(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 (12)

• Galaxy Groups in the SDSS DR4: I. The Catalogue and Basic Properties
• Transients from Initial Conditions in Cosmological Simulations
• Improving Cosmological Distance Measurements by Reconstruction of the Baryon Acoustic Peak
• Galaxy Groups in the SDSS DR4: II. halo occupation statistics
• Towards a Concordant Model of Halo Occupation Statistics
• Density profiles of galaxy groups and clusters from SDSS galaxy-galaxy weak lensing
• 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
• Reconstructing the cosmic density field with the distribution of dark matter halos
• Scale-dependent Galaxy Bias
• Mapping the real space distributions of galaxies in SDSS DR7: I. Two Point Correlation Functions
• Cosmic Velocity Field Reconstruction Using AI

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