Cosmic String Detection with Tree-Based Machine Learning

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, $0.9^{\prime }$-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.

7 pages, 3 figures, 2 tables, Comments are welcome

References in corpus (17)

• Popular Ensemble Methods: An Empirical Study
• Stochastic gravitational wave background from smoothed cosmic string loops
• New limits on cosmic strings from gravitational wave observation
• Fitting CMB data with cosmic strings and inflation
• Small-Angle CMB Temperature Anisotropies Induced by Cosmic Strings
• Stochastic gravitational waves from cosmic string loops in scaling
• New CMB constraints for Abelian Higgs cosmic strings
• CMB polarization power spectra contributions from a network of cosmic strings
• The CMB temperature bispectrum induced by cosmic strings
• Cosmic strings reborn?
• Cosmic Strings
• Constraints on the Nambu-Goto cosmic string contribution to the CMB power spectrum in light of new temperature and polarisation data
• All sky CMB map from cosmic strings integrated Sachs-Wolfe effect
• A Bayesian Framework for Cosmic String Searches in CMB Maps
• Multi-Scale Pipeline for the Search of String-Induced CMB Anisotropies
• Level Crossing Analysis of Cosmic Microwave Background Radiation: A method for detecting cosmic strings
• Gravitational Waves and Light Cosmic Strings

Cited by in corpus (10)

• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• On the 2D Dirac oscillator in the presence of vector and scalar potentials in the cosmic string spacetime in the context of spin and pseudospin symmetries
• Clustering of Local Extrema in Planck CMB maps
• Persistent Homology of Fractional Gaussian Noise
• Information Theoretic Bounds on Cosmic String Detection in CMB Maps with Noise
• Inferring Cosmic String Tension through the Neural Network Prediction of String Locations in CMB Maps
• Planck Limits on Cosmic String Tension Using Machine Learning
• Inpainting via Generative Adversarial Networks for CMB data analysis
• The Global 21 cm Signal of a Network of Cosmic String Wakes
• Cosmic Strings-induced CMB anisotropies in light of Weighted Morphology