NECOLA: Towards a Universal Field-level Cosmological Emulator

Abstract

We train convolutional neural networks to correct the output of fast and approximate N-body simulations at the field level. Our model, Neural Enhanced COLA --NECOLA--, takes as input a snapshot generated by the computationally efficient COLA code and corrects the positions of the cold dark matter particles to match the results of full N-body Quijote simulations. We quantify the accuracy of the network using several summary statistics, and find that NECOLA can reproduce the results of the full N-body simulations with sub-percent accuracy down to $k\simeq 1h{\mathrm{Mpc}}^{-1}$. Furthermore, the model, that was trained on simulations with a fixed value of the cosmological parameters, is also able to correct the output of COLA simulations with different values of ${\Omega }_{\mathrm{m}}$, ${\Omega }_{\mathrm{b}}$, $h$, $n_s$, ${\sigma }_8$, $w$, and $M_{\nu }$ with very high accuracy: the power spectrum and the cross-correlation coefficients are within $\simeq 1\%$ down to $k=1h{\mathrm{Mpc}}^{-1}$. Our results indicate that the correction to the power spectrum from fast/approximate simulations or field-level perturbation theory is rather universal. Our model represents a first step towards the development of a fast field-level emulator to sample not only primordial mode amplitudes and phases, but also the parameter space defined by the values of the cosmological parameters.

9 pages, 3 figures and 1 table

References in corpus (5)

• AbacusSummit: A Massive Set of High-Accuracy, High-Resolution $N$-Body Simulations
• The Mira-Titan Universe II: Matter Power Spectrum Emulation
• Constraining $M_{\nu }$ with the Bispectrum II: The Total Information Content of the Galaxy Bispectrum
• The halo model in a massive neutrino cosmology
• Generating Log-normal Mock Catalog of Galaxies in Redshift Space

Cited by in corpus (20)

• Large-scale dark matter simulations
• The CAMELS project: public data release
• Going Beyond the Galaxy Power Spectrum: an Analysis of BOSS Data with Wavelet Scattering Transforms
• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• Field Level Neural Network Emulator for Cosmological N-body Simulations
• Machine Learning for Observational Cosmology
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
• Enabling matter power spectrum emulation in beyond-$\Lambda$CDM cosmologies with COLA
• Revisiting Vainshtein Screening for fast N-body simulations
• Cosmic Cartography: Bayesian reconstruction of the galaxy density informed by large-scale structure
• Quijote-PNG: Quasi-maximum likelihood estimation of Primordial Non-Gaussianity in the non-linear halo density field
• A tomographic spherical mass map emulator of the KiDS-1000 survey using conditional generative adversarial networks
• A field-level emulator for modified gravity
• Cosmological Inference with Cosmic Voids and Neural Network Emulators
• Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
• Power Spectrum Emulators from Neural Networks and Tree-Based Methods
• Towards an optimal extraction of cosmological parameters from galaxy cluster surveys using convolutional neural networks
• nuGAN: Generative Adversarial Emulator for Cosmic Web with Neutrinos
• Improving cosmological covariance matrices with machine learning