Towards detecting Primordial non-Gaussianity in the CMB using Spherical Convolutional Neural Networks

Abstract

This paper explores a novel application of spherical convolutional neural networks (CNNs) to detect primordial non-Gaussianity in the cosmic microwave background (CMB), a key probe of inflationary dynamics. While effective, traditional estimators encounter computational challenges, especially when considering summary statistics beyond the bispectrum. We propose spherical CNNs as an alternative, directly analysing full-sky CMB maps to overcome limitations in previous machine learning (ML) approaches that relied on data summaries. By training on simulated CMB maps with varying amplitudes of non-Gaussianity, our spherical CNN models show promising alignment with optimal error bounds of traditional methods, albeit at lower-resolution maps. While we explore several different architectures, results from DeepSphere CNNs most closely match the Fisher forecast for Gaussian test sets under noisy and masked conditions. Our study suggests that spherical CNNs could complement existing methods of non-Gaussianity detection in future datasets, provided additional training data and parameter tuning are applied. We discuss the potential for CNN-based techniques to scale with larger data volumes, paving the way for applications to future CMB data sets.

11 pages, 1 figure, prepared for submission to MNRAS

References in corpus (35)

• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Planck 2018 results. I. Overview and the cosmological legacy of Planck
• The Simons Observatory: Science goals and forecasts
• First Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Tests of Gaussianity
• Planck 2015 results. XVII. Constraints on primordial non-Gaussianity
• Constraints on local primordial non-Gaussianity from large scale structure
• Planck 2013 Results. XXIV. Constraints on primordial non-Gaussianity
• Measuring primordial non-Gaussianity in the cosmic microwave background
• Detection of primordial non-Gaussianity (fNL) in the WMAP 3-year data at above 99.5% confidence
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• A novel sampling theorem on the sphere
• The Clustering of Galaxies in SDSS-III DR9 Baryon Oscillation Spectroscopic Survey: Constraints on Primordial Non-Gaussianity
• Primordial Non-Gaussianity and Analytical Formula for Minkowski Functionals of the Cosmic Microwave Background and Large-scale Structure
• Measurement of the cosmic microwave background bispectrum on the COBE DMR sky maps
• Redshift-weighted constraints on primordial non-Gaussianity from the clustering of the eBOSS DR14 quasars in Fourier space
• Constraints on primordial non-Gaussianity from 800,000 photometric quasars
• Limits on Primordial Non-Gaussianity from Minkowski Functionals of the WMAP Temperature Anisotropies
• Algorithms for bispectra: forecasting, optimal analysis, and simulation
• Primordial Non-Gaussianity in the Cosmic Microwave Background
• Non Gaussianity and Minkowski Functionals: forecasts for Planck
• Improved simulation of non-Gaussian temperature and polarization CMB maps
• High-Resolution Simulations of Cosmic Microwave Background non-Gaussian Maps in Spherical Coordinates
• Sloan Digital Sky Survey III Photometric Quasar Clustering: Probing the Initial Conditions of the Universe using the Largest Volume
• Temperature and Polarization CMB Maps from Primordial non-Gaussianities of the Local Type
• Convolutional Neural Networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
• Model-independent analyses of non-Gaussianity in Planck CMB maps using Minkowski Functionals
• Biasing and the search for primordial non-Gaussianity beyond the local type
• The integrated bispectrum as a test of CMB non-Gaussianity: detection power and limits on f_NL with WMAP data
• Fundamental limits on constraining primordial non-Gaussianity
• Primordial non-Gaussianity and non-Gaussian Covariance
• A Neural-Network based estimator to search for primordial non-Gaussianity in Planck CMB maps
• CMB constraints on running non-Gaussianity
• Optimization Study for the Experimental Configuration of CMB-S4
• Improving constraints on primordial non-Gaussianity using neural network based reconstruction
• Constraining primordial non-Gaussianity using Neural Networks