Search

There are several supervised machine learning methods used for the application of automated morphological classification of galaxies; however, there has not yet been a clear comparison of these different methods using imaging data, or an investigation for maximizing their effectiveness. We carry out a comparison between several common machine learning methods for galaxy classification [Convolutional Neural Network (CNN), K-nearest neighbour, logistic regression, Support Vector Machine, Random Forest, and Neural Networks] by using Dark Energy Survey (DES) data combined with visual classifications from the Galaxy Zoo 1 project (GZ1). Our goal is to determine the optimal machine learning methods when using imaging data for galaxy classification. We show that CNN is the most successful method of these ten methods in our study. Using a sample of ∼2800 galaxies with visual classification from GZ1, we reach an accuracy of ∼0.99 for the morphological classification of ellipticals and spirals. The further investigation of the galaxies that have a different ML and visual classification but with high predicted probabilities in our CNN usually reveals the incorrect classification provided by GZ1. We further find the galaxies having a low probability of being either spirals or ellipticals are visually lenticulars (S0), demonstrating that supervised learning is able to rediscover that this class of galaxy is distinct from both ellipticals and spirals. We confirm that ∼2.5 per cent galaxies are misclassified by GZ1 in our study. After correcting these galaxies' labels, we improve our CNN performance to an average accuracy of over 0.99 (accuracy of 0.994 is our best result). [ABSTRACT FROM AUTHOR]

The Emission Line Galaxy survey made by the Dark Energy Spectroscopic Instrument (DESI) survey will be created from five passes of the instrument on the sky. On each pass, the constrained mobility of the ends of the fibres in the DESI focal plane means that the angular distribution of targets that can be observed is limited. Thus, the clustering of samples constructed using a limited number of passes will be strongly affected by missing targets. In two recent papers, we showed how the effect of missing galaxies can be corrected when calculating the correlation function using a weighting scheme for pairs. Using mock galaxy catalogues we now show that this method provides an unbiased estimator of the true correlation function for the DESI survey after any number of passes. We use multiple mocks to determine the expected errors given one to four passes, compared to an idealized survey observing an equivalent number of randomly selected targets. On BAO scales, we find that the error is a factor of 2 worse after one pass, but that after three or more passes, the errors are very similar. Thus, we find that the fibre assignment strategy enforced by the design of DESI will not affect the cosmological measurements to be made by the survey, and can be removed as a potential risk for this experiment. [ABSTRACT FROM AUTHOR]