Neural style transfer of weak lensing mass maps

Abstract

We propose a new generative model of projected cosmic mass density maps inferred from weak gravitational lensing observations of distant galaxies (weak lensing mass maps). We construct the model based on a neural style transfer so that it can transform Gaussian weak lensing mass maps into deeply non-Gaussian counterparts as predicted in ray-tracing lensing simulations. We develop an unpaired image-to-image translation method with Cycle-Consistent Generative Adversarial Networks (Cycle GAN), which learn efficient mapping from an input domain to a target domain. Our model is designed to enjoy important advantages; it is trainable with no need for paired simulation data, flexible to make the input domain visually meaningful, and expandable to rapidly-produce a map with a larger sky coverage than training data without additional learning. Using 10,000 lensing simulations, we find that appropriate labeling of training data based on field variance allows the model to reproduce a correct scatter in summary statistics for weak lensing mass maps. Compared with a popular log-normal model, our model improves in predicting the statistical natures of three-point correlations and local properties of rare high-density regions. We also demonstrate that our model enables us to produce a continuous map with a sky coverage of $\sim 166{\mathrm{deg}}^2$ but similar non-Gaussian features to training data covering $\sim 12{\mathrm{deg}}^2$ in a GPU minute. Hence, our model can be beneficial to massive productions of synthetic weak lensing mass maps, which is of great importance in future precise real-world analyses.

19 pages, 12 figures, 3 tables. Accepted for publication in the Open Journal of Astrophysics. A trial dataset of fake weak lensing mass maps generated by our GANs is available at https://www.dropbox.com/scl/fo/hq1o41e8jwsfm4gqtkmnu/h?rlkey=0ymsucz2nzoju3gew8tsyz7qw&dl=0

References in corpus (94)

• The cosmological simulation code GADGET-2
• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Weak Gravitational Lensing
• Halo Models of Large Scale Structure
• Large-Scale Structure of the Universe and Cosmological Perturbation Theory
• Revising the Halofit Model for the Nonlinear Matter Power Spectrum
• Dark Energy Survey Year 3 Results: Cosmology from Cosmic Shear and Robustness to Modeling Uncertainty
• Cosmological parameters from lensing power spectrum and bispectrum tomography
• Ray Tracing Simulations of Weak Lensing by Large-Scale Structure
• Power Spectrum Super-Sample Covariance
• The Effect of Covariance Estimator Error on Cosmological Parameter Constraints
• Cosmology with the shear-peak statistics
• Simulations of Wide-Field Weak Lensing Surveys I: Basic Statistics and Non-Gaussian Effects
• Blinded challenge for precision cosmology with large-scale structure: results from effective field theory for the redshift-space galaxy power spectrum
• Improving lognormal models for cosmological fields
• Searching for massive clusters in weak lensing surveys
• Cosmology Constraints from the Weak Lensing Peak Counts and the Power Spectrum in CFHTLenS
• A New Algorithm for Computing Statistics of Weak Lensing by Large-Scale Structure
• Cosmology constraints from shear peak statistics in Dark Energy Survey Science Verification data
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Precision calculations of the cosmic shear power spectrum projection
• A new approach to observational cosmology using the scattering transform
• KiDS-450: Cosmological Constraints from Weak Lensing Peak Statistics - II: Inference from Shear Peaks using N-body Simulations
• Probing Cosmology with Weak Lensing Minkowski Functionals
• Density split statistics: Cosmological constraints from counts and lensing in cells in DES Y1 and SDSS data
• Information content of weak lensing power spectrum and bispectrum: including the non-Gaussian error covariance matrix
• Algorithms for bispectra: forecasting, optimal analysis, and simulation
• 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
• Probability Distribution Functions of Cosmological Lensing: Convergence, Shear, and Magnification
• Cosmological Information in Weak Lensing Peaks
• Weak lensing cosmology with convolutional neural networks on noisy data
• Cosmic shear covariance: The log-normal approximation
• Density split statistics: joint model of counts and lensing in cells
• An optimal filter for the detection of galaxy clusters through weak lensing
• Lognormal Property of Weak Lensing Fields
• Weighing the Cosmological Energy Contents with Weak Gravitational Lensing
• The Limits of Cosmic Shear
• Weak Lensing from Space III: Cosmological Parameters
• Cosmology with Minkowski functionals and moments of the weak lensing convergence field
• Cosmic Shear Cosmology Beyond 2-Point Statistics: A Combined Peak Count and Correlation Function Analysis of DES-Y1
• Constraining neutrino mass with tomographic weak lensing one-point probability distribution function and power spectrum
• Comparing approximate methods for mock catalogues and covariance matrices III: Bispectrum
• Cosmological Simulations for Combined-Probe Analyses: Covariance and Neighbour-Exclusion Bias
• Weak Gravitational Lensing Bispectrum
• Testing Quintessence models with large-scale structure growth
• From Weak Lensing to non-Gaussianity via Minkowski Functionals
• Nuw CDM cosmology from the weak lensing convergence PDF
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• Statistical and Systematic Errors in Measurement of Weak-Lensing Minkowski Functionals: Application to Canada-France-Hawaii Lensing Survey
• Cosmic Shear Covariance Matrix in $w$CDM: Cosmology Matters
• Euclid Preparation. XXVIII. Forecasts for ten different higher-order weak lensing statistics
• Gravitational Lensing Simulations I : Covariance Matrices and Halo Catalogues
• The Weak Lensing Bispectrum
• Scatter and bias in weak lensing selected clusters
• Mock galaxy shape catalogs in the Subaru Hyper Suprime-Cam Survey
• Optimized detection of shear peaks in weak lensing maps
• Impact of the non-Gaussian covariance of the weak lensing power spectrum and bispectrum on cosmological parameter estimation
• Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
• The Origin of Weak Lensing Convergence Peaks
• Testing a new analytic model for gravitational lensing probabilities
• The effect of baryons in the cosmological lensing PDFs
• Accurate Analytic Model for the Weak Lensing Convergence One-Point Probability Distribution Function and its Auto-Covariance
• $\kappa$TNG: Effect of Baryonic Processes on Weak Lensing with IllustrisTNG Simulations
• Denoising Weak Lensing Mass Maps with Deep Learning
• Noise reduction for weak lensing mass mapping: An application of generative adversarial networks to Subaru Hyper Suprime-Cam first-year data
• Probabilistic Mass Mapping with Neural Score Estimation
• The MillenniumTNG Project: The impact of baryons and massive neutrinos on high-resolution weak gravitational lensing convergence maps
• Constraining Cosmology with High Convergence Regions in Weak Lensing Surveys
• CosmoGridV1: a simulated $w$CDM theory prediction for map-level cosmological inference
• ICE-COLA: fast simulations for weak lensing observables
• Classifying Galaxy Morphologies with Few-Shot Learning
• Phase Correlations in Non-Gaussian Fields
• Fast Weak Lensing Simulations with Halo Model
• Gaussianizing the non-Gaussian lensing convergence field I: the performance of the Gaussianization
• GLASS: Generator for Large Scale Structure
• Probability distribution function of the aperture mass field with large deviation theory
• How to quantify fields or textures? A guide to the scattering transform
• Hyper Suprime-Cam Year 3 Results: Cosmology from Cosmic Shear Two-point Correlation Functions
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• KaRMMa -- Kappa Reconstruction for Mass Mapping
• Dark Energy from the log-transformed convergence field
• Enhancing cosmic shear with the multi-scale lensing PDF
• Investigating Cosmological GAN Emulators Using Latent Space Interpolation
• Cosmological Studies from HSC-SSP Tomographic Weak Lensing Peak Abundances
• Fast and realistic large-scale structure from machine-learning-augmented random field simulations
• Statistical connection of peak counts to power spectrum and moments in weak lensing field
• Fast generation of weak lensing maps by the inverse-Gaussianization method
• Cosmological Constraints from Weak Lensing Peaks: Can Halo Models Accurately Predict Peak Counts?
• Enhancing the Cosmic Shear Power Spectrum
• Perturbative Gaussianizing transforms for cosmological fields
• Testing the Reliability of Fast Methods for Weak Lensing Simulations: WL-MOKA on PINOCCHIO
• Synthetic light cone catalogues of modern redshift and weak lensing surveys with AbacusSummit
• Reconstruction of weak lensing mass maps for non-Gaussian studies in the celestial sphere

Cited by in corpus (2)

• Denoising weak lensing mass maps with diffusion model: systematic comparison with generative adversarial network
• Replicating weak-lensing summary-statistic covariances with normalizing flows