Deep learning for a space-variant deconvolution in galaxy surveys - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Access content directly
Journal Articles Astronomy and Astrophysics - A&A Year : 2020

Deep learning for a space-variant deconvolution in galaxy surveys

Abstract

The deconvolution of large survey images with millions of galaxies requires developing a new generation of methods that can take a space-variant point spread function into account. These methods have also to be accurate and fast. We investigate how deep learning might be used to perform this task. We employed a U-net deep neural network architecture to learn parameters that were adapted for galaxy image processing in a supervised setting and studied two deconvolution strategies. The first approach is a post-processing of a mere Tikhonov deconvolution with closed-form solution, and the second approach is an iterative deconvolution framework based on the alternating direction method of multipliers (ADMM). Our numerical results based on GREAT3 simulations with realistic galaxy images and point spread functions show that our two approaches outperform standard techniques that are based on convex optimization, whether assessed in galaxy image reconstruction or shape recovery. The approach based on a Tikhonov deconvolution leads to the most accurate results, except for ellipticity errors at high signal-to-noise ratio. The ADMM approach performs slightly better in this case. Considering that the Tikhonov approach is also more computation-time efficient in processing a large number of galaxies, we recommend this approach in this scenario.
Fichier principal
Vignette du fichier
aa37039-19.pdf (3.49 Mo) Télécharger le fichier
Origin : Publication funded by an institution
Loading...

Dates and versions

cea-02936950 , version 1 (11-09-2020)

Identifiers

Cite

Florent Sureau, Alexis Lechat, Jean-Luc Starck. Deep learning for a space-variant deconvolution in galaxy surveys. Astronomy and Astrophysics - A&A, 2020, 641, pp.A67. ⟨10.1051/0004-6361/201937039⟩. ⟨cea-02936950⟩
94 View
80 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More