(DarkAI) Mapping the large-scale density field of dark matter using artificial intelligence

Abstract

Herein, we present a deep-learning technique for reconstructing the dark-matter density field from the redshift-space distribution of dark-matter halos. We built a UNet-architecture neural network and trained it using the COmoving Lagrangian Acceleration fast simulation, which is an approximation of the N-body simulation with $512^3$ particles in a box size of 500 Mpc $h^{-1}$. Further, we tested the resulting UNet model not only with training-like test samples but also with standard N-body simulations, such as the Jiutian simulation with $6144^3$ particles in a box size of 1000 Mpc $h^{-1}$ and the ELUCID simulation, which has a different cosmology. The real-space dark-matter density fields in the three simulations can be reconstructed reliably with only a small reduction of the cross-correlation power spectrum at 1% and 10% levels at $k=0.1$ and $0.3h\mathrm{Mp}{\mathrm{c}}^{-1}$, respectively. The reconstruction clearly helps to correct for redshift-space distortions and is unaffected by the different cosmologies between the training (Planck2018) and test samples (WMAP5). Furthermore, we tested the application of the UNet-reconstructed density field to obtain the velocity \& tidal field and found that this approach provides better results compared to the traditional approach based on the linear bias model, showing a 12.2% improvement in the correlation slope and a 21.1% reduction in the scatter between the predicted and true velocities. Thus, our method is highly efficient and has excellent extrapolation reliability beyond the training set. This provides an ideal solution for determining the three-dimensional underlying density field from the plentiful galaxy survey data.

14 pages, 16 figures

References in corpus (59)

• The Sloan Digital Sky Survey: Technical Summary
• The cosmological simulation code GADGET-2
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The 2dF Galaxy Redshift Survey: Spectra and redshifts
• Halo occupation numbers and galaxy bias
• Galaxy Groups in the SDSS DR4: I. The Catalogue and Basic Properties
• Theoretical Models of the Halo Occupation Distribution: Separating Central and Satellite Galaxies
• The 2dF Galaxy Redshift Survey: correlation functions, peculiar velocities and the matter density of the Universe
• A measurement of the cosmological mass density from clustering in the 2dF Galaxy Redshift Survey
• Transients from Initial Conditions in Cosmological Simulations
• Constraining Galaxy Formation and Cosmology with the Conditional Luminosity Function of Galaxies
• New constraints on the evolution of the stellar-to-dark matter connection: a combined analysis of galaxy-galaxy lensing, clustering, and stellar mass functions from z=0.2 to z=1
• Improving Cosmological Distance Measurements by Reconstruction of the Baryon Acoustic Peak
• Fingers of God
• A Halo-Based Galaxy Group Finder: Calibration and Application to the 2dFGRS
• Spatial correlation function and pairwise velocity dispersion of galaxies: CDM models versus the Las Campanas Survey
• On the Mass-to-Light Ratio of Large Scale Structure
• Solving Large Scale Structure in Ten Easy Steps with COLA
• 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)
• Towards a Concordant Model of Halo Occupation Statistics
• Linking Early and Late Type Galaxies to their Dark Matter Haloes
• Density profiles of galaxy groups and clusters from SDSS galaxy-galaxy weak lensing
• Wiener Reconstruction of The Large Scale Structure
• Learning to Predict the Cosmological Structure Formation
• Clustering in the 1.2 Jy IRAS Galaxy Redshift Survey II: Redshift Distortions and ξ(r_p,π)
• Satellite Kinematics II: The Halo Mass-Luminosity Relation of Central Galaxies in SDSS
• Red Galaxy Growth and the Halo Occupation Distribution
• Galaxy Clustering & Galaxy-Galaxy Lensing: A Promising Union to Constrain Cosmological Parameters
• ELUCID - Exploring the Local Universe with reConstructed Initial Density field I: Hamiltonian Markov Chain Monte Carlo Method with Particle Mesh Dynamics
• ELUCID - Exploring the Local Universe with reConstructed Initial Density field III: Constrained Simulation in the SDSS Volume
• 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
• An Extended Halo-based Group/Cluster finder: application to the DESI legacy imaging surveys DR8
• Fast cosmic web simulations with generative adversarial networks
• The 2dF Galaxy Redshift Survey: Wiener Reconstruction of the Cosmic Web
• Reconstructing the Initial Density Field of the Local Universe: Method and Test with Mock Catalogs
• Reconstructing the cosmic density field with the distribution of dark matter halos
• Fast and accurate mock catalogue generation for low-mass galaxies
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• Machine learning cosmological structure formation
• 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 $0.1$
• Classifying the Large Scale Structure of the Universe with Deep Neural Networks
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• On density and velocity fields and beta from the IRAS PSCz survey
• An interpretable machine learning framework for dark matter halo formation
• Scale-dependent Galaxy Bias
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• The specific star formation rate and stellar mass fraction of low-mass central galaxies in cosmological simulations
• 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
• Linking haloes to galaxies: how many halo properties are needed?
• Cosmic Velocity Field Reconstruction Using AI
• Measurement of Redshift Space Power Spectrum for BOSS galaxies and the Growth Rate at redshift 0.57
• ELUCID -- Exploring the Local Universe with the reConstructed Initial Density field. II: Reconstruction diagnostics, applied to numerical halo catalogs
• 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 (11)

• Statistical properties of filaments in the cosmic web
• DarkAI: Reconstructing the density, velocity and tidal field of dark matter from a DESI-like bright galaxy sample
• Improving Constraint on ${\Omega }_m$ from SDSS Using Marked Correlation Functions
• Galaxy and halo properties around cosmic filaments from Sloan Digital Sky Survey Data Release 7 and the ELUCID simulation
• Deep learning for cosmological parameter inference from a dark matter halo density field
• GrAviPaSt's Lens to the Past: Unveiling the Evolution of Filamentary Structures
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• Fast Sampling of Cosmological Initial Conditions with Gaussian Neural Posterior Estimation
• ELUCID-DESI I: A Parallel MPI Implementation of the Initial Condition Solver for Large-Scale Reconstruction Simulations
• Enhancing Cosmological Constraints by Two-dimensional $\beta$-cosmic-web Weighted Angular Correlation Functions
• The Filament Rift: $\Lambda$CDM's Structural Challenge Against Observation