Noise reduction for weak lensing mass mapping: An application of generative adversarial networks to Subaru Hyper Suprime-Cam first-year data

TL;DR

This paper introduces a deep-learning GAN-based method to effectively reduce noise in weak lensing mass maps from Subaru HSC data, enhancing the extraction of cosmological information and cluster detection.

Contribution

We develop and apply a conditional GAN approach trained on realistic mock data to denoise weak lensing maps, preserving non-Gaussian features and improving cosmological analysis.

Findings

Ensemble GANs reproduce the PDFs of lensing convergence accurately.

About 60% of high-significance peaks correspond to massive clusters.

Denoised maps retain cosmological information and are consistent with ΛCDM predictions.

Abstract

We propose a deep-learning approach based on generative adversarial networks (GANs) to reduce noise in weak lensing mass maps under realistic conditions. We apply image-to-image translation using conditional GANs to the mass map obtained from the first-year data of Subaru Hyper Suprime-Cam (HSC) survey. We train the conditional GANs by using 25000 mock HSC catalogues that directly incorporate a variety of observational effects. We study the non-Gaussian information in denoised maps using one-point probability distribution functions (PDFs) and also perform matching analysis for positive peaks and massive clusters. An ensemble learning technique with our GANs is successfully applied to reproduce the PDFs of the lensing convergence. About $60\%$ of the peaks in the denoised maps with height greater than $5\sigma$ have counterparts of massive clusters within a separation of 6 arcmin. We show that PDFs in the denoised maps are not compromised by details of multiplicative biases and photometric redshift distributions, nor by shape measurement errors, and that the PDFs show stronger cosmological dependence compared to the noisy counterpart. We apply our denoising method to a part of the first-year HSC data to show that the observed mass distribution is statistically consistent with the prediction from the standard $\Lambda$CDM model.