Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising
Science · 30.04.2026 · 392 (6797)
DOI: 10.1126/science.ady9404 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 30.04.2026. Verfasst von Yuduo Guo und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 108 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, National key R&D program of China.
Abstract (Originalsprache)
The detection limit of astronomical imaging observations is limited by several noise sources. Some of that noise is correlated between neighboring pixels and exposures, so in principle it could be learned and corrected. We present the Astronomical Self-supervised Transformer-based Denoising (ASTERIS) algorithm, which integrates spatiotemporal information across multiple exposures. Benchmarking on mock data indicated that ASTERIS improves detection limits by 1.0 magnitude at 90% completeness and purity while preserving the point spread function and photometric accuracy. Observational validation using data from the James Webb Space Telescope (JWST) and the Subaru Telescope identified previously undetectable features, including low-surface-brightness galaxy structures and gravitationally lensed arcs. Applied to deep JWST images, ASTERIS identified three times more redshift ≳9 galaxy candidates than previous methods, with rest-frame ultraviolet luminosity 1.0 magnitude fainter.
Autor:innen und Institutionen
- Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China.
- Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing, China.
- Department of Astronomy, Tsinghua University, Beijing, China.
- Kavli Institute for the Physics and Mathematics of the Universe, The University of Tokyo, Kashiwa, Japan.
- National Astronomical Observatory of Japan, Tokyo, Japan.
- Institute for Cosmic Ray Research, The University of Tokyo, Kashiwa, Japan.
ORCID-Profile: Yuduo Guo, Hao Zhang, Mingyu Li, Fujiang Yu, Yunjing Wu, Yuhan Hao, Yongming Liang, Jiamin Wu, Zheng Cai, Qionghai Dai
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- National key R&D program of China
Zitieren
APA
Guo, Y., Zhang, H., Li, M., Yu, F., Wu, Y., Hao, Y., Huang, S., Liang, Y., Lin, X., Li, X., Wu, J., Cai, Z., & Dai, Q. (2026). Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising. Science, 392(6797). https://doi.org/10.1126/science.ady9404
Vancouver
Guo Y, Zhang H, Li M, Yu F, Wu Y, Hao Y, et al. Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising. Science. 2026;392(6797). doi:10.1126/science.ady9404
BibTeX
@article{Guo2026,
author = {Guo, Yuduo and Zhang, Hao and Li, Mingyu and Yu, Fujiang and Wu, Yunjing and Hao, Yuhan and Huang, Song and Liang, Yongming and Lin, Xiaojing and Li, Xinyang and Wu, Jiamin and Cai, Zheng and Dai, Qionghai},
title = {Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising},
journal = {Science},
year = {2026},
volume = {392},
number = {6797},
doi = {10.1126/science.ady9404}
}
EUVIMED