ForSE: a GAN based algorithm for extending CMB foreground models to sub-degree angular scales

TL;DR

ForSE is a GAN-based Python tool that generates realistic small-scale Galactic foreground features at sub-degree scales, aiding CMB data analysis by modeling complex non-Gaussian radiation patterns.

Contribution

It introduces a novel GAN-based method for extending large-scale Galactic foreground models to smaller scales, improving simulation accuracy for CMB experiments.

Findings

Successfully generates small-scale features with correct statistical properties.

Produces realistic thermal dust emission maps at 12 arc-minutes resolution.

Maintains amplitude scaling consistent with real sky observations.

Abstract

We present ForSE (Foreground Scale Extender), a novel Python package which aims at overcoming the current limitations in the simulation of diffuse Galactic radiation, in the context of Cosmic Microwave Background experiments (CMB). ForSE exploits the ability of generative adversarial neural networks (GANs) to learn and reproduce complex features present in a set of images, with the goal of simulating realistic and non-Gaussian foreground radiation at sub-degree angular scales. This is of great importance in order to estimate the foreground contamination to lensing reconstruction, de-lensing and primordial B-modes, for future CMB experiments. We applied this algorithm to Galactic thermal dust emission in both total intensity and polarization. Our results show how ForSE is able to generate small scale features (at 12 arc-minutes) having as input the large scale ones (80 arc-minutes). The injected structures have statistical properties, evaluated by means of the Minkowski functionals, in good agreement with those of the real sky and which show the correct amplitude scaling as a function of the angular dimension. The obtained thermal dust Stokes Q and U full sky maps as well as the ForSE package are publicly available for download.