Cosmic String Detection with Tree-Based Machine Learning

TL;DR

This paper applies tree-based machine learning algorithms to detect cosmic strings in CMB maps, achieving improved sensitivity over existing methods, especially for high-resolution and realistic noise conditions.

Contribution

It introduces a novel approach using random forest and gradient boosting classifiers with specialized feature vectors for cosmic string detection in CMB data.

Findings

Detects cosmic strings with $G  2.1 imes 10^{-10}$ in noise-free conditions

Achieves detection thresholds better than previous methods

Demonstrates effectiveness under realistic CMB S4-like noise and resolution

Abstract

We explore the use of random forest and gradient boosting, two powerful tree-based machine learning algorithms, for the detection of cosmic strings in maps of the cosmic microwave background (CMB), through their unique Gott-Kaiser-Stebbins effect on the temperature anisotropies.The information in the maps is compressed into feature vectors before being passed to the learning units. The feature vectors contain various statistical measures of processed CMB maps that boost the cosmic string detectability. Our proposed classifiers, after training, give results improved over or similar to the claimed detectability levels of the existing methods for string tension, $G\mu$. They can make $3\sigma$ detection of strings with $G\mu \gtrsim 2.1\times 10^{-10}$ for noise-free, $0.9'$-resolution CMB observations. The minimum detectable tension increases to $G\mu \gtrsim 3.0\times 10^{-8}$ for a more realistic, CMB S4-like (II) strategy, still a significant improvement over the previous results.