Testing the ABS method with the simulated Planck temperature maps

TL;DR

This paper evaluates the robustness of the ABS method for extracting the CMB temperature power spectrum from simulated Planck data, demonstrating high accuracy even under challenging foreground conditions.

Contribution

The study provides a comprehensive validation of the ABS estimator's ability to recover the CMB power spectrum from realistic multi-frequency simulations without prior foreground information.

Findings

ABS recovers the CMB power spectrum with less than 0.5% error when masking the Galactic plane.

The method remains unbiased and accurate in extreme foreground scenarios.

Recovered power spectra are consistent with input values within 1-sigma across most scales.

Abstract

In this study, we apply the Analytical method of Blind Separation (ABS) of the cosmic microwave background (CMB) from foregrounds to estimate the CMB temperature power spectrum from multi-frequency microwave maps. We test the robustness of the ABS estimator and assess the accuracy of the power spectrum recovery by using realistic simulations based on the seven-frequency Planck data, including various frequency-dependent and spatially-varying foreground components (synchrotron, free-free, thermal dust and anomalous microwave emission), as well as an uncorrelated Gaussian-distributed instrumental noise. Considering no prior information about the foregrounds, the ABS estimator can analytically recover the CMB power spectrum over almost all scales with less than $0.5\%$ error for maps where the Galactic plane region ($|b|<10^{\circ}$) is masked out. To further test the flexibility and effectiveness of the ABS approach in a variety of situations, we apply the ABS to the simulated Planck maps in three cases: (1) without any mask, (2) imposing a two-times-stronger synchrotron emission and (3) including only the Galactic plane region ($|b|<10^{\circ}$) in the analysis. In such extreme cases, the ABS approach can still provide an unbiased estimate of band powers at the level of 1 $\mu\rm{K}^2$ on average over all $\ell$ range, and the recovered powers are consistent with the input values within 1-$\sigma$ for most $\ell$ bins.