The Astrophysical Journal, 981:52 (10pp), 2025 March 1
https://doi.org/10.3847/1538-4357/adb1b7
Sangjun Cha1 , M. James Jee1,2 , Sungwook E. Hong3,4 , Sangnam Park5 , Dongsu Bak5 , and Taehwan Kim6
1 Department of Astronomy, Yonsei University, 50 Yonsei-ro, Seoul 03722, Republic of Korea; mkjee@yonsei.ac.kr
2 Department of Physics and Astronomy, University of California, Davis, One Shields Avenue, Davis, CA 95616, USA
3 Korea Astronomy and Space Science Institute, 776 Daedeok-daero, Yuseong-gu, Daejeon 34055, Republic of Korea
4 Astronomy Campus, University of Science and Technology, 776 Daedeok-daero, Yuseong-gu, Daejeon 34055, Republic of Korea
5 Physics Department & Natural Science Research Institute, University of Seoul, 163 Seoulsiripdaero, Dongdaemun-gu, Seoul 02504, Republic of Korea
6 Artificial Intelligence Graduate School, UNIST, Ulsan, Republic of Korea
Received 2024 October 25; revised 2025 January 21; accepted 2025 January 31; published 2025 February 26
Abstract
Traditional weak-lensing mass reconstruction techniques suffer from various artifacts, including noise
amplification and the mass-sheet degeneracy. In S. E. Hong et al., we demonstrated that many of these pitfalls
of traditional mass reconstruction can be mitigated using a deep learning approach based on a convolutional neural network (CNN). In this paper, we present our improvements and report on the detailed performance of our CNN algorithm applied to next-generation wide-field (WF) observations. Assuming the field of view (3. 5 ´ 3. 5) and depth (27 mag at 5σ) of the Vera C. Rubin Observatory, we generated training data sets of mock shear catalogs with a source density of 33 arcmin−2 from cosmological simulation ray-tracing data. We find that the current CNN method provides high-fidelity reconstructions consistent with the true convergence field, restoring both small- and large-scale structures. In addition, the cluster detection utilizing our CNN reconstruction achieves ∼75% completeness down to ∼1014 Me. We anticipate that this CNN-based mass reconstruction will be a powerful tool in the Rubin era, enabling fast and robust WF mass reconstructions on a routine basis.
