Fast and realistic large-scale structure from machine-learning-augmented random field simulations

Abstract

Producing thousands of simulations of the dark matter distribution in the Universe with increasing precision is a challenging but critical task to facilitate the exploitation of current and forthcoming cosmological surveys. Many inexpensive substitutes to full $N$-body simulations have been proposed, even though they often fail to reproduce the statistics of the smaller, non-linear scales. Among these alternatives, a common approximation is represented by the lognormal distribution, which comes with its own limitations as well, while being extremely fast to compute even for high-resolution density fields. In this work, we train a generative deep learning model, mainly made of convolutional layers, to transform projected lognormal dark matter density fields to more realistic dark matter maps, as obtained from full $N$-body simulations. We detail the procedure that we follow to generate highly correlated pairs of lognormal and simulated maps, which we use as our training data, exploiting the information of the Fourier phases. We demonstrate the performance of our model comparing various statistical tests with different field resolutions, redshifts and cosmological parameters, proving its robustness and explaining its current limitations. When evaluated on 100 test maps, the augmented lognormal random fields reproduce the power spectrum up to wavenumbers of $1h{\mathrm{Mpc}}^{-1}$, and the bispectrum within 10%, and always within the error bars, of the fiducial target simulations. Finally, we describe how we plan to integrate our proposed model with existing tools to yield more accurate spherical random fields for weak lensing analysis.

arXiv comment16 pages, 11 figures. Matches MNRAS published version, which includes more tests with e.g. varying cosmological parameters

References in corpus (73)

• Array Programming with NumPy
• The Structure of Cold Dark Matter Halos
• The cosmological simulation code GADGET-2
• Simulating the joint evolution of quasars, galaxies and their large-scale distribution
• Particle Dark Matter: Evidence, Candidates and Constraints
• The Cosmic Linear Anisotropy Solving System (CLASS) II: Approximation schemes
• Semi-Analytic Modelling of Galaxy Formation: The Local Universe
• Resolving Cosmic Structure Formation with the Millennium-II Simulation
• Formation of Galaxy Clusters
• A Recipe for Galaxy Formation Shaun Cole
• Evolution of structure in cold dark matter universes
• Scaling relations for galaxy clusters in the Millennium-XXL simulation
• Solving Large Scale Structure in Ten Easy Steps with COLA
• The Quijote simulations
• Cosmic Complementarity: Joint Parameter Estimation from CMB Experiments and Redshift Surveys
• The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
• Cosmology and the Bispectrum
• nbodykit: an open-source, massively parallel toolkit for large-scale structure
• Correcting for the alias effect when measuring the power spectrum using FFT
• Accurate Estimators of Correlation Functions in Fourier Space
• Learning to Predict the Cosmological Structure Formation
• FastPM: a new scheme for fast simulations of dark matter and halos
• Putting the Precision in Precision Cosmology: How accurate should your data covariance matrix be?
• The Rise and Fall of Satellites in Galaxy Clusters
• EZmocks: extending the Zel'dovich approximation to generate mock galaxy catalogues with accurate clustering statistics
• Primordial non-Gaussianity and Bispectrum Measurements in the Cosmic Microwave Background and Large-Scale Structure
• Mock galaxy catalogs using the quick particle mesh method
• Cosmology with the shear-peak statistics
• Modelling Baryon Acoustic Oscillations with Perturbation Theory and Stochastic Halo Biasing
• How Dark Matter Came to Matter
• Improving lognormal models for cosmological fields
• Cosmology constraints from shear peak statistics in Dark Energy Survey Science Verification data
• Lagrangian theory of gravitational instability of Friedman-Lemaitre cosmologies - generic third-order model for non-linear clustering
• KiDS-450: Cosmological Constraints from Weak Lensing Peak Statistics - II: Inference from Shear Peaks using N-body Simulations
• Cosmological structure formation in a homogeneous dark energy background
• An accurate tool for the fast generation of dark matter halo catalogs
• KiDS-450: Cosmological Constraints from Weak Lensing Peak Statistics-I: Inference from Analytical Prediction of High Signal-to-Noise Ratio Convergence Peaks
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• AI-assisted super-resolution cosmological simulations
• Search for dark matter at colliders
• Cosmic shear covariance: The log-normal approximation
• New Interpretable Statistics for Large Scale Structure Analysis and Generation
• Predicting the number, spatial distribution and merging history of dark matter haloes
• Fast cosmic web simulations with generative adversarial networks
• Lognormal Property of Weak Lensing Fields
• Fourier analysis of luminosity-dependent galaxy clustering
• Estimating Cosmological Parameter Covariance
• Characterizing the non-linear growth of large-scale structure in the Universe
• Cosmic Shear Cosmology Beyond 2-Point Statistics: A Combined Peak Count and Correlation Function Analysis of DES-Y1
• Phase Information and the Evolution of Cosmological Density Perturbations
• A new model to predict weak-lensing peak counts II. Parameter constraint strategies
• A new model to predict weak-lensing peak counts I. Comparison with $N$-body Simulations
• Super-resolution emulator of cosmological simulations using deep physical models
• Optimal capture of non-Gaussianity in weak lensing surveys: power spectrum, bispectrum and halo counts
• CARPool: fast, accurate computation of large-scale structure statistics by pairing costly and cheap cosmological simulations
• Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
• Measuring primordial non-Gaussianity through weak lensing peak counts
• Cosmological constraints from the capture of non-Gaussianity in Weak Lensing data
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• Universal Behavior of Phase Correlations in Non-linear Gravitational Clustering
• Finding universal relations in subhalo properties with artificial intelligence
• A gradient based method for modeling baryons and matter in halos of fast simulations
• A new model to predict weak-lensing peak counts III. Filtering technique comparisons
• Nonlinear 3D Cosmic Web Simulation with Heavy-Tailed Generative Adversarial Networks
• CARPool Covariance: Fast, unbiased covariance estimation for large-scale structure observables
• Simulating cosmologies beyond $\Lambda$CDM with PINOCCHIO
• The Weak Lensing Bispectrum Induced By Gravity
• The DESI $N$-body Simulation Project -- II. Suppressing sample variance with fast simulations
• High mass and halo resolution from fast low resolution simulations
• MUSCLE-UPS: Improved Approximations of the Matter Field with the Extended Press-Schechter Formalism and Lagrangian Perturbation Theory
• Constraining the mass-concentration relation through weak lensing peak function
• Beyond the Lognormal Approximation: a General Simulation Scheme
• Dark Matter with N-Body Numerical Simulations

Cited by in corpus (11)

• KiDS-SBI: Simulation-based inference analysis of KiDS-1000 cosmic shear
• GLASS: Generator for Large Scale Structure
• Quijote-PNG: Quasi-maximum likelihood estimation of Primordial Non-Gaussianity in the non-linear halo density field
• $\text{PineTree}$: A generative, fast, and differentiable halo model for wide-field galaxy surveys
• KiDS-Legacy: Covariance validation and the unified OneCovariance framework for projected large-scale structure observables
• Psi-GAN: A power-spectrum-informed generative adversarial network for the emulation of large-scale structure maps across cosmologies and redshifts
• Secondary halo bias through cosmic time II: Reconstructing halo properties using clustering information
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery
• Neural style transfer of weak lensing mass maps
• Generative modeling of convergence maps based on predicted one-point statistics
• Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra