Field Level Neural Network Emulator for Cosmological N-body Simulations

Abstract

We build a field level emulator for cosmic structure formation that is accurate in the nonlinear regime. Our emulator consists of two convolutional neural networks trained to output the nonlinear displacements and velocities of N-body simulation particles based on their linear inputs. Cosmology dependence is encoded in the form of style parameters at each layer of the neural network, enabling the emulator to effectively interpolate the outcomes of structure formation between different flat $\Lambda$CDM cosmologies over a wide range of background matter densities. The neural network architecture makes the model differentiable by construction, providing a powerful tool for fast field level inference. We test the accuracy of our method by considering several summary statistics, including the density power spectrum with and without redshift space distortions, the displacement power spectrum, the momentum power spectrum, the density bispectrum, halo abundances, and halo profiles with and without redshift space distortions. We compare these statistics from our emulator with the full N-body results, the COLA method, and a fiducial neural network with no cosmological dependence. We find our emulator gives accurate results down to scales of $k\sim 1{\mathrm{Mpc}}^{-1}h$, representing a considerable improvement over both COLA and the fiducial neural network. We also demonstrate that our emulator generalizes well to initial conditions containing primordial non-Gaussianity, without the need for any additional style parameters or retraining.

11 pages, 4 figures

References in corpus (21)

• Dark Energy Survey Year 3 Results: Cosmological Constraints from Galaxy Clustering and Weak Lensing
• Fast likelihood-free cosmology with neural density estimators and active learning
• ELUCID - Exploring the Local Universe with reConstructed Initial Density field I: Hamiltonian Markov Chain Monte Carlo Method with Particle Mesh Dynamics
• Towards an Optimal Estimation of Cosmological Parameters with the Wavelet Scattering Transform
• AI-assisted super-resolution cosmological simulations
• Stringent ${\sigma }_8$ constraints from small-scale galaxy clustering using a hybrid MCMC+emulator framework
• Generating Log-normal Mock Catalog of Galaxies in Redshift Space
• Bayesian inference of cosmic density fields from non-linear, scale-dependent, and stochastic biased tracers
• Going Beyond the Galaxy Power Spectrum: an Analysis of BOSS Data with Wavelet Scattering Transforms
• The Aemulus Project V: Cosmological constraint from small-scale clustering of BOSS galaxies
• The BACCO simulation project: biased tracers in real space
• Primordial Non-Gaussianity
• Learning cosmology and clustering with cosmic graphs
• Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
• FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver
• Quijote-PNG: Simulations of primordial non-Gaussianity and the information content of the matter field power spectrum and bispectrum
• Information Content of Higher-Order Galaxy Correlation Functions
• The completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: measurement of the growth rate of structure from the small-scale clustering of the luminous red galaxy sample
• NECOLA: Towards a Universal Field-level Cosmological Emulator
• Combined full shape analysis of BOSS galaxies and eBOSS quasars using an iterative emulator
• Detection of spatial clustering in the 1000 richest SDSS DR8 redMaPPer clusters with Nearest Neighbor distributions

Cited by in corpus (22)

• $\mathrm{S}\mathrm{IM}\mathrm{BIG}$: Mock Challenge for a Forward Modeling Approach to Galaxy Clustering
• Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
• Improving constraints on primordial non-Gaussianity using neural network based reconstruction
• Explaining dark matter halo density profiles with neural networks
• Cosmic Cartography: Bayesian reconstruction of the galaxy density informed by large-scale structure
• $\text{PineTree}$: A generative, fast, and differentiable halo model for wide-field galaxy surveys
• A field-level emulator for modified gravity
• Psi-GAN: A power-spectrum-informed generative adversarial network for the emulation of large-scale structure maps across cosmologies and redshifts
• COmoving Computer Acceleration (COCA): $N$-body simulations in an emulated frame of reference
• Cosmological Inference with Cosmic Voids and Neural Network Emulators
• Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
• Cosmological perturbation theory for large scale structure in phase space
• Analytic auto-differentiable $\Lambda$CDM cosmography
• The First Star-by-star $N$-body/Hydrodynamics Simulation of Our Galaxy Coupling with a Surrogate Model
• Cosmic Strings-induced CMB anisotropies in light of Weighted Morphology
• Towards an optimal extraction of cosmological parameters from galaxy cluster surveys using convolutional neural networks
• Power Spectrum Emulators from Neural Networks and Tree-Based Methods
• Seeing Wiggles without Seeing Wiggles: BAO Recovery in 21 cm Intensity Mapping with Deep Learning
• DeepVoid: A Deep Learning Void Detector
• Predicting large scale cosmological structure evolution with generative adversarial network-based autoencoders
• Incorporating curved geometry in cosmological simulations
• Fast Sampling of Cosmological Initial Conditions with Gaussian Neural Posterior Estimation