Decision Tree Classifiers for Star/Galaxy Separation

TL;DR

This study evaluates 13 decision tree algorithms for star/galaxy classification in SDSS data, finding the Functional Tree algorithm offers superior completeness and low contamination, especially at faint magnitudes, outperforming existing classifiers.

Contribution

The paper systematically compares multiple decision tree algorithms for star/galaxy separation and identifies the Functional Tree as the most effective method.

Findings

Functional Tree achieves 85.2% completeness for 14≤r≤21

FT maintains >80% completeness at r>19 with ~2.5% contamination

FT classifier outperforms SDSS parametric, 2DPHOT, and Ball et al. classifiers

Abstract

We study the star/galaxy classification efficiency of 13 different decision tree algorithms applied to photometric objects in the Sloan Digital Sky Survey Data Release Seven (SDSS DR7). Each algorithm is defined by a set of parameters which, when varied, produce different final classification trees. We extensively explore the parameter space of each algorithm, using the set of $884,126$ SDSS objects with spectroscopic data as the training set. The efficiency of star-galaxy separation is measured using the completeness function. We find that the Functional Tree algorithm (FT) yields the best results as measured by the mean completeness in two magnitude intervals: $14\le r\le21$ ($85.2%$) and $r\ge19$ ($82.1%$). We compare the performance of the tree generated with the optimal FT configuration to the classifications provided by the SDSS parametric classifier, 2DPHOT and Ball et al. (2006). We find that our FT classifier is comparable or better in completeness over the full magnitude range $15\le r\le21$, with much lower contamination than all but the Ball et al. classifier. At the faintest magnitudes ($r>19$), our classifier is the only one able to maintain high completeness ($>$80%) while still achieving low contamination ($\sim2.5%$). Finally, we apply our FT classifier to separate stars from galaxies in the full set of $69,545,326$ SDSS photometric objects in the magnitude range $14\le r\le21$.