Generative modelling for mass-mapping with fast uncertainty quantification

Abstract

Understanding the nature of dark matter in the Universe is an important goal of modern cosmology. A key method for probing this distribution is via weak gravitational lensing mass-mapping - a challenging ill-posed inverse problem where one infers the convergence field from observed shear measurements. Upcoming stage IV surveys, such as those made by the Vera C. Rubin Observatory and Euclid satellite, will provide a greater quantity and precision of data for lensing analyses, necessitating high-fidelity mass-mapping methods that are computationally efficient and that also provide uncertainties for integration into downstream cosmological analyses. In this work we introduce MMGAN, a novel mass-mapping method based on a regularised conditional generative adversarial network (GAN) framework, which generates approximate posterior samples of the convergence field given shear data. We adopt Wasserstein GANs to improve training stability and apply regularisation techniques to overcome mode collapse, issues that otherwise are particularly acute for conditional GANs. We train and validate our model on a mock COSMOS-style dataset before applying it to true COSMOS survey data. Our approach significantly outperforms the Kaiser-Squires technique and achieves similar reconstruction fidelity as alternative state-of-the-art deep learning approaches. Notably, while alternative approaches for generating samples from a learned posterior are slow (e.g. requiring $\sim$10 GPU minutes per posterior sample), MMGAN can produce a high-quality convergence sample in less than a second.

Updated to the MNRAS published paper on 9/9/25

References in corpus (30)

• Planck 2015 results. XIII. Cosmological parameters
• Generative Adversarial Networks
• Generative Adversarial Networks: An Overview
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Weak Gravitational Lensing
• First results from the IllustrisTNG simulations: matter and galaxy clustering
• COSMOS Photometric Redshifts with 30-bands for 2-deg2
• COSMOS : Hubble Space Telescope Observations
• Weak lensing for precision cosmology
• Evidence for the accelerated expansion of the Universe from weak lensing tomography with COSMOS
• The XMM-Newton wide-field survey in the COSMOS field: VI. Statistical properties of clusters of galaxies
• Cosmology Constraints from the Weak Lensing Peak Counts and the Power Spectrum in CFHTLenS
• 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
• Cosmological Constraints From Weak Lensing Peak Statistics With CFHT Stripe 82 Survey
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Dark Energy Survey Year 1 Results: Curved-Sky Weak Lensing Mass Map
• Cosmic Shear Cosmology Beyond 2-Point Statistics: A Combined Peak Count and Correlation Function Analysis of DES-Y1
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• High Resolution Weak Lensing Mass-Mapping Combining Shear and Flexion
• $\kappa$TNG: Effect of Baryonic Processes on Weak Lensing with IllustrisTNG Simulations
• 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 DES view of the Eridanus supervoid and the CMB Cold Spot
• Spherical Bayesian mass-mapping with uncertainties: full sky observations on the celestial sphere
• Weak lensing mass reconstruction using sparsity and a Gaussian random field
• The Integrated Bispectrum and Beyond
• Sparse Bayesian mass-mapping with uncertainties: local credible intervals
• Sparse Bayesian mass-mapping with uncertainties: peak statistics and feature locations
• Ray-tracing log-normal simulation for weak gravitational lensing: application to the cross-correlation with galaxies

Cited by in corpus (3)

• 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