DarkAI: Reconstructing the density, velocity and tidal field of dark matter from a DESI-like bright galaxy sample

Abstract

Reconstructing the mass density, velocity, and tidal (MTV) fields of dark matter from galaxy surveys is essential for advancing our understanding of the LSS of the Universe. In this work, we present a machine learning-based framework using a UNet convolutional neural network to reconstruct the MTV fields from mock samples of the DESI bright galaxy survey within the redshift range $0.1<z<0.4$. Our approach accounts for realistic observational effects, including geometric selection, flux-limited data, and redshift space distortion (RSD) effects, thereby improving the fidelity of the reconstructed fields. Testing on mock galaxy catalogs generated from the Jiutian N-body simulation, our method achieves significant accuracy level. The reconstructed density field exhibits strong consistency with the true field, effectively eliminating most RSD effects and achieving a cross-correlation power spectrum coefficient greater than 0.985 on scales with $k<0.1h{\mathrm{Mpc}}^{-1}$. The velocity field reconstruction accurately captures large-scale coherent flows and small-scale turbulent features, exhibiting slopes of grid-to-grid relationships close to unity and scatter below $\sim$100 $\mathrm{km}{\mathrm{s}}^{-1}$. Additionally, the tidal field is reconstructed without bias, successfully recovering the features of the large-scale cosmic web, including clusters, filaments, sheets, and voids. Our results confirm that the proposed framework effectively captures the large-scale distribution and dynamics of dark matter while addressing key systematic challenges. These advancements provide a reliable and robust tool for analyzing current and future galaxy surveys, paving the way for new insights into cosmic structure formation and evolution.

arXiv comment23 pages, 20 figures

References in corpus (65)

• Array Programming with NumPy
• The NumPy array: a structure for efficient numerical computation
• The Sloan Digital Sky Survey: Technical Summary
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• The cosmological simulation code GADGET-2
• The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The 2dF Galaxy Redshift Survey: Spectra and redshifts
• The Dark Side of the Halo Occupation Distribution
• The Connection between Galaxies and their Dark Matter Halos
• Modeling Luminosity-Dependent Galaxy Clustering Through Cosmic Time
• Linking halo mass to galaxy luminosity
• Fingers of God
• The Early Data Release of the Dark Energy Spectroscopic Instrument
• Evolution of the Galaxy - Dark Matter Connection and the Assembly of Galaxies in Dark Matter Halos
• Galaxy Groups in the SDSS DR4: II. halo occupation statistics
• Cosmology from the Chinese Space Station Optical Survey (CSS-OS)
• The Atacama Cosmology Telescope: A Catalog of > 4000 Sunyaev-Zel'dovich Galaxy Clusters
• DESI 2024 III: Baryon Acoustic Oscillations from Galaxies and Quasars
• DESI Bright Galaxy Survey: Final Target Selection, Design, and Validation
• Correlated Fluctuations in Luminosity Distance and the (Surprising) Importance of Peculiar Motion in Supernova Surveys
• Wiener Reconstruction of The Large Scale Structure
• Galaxy spin alignment in filaments and sheets: observational evidence
• The Clustering of DESI-like Luminous Red Galaxies Using Photometric Redshifts
• Masses of galaxy clusters from gravitational lensing
• Primordial non-Gaussianity from the large scale structure
• ELUCID - Exploring the Local Universe with reConstructed Initial Density field III: Constrained Simulation in the SDSS Volume
• The effect of peculiar velocities on supernova cosmology
• HBT+: an improved code for finding subhalos and building merger trees in cosmological simulations
• Resolving Subhaloes' Lives with the Hierarchical Bound-Tracing Algorithm
• On the road to percent accuracy: nonlinear reaction of the matter power spectrum to dark energy and modified gravity
• Wiener Reconstruction of Density, Velocity, and Potential Fields from All-Sky Galaxy Redshift Surveys
• Cosmic flows in the nearby Universe: new peculiar velocities from SNe and cosmological constraints
• Simulating the Formation of the Local Galaxy Population
• Reconstructing the Cosmic Velocity and Tidal Fields with Galaxy Groups Selected from the Sloan Digital Sky Survey
• Constraining local non-Gaussianities with kSZ tomography
• The 2dF Galaxy Redshift Survey: Wiener Reconstruction of the Cosmic Web
• Reconstructing the cosmic density field with the distribution of dark matter halos
• Reconstructing the Initial Density Field of the Local Universe: Method and Test with Mock Catalogs
• DESI 2024 II: Sample Definitions, Characteristics, and Two-point Clustering Statistics
• Reconstructing cosmological initial conditions from galaxy peculiar velocities. I. Reverse Zeldovich Approximation
• Large-Scale Bulk Motions Complicate the Hubble Diagram
• Mapping the Real Space Distributions of Galaxies in SDSS DR7: II. Measuring the growth rate, clustering amplitude of matter and biases of galaxies at redshift $0.1$
• Possible observational evidence that cosmic filaments spin
• Cosmological parameters from the likelihood analysis of the galaxy power spectrum and bispectrum in real space
• The kinetic SZ tomography with spectroscopic redshift surveys
• On density and velocity fields and beta from the IRAS PSCz survey
• Scale-dependent Galaxy Bias
• Mapping the real space distributions of galaxies in SDSS DR7: I. Two Point Correlation Functions
• Scale dependence of galaxy biasing investigated by weak gravitational lensing: An assessment using semi-analytic galaxies and simulated lensing data
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Relative velocity of dark matter and barions in clusters of galaxies and measurements of their peculiar velocities
• Reconstructing the cosmological density and velocity fields from redshifted galaxy distributions using V-net
• Effective cosmic density field reconstruction with convolutional neural network
• Cosmic Velocity Field Reconstruction Using AI
• X-ray Cluster Constraints on Non-Gaussianity
• Weak-Lensing Detection of Intracluster Filaments in the Coma Cluster
• (DarkAI) Mapping the large-scale density field of dark matter using artificial intelligence
• ELUCID -- Exploring the Local Universe with the reConstructed Initial Density field. II: Reconstruction diagnostics, applied to numerical halo catalogs
• CSST large-scale structure analysis pipeline: I. constructing reference mock galaxy redshift surveys
• The sparkling Universe: a scenario for cosmic void motions
• Narrowing down the Hubble tension to the first two rungs of distance ladders
• 21-cm foreground removal using AI and frequency-difference technique
• Nonlinear Reconstruction of the Velocity Field
• Toward a more stringent test of gravity with redshift space power spectrum: simultaneous probe of growth and amplitude of large-scale structure

Cited by in corpus (2)

• ELUCID-DESI I: A Parallel MPI Implementation of the Initial Condition Solver for Large-Scale Reconstruction Simulations
• From Redshift to Real Space: Combining Linear Theory With Neural Networks