Multiwavelength classification of X-ray selected galaxy cluster candidates using convolutional neural networks

Matej Kosiba (1, 2) , Maggie Lieu (2, 3) , Bruno Altieri (2) , Nicolas Clerc (4) , Lorenzo Faccioli (5) , Sarah Kendrew (6) , Ivan Valtchanov (7) , Tatyana Sadibekova (8) , Marguerite Pierre (5) , Filip Hroch (1) , Norbert Werner (9, 1, 10) , Lukáš Burget (11) , Christian Garrel (5) , Elias Koulouridis (5, 12) , Evelina Gaynullina (8) , Mona Molham (13) , Miriam E. Ramos-Ceja (14) , Alina Khalikova (8)

1 SCI / MUNI - Faculty of Science [Brno]
2 ESAC - European Space Astronomy Centre
3 UON - University of Nottingham, UK
4 IRAP - Institut de recherche en astrophysique et planétologie
5 AIM (UMR_7158 / UMR_E_9005 / UM_112) - Astrophysique Interprétation Modélisation
6 STSci - Space Telescope Science Institute
7 Telespazio
8 Ulugh Beg Astronomical Institute
9 ELTE - Eötvös Loránd University
10 Hiroshima University
11 FIT / BUT - Faculty of Information Technology [Brno]
12 NOA - National Observatory of Athens
13 NRIAG - National Research Institute of Astronomy and Geophysics [Helwan]
14 MPE - Max Planck Institute for Extraterrestrial Physics

Galaxy clusters appear as extended sources in XMM-Newton images, but not all extended sources are clusters. So, their proper classification requires visual inspection with optical images, which is a slow process with biases that are almost impossible to model. We tackle this problem with a novel approach, using convolutional neural networks (CNNs), a state-of-the-art image classification tool, for automatic classification of galaxy cluster candidates. We train the networks on combined XMM-Newton X-ray observations with their optical counterparts from the all-sky Digitized Sky Survey. Our data set originates from the X-CLASS survey sample of galaxy cluster candidates, selected by a specially developed pipeline, the XAmin, tailored for extended source detection and characterisation. Our data set contains 1 707 galaxy cluster candidates classified by experts. Additionally, we create an official Zooniverse citizen science project, The Hunt for Galaxy Clusters, to probe whether citizen volunteers could help in a challenging task of galaxy cluster visual confirmation. The project contained 1 600 galaxy cluster candidates in total of which 404 overlap with the expert's sample. The networks were trained on expert and Zooniverse data separately. The CNN test sample contains 85 spectroscopically confirmed clusters and 85 non-clusters that appear in both data sets. Our custom network achieved the best performance in the binary classification of clusters and non-clusters, acquiring accuracy of 90 %, averaged after 10 runs. The results of using CNNs on combined X-ray and optical data for galaxy cluster candidate classification are encouraging and there is a lot of potential for future usage and improvements.

Domaines: Astrophysique [astro-ph]

Matej Kosiba, Maggie Lieu, Bruno Altieri, Nicolas Clerc, Lorenzo Faccioli, et al.. Multiwavelength classification of X-ray selected galaxy cluster candidates using convolutional neural networks. Monthly Notices of the Royal Astronomical Society, 2020, ⟨10.1093/mnras/staa1723⟩. ⟨hal-02866796⟩