Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA

Abstract

Future Square Kilometre Array (SKA) surveys are expected to generate huge datasets of 21cm maps on cosmological scales from the Epoch of Reionization (EoR). We assess the viability of exploiting machine learning techniques, namely, convolutional neural networks (CNN), to simultaneously estimate the astrophysical and cosmological parameters from 21cm maps from semi-numerical simulations. We further convert the simulated 21cm maps into SKA-like mock maps using the detailed SKA antennae distribution, thermal noise and a recipe for foreground cleaning. We successfully design two CNN architectures (VGGNet-like and ResNet-like) that are both efficiently able to extract simultaneously three astrophysical parameters, namely the photon escape fraction (f${}_{\mathrm{esc}}$), the ionizing emissivity power dependence on halo mass ($C_{\mathrm{ion}}$) and the ionizing emissivity redshift evolution index ($D_{\mathrm{ion}}$), and three cosmological parameters, namely the matter density parameter (${\Omega }_m$), the dimensionless Hubble constant ($h$), and the matter fluctuation amplitude (${\sigma }_8$), from 21cm maps at several redshifts. With the presence of noise from SKA, our designed CNNs are still able to recover these astrophysical and cosmological parameters with great accuracy ($R^2>92\%$), improving to $R^2>99\%$ towards low redshift and low neutral fraction values. Our results show that future 21cm observations can play a key role to break degeneracy between models and tightly constrain the astrophysical and cosmological parameters, using only few frequency channels.

Accepted for publication in MNRAS

References in corpus (58)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Planck 2015 results. XIII. Cosmological parameters
• Nine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Parameter Results
• LOFAR: The LOw-Frequency ARray
• Cosmology at Low Frequencies: The 21 cm Transition and the High-Redshift Universe
• Observational constraints on Cosmic Reionization
• Hydrogen Epoch of Reionization Array (HERA)
• The Precision Array for Probing the Epoch of Reionization: 8 Station Results
• 21 Centimeter Fluctuations from Cosmic Gas at High Redshifts
• The Clustering of Luminous Red Galaxies in the Sloan Digital Sky Survey Imaging Data
• The Reionization of the Universe by the First Stars and Quasars
• Reionization and the Cosmic Dawn with the Square Kilometre Array
• Simulations and Analytic Calculations of Bubble Growth During Hydrogen Reionization
• New Measurements of the Ionizing Ultraviolet Background over 2 < z < 5 and Implications for Hydrogen Reionization
• Science with the Murchison Widefield Array
• The Epoch of Reionization Window: I. Mathematical Formalism
• Large Lyman-alpha opacity fluctuations and low CMB tau in models of late reionization with large islands of neutral hydrogen extending to z<5.5
• Inferring the astrophysics of reionization and cosmic dawn from galaxy luminosity functions and the 21-cm signal
• 21CMMC: an MCMC analysis tool enabling astrophysical parameter studies of the cosmic 21 cm signal
• 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
• Escape of Lyman continuum radiation from local galaxies - Detection of leakage from the young starburst Tol 1247-232
• No evidence for a significant AGN contribution to cosmic hydrogen reionization
• Fast Large Volume Simulations of the 21 cm Signal from the Reionization and pre-Reionization Epochs
• Cosmic reionization after Planck
• Constraining cosmological parameters using Sunyaev-Zel'dovich cluster surveys
• Non-Gaussian information from weak lensing data via deep learning
• Eliminating the optical depth nuisance from the CMB with 21 cm cosmology
• Joint CMB and Weak Lensing Analysis; Physically Motivated Constraints on Cosmological Parameters
• Quantifying the non-Gaussianity in the EoR 21-cm signal through bispectrum
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• Cosmic Reionization and the 21-cm signal: Comparison between an analytical model and a simulation
• Cosmic reionization after Planck II: contribution from quasars
• Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks
• Constraining the contribution of active galactic nuclei to reionisation
• A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
• Galactic Outflows and Photoionization Heating in the Reionization Epoch
• Constraining cosmological parameters by Gamma Ray Burst X - ray afterglow lightcurves
• Probing non-Gaussian features in the HI distribution at the epoch of reionization
• Dark-ages Reionization and Galaxy Formation Simulation - X. The small contribution of quasars to reionization
• 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
• Constraining cosmological parameters in FLRW metric with lensed GW+EM signals
• Recovering the HII region size statistics from 21-cm tomography
• The impact of spin temperature fluctuations on the 21-cm moments
• The Reionization of Carbon
• The Difference PDF of 21-cm Fluctuations: A Powerful Statistical Tool for Probing Cosmic Reionization
• A deep learning model to emulate simulations of cosmic reionization
• Machine Learning Applied to the Reionization History of the Universe in the 21 cm Signal
• Epoch of Reionisation 21cm Forecasting From MCMC-Constrained Semi-Numerical Models
• Constraining the reionization history using deep learning from 21cm tomography with the Square Kilometre Array
• Constraining cosmological parameters with the clustering properties of galaxy clusters in optical and X-ray bands
• Constraints on Cosmological Parameters from the Lyman-alpha Forest Power Spectrum and COBE-DMR
• Photon Number Conserving Models of H II Bubbles during Reionization
• ARTIST: Fast radiative transfer for large-scale simulations of the epoch of reionisation
• Upper Limits on the 21 cm Power Spectrum at z = 5.9 from Quasar Absorption Line Spectroscopy

