Improving constraints on primordial non-Gaussianity using neural network based reconstruction

Abstract

We study the use of U-Nets in reconstructing the linear dark matter density field and its consequences for constraining cosmological parameters, in particular primordial non-Gaussianity. Our network is able to reconstruct the initial conditions of redshift $z=0$ density fields from N-body simulations with $90\%$ accuracy out to $k\le 0.4$ h/Mpc, competitive with state-of-the-art reconstruction algorithms at a fraction of the computational cost. We study the information content of the reconstructed $z=0$ density field with a Fisher analysis using the QUIJOTE simulation suite, including non-Gaussian initial conditions. Combining the pre- and post-reconstructed power spectrum and bispectrum data up to $k_{\max }=0.52$ h/Mpc, we find significant improvements on all parameters. Most notably, we find a factor $3.65$ (local), $3.54$ (equilateral) and $2.90$ (orthogonal) improvement on the marginalized errors of $f_{\mathrm{NL}}$ as compared to only using the pre-reconstructed data. We show that these improvements can be attributed to a combination of reduced data covariance and parameter degeneracy. The results constitute an important step towards more optimal inference of primordial non-Gaussianity from non-linear scales.

22 pages, 8 figures, 3 tables, codes available at https://github.com/tsfloss/URecon and https://github.com/tsfloss/DensityFieldTools. v2 matches version accepted for JCAP

References in corpus (10)

• The Effective Field Theory of Inflation
• Why your model parameter confidences might be too optimistic -- unbiased estimation of the inverse covariance matrix
• The Effective Field Theory of Cosmological Large Scale Structures
• Improving Cosmological Distance Measurements by Reconstruction of the Baryon Acoustic Peak
• Cosmological Collider Physics
• Non-Gaussianity as a Particle Detector
• Line-Intensity Mapping: 2017 Status Report
• Constraints on primordial non-Gaussianity from 800,000 photometric quasars
• Effective cosmic density field reconstruction with convolutional neural network
• Predicting the Initial Conditions of the Universe using a Deterministic Neural Network

Cited by in corpus (8)

• Capturing primordial non-Gaussian signatures in the late Universe by multi-scale extrema of the cosmic log-density field
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery
• Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
• Neural Network Reconstruction of Non-Gaussian Initial Conditions from Dark Matter Halos
• Modelling the covariance matrix for the power spectra before and after the BAO reconstruction
• Power Spectrum Emulators from Neural Networks and Tree-Based Methods
• Towards detecting Primordial non-Gaussianity in the CMB using Spherical Convolutional Neural Networks
• Fast Sampling of Cosmological Initial Conditions with Gaussian Neural Posterior Estimation