Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising
原文开头
Yuduo Guo1,2†, Hao Zhang1,2†, Mingyu Li3†, Fujiang Yu3, Yunjing Wu3,4, Yuhan Hao1,2, Song Huang3, Yongming Liang5,6, Xiaojing Lin3, Xinyang Li8, Jiamin Wu1,2,3*, Zheng Cai3,8,9*, Qionghai Dai1,2* 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. …
摘自《科学》(Science)第392卷 第6797期 · 2026年4月30日。仅引用开头一小段供了解文章,版权归原刊所有,全文请阅读原刊。