Understanding the Impact of Semi-numeric Reionization Models when using CNNs

Abstract

Interpreting 21cm measurements from current and upcoming experiments like HERA and the SKA will provide new scientific insights and exciting implications for astrophysics and cosmology regarding the Epoch of Reionization (EoR). Several recent works have proposed using machine learning methods, such as convolutions neural networks (CNNs), to analyze images of reionization generated by these experiments since they could take full advantage of information contained in the image. Generally, these studies have used only a single semi-numeric method to generate the input 21cm data. In this work, we investigate the extent to which training CNNs for reionization applications depends on the underlying semi-numeric models. Working in the context of predicting CMB optical depth from 21cm images, we compare networks trained on similar datasets from 21cmfast and zreion, two widely used semi-numeric reionization methods. We show that neural networks trained on input data from only one model produce poor predictions on data from the other model. Satisfactory results are only achieved when both models are included in the training data. This finding has important implications for future analyses on observation data, and encourages the use of multiple models to produce images that capture the full complexity of the EoR.

33 pages, 18 figures

References in corpus (13)

• Observational constraints on Cosmic Reionization
• Efficient Simulations of Early Structure Formation and Reionization
• The morphology of HII regions during reionization
• Line Emitting Galaxies Beyond a Redshift of 7: An Improved Method for Estimating the Evolving Neutrality of the Intergalactic Medium
• Inferences on the Timeline of Reionization at z~8 From the KMOS Lens-Amplified Spectroscopic Survey
• 21cmFAST v3: A Python-integrated C code forgenerating 3D realizations of the cosmic 21cm signal
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• The 21 cm-kSZ-kSZ Bispectrum during the Epoch of Reionization
• The Effect of Pair Cascades on the High-Energy Spectral Cutoff in Gamma-Ray Bursts
• Constraining the Reionization History using Bayesian Normalizing Flows
• Single Shot MC Dropout Approximation
• Deep-Learning Study of the 21cm Differential Brightness Temperature During the Epoch of Reionization
• Contribution of Radio Halos to the Foreground for SKA EoR Experiments