SpArcFiRe: Enhancing Spiral Galaxy Recognition using Arm Analysis and Random Forests

Abstract

Automated machine classifications of galaxies are necessary because the size of upcoming surveys will overwhelm human volunteers. We improve upon existing machine classification methods by adding the output of SpArcFiRe to the inputs of a machine learning model. We use the human classifications from Galaxy Zoo 1 (GZ1) to train a random forest of decision trees to reproduce the human vote distributions of the Spiral class. We prefer the random forest model over other black box models like neural networks because it allows us to trace post hoc the precise reasoning behind the classification of each galaxy. We find that, across a sample of 470,000 Sloan galaxies that are large enough that details could be seen if they were there, the combination of SpArcFiRe outputs with existing SDSS features provides a better machine classification than either one alone on comparison to Galaxy Zoo 1. We suggest that adding SpArcFiRe outputs as features to any machine learning algorithm will likely improve its performance.

Asymmetry in Galaxy Spin Directions—Analysis of Data from DES and Comparison to Four Other Sky Surveys

“…An analysis based on automatic annotation [207] using the SPARCFIRE algorithm [208,209] showed that the spin directions of galaxies annotated by Galaxy Zoo are distributed randomly. When just applying the automatic annotation to galaxies annotated as spiral by Galaxy Zoo, the asymmetry was statistically significant, with 2.52σ or stronger.…”

Asymmetry in Galaxy Spin Directions -- Analysis of Data from DES and Comparison to Four Other Sky Surveys

“…An analysis based on automatic annotation [211] using the SPARCFIRE algorithm [212,213] showed that the spin directions of galaxies annotated by Galaxy Zoo are distributed randomly. When just applying the automatic annotation to galaxies annotated as spiral by Galaxy Zoo, the asymmetry was statistically significant, with 2.52σ or stronger.…”

A catalog of broad morphology of Pan-STARRS galaxies based on deep learning

“…The use of machine learning provided more effective methods for the purpose of galaxy image classification (Shamir 2009;Huertas-Company et al 2009;Banerji et al 2010;Shamir et al 2013;Schutter and Shamir 2015;Kuminski et al 2014;Dieleman et al 2015;Hocking et al 2017;Kuminski and Shamir 2018;Silva et al 2018), and the use of such methods also provided computer-generated catalogs of galaxy morphology (Huertas-Company et al 2010;Simard et al 2011;Shamir and Wallin 2014;Kuminski and Shamir 2016;Huertas-Company et al 2015a,b;Timmis and Shamir 2017;Paul et al 2018;Shamir 2019). Automatic annotation methods were also tested on Pan-STARRS data by using the photometric measurements of colors and moments, classified by a Random Forest classifier to achieve a considerable accuracy of ∼ 89% (Baldeschi et al 2020).…”