Paper detail

Estimating the Photometric Redshifts of Galaxies and QSOs Using Regression Techniques in Machine Learning

Measuring distances of cosmological sources such as galaxies, stars and quasars plays an increasingly critical role in modern cosmology. Obtaining the optical spectrum and consequently calculating the redshift as a distance indicator could instantly classify these objects. As long as spectroscopic observations are not available for many galaxies and the process of measuring the redshift is time-consuming and infeasible for large samples, machine learning (ML) approaches could be applied to determine the redshifts of galaxies from different features including their photometric colors. In this paper, by using the flux magnitudes from the Sloan Digital Sky Survey (SDSS) catalog, we develop two ML regression algorithms (Decision Tree and Random Forest) for estimating the redshifts taking color indices as input features. We find that the Random Forest algorithm produces the optimum result for the redshift prediction, and it will be further improved when the dataset is limited to a subset with z $\le$ 2 giving the normalised standard deviation $\overline{ΔZ}_{\text {norm}}=0.005$ and the standard deviation $σ_{Δz}=0.12$. This work shows a great potential of using the ML approach to determine the photometric redshifts of distant sources.