Planck Limits on Cosmic String Tension Using Machine Learning

TL;DR

This paper introduces machine learning pipelines to analyze Planck data for cosmic string tension, providing new upper bounds and forecasts for future surveys using neural networks and feature-based methods.

Contribution

It presents two novel machine learning approaches for constraining cosmic string tension from CMB data, including a neural network and a feature-based tree method.

Findings

Planck data constrains cosmic string tension to Gμ ≲ 8.6×10⁻⁷ at 3σ.

Forecasts suggest future surveys could detect tensions as low as Gμ ≈ 1.9×10⁻⁷.

Two machine learning pipelines effectively analyze CMB anisotropies for cosmic strings.

Abstract

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 {\it 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 network with the goal to explore possible non-trivial features of the CS imprints. The two pipelines are trained on {\it Planck} simulations and when applied to {\it Planck} \texttt{SMICA} map yield the $3\sigma$ upper bound of $G\mu\lesssim 8.6\times 10^{-7}$. 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 $G\mu_{\rm min}\sim 1.9\times 10^{-7}$.