Quadtree features for machine learning on CMDs

TL;DR

This paper introduces a quadtree-based feature extraction method for color-magnitude diagrams, enabling effective machine learning analysis of star clusters in large astronomical surveys.

Contribution

It presents a novel quadtree-like featurization technique for CMDs that handles variable star counts and permutation invariance without manual intervention.

Findings

Features predict distance modulus with 0.33 dex scatter.

Features predict metallicity with 0.16 dex scatter.

Method is robust to noise and contamination.

Abstract

The upcoming facilities like the Vera C. Rubin Observatory will provide extremely deep photometry of thousands of star clusters to the edge of the Galaxy and beyond, which will require adequate tools for automatic analysis, capable of performing tasks such as the characterization of a star cluster through the analysis of color-magnitude diagrams (CMDs). The latter are essentially point clouds in N-dimensional space, with the number of dimensions corresponding to the photometric bands employed. In this context, machine learning techniques suitable for tabular data are not immediately applicable to CMDs because the number of stars included in a given CMD is variable, and equivariance for permutations is required. To address this issue without introducing ad-hoc manipulations that would require human oversight, here we present a new CMD featurization procedure that summarizes a CMD by means of a quadtree-like structure through iterative partitions of the color-magnitude plane, extracting a fixed number of meaningful features of the relevant subregion from any given CMD. The present approach is robust to photometric noise and contamination and it shows that a simple linear regression on our features predicts distance modulus (metallicity) with a scatter of 0.33 dex (0.16 dex) in cross-validation.