A Neural-Network based estimator to search for primordial non-Gaussianity in Planck CMB maps

TL;DR

This paper introduces an upgraded estimator combining Minkowski Functionals and Neural Networks to detect primordial non-Gaussianity in Planck CMB maps, effectively distinguishing between primordial signals and foreground contaminations.

Contribution

The paper presents a novel combined estimator that integrates Minkowski Functionals with Neural Networks, optimized for identifying primordial non-Gaussianity amidst foreground residuals in CMB data.

Findings

Estimator accurately constrains f_NL to about 33 ± 23 for the SMICA map.

Consistent f_NL constraints across different Planck maps despite varying noise features.

Method effectively discriminates between primordial and secondary non-Gaussian signatures.

Abstract

We present an upgraded combined estimator, based on Minkowski Functionals and Neural Networks, with excellent performance in detecting primordial non-Gaussianity in simulated maps that also contain a weighted mixture of Galactic contaminations, besides real pixel's noise from Planck cosmic microwave background radiation data. We rigorously test the efficiency of our estimator considering several plausible scenarios for residual non-Gaussianities in the foreground-cleaned Planck maps, with the intuition to optimize the training procedure of the Neural Network to discriminate between contaminations with primordial and secondary non-Gaussian signatures. We look for constraints of primordial local non-Gaussianity at large angular scales in the foreground-cleaned Planck maps. For the $\mathtt{SMICA}$ map we found ${f}_{\rm \,NL} = 33 \pm 23$, at $1\sigma$ confidence level, in excellent agreement with the WMAP-9yr and Planck results. In addition, for the other three Planck maps we obtain similar constraints with values in the interval ${f}_{\rm \,NL} \in [33, 41]$, concomitant with the fact that these maps manifest distinct features in reported analyses, like having different pixel's noise intensities.