A Caltech Library Service

How to Find Variable Active Galactic Nuclei with Machine Learning

Faisst, Andreas L. and Prakash, Abhishek and Capak, Peter L. and Lee, Bomee (2019) How to Find Variable Active Galactic Nuclei with Machine Learning. Astrophysical Journal Letters, 881 (1). Art. No. L9. ISSN 2041-8213. doi:10.3847/2041-8213/ab3581.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Machine-learning (ML) algorithms will play a crucial role in studying the large data sets delivered by new facilities over the next decade and beyond. Here, we investigate the capabilities and limits of such methods in finding galaxies with brightness-variable active galactic nuclei (AGNs). Specifically, we focus on an unsupervised method based on self-organizing maps (SOM) that we apply to a set of nonparametric variability estimators. This technique allows us to maintain domain knowledge and systematics control while using all the advantages of ML. Using simulated light curves that match the noise properties of observations, we verify the potential of this algorithm in identifying variable light curves. We then apply our method to a sample of ~8300 WISE color-selected AGN candidates in Stripe 82, in which we have identified variable light curves by visual inspection. We find that with ML we can identify these variable classified AGN with a purity of 86% and a completeness of 66%, a performance that is comparable to that of more commonly used supervised deep-learning neural networks. The advantage of the SOM framework is that it enables not only a robust identification of variable light curves in a given data set, but it is also a tool to investigate correlations between physical parameters in multidimensional space—such as the link between AGN variability and the properties of their host galaxies. Finally, we note that our method can be applied to any time-sampled light curve (e.g., supernovae, exoplanets, pulsars, and other transient events).

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Faisst, Andreas L.0000-0002-9382-9832
Prakash, Abhishek0000-0003-4451-4444
Capak, Peter L.0000-0003-3578-6843
Lee, Bomee0000-0003-1954-5046
Additional Information:© 2019 The American Astronomical Society. Received 2019 June 24; revised 2019 July 23; accepted 2019 July 24; published 2019 August 6. We thank the anonymous referee for the useful comments that improved this paper. We also thank J. Tan for proofreading the manuscript. This work was supported by Joint Survey Processing (JSP) at IPAC/Caltech, which is aimed at combined analysis of Euclid, LSST, and WFIRST. This work was supported by Joint Survey Processing (JSP) at IPAC/Caltech which was funded by NASA grant 80NM0018F0803. This publication makes use of data products from the Wide-field Infrared Survey Explorer, which is a joint project of the University of California, Los Angeles, and the Jet Propulsion Laboratory/California Institute of Technology, funded by the National Aeronautics and Space Administration.
Group:Infrared Processing and Analysis Center (IPAC)
Funding AgencyGrant Number
Infrared Processing and Analysis Center (IPAC)UNSPECIFIED
Subject Keywords:galaxies: active – galaxies: evolution – galaxies: photometry – methods: data analysis
Issue or Number:1
Record Number:CaltechAUTHORS:20190806-125453442
Persistent URL:
Official Citation:Andreas L. Faisst et al 2019 ApJL 881 L9
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:97673
Deposited By: Tony Diaz
Deposited On:07 Aug 2019 15:02
Last Modified:16 Nov 2021 17:33

Repository Staff Only: item control page