Generative modelling for mass-mapping with fast uncertainty quantification

TL;DR

This paper introduces MMGAN, a fast and stable generative model for mass-mapping in cosmology that efficiently produces uncertainty estimates from shear data, outperforming traditional and existing deep learning methods.

Contribution

The paper presents MMGAN, a novel Wasserstein GAN-based framework for rapid, high-fidelity mass-mapping with uncertainty quantification in weak gravitational lensing.

Findings

Outperforms Kaiser-Squires in reconstruction quality

Achieves similar fidelity to state-of-the-art deep learning methods

Generates posterior samples in less than a second

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.