CMBFSCNN: Cosmic Microwave Background Polarization Foreground Subtraction with Convolutional Neural Network

TL;DR

This paper extends a machine learning method, CMBFSCNN, to effectively remove foreground contamination and recover CMB polarization signals, including lensing effects, from simulated multi-frequency data for experiments like CMB-S4 and LiteBIRD.

Contribution

The study demonstrates the application of CMBFSCNN to simulated data with lensing effects, achieving accurate recovery of CMB polarization and lensing B-mode spectra, and introduces a noise reduction technique using half-split maps.

Findings

Reliable recovery of CMB Q/U maps with low mean absolute difference.

Effective removal of foregrounds from simulated observational maps.

Precise reconstruction of EE and lensing B-mode power spectra.

Abstract

In our previous study, we introduced a machine-learning technique, namely CMBFSCNN, for the removal of foreground contamination in cosmic microwave background (CMB) polarization data. This method was successfully employed on actual observational data from the Planck mission. In this study, we extend our investigation by considering the CMB lensing effect in simulated data and utilizing the CMBFSCNN approach to recover the CMB lensing B-mode power spectrum from multi-frequency observational maps. Our method is first applied to simulated data with the performance of CMB-S4 experiment. We achieve reliable recovery of the noisy CMB Q (or U) maps with a mean absolute difference of $0.016\pm0.008\ \mu$K (or $0.021\pm0.002\ \mu$K) for the CMB-S4 experiment. To address the residual instrumental noise in the foreground-cleaned map, we employ a "half-split maps" approach, where the entire dataset is divided into two segments sharing the same sky signal but having uncorrelated noise. Using cross-correlation techniques between two recovered half-split maps, we effectively reduce instrumental noise effects at the power spectrum level. As a result, we achieve precise recovery of the CMB EE and lensing B-mode power spectra. Furthermore, we also extend our pipeline to full-sky simulated data with the performance of LiteBIRD experiment. As expected, various foregrounds are cleanly removed from the foreground contamination observational maps, and recovered EE and lensing B-mode power spectra exhibit excellent agreement with the true results. Finally, we discuss the dependency of our method on the foreground models.