Accurate and Unbiased Reconstruction of CMB B Mode using Deep Learning

TL;DR

This paper introduces PrimeNet, an autoencoder that accurately reconstructs CMB B mode maps and spectra from simulated data, achieving cosmic variance-limited precision down to r=0.0001, even with complex foregrounds.

Contribution

The work presents a novel deep learning autoencoder that outperforms previous methods in unbiasedly reconstructing CMB B modes with high precision and robustness.

Findings

Achieves cosmic variance-limited reconstruction down to r=0.0001

Performs well with complex foreground models

Predicts accurate results even for data with r=0, unseen during training

Abstract

An ingeniously designed autoencoder (PrimeNet) using simulated observations of future generation ECHO satellite mission recovers CMB B mode map, angular spectrum for multipoles $\ell \lesssim 9$ and tensor to scalar ratio $r$ {\it limited only by cosmic variance down to $r= 0.0001$ and below}. We use diverse, realistically complex and detailed foreground models. PrimeNet predicts accurate results even when data with $r=0$ are tested which were not used in training, implying robust and efficient predictive power. The work eliminates a major bottleneck of weak CMB B mode reconstruction and takes a leap forward for understanding fundamental physics of the primordial Universe.