Large-scale density and velocity field reconstructions with neural networks

Abstract

We assess a neural network (NN) method for reconstructing 3D cosmological density and velocity fields (target) from discrete and incomplete galaxy distributions (input). We employ second-order Lagrangian Perturbation Theory to generate a large ensemble of mock data to train an autoencoder (AE) architecture with a Mean Squared Error (MSE) loss function. The AE successfully captures nonlinear features arising from gravitational dynamics and the discreteness of the galaxy distribution. It preserves the positivity of the reconstructed density field and exhibits a weaker suppression of the power on small scales than the traditional linear Wiener filter (WF), which we use as a benchmark. In the density reconstruction, the reduction of the AE MSE relative to the WF is $\sim 15\%$, whereas, for the velocity reconstruction, a relative reduction of up to a factor of two can be achieved. The AE is advantageous to the WF at recovering the distribution of the target fields, especially at the tails. In fact, trained with an MSE loss, any NN estimate approaches the unbiased mean of the underlying target given the input. This implies a slope of unity in the linear regression of the true on the NN-reconstructed field. Only for the special case of Gaussian fields, the NN and WF estimates are equivalent. Nonetheless, we also recover a linear regression slope of unity for the WF with non-Gaussian fields.

18 pages, 13 figures. Accepted in MNRAS

References in corpus (22)

• The DESI Experiment Part I: Science,Targeting, and Survey Design
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: measurement of the BAO and growth rate of structure of the luminous red galaxy sample from the anisotropic correlation function between redshifts 0.6 and 1
• The Clustering of the SDSS Main Galaxy Sample II: Mock galaxy catalogues and a measurement of the growth of structure from Redshift Space Distortions at $z=0.15$
• Cosmological parameters from the comparison of peculiar velocities with predictions from the 2M++ density field
• AbacusSummit: A Massive Set of High-Accuracy, High-Resolution $N$-Body Simulations
• Reconstructed Density and Velocity Fields from the 2MASS Redshift Survey
• The 6dF Galaxy Survey: Peculiar Velocity Field and Cosmography
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Growth rate of structure measurement from anisotropic clustering analysis in configuration space between redshift 0.6 and 1.1 for the Emission Line Galaxy sample
• Joint analysis of 6dFGS and SDSS peculiar velocities for the growth rate of cosmic structure and tests of gravity
• Bayesian reconstruction of the cosmological large-scale structure: methodology, inverse algorithms and numerical optimization
• Growth rate of cosmological perturbations at z ~ 0.1 from a new observational test
• The peculiar velocity field up to $z\sim 0.05$ by forward-modeling Cosmicflows-3 data
• The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
• Learning cosmology and clustering with cosmic graphs
• Constrained realizations of 2MRS density and peculiar velocity fields: growth rate and local flow
• Peculiar-velocity cosmology with Types Ia and II supernovae
• The 2MASS Redshift Survey in the Zone of Avoidance
• Cosmic Velocity Field Reconstruction Using AI
• Revealing the Local Cosmic Web from Galaxies by Deep Learning
• Convolutional Neural Network-reconstructed velocity for kinetic SZ detection
• Cosmology from Galaxy Redshift Surveys with PointNet
• De-noising non-Gaussian fields in cosmology with normalizing flows

Cited by in corpus (7)

• Reconstructing the cosmological density and velocity fields from redshifted galaxy distributions using V-net
• Neural network reconstruction of density and velocity fields from the 2MASS Redshift Survey
• Dynamics of pairwise motions in the fully non-linear regime in LCDM and Modified Gravity cosmologies
• Peculiar Velocity Reconstruction From Simulations and Observations Using Deep Learning Algorithms
• The Velocity Field Olympics: Assessing velocity field reconstructions with direct distance tracers
• AVISM: Algorithm for Void Identification in coSMology
• From Redshift to Real Space: Combining Linear Theory With Neural Networks