Publication detail

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

KOSIBA, M. BURGET, L.

Original Title

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

Type

journal article in Web of Science

Language

English

Original Abstract

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 XMM CLuster Archive Super Survey (X-CLASS) survey sample of galaxy cluster candidates, selected by a specially developed pipeline, the XAmin, tailored for extended source detection and characterization. Our data set contains 1707 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 1600 galaxy cluster candidates in total of which 404 overlap with the experts 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 90percent, 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.

Keywords

galaxies: clusters: general - methods: data analysis - techniques: image processing

Authors

KOSIBA, M.; BURGET, L.

Released

17. 6. 2020

ISBN

1365-2966

Periodical

Monthly Notices of the Royal Astronomical Society

Year of study

496

Number

4

State

United Kingdom of Great Britain and Northern Ireland

Pages from

4141

Pages to

4153

Pages count

13

URL

https://academic.oup.com/mnras/article-abstract/496/4/4141/5858922?redirectedFrom=fulltext

BibTex

@article{BUT168176,
  author="KOSIBA, M. and BURGET, L.",
  title="Multiwavelength classification of X-ray selected galaxy cluster candidates using convolutional neural networks",
  journal="Monthly Notices of the Royal Astronomical Society",
  year="2020",
  volume="496",
  number="4",
  pages="4141--4153",
  doi="10.1093/mnras/staa1723",
  issn="1365-2966",
  url="https://academic.oup.com/mnras/article-abstract/496/4/4141/5858922?redirectedFrom=fulltext"
}

Documents

kosiba_mnras2020_2006.05998.pdf