A Convolutional Neural Network For Cosmic String Detection in CMB Temperature Maps

TL;DR

This paper details a convolutional neural network designed to detect cosmic strings in CMB temperature maps, accurately locating strings and estimating their tension even in noisy, realistic simulations.

Contribution

Introduces a CNN model trained on simulated CMB maps to detect cosmic strings and estimate their tension, demonstrating high accuracy in realistic scenarios.

Findings

Accurately detects cosmic strings with tension as low as Gμ=5×10⁻⁹

Performs well on realistic Nambu-Goto simulations

Code is publicly available online

Abstract

We present in detail the convolutional neural network used in our previous work to detect cosmic strings in cosmic microwave background (CMB) temperature anisotropy maps. By training this neural network on numerically generated CMB temperature maps, with and without cosmic strings, the network can produce prediction maps that locate the position of the cosmic strings and provide a probabilistic estimate of the value of the string tension $G\mu$. Supplying noiseless simulations of CMB maps with arcmin resolution to the network resulted in the accurate determination both of string locations and string tension for sky maps having strings with string tension as low as $G\mu=5\times10^{-9}$. The code is publicly available online. Though we trained the network with a long straight string toy model, we show the network performs well with realistic Nambu-Goto simulations.