PkANN - II. A non-linear matter power spectrum interpolator developed using artificial neural networks

Abstract

In this paper we introduce PkANN, a freely available software package for interpolating the non-linear matter power spectrum, constructed using Artificial Neural Networks (ANNs). Previously, using Halofit to calculate matter power spectrum, we demonstrated that ANNs can make extremely quick and accurate predictions of the power spectrum. Now, using a suite of 6380 N-body simulations spanning 580 cosmologies, we train ANNs to predict the power spectrum over the cosmological parameter space spanning $3\sigma$ confidence level (CL) around the concordance cosmology. When presented with a set of cosmological parameters (${\Omega }_{\mathrm{m}}{h}^2,{\Omega }_{\mathrm{b}}{h}^2,n_s,w,{\sigma }_8,\sum m_{\nu }$ and redshift $z$), the trained ANN interpolates the power spectrum for $z\le 2$ at sub-per cent accuracy for modes up to $k\le 0.9h{\text{Mpc}}^{-1}$. PkANN is faster than computationally expensive N-body simulations, yet provides a worst-case error $<1$ per cent fit to the non-linear matter power spectrum deduced through N-body simulations. The overall precision of PkANN is set by the accuracy of our N-body simulations, at 5 per cent level for cosmological models with $\sum m_{\nu }<0.5$ eV for all redshifts $z\le 2$. For models with $\sum m_{\nu }>0.5$ eV, predictions are expected to be at 5 (10) per cent level for redshifts $z>1$ ($z\le 1$). The PkANN interpolator may be freely downloaded from http://zuserver2.star.ucl.ac.uk/~fba/PkANN

21 pages, 14 figures, 2 tables

References in corpus (11)

• Effects of Baryons and Dissipation on the Matter Power Spectrum
• The Effect of Thermal Neutrino Motion on the Non-linear Cosmological Matter Power Spectrum
• Impact of massive neutrinos on nonlinear matter power spectrum
• Cosmic Calibration: Constraints from the Matter Power Spectrum and the Cosmic Microwave Background
• Nonlinear power spectrum in the presence of massive neutrinos: perturbation theory approach, galaxy bias and parameter forecasts
• Cosmic Calibration
• Perturbation Theory Reloaded II: Non-linear Bias, Baryon Acoustic Oscillations and Millennium Simulation In Real Space
• Fast cosmological parameter estimation using neural networks
• {\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
• PkANN - I. Non-linear matter power spectrum interpolation through artificial neural networks
• Pico: Parameters for the Impatient Cosmologist

Cited by in corpus (43)

• An accurate halo model for fitting non-linear cosmological power spectra and baryonic feedback models
• HMcode-2020: Improved modelling of non-linear cosmological power spectra with baryonic feedback
• Accurate halo-model matter power spectra with dark energy, massive neutrinos and modified gravitational forces
• Dark Quest. I. Fast and Accurate Emulation of Halo Clustering Statistics and Its Application to Galaxy Clustering
• The BACCO Simulation Project: Exploiting the full power of large-scale structure for cosmology
• COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys
• The Mira-Titan Universe II: Matter Power Spectrum Emulation
• Cosmological constraints from the tomographic cross-correlation of DESI Luminous Red Galaxies and Planck CMB lensing
• 2MTF VI. Measuring the velocity power spectrum
• Analysing the 21cm signal from the Epoch of Reionization with artificial neural networks
• Cosmology with the Large Synoptic Survey Telescope: an Overview
• Cosmological constraints from the CFHTLenS shear measurements using a new, accurate and flexible way of predicting nonlinear mass clustering
• Accurate emulator for the redshift-space power spectrum of dark matter halos and its application to galaxy power spectrum
• Matter Power Spectrum Emulator for f(R) Modified Gravity Cosmologies
• Dreaming of atmospheres
• Including beyond-linear halo bias in halo models
• FORGE -- the f(R) gravity cosmic emulator project I: Introduction and matter power spectrum emulator
• Precision modelling of the matter power spectrum in a Planck-like Universe
• CosmicNet II: Emulating extended cosmologies with efficient and accurate neural networks
• Kernel-Based Emulator for the 3D Matter Power Spectrum from CLASS
• Machine Learning for Observational Cosmology
• Improving constraints on the reionization parameters using 21-cm bispectrum
• Non-Linear Matter Power Spectrum Covariance Matrix Errors and Cosmological Parameter Uncertainties
• Extending the Coyote emulator to dark energy models with standard $w_0$-$w_a$ parametrization of the equation of state
• Multi-Fidelity Emulation for the Matter Power Spectrum using Gaussian Processes
• $\text{matryoshka}$: Halo Model Emulator for the Galaxy Power Spectrum
• Parameter Inference for Weak Lensing using Gaussian Processes and MOPED
• CSST Cosmological Emulator I: Matter Power Spectrum Emulation with one percent accuracy to k = 10 h/Mpc
• Analysis of Unified Galaxy Power Spectrum Multipole Measurements
• Fitting and forecasting non-linear coupled dark energy
• The e-MANTIS emulator: fast predictions of the non-linear matter power spectrum in $f(R)$CDM cosmology
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• LINNA: Likelihood Inference Neural Network Accelerator
• $\text{matryoshka}$ II: Accelerating Effective Field Theory Analyses of the Galaxy Power Spectrum
• Non-parametric reconstruction of cosmological observables using Gaussian Processes Regression
• The Peculiar Velocity Correlation Function
• FREmu: Power Spectrum Emulator for $f(R)$ Gravity
• Analysing the Epoch of Reionization with three-point correlation functions and machine learning techniques
• DeepSSM: an emulator of gravitational wave spectra from sound waves during cosmological first-order phase transitions
• An Optimally Weighted Estimator of the Linear Power Spectrum Disentangling the Growth of Density Perturbations Across Galaxy Surveys
• Power Spectrum Emulators from Neural Networks and Tree-Based Methods
• On the accuracy of posterior recovery with neural network emulators
• Neural Network Acceleration of Large-scale Structure Theory Calculations