Forklens: Accurate weak-lensing shear measurement with deep learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zekang, Shan, Huanyuan, Li, Nan, Wei, Chengliang, Yao, Ji, Ban, Zhang, Fang, Yuedong, Guo, Qi, Liu, Dezi, Li, Guoliang, Lin, Lin, Li, Ming, Li, Ran, Li, Xiaobo, Luo, Yu, Meng, Xianmin, Nie, Jundan, Qi, Zhaoxiang, Qiu, Yisheng, Shao, Li, Tian, Hao, Wang, Lei, Wang, Wei, Xian, Jingtian, Xu, Youhua, Zhang, Tianmeng, Zhang, Xin, Zhou, Zhimin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914726675480576
author Zhang, Zekang
Shan, Huanyuan
Li, Nan
Wei, Chengliang
Yao, Ji
Ban, Zhang
Fang, Yuedong
Guo, Qi
Liu, Dezi
Li, Guoliang
Lin, Lin
Li, Ming
Li, Ran
Li, Xiaobo
Luo, Yu
Meng, Xianmin
Nie, Jundan
Qi, Zhaoxiang
Qiu, Yisheng
Shao, Li
Tian, Hao
Wang, Lei
Wang, Wei
Xian, Jingtian
Xu, Youhua
Zhang, Tianmeng
Zhang, Xin
Zhou, Zhimin
author_facet Zhang, Zekang
Shan, Huanyuan
Li, Nan
Wei, Chengliang
Yao, Ji
Ban, Zhang
Fang, Yuedong
Guo, Qi
Liu, Dezi
Li, Guoliang
Lin, Lin
Li, Ming
Li, Ran
Li, Xiaobo
Luo, Yu
Meng, Xianmin
Nie, Jundan
Qi, Zhaoxiang
Qiu, Yisheng
Shao, Li
Tian, Hao
Wang, Lei
Wang, Wei
Xian, Jingtian
Xu, Youhua
Zhang, Tianmeng
Zhang, Xin
Zhou, Zhimin
contents 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. 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. 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. 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 $\sim 36\%$ higher Pearson coefficient on galaxy ellipticity measurements. 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.
format Preprint
id arxiv_https___arxiv_org_abs_2301_02986
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Forklens: Accurate weak-lensing shear measurement with deep learning
Zhang, Zekang
Shan, Huanyuan
Li, Nan
Wei, Chengliang
Yao, Ji
Ban, Zhang
Fang, Yuedong
Guo, Qi
Liu, Dezi
Li, Guoliang
Lin, Lin
Li, Ming
Li, Ran
Li, Xiaobo
Luo, Yu
Meng, Xianmin
Nie, Jundan
Qi, Zhaoxiang
Qiu, Yisheng
Shao, Li
Tian, Hao
Wang, Lei
Wang, Wei
Xian, Jingtian
Xu, Youhua
Zhang, Tianmeng
Zhang, Xin
Zhou, Zhimin
Cosmology and Nongalactic Astrophysics
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. 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. 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. 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 $\sim 36\%$ higher Pearson coefficient on galaxy ellipticity measurements. 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.
title Forklens: Accurate weak-lensing shear measurement with deep learning
topic Cosmology and Nongalactic Astrophysics
url https://arxiv.org/abs/2301.02986