即将进行的调查,如维拉C。Rubin Observatory Legacy Survey of Space and Time(LSST)计划将在未来10年内,每晚探测到1000万个随时间变化的源。这些信息将以连续流的形式传输给经纪人,经纪人将使用机器学习算法为各种科学案例选择最有希望的事件。我们研究了贝叶斯神经网络(BNN)在这类分类任务中的优势和挑战。BNN被发现是准确的分类器,也提供了额外的信息:它们量化了分类的不确定性,可以利用这些不确定性来更有效地分析即将到来的数据雪崩。
英文摘要:
Upcoming surveys such as the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will detect up to 10 million time-varying sources in the sky every night for ten years. This information will be transmitted in a continuous stream to brokers that will select the most promising events for a variety of science cases using machine learning algorithms. We study the benefits and challenges of Bayesian Neural Networks (BNNs) for this type of classification tasks. BNNs are found to be accurate classifiers which also provide additional information: they quantify the classification uncertainty which can be harnessed to analyse this upcoming data avalanche more efficiently.
Amortized Bayesian Inference for Supernovae in the Era of the Vera Rubin Observatory Using Normalizing Flows
Vera Rubin天文台将于2024年年中开始观测,这将使我们的超新星发现率提高到每年超过100万颗。人们一直在大力推动开发新的方法来识别、分类并最终理解鲁宾天文台发现的数百万颗超新星。在这里,我们提出了第一个基于模拟的推理方法,使用归一化流,训练快速推断多变量,Rubin类数据流中的玩具超新星模型的参数。我们发现,我们的方法是很好的校准相比,传统的推理方法(特别是MCMC),在测试时间只需要万分之一的CPU小时。
The automation of optical transient discovery and classification in Rubin-era time-domain astronomy
Northwestern University(西北大学);Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA)(天体物理学跨学科探索与研究中心);University of Minnesota(明尼苏达大学);California Institute of Technology(加州理工学院)
Redshift Assessment Infrastructure Layers (RAIL): Rubin-era photometric redshift stress-testing and at-scale production
Ruhr University Bochum(鲁尔大学波鸿);SLAC National Accelerator Laboratory(斯坦福直线加速器中心);Kavli Institute for Particle Astrophysics and Cosmology (KIPAC), Stanford University(卡弗里粒子天体物理与宇宙学研究所,斯坦福大学);Université Clermont-Auvergne, CNRS, LPCA(克莱蒙奥弗涅大学,法国国家科学研究中心,LPCA);McWilliams Center for Cosmology and Astrophysics, Department of Physics, Carnegie Mellon University(梅斯威尔宇宙学与天体物理中心,卡内基梅隆大学物理系)
RAIL 是一个开源 Python 库,用于大规模概率光度红移估计,提供模块化工具进行端到端压力测试和红移 PDF 估算,适用于多种科学目标。
Unresolved Binary Systems in the Rubin Era I: An Autoencoder Framework for Binary Identification Applied to 47 Tucanae
University of Toronto(多伦多大学);Dunlap Institute for Astronomy & Astrophysics(邓普天文学与天体物理研究所);David A. Dunlap Department of Astronomy & Astrophysics(大卫·A·邓普普天文学与天体物理系);Department of Statistical Sciences(统计科学系);Data Sciences Institute(数据科学研究所)
Hyrax: An Extensible Framework for Rapid ML Experimentation and Unsupervised Discovery in the Era of Rubin, Roman, and Euclid
Dept. of Astronomy \& the DiRAC Institute, University of Washington, Box 351580, Seattle, WA 98195, USA;School of Physics;Astronomy, University of Minnesota, Minneapolis, MN 55455, USA;Department of Astronomy;Planetary Science, Northern Arizona University, Flagstaff, USA;McWilliams Center for Cosmology;Astrophysics, Department of Physics, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Rubin LSST observing strategies to maximize volume and uniformity coverage of Star Forming Regions in the Galactic Plane
在全天巡天时代,绘制银河系最年轻的恒星星族的完整地图是现代天体物理学中最具挑战性的目标之一。最年轻的恒星组成部分的特性是至关重要的,不仅对银河系结构的全球概览,银河系薄盘,其旋臂,但也为当地的研究。事实上,恒星形成区(SFR)的识别以及与它们形成的环境的比较,对于将它们置于周围巨大分子云的背景下以及理解与恒星和行星形成过程相关的未知物理机制也是至关重要的。在10年的观察中,Vera C. Rubin Legacy Survey of Space and Time(Rubin-LSST)将实现精致的光度深度,这将使我们能够显着扩展我们能够发现新SFR的体积,并扩大我们自己的银河系的详细知识领域。本文描述了一个度量,它估计了< 10 Myr and masses >Rubin LSST观测在5 σ星等显著性的GRI带中将探测到的年龄为t 0.3 M $_\odot$的年轻恒星的总数。我们采用最新的模拟Rubin-LSST调查策略来检查我们的指标结果,以评估不同的观察策略可能对我们的科学案例产生的影响。
Lomonosov Moscow State University(莫斯科国立大学);Carnegie Mellon University(卡内基梅隆大学);Stockholm University(斯德哥尔摩大学);University of Surrey(萨里大学);National Research University Higher School of Economics(高等经济大学);Space Research Institute of the Russian Academy of Sciences(俄罗斯科学院太空研究所)
Predicting the Spectroscopic Features of Galaxies by Applying Manifold Learning on Their Broad-Band Colors: Proof of Concept and Potential Applications for Euclid, Roman, and Rubin LSST
Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP
NASA FINESST Fellow;Department of Physics and Astronomy, University of Delaware(物理与天文学系,德雷克塞尔大学);University of Delaware, Data Science Institute(德雷克塞尔大学数据科学研究所);Joseph R. Biden, Jr. School of Public Policy and Administration, University of Delaware(德雷克塞尔大学公共政策与行政学院);Vera C. Rubin Observatory(维拉·鲁宾天文台);Division of Physics, Mathematics, and Astronomy, California Institute of Technology(物理、数学与天文学系,加州理工学院);Center for Data Driven Discovery, California Institute of Technology(数据驱动发现中心,加州理工学院)
Deep Learning for Multi-Messenger Astrophysics: A Gateway for Discovery in the Big Data Era
NCSA, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校国家超级计算应用中心);Department of Astronomy, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校天文学系);California Institute of Technology(加州理工学院);Las Cumbres Observatory(拉斯坎布雷斯天文台);Caltech/IPAC-NExScI(加州理工学院/红外处理与分析中心-系外行星科学研究所);Department of Physics and Astronomy, University of Delaware(特拉华大学物理与天文学系);Data Science Institute, University of Delaware(特拉华大学数据科学研究所);Center for Urban Science and Progress, New York University(纽约大学城市科学与进步中心);The Oskar Klein Centre for Cosmoparticle Physics, Stockholm University(斯德哥尔摩大学奥斯卡·克莱因宇宙粒子物理中心);The University of Chicago(芝加哥大学);IBM Systems(IBM系统部)