CENN: A fully convolutional neural network for CMB recovery in realistic microwave sky simulations

Abstract

Component separation is the process with which emission sources in astrophysical maps are generally extracted by taking multi-frequency information into account. It is crucial to develop more reliable methods for component separation for future CMB experiments. We aim to develop a new method based on fully convolutional neural networks called the Cosmic microwave background Extraction Neural Network (CENN) in order to extract the CMB signal in total intensity. The frequencies used are the Planck channels 143, 217 and 353 GHz. We validate the network at all sky, and at three latitude intervals: lat1=0^{\circ}<b<5^{\circ}, lat2=5^{\circ}<b<30^{\circ} and lat3=30^{\circ}<b<90^{\circ}, without using any Galactic or point source masks. For training, we make realistic simulations in the form of patches of area 256 pixels, which contain the CMB, Dust, CIB and PS emissions, Sunyaev-Zel'dovich effect and the instrumental noise. After validate the network, we compare the power spectrum from input and output maps. We analyse the power spectrum from the residuals at each latitude interval and at all sky and we study the performance of our model dealing with high contamination at small scales. We obtain a power spectrum with an error of 13{\pm}113 μK^2 for multipoles up to above 4000. For residuals, we obtain 700{\pm}60 μK^2 for lat1, 80{\pm}30 μK^2 for lat2 and 30{\pm}20 μK^2 for lat3. For all sky, we obtain 20{\pm}10 μK^2. We validate the network in a patch with strong contamination at small scales, obtaining an error of 50{\pm}120 μK^2 and residuals of 40{\pm}10 μK^2. Therefore, fully convolutional neural networks are promising methods to perform component separation in future CMB experiments. Particularly, CENN is reliable against different levels of contamination from Galactic and point source foregrounds at both large and small scales.

arXiv commentAccepted for publication in Astronomy & Astrophysics journal. 11 pages, 6 figures

References in corpus (38)

• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Planck 2018 results. I. Overview and the cosmological legacy of Planck
• The Simons Observatory: Science goals and forecasts
• Cosmology with the Sunyaev-Zel'dovich Effect
• The Cosmic Infrared Background: Measurements and Implications
• The Microwave Anisotropy Probe (MAP) Mission
• The Cosmic Infrared Background Resolved by Spitzer. Contributions of Mid-Infrared Galaxies to the Far-Infrared Background
• Planck 2018 results. IV. Diffuse component separation
• Joint Bayesian component separation and CMB power spectrum estimation
• A full sky, low foreground, high resolution CMB map from WMAP
• Radio and Millimeter Continuum Surveys and their Astrophysical Implications
• Planck 2015 results. IX. Diffuse component separation: CMB maps
• Component separation methods for the Planck mission
• Extragalactic Source Counts and Contributions to the Anisotropies of the Cosmic Microwave Background. Predictions for the Planck Surveyor mission
• The pre-launch Planck Sky Model: a model of sky emission at submillimetre to centimetre wavelengths
• Multi-Detector Multi-Component spectral matching and applications for CMB data analysis
• Herschel-ATLAS Galaxy Counts and High Redshift Luminosity Functions: The Formation of Massive Early Type Galaxies
• Far-infrared to millimeter astrophysical dust emission I: A model based on physical properties of amorphous solids
• A hybrid model for the evolution of galaxies and Active Galactic Nuclei in the infrared
• High--frequency predictions for number counts and spectral properties of extragalactic radio sources. New evidences of a break at mm wavelengths in spectra of bright blazar sources
• Observational Constraints on the Physical Properties of Interstellar Dust in the Post-Planck Era
• The S-PASS view of polarized Galactic Synchrotron at 2.3 GHz as a contaminant to CMB observations
• Predictions on the angular power spectrum of clustered extragalactic point sources at CMB frequencies from flat and all--sky 2D-simulations
• Updated design of the CMB polarization experiment satellite LiteBIRD
• Characterization of foreground emission at degree angular scale for CMB B-modes observations. Thermal Dust and Synchrotron signal from Planck and WMAP data
• Far-Infrared to Millimeter Astrophysical Dust Emission. II: Comparison of the Two-Level Systems (TLS) model with Astronomical Data
• CMB power spectrum estimation and map reconstruction with the Expectation - Maximization algorithm
• Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning
• Convolutional Neural Networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
• The local luminosity function of star-forming galaxies derived from the Planck Early Release Compact Source Catalogue
• The bispectrum of polarized galactic foregrounds
• ForSE: a GAN based algorithm for extending CMB foreground models to sub-degree angular scales
• Recovering the CMB Signal with Machine Learning
• Cosmic Microwave Background Polarisation: foreground contrast and component separation
• Single frequency CMB B-mode inference with realistic foregrounds from a single training image
• Foreground model recognition through Neural Networks for CMB B-mode observations
• Bayesian foreground analysis with CMB data
• Point Source Detection with Fully-Convolutional Networks: Performance in Realistic Simulations

Cited by in corpus (6)

• Recovering Cosmic Microwave Background Polarization Signals with Machine Learning
• Delensing of Cosmic Microwave Background Polarization with machine learning
• Inference of the optical depth to reionization $\tau$ from $\text{Planck}$ CMB maps with convolutional neural networks
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery
• Constraining the polarisation flux density and angle of point sources by training a convolutional neural network
• Cluster optical depth and pairwise velocity estimation using machine learning