Recovering Cosmic Microwave Background Polarization Signals with Machine Learning

Abstract

Primordial B-mode detection is one of the main goals of current and future cosmic microwave background (CMB) experiments. However, the weak B-mode signal is overshadowed by several Galactic polarized emissions, such as thermal dust emission and synchrotron radiation. Subtracting foreground components from CMB observations is one of the key challenges in searching for the primordial B-mode signal. Here, we construct a deep convolutional neural network (CNN) model, called \texttt{CMBFSCNN} (Cosmic Microwave Background Foreground Subtraction with CNN), which can cleanly remove various foreground components from simulated CMB observational maps at the sensitivity of the CMB-S4 experiment. Noisy CMB Q (or U) maps are recovered with a mean absolute difference of $0.018\pm 0.023\mu$K (or $0.021\pm 0.028\mu$K). To remove the residual instrumental noise from the foreground-cleaned map, inspired by the needlet internal linear combination method, we divide the whole data set into two ``half-split maps,'' which share the same sky signal, but have uncorrelated noise, and perform a cross-correlation technique to reduce the instrumental noise effects at the power spectrum level. We find that the CMB EE and BB power spectra can be precisely recovered with significantly reduced noise effects. Finally, we apply this pipeline to current Planck observations. As expected, various foregrounds are cleanly removed from the Planck observational maps, with the recovered EE and BB power spectra being in good agreement with the official Planck results.

arXiv comment9 pages, 4 figures, 1 table

References in corpus (34)

• Cosmological parameters from SDSS and WMAP
• The Simons Observatory: Science goals and forecasts
• A high-bias, low-variance introduction to Machine Learning for physicists
• Extrapolation of Galactic Dust Emission at 100 Microns to CMBR Frequencies Using FIRAS
• A unified pseudo-$C_{\ell }$ framework
• The Quest for B Modes from Inflationary Gravitational Waves
• Joint Bayesian component separation and CMB power spectrum estimation
• Planck 2013 results. XII. Component separation
• The Python Sky Model: software for simulating the Galactic microwave sky
• Robust forecasts on fundamental physics from the foreground-obscured, gravitationally-lensed CMB polarization
• Three-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Foreground Polarization
• Planck 2013 results. VI. High Frequency Instrument data processing
• The LiteBIRD Satellite Mission - Sub-Kelvin Instrument
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• The S-PASS view of polarized Galactic Synchrotron at 2.3 GHz as a contaminant to CMB observations
• Planck 2013 results. II. Low Frequency Instrument data processing
• Sensitivity and foreground modelling for large-scale CMB B-mode polarization satellite missions
• Planck Early Results. V. The Low Frequency Instrument data processing
• Characterization of foreground emission at degree angular scale for CMB B-modes observations. Thermal Dust and Synchrotron signal from Planck and WMAP data
• Synchrotron Spectral Curvature from 22 MHz to 23 GHz
• Forecasting performance of CMB experiments in the presence of complex foreground contaminations
• Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning
• Mitigating Complex Dust Foregrounds in Future CMB Polarization Experiments
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• CMB polarization map derived from the WMAP 5 year data through Harmonic Internal Linear Combination
• ForSE: a GAN based algorithm for extending CMB foreground models to sub-degree angular scales
• Recovering the CMB Signal with Machine Learning
• Impact on the tensor-to-scalar ratio of incorrect Galactic foreground modelling
• In-flight polarization angle calibration for LiteBIRD: blind challenge and cosmological implications
• An Improved Diffuse Foreground Subtraction by ILC method: CMB Map and Angular Power Spectrum using Planck and WMAP Observations
• Exploring two-spin internal linear combinations for the recovery of the CMB polarization
• Foreground model recognition through Neural Networks for CMB B-mode observations
• CENN: A fully convolutional neural network for CMB recovery in realistic microwave sky simulations
• Efficient ILC analysis on polarization maps after EB leakage correction

Cited by in corpus (5)

• Delensing of Cosmic Microwave Background Polarization with machine learning
• Lensing reconstruction from the cosmic microwave background polarization with machine learning
• Deep Needlet: A CNN based full sky component separation method in Needlet space
• Neural Networks for cosmological model selection and feature importance using Cosmic Microwave Background data
• Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra