A tomographic spherical mass map emulator of the KiDS-1000 survey using conditional generative adversarial networks

Abstract

Large sets of matter density simulations are becoming increasingly important in large-scale structure cosmology. Matter power spectra emulators, such as the Euclid Emulator and CosmicEmu, are trained on simulations to correct the non-linear part of the power spectrum. Map-based analyses retrieve additional non-Gaussian information from the density field, whether through human-designed statistics such as peak counts, or via machine learning methods such as convolutional neural networks. The simulations required for these methods are very resource-intensive, both in terms of computing time and storage. Map-level density field emulators, based on deep generative models, have recently been proposed to address these challenges. In this work, we present a novel mass map emulator of the KiDS-1000 survey footprint, which generates noise-free spherical maps in a fraction of a second. It takes a set of cosmological parameters $({\Omega }_M,{\sigma }_8)$ as input and produces a consistent set of 5 maps, corresponding to the KiDS-1000 tomographic redshift bins. To construct the emulator, we use a conditional generative adversarial network architecture and the spherical CNN $\text{DeepSphere}$, and train it on N-body-simulated mass maps. We compare its performance using an array of quantitative comparison metrics: angular power spectra $C_{\ell }$, pixel/peaks distributions, $C_{\ell }$ correlation matrices, and Structural Similarity Index. Overall, the average agreement on these summary statistics is $<10\%$ for the cosmologies at the centre of the simulation grid, and degrades slightly on grid edges. Finally, we perform a mock cosmological parameter estimation using the emulator and the original simulation set. We find good agreement in these constraints, for both likelihood and likelihood-free approaches. The emulator is available at https://tfhub.dev/cosmo-group-ethz/models/kids-cgan/1.

38 pages, 17 figures, 2 tables. Link to software: https://tfhub.dev/cosmo-group-ethz/models/kids-cgan/1

References in corpus (64)

• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Generative Adversarial Networks
• Generative Adversarial Networks: An Overview
• Geometric deep learning: going beyond Euclidean data
• Revising the Halofit Model for the Nonlinear Matter Power Spectrum
• First Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Angular Power Spectrum
• KiDS-1000 Cosmology: Cosmic shear constraints and comparison between two point statistics
• The Fourteenth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the extended Baryon Oscillation Spectroscopic Survey and from the second phase of the Apache Point Observatory Galactic Evolution Experiment
• Cosmology with cosmic shear observations: a review
• Weak Gravitational Lensing by Large-Scale Structure
• Dark Energy Survey Year 3 Results: Cosmology from Cosmic Shear and Robustness to Data Calibration
• Dark Energy Survey Year 3 Results: Cosmology from Cosmic Shear and Robustness to Modeling Uncertainty
• Weak lensing for precision cosmology
• Dark Energy Survey Year 1 Results: Constraints on Extended Cosmological Models from Galaxy Clustering and Weak Lensing
• HMcode-2020: Improved modelling of non-linear cosmological power spectra with baryonic feedback
• Cosmological constraints from cosmic shear two-point correlation functions with HSC survey first-year data
• Dark Energy Survey Year 1 Results: A Precise H0 Measurement from DES Y1, BAO, and D/H Data
• Parameter inference with estimated covariance matrices
• Fast likelihood-free cosmology with neural density estimators and active learning
• Learning to Predict the Cosmological Structure Formation
• The Three-Point Correlation Function in Cosmology
• The BACCO Simulation Project: Exploiting the full power of large-scale structure for cosmology
• Euclid preparation: II. The EuclidEmulator -- A tool to compute the cosmology dependence of the nonlinear matter power spectrum
• Cosmology with the shear-peak statistics
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• CFHTLenS: Cosmological constraints from a combination of cosmic shear two-point and three-point correlations
• Galaxy alignments: Observations and impact on cosmology
• KiDS-1000 catalogue: Redshift distributions and their calibration
• KiDS-1000 catalogue: Weak gravitational lensing shear measurements
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• KiDS-1000 Cosmology: constraints beyond flat $\Lambda$CDM
• The Mira-Titan Universe II: Matter Power Spectrum Emulation
• Non-Gaussian information from weak lensing data via deep learning
• KiDS-1000 Methodology: Modelling and inference for joint weak gravitational lensing and spectroscopic galaxy clustering analysis
• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• Automatic physical inference with information maximising neural networks
• Dependence of cosmic shear covariances on cosmology - Impact on parameter estimation
• Dark Energy Survey Year 1 Results: Curved-Sky Weak Lensing Mass Map
• Fast cosmic web simulations with generative adversarial networks
• Baryonic effects for weak lensing. Part I. Power spectrum and covariance matrix
• Cosmology with Minkowski functionals and moments of the weak lensing convergence field
• Cosmological constraints from noisy convergence maps through deep learning
• Cosmic Shear Cosmology Beyond 2-Point Statistics: A Combined Peak Count and Correlation Function Analysis of DES-Y1
• Dark matter statistics for large galaxy catalogs: power spectra and covariance matrices
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• Distinguishing standard and modified gravity cosmologies with machine learning
• Dark Energy Survey Year 3 results: cosmology with moments of weak lensing mass maps -- validation on simulations
• Cosmological Forecast for non-Gaussian Statistics in large-scale weak Lensing Surveys
• astroABC: An Approximate Bayesian Computation Sequential Monte Carlo sampler for cosmological parameter estimation
• Optimal capture of non-Gaussianity in weak lensing surveys: power spectrum, bispectrum and halo counts
• Euclid: impact of nonlinear prescriptions on cosmological parameter estimation from weak lensing cosmic shear
• The cosmological information of shear peaks: beyond the abundance
• Lossless, Scalable Implicit Likelihood Inference for Cosmological Fields
• CosmoGridV1: a simulated $w$CDM theory prediction for map-level cosmological inference
• Simultaneously constraining cosmology and baryonic physics via deep learning from weak lensing
• NECOLA: Towards a Universal Field-level Cosmological Emulator
• Fast Generation of Covariance Matrices for Weak Lensing
• Neural networks as optimal estimators to marginalize over baryonic effects
• Fast Lightcones for Combined Cosmological Probes
• Cosmological Parameter Estimation and Inference using Deep Summaries
• Parameter inference and model comparison using theoretical predictions from noisy simulations
• Cosmological models discrimination with Weak Lensing

Cited by in corpus (3)

• Probabilistic Mass Mapping with Neural Score Estimation
• KaRMMa -- Kappa Reconstruction for Mass Mapping
• Denoising weak lensing mass maps with diffusion model: systematic comparison with generative adversarial network