Machine-learning Classifiers for Intermediate Redshift Emission-line Galaxies

Abstract

Classification of intermediate redshift (z = 0.3-0.8) emission line galaxies as star-forming galaxies, composite galaxies, active galactic nuclei (AGN), or low-ionization nuclear emission regions (LINERs) using optical spectra alone was impossible because the lines used for standard optical diagnostic diagrams: [N II], Hα, and [S II] are redshifted out of the observed wavelength range. In this work, we address this problem using four supervised machine learning classification algorithms: k-nearest neighbors (KNN), support vector classifier (SVC), random forest (RF), and a multi-layer perceptron (MLP) neural network. For input features, we use properties that can be measured from optical galaxy spectra out to z < 0.8-[O III]/Hβ, [O II]/Hβ, [O III] line width, and stellar velocity dispersion-and four colors (u − g, g − r, r − i, and i − z) corrected to z = 0.1. The labels for the low redshift emission line galaxy training set are determined using standard optical diagnostic diagrams. RF has the best area under curve (AUC) score for classifying all four galaxy types, meaning highest distinguishing power. Both the AUC scores and accuracies of the other algorithms are ordered as MLP>SVC>KNN. The classification accuracies with all eight features (and the four spectroscopicallydetermined features only) are 93.4% (92.3%) for star-forming galaxies, 69.4% (63.7%) for composite galaxies, 71.8% (67.3%) for AGNs, and 65.7% (60.8%) for LINERs. The stacked spectrum of galaxies of the same type as determined by optical diagnostic diagrams at low redshift and RF at intermediate redshift are broadly consistent. Our publicly available code a and trained models will be instrumental for classifying emission line galaxies in upcoming wide-field spectroscopic surveys.

Predicting the redshift of gamma-ray loud AGNs using Supervised Machine Learning: Part 2

“…This can, in turn, enhance our knowledge about the cosmic evolution of blazars (Singal et al 2012(Singal et al , 2014Singal 2015;Singal et al 2013a;Chiang et al 1995;Ackermann et al 2015;Singal et al 2013b;Ackermann et al 2012), the structure of the magnetic field in the intergalactic medium, (Marcotulli et al 2020;Venters & Pavlidou 2013;Fermi-LAT Collaboration et al 2018) as well as constraining cosmological parameters (Domínguez et al 2019;Petrosian 1976;Singal et al 2013b). In recent years the number of studies focusing on photometric redshift estimation of high redshift AGN, using a machine learning (MLapproach, has increased significantly (Jones & Singal 2017;Cavuoti et al 2014;Fotopoulou & Paltani 2018;Logan & Fotopoulou 2020;Yang et al 2017;Zhang et al 2019;Curran 2020;Nakoneczny et al 2020;Pasquet-Itam & Pasquet 2018;Jones & Singal 2017). This is primarily due to the availability of large data sets from all-sky surveys like the Sloan Digital Sky Survey (SDSS) (Aihara et al 2011) and Wide-field Infrared Survey Explorer (WISE) (Brescia et al 2019;Ilbert et al 2008;Hildebrandt et al 2010;Brescia et al 2013;Wright et al 2010;D'Isanto & Polsterer 2018).…”

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

“…These methods include leveraging training sets 6 , utilizing template spectra for comparisons 7 and mostly template fitting methods 8 . Additionally, for over a decade, cosmologists have used ML techniques based on neural networks and regression algorithms to determine photometric redshifts 9 . In an attempt to establish a quantitative approach towards the performance of Random Forests, Carliles et al 2010 concludes that in contrast to other regression techniques, Random Forest regression overcomes several vital weaknesses 10 .…”

Predicting the redshift of gamma-ray loud AGNs using supervised machine learning

“…In the current literature, multiple works exist which focus on extracting reliable photometric redshift of AGNs (Cavuoti et al 2014;Fotopoulou & Paltani 2018;Logan & Fotopoulou 2020;Yang et al 2017;Zhang et al 2019;Curran 2020;Nakoneczny et al 2020;Pasquet-Itam & Pasquet 2018;Jones & Singal 2017). In the current blazar literature, a lot of effort has also been placed in classifying blazars of uncertain type (e.g., Chiaro et al 2016;Kang et al 2019) and unidentified Fermi objects (e.g., Liodakis & Blinov 2019).…”