We present a new, fully generative model of optical telescope image sets, along with a variational procedure for inference. Each pixel intensity is treated as a Poisson random variable, with a rate parameter dependent on latent properties of stars and galaxies. Key latent properties are themselves random, with scientific prior distributions constructed from large ancillary data sets. We check our approach on synthetic images. We also run it on images from a major sky survey, where it exceeds the performance of the current state-of-the-art method for locating celestial bodies and measuring their colors.
Approximate Inference for Constructing Astronomical Catalogs from Images
University of California – Berkeley（加州大学伯克利分校）；Columbia University（哥伦比亚大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；Princeton University（普林斯顿大学）；The Voleon Group（Voleon集团）
alpha-Deep Probabilistic Inference (alpha-DPI): efficient uncertainty quantification from exoplanet astrometry to black hole feature extraction
California Institute of Technology（加州理工学院）；Perimeter Institute for Theoretical Physics（圆周理论物理研究所）；University of Waterloo（滑铁卢大学）；Harvard University（哈佛大学）；Center for Astrophysics — Harvard & Smithsonian（哈佛-史密森尼天体物理中心）
Neural Posterior Estimation for Cataloging Astronomical Images with Spatially Varying Backgrounds and Point Spread Functions
Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48109, USA（电气工程与计算机科学系，密歇根大学，安娜堡分校）；Department of Physics and Astronomy and PITT PACC, University of Pittsburgh, Pittsburgh, PA 15260, USA（物理与天文学系及PITT PACC，匹兹堡大学，匹兹堡分校）；Department of Physics, University of Michigan, Ann Arbor, MI 48109, USA（物理系，密歇根大学，安娜堡分校）；Leinweber Center for Theoretical Physics, University of Michigan, Ann Arbor, MI 48109, USA（理论物理中心，密歇根大学，安娜堡分校）；Department of Statistics, University of Michigan, Ann Arbor, MI 48109, USA（统计学系，密歇根大学，安娜堡分校）
Accelerating lensed quasar discovery and modeling with physics-informed variational autoencoders
Technical University of Munich（慕尼黑工业大学）；Max-Planck-Institut für Astrophysik（马克斯·普朗克天体物理研究所）；Università degli Studi di Milano（米兰大学）；INAF – IASF Milano（意大利国家天体物理研究所米兰分部）；Academia Sinica Institute of Astronomy and Astrophysics (ASIAA)（中央研究院天文及天文物理研究所）；Aix-Marseille Université（艾克斯-马赛大学）；American Museum of Natural History（美国自然历史博物馆）；Lehman College of the CUNY（纽约城市大学莱曼学院）
本文提出物理信息变分自编码器模型 VariLens，可在单 CPU 毫秒级完成透镜分类与 SIE 参数建模，并从约8000万源中筛选出42个待光谱确认的透镜类星体候选体。
