Photometric Super-Resolution for Improving Galaxy Morphological Measurements using Conditional Generative Adversarial Networks
University of California, Santa Cruz（加州大学圣克鲁兹分校）；The Johns Hopkins University（约翰斯·霍普金斯大学）；Vall d´Hebron Institute of Oncology (VHIO)（瓦尔德赫布龙肿瘤研究所）；University of Hawaii, Hilo（夏威夷大学希洛分校）
Samuel Kahn, Ryan Hausen, Hubert Bretonnière, Nicole Drakos, Brant Robertson
备注：
28 pages, 18 figures. Submitted to AAS Journals on March 13, 2026
从天文学图像中测量星系形态学参数在现代分析中广泛存在，包括星系演化和宇宙弱透镜效应研究。形态学参数估计的精度和准确性受多个关键因素影响。图像的有效视宁度，由点扩散函数（PSF）总结，限制了星系特征或光度分布的解析能力。探测器的像素尺度也影响分辨率和给定目标可用的统计信息量。观测深度决定了图像的信噪比。提高这些因素的成本很高，无论是探测器升级、天文台设计还是观测时间。本文开发了一个名为Neo的条件生成对抗网络，旨在将现有地面图像转换为更清晰、更精细尺度的图像，与空间图像质量相当。我们证明，当Neo被训练以将Subaru Hyper Suprime-Camera（HSC）图像转换为近似Hubble Space Telescope（HST）数据时，它能将测量形态学参数的准确性提高2-10倍。Neo设计用于适用于正在进行的大型巡天项目，如Vera C. Rubin Observatory进行的Legacy Survey of Space and Time（LSST），结合HST、James Webb Space Telescope和Nancy Grace Roman Space Telescope等空间望远镜。这些结果表明，Neo可以用于基于大规模地面巡天数据集如LSST的宇宙学和星系演化分析。模型代码是开源的，并可在https://purl.archive.org/neo/code上获得。
英文摘要：
The measurement of galaxy morphological parameters from astronomical images features in a wide range of modern analyses, including galaxy evolution and cosmological weak lensing studies. The precision and accuracy of morphological parameter estimation can be influenced by several key factors. The effective seeing of the image, summarized by the point spread function (PSF), limits how galaxy features or light profiles are resolved. The pixel scale of the detector also influences the resolution and the amount of statistical information available for a given object. The depth of the observations determines the signal-to-noise ratio of the image. Improving each of these factors is very costly, either in terms of detector upgrades, observatory design, or observing time. Here, we develop a conditional generative adversarial network, called Neo, trained to transform existing ground-based images into sharper, finer-scale images comparable to space-based image quality. We demonstrate that Neo improves the accuracy of measured morphological parameters by factors of $2$-$10$ when trained to translate Subaru Hyper Suprime-Camera (HSC) images to approximate Hubble Space Telescope (HST) data. Neo is designed for applicability to ongoing, large-scale surveys such as the Legacy Survey of Space and Time (LSST) conducted by Vera C. Rubin Observatory in combination with space telescopes such as HST, James Webb Space Telescope, and Nancy Grace Roman Space Telescope. These results suggest that Neo could be used to improve both cosmological and galaxy evolution analyses based on massive, ground-based survey datasets like LSST. The model code is open source and available at https://purl.archive.org/neo/code.
Galaxy spectroscopy without spectra: Galaxy properties from photometric images with conditional diffusion models
University of Bern（伯尔尼大学）；Ludwig-Maximilians Universität München（慕尼黑大学）；INAF - Astronomical Observatory of Capodimonte（意大利国家天体物理研究所卡波迪蒙特天文台）；INFN - Sezione di Napoli（意大利国家核物理研究所那不勒斯分所）；University Federico II（那不勒斯费德里科二世大学）；University of Bologna（博洛尼亚大学）；ARTORG Center（ARTORG中心）；AIMI
Star formation and morphological properties of galaxies in the Pan-STARRS $3 π$ survey- I. A machine learning approach to galaxy and supernova classification
The miniJPAS and J-NEP surveys: Machine learning for star-galaxy separation
Universidade Federal do Espírito Santo（圣埃斯皮里图联邦大学）；INAF -- Osservatorio Astronomico di Trieste（意大利国家天体物理研究所的里雅斯特天文台）；IFPU -- Institute for Fundamental Physics of the Universe（宇宙基础物理研究所）；Universidade Federal da Bahia（巴伊亚联邦大学）；Instituto de Física, Universidade de São Paulo（圣保罗大学物理研究所）；Observatório Nacional（国家天文台）；Instituto de Astrofísica de Andalucía - CSIC（安达卢西亚天体物理研究所-西班牙高等科学研究理事会）；Donostia International Physics Center (DIPC)（圣塞巴斯蒂安国际物理中心）；Centro de Estudios de Física del Cosmos de Aragón (CEFCA)（阿拉贡宇宙物理学研究中心）；Instituto de Astrofísica de Canarias（加那利天体物理研究所）；National Astronomical Observatory of China, Chinese Academy of Sciences（中国科学院国家天文台）；Steward Observatory, University of Arizona（亚利桑那大学斯图尔德天文台）
Morphological classification of eclipsing binary stars using computer vision methods
Institute of Physics, Faculty of Science, Pavol Jozef S af\'arik University in Ko s ice, Park Angelinum 9, 040 01 Ko s ice, Slovakia；Astronomical Institute, Slovak Academy of Sciences, 059 60 Tatranská Lomnica, Slovakia；Astronomical Institute, Czech Academy of Sciences, Fri c ova 298, 25 165 Ond r ejov, Czech Republic
Is the `Known' Enough? An Integrated Machine Learning Framework for Eclipsing Binary Classification and Parameter Estimation Based on Well-Characterized Systems
