An_2018_ApJ_862_101.pdf (1.68 MB)
Download file

A Machine-learning Method for Identifying Multiwavelength Counterparts of Submillimeter Galaxies: Training and Testing Using AS2UDS and ALESS

Download (1.68 MB)
journal contribution
posted on 25.07.2019, 14:57 by FX An, SM Stach, I Smail, AM Swinbank, O Almaini, C Simpson, W Hartley, DT Maltby, RJ Ivison, V Arumugam, JL Wardlow, EA Cooke, B Gullberg, AP Thomson, C-C Chen, JM Simpson, JE Geach, D Scott, JS Dunlop, D Farrah, P van der Werf, AW Blain, C Conselice, M Michalowski, SC Chapman, KEK Coppin
We describe the application of supervised machine-learning algorithms to identify the likely multiwavelength counterparts to submillimeter sources detected in panoramic, single-dish submillimeter surveys. As a training set, we employ a sample of 695 (S 870μm gsim 1 mJy) submillimeter galaxies (SMGs) with precise identifications from the ALMA follow-up of the SCUBA-2 Cosmology Legacy Survey's UKIDSS-UDS field (AS2UDS). We show that radio emission, near-/mid-infrared colors, photometric redshift, and absolute H-band magnitude are effective predictors that can distinguish SMGs from submillimeter-faint field galaxies. Our combined radio + machine-learning method is able to successfully recover ~85% of ALMA-identified SMGs that are detected in at least three bands from the ultraviolet to radio. We confirm the robustness of our method by dividing our training set into independent subsets and using these for training and testing, respectively, as well as applying our method to an independent sample of ~100 ALMA-identified SMGs from the ALMA/LABOCA ECDF-South Survey (ALESS). To further test our methodology, we stack the 870 μm ALMA maps at the positions of those K-band galaxies that are classified as SMG counterparts by the machine learning but do not have a >4.3σ ALMA detection. The median peak flux density of these galaxies is S 870μm = (0.61 ± 0.03) mJy, demonstrating that our method can recover faint and/or diffuse SMGs even when they are below the detection threshold of our ALMA observations. In future, we will apply this method to samples drawn from panoramic single-dish submillimeter surveys that currently lack interferometric follow-up observations to address science questions that can only be tackled with large statistical samples of SMGs.


F.X.A. acknowledges support from the China Scholarship Council for studying two years at Durham University. All Durham coauthors acknowledge STFC support through grant ST/P000541/1. I.R.S., B.G., and E.A.C. acknowledge the ERC Advanced Grant DUSTYGAL (321334). I.R.S. also acknowledges a Royal Society/Wolfson Merit Award. F.X.A. also acknowledges support from the National Key Research and Development Program of China (No. 2017YFA0402703) and NSFC grant (11773076). J.L.W. acknowledges the support of an Ernest Rutherford Fellowship. J.E.G. acknowledges the Royal Society. F.X.A acknowledges Ryley Hill for helpful discussions about the machine-learning algorithms. We thank the staff at UKIRT for their efforts in ensuring the success of the UDS project. The James Clerk Maxwell Telescope has historically been operated by the Joint Astronomy Centre on behalf of the Science and Technology Facilities Council of the United Kingdom, the National Research Council of Canada, and the Netherlands Organisation for Scientific Research. Additional funds for the construction of SCUBA-2 were provided by the Canada Foundation for Innovation. This paper makes use of the following ALMA data: ADS/JAO.ALMA#2012.1.00090.S, 2015.1.01528.S, and 2016.1.00434.S. ALMA is a partnership of the ESO (representing its member states), NSF (USA), and NINS (Japan), together with the NRC (Canada), NSC and ASIAA (Taiwan), and KASI (Republic of Korea), in cooperation with the Republic of Chile. The Joint ALMA Observatory is operated by the ESO, AUI/NRAO, and NAOJ.



Astrophysical Journal, 2018, 862 (2)

Author affiliation

/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Physics and Astronomy


VoR (Version of Record)

Published in

Astrophysical Journal


American Astronomical Society, IOP Publishing





Acceptance date


Copyright date


Available date


Publisher version