Denoising Weak Lensing Mass Maps with Deep Learning

Abstract

Weak gravitational lensing is a powerful probe of the large-scale cosmic matter distribution. Wide-field galaxy surveys allow us to generate the so-called weak lensing maps, but actual observations suffer from noise due to imperfect measurement of galaxy shape distortions and to the limited number density of the source galaxies. In this paper, we explore a deep-learning approach to reduce the noise. We develop an image-to-image translation method with conditional adversarial networks (CANs), which learn efficient mapping from an input noisy weak lensing map to the underlying noise field. We train the CANs using $30000$ image pairs obtained from $1000$ ray-tracing simulations of weak gravitational lensing. We show that the trained CANs reproduce the true one-point probability distribution function (PDF) of the noiseless lensing map with a bias less than $1\sigma$ on average, where $\sigma$ is the statistical error. We perform a Fisher analysis to make forecast for cosmological parameter inference with the one-point lensing PDF. By our denoising method using CANs, the first derivative of the PDF with respect to the cosmic mean matter density and the amplitude of the primordial curvature perturbations becomes larger by $\sim 50\%$. This allows us to improve the cosmological constraints by $\sim 30-40\%$ with using observational data from ongoing and upcoming galaxy imaging surveys.

arXiv comment15 pages, 12 figures, accepted for publication in Phys. Rev. D

References in corpus (46)

• Weak Gravitational Lensing
• Cosmology with cosmic shear observations: a review
• Weak lensing for precision cosmology
• Detection of (dark) matter concentrations via weak gravitational lensing
• The Skewness of the Aperture Mass Statistic
• Ray Tracing Simulations of Weak Lensing by Large-Scale Structure
• The first-year shear catalog of the Subaru Hyper Suprime-Cam SSP Survey
• Cosmology with the shear-peak statistics
• Simulations of Wide-Field Weak Lensing Surveys I: Basic Statistics and Non-Gaussian Effects
• Searching for massive clusters in weak lensing surveys
• A New Algorithm for Computing Statistics of Weak Lensing by Large-Scale Structure
• The Third Gravitational Lensing Accuracy Testing (GREAT3) Challenge Handbook
• Probing Cosmology with Weak Lensing Peak Counts
• Non-Gaussian information from weak lensing data via deep learning
• Probing Cosmology with Weak Lensing Minkowski Functionals
• Emulating the CFHTLenS Weak Lensing data: Cosmological Constraints from moments and Minkowski functionals
• Maximum-Likelihood Cluster Recontruction
• Detection of dark matter Skewness in the VIRMOS-DESCART survey: Implications for Ω_0
• Power Spectra Estimation for Weak Lensing
• A maximum-entropy method for reconstructing the projected mass distribution of gravitational lenses
• Maximum-entropy weak lens reconstruction: improved methods and application to data
• Numerical study of statistical properties of the lensing excursion angles
• Noisy weak-lensing convergence peak statistics near clusters of galaxies and beyond
• Weak Lensing Mass Reconstruction using Wavelets
• Weak lensing, dark matter and dark energy
• Shear Power Spectrum Reconstruction using Pseudo-Spectrum Method
• A new model to predict weak-lensing peak counts I. Comparison with $N$-body Simulations
• Constraining Neutrino Mass with the Tomographic Weak Lensing Bispectrum
• Constraining neutrino mass with weak lensing Minkowski Functionals
• Constraining neutrino mass with tomographic weak lensing peak counts
• Statistical and Systematic Errors in Measurement of Weak-Lensing Minkowski Functionals: Application to Canada-France-Hawaii Lensing Survey
• Scatter and bias in weak lensing selected clusters
• Probing cosmology with weak lensing selected clusters I: Halo approach and all-sky simulations
• Improving Weak Lensing Mass Map Reconstructions using Gaussian and Sparsity Priors: Application to DES SV
• Higher-order moments of the lensing shear and other spin two fields
• The Three-Point Correlation Function for Spin-2 Fields
• Implication of Omega_m through the Morphological Analysis of Weak Lensing Fields
• Constraining Cosmology with High Convergence Regions in Weak Lensing Surveys
• The Topology of Weak Lensing Fields
• The imprint of $f(R)$ gravity on weak gravitational lensing I: Connection between observables and large scale structure
• Fourier Band-Power E/B-mode Estimators for Cosmic Shear
• Dark Energy from the log-transformed convergence field
• Weak lensing: Dark Matter, Dark Energy and Dark Gravity
• Effect of Mask Regions on Weak Lensing Statistics
• Wavelet Helmholtz decomposition for weak lensing mass map reconstruction
• Statistical properties of filaments in weak gravitational lensing

Cited by in corpus (28)

• Likelihood-free inference with neural compression of DES SV weak lensing map statistics
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Weak lensing cosmology with convolutional neural networks on noisy data
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Dark Energy Survey Year 3 results: curved-sky weak lensing mass map reconstruction
• Gravitational wave signal recognition of O1 data by deep learning
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• Noise reduction for weak lensing mass mapping: An application of generative adversarial networks to Subaru Hyper Suprime-Cam first-year data
• Cosmological test of gravity using weak lensing voids
• HIGAN: Cosmic Neutral Hydrogen with Generative Adversarial Networks
• Deep learning for intensity mapping observations: Component extraction
• Revealing the Local Cosmic Web from Galaxies by Deep Learning
• Deep Learning for Line Intensity Mapping Observations: Information Extraction from Noisy Maps
• The self similarity of weak lensing peaks
• The Sejong Suite: Cosmological Hydrodynamical Simulations with Massive Neutrinos, Dark Radiation, and Warm Dark Matter
• FERIA: Flat Envelope Model with Rotation and Infall under Angular Momentum Conservation
• Forklens: Accurate weak-lensing shear measurement with deep learning
• Predicting 21cm-line map from Lyman $\alpha$ emitter distribution with Generative Adversarial Networks
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• Galaxy Spectra Networks (GaSNet). III. Generative pre-trained network for spectrum reconstruction, redshift estimate and anomaly detection
• Weak-lensing Mass Reconstruction of Galaxy Clusters with a Convolutional Neural Network -- II: Application to Next-Generation Wide-Field Surveys
• Neural style transfer of weak lensing mass maps
• Distribution-free uncertainty quantification for inverse problems: application to weak lensing mass mapping
• Probabilistic Mapping of Dark Matter by Neural Score Matching
• Denoising weak lensing mass maps with diffusion model: systematic comparison with generative adversarial network
• A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping
• Replicating weak-lensing summary-statistic covariances with normalizing flows