English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  A deep learning approach to galaxy cluster X-ray masses

Ntampaka, M., ZuHone, J., Eisenstein, D., Nagai, D., Vikhlinin, A., Hernquist, L., et al. (2019). A deep learning approach to galaxy cluster X-ray masses. The Astrophysical Journal, 876(1): 82. doi:10.3847/1538-4357/ab14eb.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0003-AFAC-7 Version Permalink: http://hdl.handle.net/21.11116/0000-0003-AFAD-6
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Ntampaka, M., Author
ZuHone, J., Author
Eisenstein, D., Author
Nagai, D., Author
Vikhlinin, A., Author
Hernquist, L., Author
Marinacci, F., Author
Nelson, D.1, Author              
Pakmor, R.2, Author              
Pillepich, A., Author
Torrey, P., Author
Vogelsberger, M., Author
Affiliations:
1Galaxy Formation, MPI for Astrophysics, Max Planck Society, ou_2205643              
2Stellar Astrophysics, MPI for Astrophysics, Max Planck Society, ou_159882              

Content

show
hide
Free keywords: -
 Abstract: We present a machine-learning (ML) approach for estimating galaxy cluster masses from Chandra mock images. We utilize a Convolutional Neural Network (CNN), a deep ML tool commonly used in image recognition tasks. The CNN is trained and tested on our sample of 7896 Chandra X-ray mock observations, which are based on 329 massive clusters from the ${\text{}}{IllustrisTNG}$ simulation. Our CNN learns from a low resolution spatial distribution of photon counts and does not use spectral information. Despite our simplifying assumption to neglect spectral information, the resulting mass values estimated by the CNN exhibit small bias in comparison to the true masses of the simulated clusters (−0.02 dex) and reproduce the cluster masses with low intrinsic scatter, 8% in our best fold and 12% averaging over all. In contrast, a more standard core-excised luminosity method achieves 15%–18% scatter. We interpret the results with an approach inspired by Google DeepDream and find that the CNN ignores the central regions of clusters, which are known to have high scatter with mass.

Details

show
hide
Language(s):
 Dates: 2019-05-07
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.3847/1538-4357/ab14eb
Other: LOCALID: 3060330
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: The Astrophysical Journal
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Bristol, England : IOP Publishing LTD
Pages: - Volume / Issue: 876 (1) Sequence Number: 82 Start / End Page: - Identifier: ISSN: 1538-4357
CoNE: https://pure.mpg.de/cone/journals/resource/954922828215_3