Denoising weak lensing mass maps with diffusion model and generative adversarial network

TL;DR

This paper compares diffusion models and GANs for weak lensing mass map denoising, demonstrating that diffusion models offer more stable training and higher accuracy in recovering the true cosmic matter distribution.

Contribution

The study introduces a diffusion model for WL denoising and systematically compares it with GANs, showing its superior performance in stability and accuracy.

Findings

Diffusion model outperforms GAN in WL denoising tasks.

Diffusion model provides more stable training process.

Multiple samples from the diffusion model better recover true signals.

Abstract

The matter distribution of the Universe can be mapped through the weak gravitational lensing (WL) effect: small distortions of the shapes of distant galaxies, which reflects the inhomogeneity of the cosmic density field. The most dominant contaminant in the WL effect is the shape noise; the signal is diluted due to the finite number of source galaxies. In order to explore the full potential of WL measurements, sharpening the signal by removing the shape noise from the observational data, i.e., WL denoising, is a pressing issue. Machine learning approaches, in particular, deep generative models, have proven effective at the WL denoising task. We implement a denoising model based on the diffusion model (DM) and conduct systematic in-depth comparisons with generative adversarial networks (GANs), which have been applied in previous works for WL denoising. Utilizing the large suite of mock simulations of WL observations, we demonstrate that DM surpasses GAN in the WL denosing task in multiple aspects: (1) the training process is more stable, (2) taking the average of multiple samples from DM can robustly reproduce the true signal, and (3) DM can recover various statistics with higher accuracy.