Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection

Abstract

We present a method to reconstruct the initial conditions of the universe using observed galaxy positions and luminosities under the assumption that the luminosities can be calibrated with weak lensing to give the mean halo mass. Our method relies on following the gradients of forward model and since the standard way to identify halos is non-differentiable and results in a discrete sample of objects, we propose a framework to model the halo position and mass field starting from the non-linear matter field using Neural Networks. We evaluate the performance of our model with multiple metrics. Our model is more than $95\%$ correlated with the halo-mass fields up to $k\sim 0.7h/Mpc$ and significantly reduces the stochasticity over the Poisson shot noise. We develop a data likelihood model that takes our modeling error and intrinsic scatter in the halo mass-light relation into account and show that a displaced log-normal model is a good approximation to it. We optimize over the corresponding loss function to reconstruct the initial density field and develop an annealing procedure to speed up and improve the convergence. We apply the method to halo number densities of $\bar{n}=2.5\times 10^{-4}-10^{-3}(h/Mpc{)}^3$, typical of current and future redshift surveys, and recover a Gaussian initial density field, mapping all the higher order information in the data into the power spectrum. We show that our reconstruction improves over the standard reconstruction. For baryonic acoustic oscillations (BAO) the gains are relatively modest because BAO is dominated by large scales where standard reconstruction suffices. We improve upon it by $\sim 15-20\%$ in terms of error on BAO peak as estimated by Fisher analysis at $z=0$. We expect larger gains will be achieved when applying this method to the broadband linear power spectrum reconstruction on smaller scales.

33 pages, 15 figures

References in corpus (10)

• Improving Cosmological Distance Measurements by Reconstruction of the Baryon Acoustic Peak
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• ELUCID - Exploring the Local Universe with reConstructed Initial Density field I: Hamiltonian Markov Chain Monte Carlo Method with Particle Mesh Dynamics
• Beyond Assembly Bias: Exploring Secondary Halo Biases for Cluster-size Haloes
• Towards optimal extraction of cosmological information from nonlinear data
• Iterative initial condition reconstruction
• Reconstructing the cosmic density field with the distribution of dark matter halos
• Fast cosmological parameter estimation using neural networks
• Halo bias in Lagrangian Space: Estimators and theoretical predictions
• Halo nonlinear reconstruction

Cited by in corpus (60)

• Cosmological Parameters and Neutrino Masses from the Final Planck and Full-Shape BOSS Data
• Modeling Biased Tracers at the Field Level
• Nearest Neighbor distributions: new statistical measures for cosmological clustering
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• AI-assisted super-resolution cosmological simulations
• A rigorous EFT-based forward model for large-scale structure
• The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
• Reconstructing large-scale structure with neutral hydrogen surveys
• Forecasts on Primordial non-Gaussianity from 21 cm Intensity Mapping experiments
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
• TARDIS Paper I: A Constrained Reconstruction Approach to Modeling the z~2.5 Cosmic Web Probed by Lyman-alpha Forest Tomography
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• ADDGALS: Simulated Sky Catalogs for Wide Field Galaxy Surveys
• A fast particle-mesh simulation of non-linear cosmological structure formation with massive neutrinos
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• The Reconstructed Power Spectrum in the Zeldovich Approximation
• AI-assisted super-resolution cosmological simulations II: Halo substructures, velocities and higher order statistics
• Consistency tests of field level inference with the EFT likelihood
• Impacts of the physical data model on the forward inference of initial conditions from biased tracers
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Reconstructing Cosmological Initial Conditions from Late-Time Structure with Convolutional Neural Networks
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• Cosmology inference at the field level from biased tracers in redshift-space
• Weighing neutrinos with the halo environment
• HInet: Generating neutral hydrogen from dark matter with neural networks
• Reconstructing the cosmological density and velocity fields from redshifted galaxy distributions using V-net
• Effective cosmic density field reconstruction with convolutional neural network
• Cosmological constraints from the power spectrum and bispectrum of 21cm intensity maps
• Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
• Joint velocity and density reconstruction of the Universe with nonlinear differentiable forward modeling
• Probing primordial non-Gaussianity with the power spectrum and bispectrum of future 21cm intensity maps
• Revealing the Local Cosmic Web from Galaxies by Deep Learning
• TARDIS Paper II: Synergistic Density Reconstruction from Lyman-alpha Forest and Spectroscopic Galaxy Surveys with Applications to Protoclusters and the Cosmic Web
• Cosmic Velocity Field Reconstruction Using AI
• LINNA: Likelihood Inference Neural Network Accelerator
• (DarkAI) Mapping the large-scale density field of dark matter using artificial intelligence
• Reconstructing dark matter distribution with peculiar velocities: Bayesian forward modelling with corrections for inhomogeneous Malmquist bias
• Reconstructing the Universe with Variational self-Boosted Sampling
• Biased tracer reconstruction with halo mass information
• HyPhy: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics
• AI-assisted super-resolution cosmological simulations III: Time evolution
• On the primordial information available to galaxy redshift surveys
• $\text{PineTree}$: A generative, fast, and differentiable halo model for wide-field galaxy surveys
• Reconstruction with velocities
• Nonlinear Reconstruction of the Velocity Field
• Optimal machine-driven acquisition of future cosmological data
• The HalfDome Multi-Survey Cosmological Simulations: N-body Simulations
• Differentiable Cosmological Hydrodynamics for Field-Level Inference and High Dimensional Parameter Constraints
• Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
• Field-level Reconstruction from Foreground-Contaminated 21-cm Maps
• Mind the gap: the power of combining photometric surveys with intensity mapping
• Map Reconstruction of radio observations with Conditional Invertible Neural Networks
• Bye-bye, Local-in-matter-density Bias: The Statistics of the Halo Field Are Poorly Determined by the Local Mass Density
• Dipole Distortions in the Intergalactic Medium
• Impact of astrophysical effects on the dark matter mass constraint with 21cm intensity mapping
• On the Connection between Field-Level Inference and $n$-point Correlation Functions
• DeepVoid: A Deep Learning Void Detector
• Testing Large-Scale Structure Measurements Against Fisher Matrix Predictions