Reionization Models Classifier using 21cm Map Deep Learning. Issue Volume 12:Issue S333(2017) (8th May 2018)

• Record Type: Journal Article
• Authors: Hassan, Sultan; Liu, Adrian; Kohn, Saul; Aguirre, James E.; Plante, Paul La; Lidz, Adam
• Editors: Jelić, V.; van der Hulst, T.
• Is Part Of: Proceedings of the International Astronomical Union. Volume 12:Issue S333(2017)
• Page Start: 47
• Page End: 51
• Publication Date: 2018-05-08
• Subjects: methods: data analysis, -- galaxies: intergalactic medium, -- abundances, -- formation, -- evolution, -- quasars: general, -- cosmology: early universe; Astronomy -- Congresses; Astronomy -- Periodicals; 520
• DOI: 10.1017/S1743921317010833
• Languages: English
• ISSNs: 1743-9213

Abstract

Abstract: Next-generation 21cm observations will enable imaging of reionization on very large scales. These images will contain more astrophysical and cosmological information than the power spectrum, and hence providing an alternative way to constrain the contribution of different reionizing sources populations to cosmic reionization. Using Convolutional Neural Networks, we present a simple network architecture that is sufficient to discriminate between Galaxy-dominated versus AGN-dominated models, even in the presence of simulated noise from different experiments such as the HERA and SKA.