A perceptron based ILC method to obtain accurate CMB B-mode angular power spectrum

TL;DR

This paper introduces a neural network-enhanced ILC method to accurately reconstruct the CMB B-mode angular power spectrum, demonstrating high precision constrained mainly by cosmic variance, relevant for upcoming polarization missions.

Contribution

It presents a novel neural network-based approach to improve the ILC technique for CMB B-mode power spectrum estimation, tailored for future observational missions.

Findings

Achieves precise B-mode spectrum reconstruction

Errors are primarily limited by cosmic variance

Demonstrates effectiveness on ECHO mission data

Abstract

Observations of the Cosmic Microwave Background (CMB) radiation have made significant contributions to our understanding of cosmology. While temperature observations of the CMB have greatly advanced our knowledge, the next frontier lies in detecting the elusive B-modes and obtaining precise reconstructions of the CMB's polarized signal in general. In anticipation of proposed and upcoming CMB polarization missions, this study introduces a novel method for accurately determining the angular power spectrum of CMB B-modes. We have developed a Neural Network-based approach to enhance the performance of the Internal Linear Combination (ILC) technique. Our method is applied to the frequency channels of the proposed ECHO (Exploring Cosmic History and Origins) mission and its performance is rigorously assessed. Our findings demonstrate the method's efficiency in achieving precise reconstructions of CMB B-mode angular power spectra, with errors constrained primarily by cosmic variance.