arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.01496astro-ph.IMastro-ph.HEcs.AIcs.LG
收藏

ORACLE:一种用于LSST的实时、分层、深度学习光度分类器

ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST

Northwestern University(西北大学);NSF-Simons AI Institute for the Sky (SkAI)(NSF-Simons天空人工智能研究所(SkAI));University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);The NSF AI Institute for Artificial Intelligence and Fundamental Interactions(NSF人工智能与基础相互作用研究所);Massachusetts Institute of Technology(麻省理工学院);Carnegie Mellon University(卡内基梅隆大学);National Center for Supercomputing Applications(国家超级计算应用中心)

Ved G. Shah, Alex Gagliano, Konstantin Malanchev, Gautham Narayan, Alex I. Malz, The LSST Dark Energy Science Collaboration

AI总结:

ORACLE是一种基于深度学习的实时光度分类器,通过分层结构和上下文信息实现高精度瞬变天体分类。

摘要:

我们介绍了ORACLE,这是首个用于实时、情境感知分类的分层深度学习模型,用于瞬变和变星天体物理现象。ORACLE是一种具有门控循环单元(GRUs)的循环神经网络,并使用定制的分层交叉熵损失函数进行训练,以在仅需单个光度观测的情况下提供高置信度的分类。每个对象的上下文信息,包括宿主星系的光度红移、偏移量、椭圆率和亮度,被连接到光曲线嵌入,并用于最终预测。在训练约0.5M个事件的Extended LSST天文时间序列分类挑战数据集上,我们实现了在顶层(瞬变 vs 变星)上的宏平均精度为0.96,仅使用第一次检测后的1天光度观测加上上下文信息,此精度在获得64天的光曲线后增加到>0.99,在1024天后为19种分类(包括超新星亚类、活动星系核、变星、微透镜事件和千新星)的精度为0.83。我们还比较了ORACLE与其他最先进的分类器,并报告了在19种分类任务上的可比性能,此外还提供了更早的准确顶层分类。本工作中使用的代码和模型权重可在我们的关联GitHub仓库(https://github.com/uiucsn/ELAsTiCC-Classification)上公开获取。

英文摘要:

We present ORACLE, the first hierarchical deep-learning model for real-time, context-aware classification of transient and variable astrophysical phenomena. ORACLE is a recurrent neural network with Gated Recurrent Units (GRUs), and has been trained using a custom hierarchical cross-entropy loss function to provide high-confidence classifications along an observationally-driven taxonomy with as little as a single photometric observation. Contextual information for each object, including host galaxy photometric redshift, offset, ellipticity and brightness, is concatenated to the light curve embedding and used to make a final prediction. Training on $\sim$0.5M events from the Extended LSST Astronomical Time-Series Classification Challenge, we achieve a top-level (Transient vs Variable) macro-averaged precision of 0.96 using only 1 day of photometric observations after the first detection in addition to contextual information, for each event; this increases to $>$0.99 once 64 days of the light curve has been obtained, and 0.83 at 1024 days after first detection for 19-way classification (including supernova sub-types, active galactic nuclei, variable stars, microlensing events, and kilonovae). We also compare ORACLE with other state-of-the-art classifiers and report comparable performance for the 19-way classification task, in addition to delivering accurate top-level classifications much earlier. The code and model weights used in this work are publicly available at our associated GitHub repository (https://github.com/uiucsn/ELAsTiCC-Classification).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