Skip to Main content Skip to Navigation
Journal articles

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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [84 references]  Display  Hide  Download

https://hal-cea.archives-ouvertes.fr/cea-02936950
Contributor : Edp Sciences <>
Submitted on : Friday, September 11, 2020 - 10:05:47 PM
Last modification on : Wednesday, October 14, 2020 - 4:21:57 AM

File

aa37039-19.pdf
Publication funded by an institution

Identifiers

Citation

F. Sureau, A. Lechat, J.-L. Starck. Deep learning for a space-variant deconvolution in galaxy surveys. Astronomy and Astrophysics - A&A, EDP Sciences, 2020, 641, pp.A67. ⟨10.1051/0004-6361/201937039⟩. ⟨cea-02936950⟩

Share

Metrics

Record views

41

Files downloads

64