Using conditional GANs for convergence map reconstruction with uncertainties

TL;DR

This paper introduces a deep learning method using conditional GANs to efficiently generate statistically robust cosmological mass maps from lensing data, addressing the ill-posed nature of the problem.

Contribution

It presents a novel cGAN-based approach that combines data-driven priors with regularisation for fast, high-fidelity mass map reconstruction with uncertainty quantification.

Findings

Successful reconstruction of convergence maps from mock data

Demonstrated the method's ability to generate samples from the Bayesian posterior

Ongoing improvements to enhance robustness and accuracy

Abstract

Understanding the large-scale structure of the Universe and unravelling the mysteries of dark matter are fundamental challenges in contemporary cosmology. Reconstruction of the cosmological matter distribution from lensing observables, referred to as 'mass-mapping' is an important aspect of this quest. Mass-mapping is an ill-posed problem, meaning there is inherent uncertainty in any convergence map reconstruction. The demand for fast and efficient reconstruction techniques is rising as we prepare for upcoming surveys. We present a novel approach which utilises deep learning, in particular a conditional Generative Adversarial Network (cGAN), to approximate samples from a Bayesian posterior distribution, meaning they can be interpreted in a statistically robust manner. By combining data-driven priors with recent regularisation techniques, we introduce an approach that facilitates the swift generation of high-fidelity, mass maps. Furthermore, to validate the effectiveness of our approach, we train the model on mock COSMOS-style data, generated using Colombia Lensing's kappaTNG mock weak lensing suite. These preliminary results showcase compelling convergence map reconstructions and ongoing refinement efforts are underway to enhance the robustness of our method further.