Galaxy Image Deconvolution for Weak Gravitational Lensing with Unrolled Plug-and-Play ADMM

TL;DR

This paper presents a physics-informed deep learning approach using unrolled Plug-and-Play ADMM for galaxy image deconvolution, significantly enhancing weak gravitational lensing measurements by reducing shear ellipticity errors.

Contribution

It introduces a novel unrolled deep learning method that learns hyperparameters and priors for PSF deconvolution in galaxy surveys, improving over traditional techniques.

Findings

38.6% reduction in shear ellipticity error at SNR=20

45.0% reduction at SNR=200

Robustness to systematic PSF errors

Abstract

Removing optical and atmospheric blur from galaxy images significantly improves galaxy shape measurements for weak gravitational lensing and galaxy evolution studies. This ill-posed linear inverse problem is usually solved with deconvolution algorithms enhanced by regularisation priors or deep learning. We introduce a so-called "physics-informed deep learning" approach to the Point Spread Function (PSF) deconvolution problem in galaxy surveys. We apply algorithm unrolling and the Plug-and-Play technique to the Alternating Direction Method of Multipliers (ADMM), in which a neural network learns appropriate hyperparameters and denoising priors from simulated galaxy images. We characterise the time-performance trade-off of several methods for galaxies of differing brightness levels as well as our method's robustness to systematic PSF errors and network ablations. We show an improvement in reduced shear ellipticity error of 38.6% (SNR=20)/45.0% (SNR=200) compared to classic methods and 7.4% (SNR=20)/33.2% (SNR=200) compared to modern methods.