Photometric Redshift Analysis using Supervised Learning Algorithms and Deep Learning

Abel Yang,De Wei, Kenny Chong

doi:10.1051/epjconf/201920609006

Abstract

We present a catalogue of galaxy photometric redshifts for the Sloan Digital Sky Survey (SDSS) Data Release 12. We use various supervised learning algorithms to calculate redshifts using photometric attributes on a spectroscopic training set. Two training sets are analysed in this paper. The first training set consists of 995,498 galaxies with redshifts up to z ≈ 0.8. On the first training set, we achieve a cost function of 0.00501 and a root mean squared error value of 0.0707 using the XGBoost algorithm. We achieved an outlier rate of 2.1% and 86.81%, 95.83%, 97.90% of our data points lie within one, two, and three standard deviation of the mean respectively. The second training set consists of 163,140 galaxies with redshifts up to z ≈ 0.2 and is merged with the Galaxy Zoo 2 full catalog. We also experimented on convolutional neural networks to predict five morphological features (Smooth, Features/Disk, Star, Edge-on, Spiral). We achieve a root mean squared error of 0.117 when validated against an unseen dataset with over 200 epochs. Morphological features from the Galaxy Zoo, trained with photometric features are found to consistently improve the accuracy of photometric redshifts.

Highlights

Redshifts of celestial objects have been a vital component in the field of astronomy and we use them to measure various attributes such as the rotation of the galaxy and the distance from us
While spectroscopy is effective in determining redshifts of galaxies, it is time consuming and expensive and not scalable to map a spectroscopic redshift for every celestial object
We train them on an individual tree and use standard deviation reduction to determine the quality of every split

Summary

Overview and Methodology

Redshifts of celestial objects have been a vital component in the field of astronomy and we use them to measure various attributes such as the rotation of the galaxy and the distance from us. While spectroscopy is effective in determining redshifts of galaxies, it is time consuming and expensive and not scalable to map a spectroscopic redshift for every celestial object. The process is repeated when building the tree down to the leaf node We use this method to find the more important features. The average results of the cost function are recorded

Results

Performance of Galaxy Zoo 2 Features

Deep Learning