Constraining the reionization history using deep learning from 21cm tomography with the Square Kilometre Array

Abstract

Upcoming 21cm surveys with the SKA1-LOW telescope will enable imaging of the neutral hydrogen distribution on cosmological scales in the early Universe. These surveys are expected to generate huge imaging datasets that will encode more information than the power spectrum. This provides an alternative unique way to constrain the reionization history, which might break the degeneracy in the power spectral analysis. Using Convolutional Neural Networks (CNN), we create a fast estimator of the neutral fraction from the 21cm maps that are produced by our large semi-numerical simulation. Our estimator is able to efficiently recover the neutral fraction ($x_{\mathrm{HI}}$) at several redshifts with a high accuracy of 99\% as quantified by the coefficient of determination $R^2$. Adding the instrumental effects from the SKA design slightly increases the loss function, but nevertheless we are still able to recover the neutral fraction with a similar high accuracy of 98\%, which is only 1 per cent less. While a weak dependence on redshift is observed, the accuracy increases rapidly with decreasing neutral fraction. This is due to the fact that the instrumental noise increases towards high redshift where the Universe is highly neutral. Our results show the promise of directly using 21cm-tomography to constrain the reionization history in a model independent way, complementing similar efforts, such as those of the optical depth measurements from the Cosmic Microwave Background (CMB) observations by {\it Planck}.

Accepted for publication in MNRAS

References in corpus (29)

• Adam: A Method for Stochastic Optimization
• LOFAR: The LOw-Frequency ARray
• Observational constraints on Cosmic Reionization
• Hydrogen Epoch of Reionization Array (HERA)
• The Precision Array for Probing the Epoch of Reionization: 8 Station Results
• Evidence of patchy hydrogen reionization from an extreme Ly$\alpha$ trough below redshift six
• The Reionization of the Universe by the First Stars and Quasars
• Reionization and the Cosmic Dawn with the Square Kilometre Array
• Science with the Murchison Widefield Array
• Quantitative Constraints on the Reionization History from the IGM Damping Wing Signature in Two Quasars at z > 7
• 21CMMC: an MCMC analysis tool enabling astrophysical parameter studies of the cosmic 21 cm signal
• Inferences on the Timeline of Reionization at z~8 From the KMOS Lens-Amplified Spectroscopic Survey
• Simulating cosmic reionization: How large a volume is large enough?
• The Neutral Hydrogen Content of Galaxies in Cosmological Hydrodynamic Simulations
• The GMRT-EoR Experiment: A new upper limit on the neutral hydrogen power spectrum at z~8.6
• Constraints on reionisation from the z=7.5 QSO ULASJ1342+0928
• Fast Large Volume Simulations of the 21 cm Signal from the Reionization and pre-Reionization Epochs
• The Global History of Reionisation
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• Anticipated Performance of the Square Kilometre Array -- Phase 1 (SKA1)
• Galactic Outflows and Photoionization Heating in the Reionization Epoch
• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• Optimal identification of HII regions during reionization in 21-cm observations
• Simulating the 21-cm signal from reionisation including non-linear ionisations and inhomogeneous recombinations
• Identifying Reionization Sources from 21cm Maps using Convolutional Neural Networks
• The Reionization of Carbon
• A deep learning model to emulate simulations of cosmic reionization
• Epoch of Reionisation 21cm Forecasting From MCMC-Constrained Semi-Numerical Models
• ARTIST: Fast radiative transfer for large-scale simulations of the epoch of reionisation

Cited by in corpus (27)

• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• The CAMELS project: public data release
• deep21: a Deep Learning Method for 21cm Foreground Removal
• Comparing Foreground Removal Techniques for Recovery of the LOFAR-EoR 21cm Power Spectrum
• An analysis of the $H_0$ tension problem in a universe with a viscous dark fluid
• Machine learning astrophysics from 21 cm lightcones: impact of network architectures and signal contamination
• Robust Field-level Likelihood-free Inference with Galaxies
• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• Exploring the cosmic 21-cm signal from the Epoch of Reionisation using the Wavelet Scattering Transform
• HIFlow: Generating Diverse HI Maps and Inferring Cosmology while Marginalizing over Astrophysics using Normalizing Flows
• Model-independently calibrating the luminosity correlations of gamma-ray bursts using deep learning
• HInet: Generating neutral hydrogen from dark matter with neural networks
• Wavelet Moments for Cosmological Parameter Estimation
• Inferring Astrophysics and Dark Matter Properties from 21cm Tomography using Deep Learning
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• Investigating X-ray sources during the epoch of reionization with the 21 cm signal
• How informative are summaries of the cosmic 21-cm signal?
• Detecting the non-Gaussianity of the 21-cm signal during reionisation with the Wavelet Scattering Transform
• Eliminating polarization leakage effect for neutral hydrogen intensity mapping with deep learning
• Deep learning method in testing the cosmic distance duality relation
• Using the sample variance of 21cm maps as a tracer of the ionisation topology
• An approach to cold dark matter deviation and the $H_0$ tension problem by using machine learning
• Predictive uncertainty on improved astrophysics recovery from multifield cosmology
• Probing the Epoch of Reionization using synergies of line intensity mapping
• Near-IR narrow-band imaging with CIRCE at the Gran Telescopio Canarias: Searching for Ly$\alpha$-emitters at $z\sim 9.3$
• What can we learn about Reionization astrophysical parameters using Gaussian Process Regression?
• Radiative transfer of 21-cm line through ionised cavities in an expanding universe