Cited by in corpus (49)

• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Simulation-Based Inference of Reionization Parameters From 3D Tomographic 21 cm Lightcone Images
• The CAMELS project: public data release
• Learning cosmology and clustering with cosmic graphs
• Machine learning astrophysics from 21 cm lightcones: impact of network architectures and signal contamination
• Robust Field-level Likelihood-free Inference with Galaxies
• Cosmology with one galaxy?
• Implicit Likelihood Inference of Reionization Parameters from the 21 cm Power Spectrum
• Removing Astrophysics in 21 cm maps with Neural Networks
• 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
• Constraining the reionization history using deep learning from 21cm tomography with the Square Kilometre Array
• Predictions for measuring the 21-cm multi-frequency angular power spectrum using SKA-Low
• HIFlow: Generating Diverse HI Maps and Inferring Cosmology while Marginalizing over Astrophysics using Normalizing Flows
• Wavelet Moments for Cosmological Parameter Estimation
• HInet: Generating neutral hydrogen from dark matter with neural networks
• A thorough investigation of the prospects of eLISA in addressing the Hubble tension: Fisher Forecast, MCMC and Machine Learning
• Inferring Astrophysics and Dark Matter Properties from 21cm Tomography using Deep Learning
• Cosmic Velocity Field Reconstruction Using AI
• Deep learning for intensity mapping observations: Component extraction
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• 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
• Multifield Cosmology with Artificial Intelligence
• Constraining the Reionization History using Bayesian Normalizing Flows
• Exploring the cosmic dawn and epoch of reionization with 21cm line
• Machine-learning recovery of foreground wedge-removed 21-cm light cones for high-$z$ galaxy mapping
• Decoding Dark Matter Substructure without Supervision
• Detecting the non-Gaussianity of the 21-cm signal during reionisation with the Wavelet Scattering Transform
• Machine Learning and Cosmology
• Cornering Extended Starobinsky Inflation with CMB and SKA
• Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
• Deep learning the astrometric signature of dark matter substructure
• Estimation of HII Bubble Size Distribution from 21cm Power Spectrum with Artificial Neural Networks
• Predicting 21cm-line map from Lyman $\alpha$ emitter distribution with Generative Adversarial Networks
• Test of Artificial Neural Networks in Likelihood-free Cosmological Constraints: A Comparison of IMNN and DAE
• Modeling Post-Reionization HI Distributions in Fuzzy Dark Matter Cosmologies Using Conditional Normalizing Flows
• Inpainting hydrodynamical maps with deep learning
• Predictive uncertainty on improved astrophysics recovery from multifield cosmology
• Deep Needlet: A CNN based full sky component separation method in Needlet space
• A new way to constrain the densities of intra-group medium in groups of galaxies with convolutional neural networks
• An Alcock-Paczynski Test on Reionization Bubbles for Cosmology
• From ANN to BNN: Inferring Reionization Parameters using Uncertainty-aware Emulators of 21-cm Summaries
• Artificial Neural Networks for Galaxy Clustering. Learning from the two-point correlation function of BOSS galaxies
• Parameters Estimation from the 21 cm signal using Variational Inference
• nuGAN: Generative Adversarial Emulator for Cosmic Web with Neutrinos
• A bubble size distribution model for the Epoch of Reionization
• Probing the Inflaton Potential with SKA
• CosmoUiT: A Vision Transformer-UNet Hybrid for Fast and Accurate Emulation of 21-cm Maps from the Epoch of Reionization