Cosmological constraints from low redshift 21 cm intensity mapping with machine learning

Abstract

The future 21 cm intensity mapping observations constitute a promising way to trace the matter distribution of the Universe and probe cosmology. Here we assess its capability for cosmological constraints using as a case study the BINGO radio telescope, that will survey the Universe at low redshifts ($0.13<z<0.45$). We use neural networks (NNs) to map summary statistics, namely, the angular power spectrum (APS) and the Minkowski functionals (MFs), calculated from simulations into cosmological parameters. Our simulations span a wide grid of cosmologies, sampled under the $\Lambda$CDM scenario, {${\Omega }_c,h$}, and under an extension assuming the Chevallier-Polarski-Linder (CPL) parameterization, {${\Omega }_c,h,w_0,w_a$}. In general, NNs trained over APS outperform those using MFs, while their combination provides 27% (5%) tighter error ellipse in the ${\Omega }_c-h$ plane under the $\Lambda$CDM scenario (CPL parameterization) compared to the individual use of the APS. Their combination allows predicting ${\Omega }_c$ and $h$ with 4.9% and 1.6% fractional errors, respectively, which increases to 6.4% and 3.7% under CPL parameterization. Although we find large bias on $w_a$ estimates, we still predict $w_0$ with 24.3% error. We also confirm our results to be robust to foreground contamination, besides finding the instrumental noise to cause the greater impact on the predictions. Still, our results illustrate the capability of future low redshift 21 cm observations in providing competitive cosmological constraints using NNs, showing the ease of combining different summary statistics.

arXiv comment17 pages, 13 figures

References in corpus (63)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Deep Learning in Neural Networks: An Overview
• The NumPy array: a structure for efficient numerical computation
• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• Exploring the Expansion History of the Universe
• Accelerating Universes with Scaling Dark Matter
• 21-cm cosmology
• The Five-Hundred-Meter Aperture Spherical Radio Telescope (FAST) Project
• MASTER of the CMB Anisotropy Power Spectrum: A Fast Method for Statistical Analysis of Large and Complex CMB Data Sets
• First Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Tests of Gaussianity
• Planck 2018 results. VII. Isotropy and Statistics of the CMB
• A unified pseudo-$C_{\ell }$ framework
• The pre-launch Planck Sky Model: a model of sky emission at submillimetre to centimetre wavelengths
• HI intensity mapping : a single dish approach
• Separation of anomalous and synchrotron emissions using WMAP polarization data
• Improving lognormal models for cosmological fields
• Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology
• Foreground component separation with generalised ILC
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• Towards a model of full-sky Galactic synchrotron intensity and linear polarisation: a re-analysis of the Parkes data
• Non-Gaussian information from weak lensing data via deep learning
• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• Nuisance hardened data compression for fast likelihood-free inference
• CMB temperature and polarisation pseudo-Cl estimators and covariances
• Emulating the CFHTLenS Weak Lensing data: Cosmological Constraints from moments and Minkowski functionals
• Weak lensing cosmology with convolutional neural networks on noisy data
• Analytic Minkowski Functionals of the Cosmic Microwave Background: Second-order Non-Gaussianity with Bispectrum and Trispectrum
• Non-Gaussian statistics of critical sets in 2 and 3D: Peaks, voids, saddles, genus and skeleton
• Non Gaussianity and Minkowski Functionals: forecasts for Planck
• Simulations for single-dish intensity mapping experiments
• 21cm foregrounds and polarization leakage: a user's guide on cleaning and mitigation strategies
• Extracting HI cosmological signal with Generalized Needlet Internal Linear Combination
• Cosmological Measurements from Angular Power Spectra Analysis of BOSS DR12 Tomography
• Constraining neutrino mass with weak lensing Minkowski Functionals
• Statistical and Systematic Errors in Measurement of Weak-Lensing Minkowski Functionals: Application to Canada-France-Hawaii Lensing Survey
• The BINGO Project I: Baryon Acoustic Oscillations from Integrated Neutral Gas Observations
• Minkowski Functionals and Cluster Analysis for CMB Maps
• Interpreting deep learning models for weak lensing
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• The imprint of $f(R)$ gravity on weak gravitational lensing II : Information content in cosmic shear statistics
• New probe of departures from general relativity using Minkowski functionals
• The BINGO Project II: Instrument Description
• Multi-scale morphology of the galaxy distribution
• The BINGO Project VII: Cosmological Forecasts from 21cm Intensity Mapping
• Local analyses of Planck maps with Minkowski Functionals
• Extracting cosmological parameters from N-body simulations using machine learning techniques
• Scale dependent non-Gaussianities in the CMB data identified with Minkowski Functionals and Scaling Indices
• Inferring galaxy dark halo properties from visible matter with Machine Learning
• Impact of astrophysics on cosmology forecasts for 21 cm surveys
• Neural networks as optimal estimators to marginalize over baryonic effects
• The BINGO Project V: Further steps in Component Separation and Bispectrum Analysis
• A Neural-Network based estimator to search for primordial non-Gaussianity in Planck CMB maps
• A Joint Analysis for Cosmology and Photometric Redshift Calculation Using Cross Correlations
• The BINGO Project IV: Simulations for mission performance assessment and preliminary component separation steps
• Beyond $\Lambda$CDM with HI intensity mapping: robustness of cosmological constraints in the presence of astrophysics
• Searching for primordial non-Gaussianity in Planck CMB maps using a combined estimator
• Topology of Luminous Red Galaxies from the Sloan Digital Sky Survey
• Tomographic local 2D analyses of the WISExSuperCOSMOS all-sky galaxy catalogue
• Analysing the Epoch of Reionization with three-point correlation functions and machine learning techniques
• The BINGO project VIII: On the recoverability of the BAO signal on HI intensity mapping simulations
• Testing synchrotron models and frequency resolution in BINGO 21 cm simulated maps using GNILC
• Morphology of the Local Volume

Cited by in corpus (1)

• The BINGO project X. Cosmological parameter constraints from HI Intensity Mapping lognormal simulations