Planck limits on cosmic string tension using machine learning

doi:10.1093/mnras/stab3030

Planck limits on cosmic string tension using machine learning

2021-10-23

2

OA

AI

DOI：10.1093/mnras/stab3030

Original

Original request for help

Save

Abstract

En 中文

We develop two parallel machine learning pipelines to estimate the contribution of cosmic strings (CSs), conveniently encoded in their tension (G mu), to the anisotropies of the cosmic microwave background radiation observed by Planck. The first approach is tree-based and feeds on certain map features derived by image processing and statistical tools. The second uses convolutional neural networks with the goal to explore possible non-trivial features of the CS imprints. The two pipelines are trained on Planck simulations and when applied to PlanckSMICA map yield the 3 sigma upper bound of G mu less than or similar to 8.6 x 10(-7). We also train and apply the pipelines to make forecasts for futuristic CMB-S4-like surveys, and conservatively find their minimum detectable tension to be G mu(min) similar to 1.9 x 10(-7)..

Keywords:

(cosmology:) cosmic background radiation

(cosmology:) early Universe

cosmology: observations

methods: data analysis

Planck limits on cosmic string tension using machine learning

Abstract

Journal

Organization