Reionization Models Classifier using 21cm Map Deep Learning

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.

Contributed talk for the IAU Symposium 333 "Peering towards Cosmic Dawn", Dubrovnik, October 2-6, 2017; to appear in the proceedings, eds. Vibor Jelic and Thijs van der Hulst [5 pages, 3 figures]

References in corpus (7)

• An Observational Determination of the Bolometric Quasar Luminosity Function
• Observational constraints on Cosmic Reionization
• Evidence of patchy hydrogen reionization from an extreme Ly$\alpha$ trough below redshift six
• Constraining the contribution of active galactic nuclei to reionisation
• Simulating the 21-cm signal from reionisation including non-linear ionisations and inhomogeneous recombinations
• The Reionization of Carbon
• Epoch of Reionisation 21cm Forecasting From MCMC-Constrained Semi-Numerical Models

Cited by in corpus (4)

• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• Likelihood-free Inference with Mixture Density Network
• Deconfusing intensity maps with neural networks