Reconstructing the cosmological density and velocity fields from redshifted galaxy distributions using V-net

Abstract

The distribution of matter that is measured through galaxy redshift and peculiar velocity surveys can be harnessed to learn about the physics of dark matter, dark energy, and the nature of gravity. To improve our understanding of the matter of the Universe, we can reconstruct the full density and velocity fields from the galaxies that act as tracer particles. In this paper, we use the simulated halos as proxies for the galaxies. We use a convolutional neural network, a V-net, trained on numerical simulations of structure formation to reconstruct the density and velocity fields. We find that, with detailed tuning of the loss function, the V-net could produce better fits to the density field in the high-density and low-density regions, and improved predictions for the probability distribution of the amplitudes of the velocities. However, the weights will reduce the precision of the estimated $\beta$ parameter. We also find that the redshift-space distortions of the halo catalogue do not significantly contaminate the reconstructed real-space density and velocity field. We estimate the velocity field $\beta$ parameter by comparing the peculiar velocities of halo catalogues to the reconstructed velocity fields, and find the estimated $\beta$ values agree with the fiducial value at the 68\% confidence level.

arXiv comment25 pages, 18 figures, 2 tables. Published JCAP

References in corpus (65)

• Adam: A Method for Stochastic Optimization
• The cosmological simulation code GADGET-2
• Nine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Parameter Results
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Machine learning and the physical sciences
• GADGET: A code for collisionless and gasdynamical cosmological simulations
• The DESI Experiment Part I: Science,Targeting, and Survey Design
• The density and peculiar velocity fields of nearby galaxies
• COLOSSUS: A python toolkit for cosmology, large-scale structure, and dark matter halos
• On the Mass-to-Light Ratio of Large Scale Structure
• Cosmology with Phase 1 of the Square Kilometre Array; Red Book 2018: Technical specifications and performance forecasts
• The halo mass function through the cosmic ages
• Cosmological parameters from the comparison of peculiar velocities with predictions from the 2M++ density field
• Correlated Fluctuations in Luminosity Distance and the (Surprising) Importance of Peculiar Motion in Supernova Surveys
• Wiener Reconstruction of The Large Scale Structure
• WALLABY -- An SKA Pathfinder HI Survey
• PINOCCHIO: pinpointing orbit-crossing collapsed hierarchical objects in a linear density field
• Learning to Predict the Cosmological Structure Formation
• Reconstructed Density and Velocity Fields from the 2MASS Redshift Survey
• The 6dF Galaxy Survey: Peculiar Velocity Field and Cosmography
• A Non Parametric Model for the Cosmic Velocity Field
• An accurate tool for the fast generation of dark matter halo catalogs
• Joint analysis of 6dFGS and SDSS peculiar velocities for the growth rate of cosmic structure and tests of gravity
• The peculiar motions of early-type galaxies in two distant regions - VII. Peculiar velocities and bulk motions
• Cosmic flows in the nearby Universe: new peculiar velocities from SNe and cosmological constraints
• Towards optimal extraction of cosmological information from nonlinear data
• Reconstructing the Cosmic Velocity and Tidal Fields with Galaxy Groups Selected from the Sloan Digital Sky Survey
• Predicting the number, spatial distribution and merging history of dark matter haloes
• The 6dF Galaxy Survey: Bulk Flows on $50-70h^{-1}$ Mpc scales
• Cosmological Parameters from the Comparison of the 2MASS Gravity Field with Peculiar Velocity Surveys
• nIFTy Cosmology: Galaxy/halo mock catalogue comparison project on clustering statistics
• Deriving accurate peculiar velocities (even at high redshift)
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• A rigorous EFT-based forward model for large-scale structure
• Improving fast generation of halo catalogs with higher-order Lagrangian perturbation theory
• The Redshift Space Momentum Power Spectrum II: measuring the growth rate from the combined 2MTF and 6dFGSv surveys
• Radio and X-ray Shocks in Clusters of galaxies
• Shock Waves and Cosmic Ray Acceleration in the Outskirts of Galaxy Clusters
• Machine learning cosmological structure formation
• Reconstruction of cosmological density and velocity fields in the Lagrangian Zel'dovich Approximation
• PINOCCHIO and the hierarchical build-up of dark matter haloes
• FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver
• Constrained realizations of 2MRS density and peculiar velocity fields: growth rate and local flow
• Peculiar Velocity Reconstruction with Fast Action Method: Tests on Mock Redshift Surveys
• Estimating cosmic velocity fields from density fields and tidal tensors
• 2MTF V. Cosmography, Beta, and the residual bulk flow
• On the dissection of degenerate cosmologies with machine learning
• From Dark Matter to Galaxies with Convolutional Networks
• Transverse Velocities with the Moving Lens Effect
• The Role of Machine Learning in the Next Decade of Cosmology
• 2MTF - VII. 2MASS Tully-Fisher survey final data release: distances for 2,062 nearby spiral galaxies
• The Halo Mass-Bias Redshift Evolution in the $\Lambda$CDM Cosmology
• Cosmology with the moving lens effect
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Reconstructing Cosmic Peculiar Velocities from the Mildly Nonlinear Density Field
• A comparison of the galaxy peculiar velocity field with the PSCz gravity field-- A Bayesian hyper-parameter method
• Simulating cosmologies beyond $\Lambda$CDM with PINOCCHIO
• Large-scale density and velocity field reconstructions with neural networks
• Joint velocity and density reconstruction of the Universe with nonlinear differentiable forward modeling
• Revealing the Local Cosmic Web from Galaxies by Deep Learning
• Cosmic Velocity Field Reconstruction Using AI
• The velocity-density relation in the spherical model
• Cosmic Flow Measurement and Mock Sampling Algorithm of Cosmicflows-4 Tully-Fisher Catalogue
• Biased Estimates of Omega from Comparing Smoothed Predicted Velocity Fields to Unsmoothed Peculiar Velocity Measurements
• HI HOD -- I. The Halo Occupation Distribution of HI Galaxies

Cited by in corpus (10)

• Target Selection for the DESI Peculiar Velocity Survey
• Cosmology inference at the field level from biased tracers in redshift-space
• Neural network reconstruction of density and velocity fields from the 2MASS Redshift Survey
• Generalized framework for likelihood-based field-level inference of growth rate from velocity and density fields
• DarkAI: Reconstructing the density, velocity and tidal field of dark matter from a DESI-like bright galaxy sample
• Peculiar Velocity Reconstruction From Simulations and Observations Using Deep Learning Algorithms
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• Lagrangian space remapping and the angular momentum reconstruction from cosmic structures
• Fast Sampling of Cosmological Initial Conditions with Gaussian Neural Posterior Estimation
• On the Connection between Field-Level Inference and $n$-point Correlation Functions