From Redshift to Real Space: Combining Linear Theory With Neural Networks

Abstract

Spectroscopic redshift surveys are key tools to trace the large-scale structure (LSS) of the Universe and test the $\Lambda$CDM model. However, using redshifts as distance proxies introduces distortions in the 3D galaxy distribution. If uncorrected, these distortions lead to systematic errors in LSS analyses and cosmological parameter estimation. We present a new method that combines linear theory (LT) and a neural network (NN) to mitigate redshift space distortions (RSDs). The hybrid LT+NN approach is trained and validated on dark matter halo fields from z = 1 snapshots of the Quijote N-body simulations. LT corrects large-scale distortions in the linear regime, while the NN learns quasi-linear and small-scale features. The LT correction is applied first, then the NN is trained on the resulting fields to improve accuracy across scales. The method uses a Mean Squared Error (MSE) loss and yields significant performance gains: approximately 50% improvement over LT alone and 12% over NN alone. The reconstructed fields from the LT+NN method show stronger correlations with the true real-space fields than either LT or NN separately. The hybrid method also improves clustering statistics such as halo-halo and halo-void correlations, with benefits extending to BAO scales. Compared to NN-only, it provides better suppression of spurious anisotropies on large and quasi-linear scales, as measured by the quadrupole moments of correlation functions. This work shows that combining a physically motivated dynamical model with a machine learning algorithm leverages the strengths of both approaches. The LT+NN method achieves high accuracy with modest training data and computational cost, making it a promising tool for future applications to more realistic galaxy surveys.

13 pages, 10 figures

References in corpus (28)

• Detection of the Baryon Acoustic Peak in the Large-Scale Correlation Function of SDSS Luminous Red Galaxies
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• A 2% Distance to z=0.35 by Reconstructing Baryon Acoustic Oscillations - I : Methods and Application to the Sloan Digital Sky Survey
• Euclid. I. Overview of the Euclid mission
• DESI DR2 Results II: Measurements of Baryon Acoustic Oscillations and Cosmological Constraints
• Fingers of God
• ZOBOV: a parameter-free void-finding algorithm
• The Quijote simulations
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Linear Redshift Distortions: A Review
• Precision cosmography with stacked voids
• A reconstruction of the initial conditions of the Universe by optimal mass transportation
• Beyond BAO: improving cosmological constraints from BOSS with measurement of the void-galaxy cross-correlation
• SOMz: photometric redshift PDFs with self organizing maps and random atlas
• A measurement of the Alcock-Paczynski effect using cosmic voids in the SDSS
• Reconstruction within the Zeldovich approximation
• An optimal FFT-based anisotropic power spectrum estimator
• Reconstruction in Fourier space
• Reconstructing Cosmological Initial Conditions from Late-Time Structure with Convolutional Neural Networks
• BAO reconstruction: a swift numerical action method for massive spectroscopic surveys
• Optimal Reconstruction of Baryon Acoustic Oscillations for DESI 2024
• Large-scale density and velocity field reconstructions with neural networks
• Euclid: Cosmology forecasts from the void-galaxy cross-correlation function with reconstruction
• Effective cosmic density field reconstruction with convolutional neural network
• Revealing the Local Cosmic Web from Galaxies by Deep Learning
• Neural network reconstruction of density and velocity fields from the 2MASS Redshift Survey
• 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