subdivision of observed Kuiper Belt objects (KBOs) into different dynamical classes is based on their current orbital evolution in numerical integrations of their orbits. Here we demonstrate that machine learning algorithms are a promising tool for reducing both the computational time and human effort required for this classification. Using a Gradient Boosting Classifier, a type of machine learning regression tree classifier trained on features derived from short numerical simulations, we sort observed KBOs into four broad, dynamically distinct populations - classical, resonant, detached, and scattering - with a >97 per cent accuracy for the testing set of 542 securely classified KBOs. Over 80 per cent of these objects have a $>3\sigma$ probability of class membership, indicating that the machine learning method is classifying based on the fundamental dynamical features of each population. We also demonstrate how, by using computational savings over traditional methods, we can quickly derive a distribution of class membership by examining an ensemble of object clones drawn from the observational errors. We find two major reasons for misclassification: inherent ambiguity in the orbit of the object - for instance, an object that is on the edge of resonance - and a lack of representative examples in the training set. This work provides a promising avenue to explore for fast and accurate classification of the thousands of new KBOs expected to be found by surveys in the coming decade.

arXiv commentAccepted for publication in MNRAS. 13 pages, 14 figures. Companion notebooks and data for this work can be found at https://github.com/rsmullen/KBO_Classifier

References in corpus (23)

• Scikit-learn: Machine Learning in Python
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Evidence for an extended scattered disk
• The Evidence for Slow Migration of Neptune from the Inclination Distribution of Kuiper Belt Objects
• OSSOS. VII. 800+ trans-Neptunian objects - the complete data release
• Orbit Fitting and Uncertainties for Kuiper Belt Objects
• Sedna and the Oort Cloud Around a Migrating Sun
• The solar nebula origin of (486958) Arrokoth, a primordial contact binary in the Kuiper belt
• Reassessing the formation of the inner Oort cloud in an embedded star cluster
• Resonance sticking in the scattered disk
• Physics enhanced neural networks predict order and chaos
• A Machine Learns to Predict the Stability of Tightly Packed Planetary Systems
• Droplets I: Pressure-Dominated Sub-0.1 pc Coherent Structures in L1688 and B18
• The curiously warped mean plane of the Kuiper belt
• Col-OSSOS: z Band Photometry Reveals Three Distinct TNO Surface Types
• A machine learns to predict the stability of circumbinary planets
• OSSOS: XIII. Fossilized Resonant Dropouts Tentatively Confirm Neptune's Migration was Grainy and Slow
• Trans-Neptunian Objects Transiently Stuck in Neptune's Mean Motion Resonances: Numerical simulations of the current population
• Resonant Kuiper Belt Objects -- a Review
• Estimating the Mass of the Local Group using Machine Learning Applied to Numerical Simulations
• OSSOS IXX: Testing Early Solar System Dynamical Models using OSSOS Centaur Detections
• The Warped Plane of the Classical Kuiper Belt
• Large Synoptic Survey Telescope Solar System Science Roadmap

Cited by in corpus (6)

• Machine Learning applied to asteroid dynamics
• Free Inclinations for Transneptunian Objects in the Main Kuiper Belt
• Machine learning prediction for mean motion resonance behaviour -- The planar case
• A von Mises-Fisher Distribution for the Orbital Poles of the Plutinos
• A Measurement of the Kuiper Belt's Mean Plane From Objects Classified By Machine Learning
• Peculiar orbits and asymmetries in extreme trans-Neptunian space