FORKLENS: Accurate weak-lensing shear measurement with deep learning^★

¹ Shanghai Astronomical Observatory, Chinese Academy of Sciences, Shanghai 200030, PR China
e-mail: zhangzekang@shao.ac.cn; hyshan@shao.ac.cn
² University of Chinese Academy of Sciences, Beijing 100049, PR China
³ Key Laboratory of Radio Astronomy and Technology, Chinese Academy of Sciences, A20 Datun Road, Chaoyang District, Beijing 100101, PR China
⁴ National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, PR China
e-mail: nan.li@nao.cas.cn
⁵ Purple Mountain Observatory, Chinese Academy of Sciences, Nanjing 210023, PR China
⁶ Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, PR China
⁷ University Observatory, Faculty of Physics, Ludwig-Maximilians-Universität, Scheinerstr. 1, 81679 Munich, Germany
⁸ South-Western Institute for Astronomy Research, Yunnan University, Kunming 650500, PR China
⁹ Research Center for Astronomical Computing, Zhejiang Laboratory, Hangzhou 311100, PR China
¹⁰ Institute for Frontiers in Astronomy and Astrophysics, Beijing Normal University, Beijing 102206, PR China
¹¹ School of Astronomy and Space Science, University of Chinese Academy of Science, Beijing 100049, PR China

Received: 13 January 2023
Accepted: 1 December 2023

Abstract

Context. Weak gravitational lensing is one of the most important probes of the nature of dark matter and dark energy. In order to extract cosmological information from next-generation weak lensing surveys (e.g., Euclid, Roman, LSST, and CSST) as much as possible, accurate measurements of weak lensing shear are required.

Aims. There are existing algorithms to measure the weak lensing shear on imaging data, which have been successfully applied in previous surveys. In the meantime, machine learning (ML) has been widely recognized in various astrophysics applications in modeling and observations. In this work, we present a fully deep-learning-based approach to measuring weak lensing shear accurately.

Methods. Our approach comprises two modules. The first one contains a convolutional neural network (CNN) with two branches for taking galaxy images and point spread function (PSF) simultaneously, and the output of this module includes the galaxy’s magnitude, size, and shape. The second module includes a multiple-layer neural network (NN) to calibrate weak-lensing shear measurements. We name the program FORKLENS and make it publicly available online.

Results. Applying FORKLENS to CSST-like mock images, we achieve consistent accuracy with traditional approaches (such as moment-based measurement and forward model fitting) on the sources with high signal-to-noise ratios (S/N > 20). For the sources with S/N < 10, FORKLENS exhibits an ~36% higher Pearson coefficient on galaxy ellipticity measurements.

Conclusions. After adopting galaxy weighting, the shear measurements with FORKLENS deliver accuracy levels to 0.2%. The whole procedure of FORKLENS is automated and costs about 0.7 milliseconds per galaxy, which is appropriate for adequately taking advantage of the sky coverage and depth of the upcoming weak lensing surveys.