arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.04072astro-ph.GAastro-ph.IM
收藏

LSST AGN 数据挑战:选择方法

The LSST AGN Data Challenge: Selection methods

Đorđe V. Savić, Isidora Jankov, Weixiang Yu, Vincenzo Petrecca, Matthew J. Temple, Qingling Ni, Raphael Shirley, Andjelka B. Kovacevic, Mladen Nikolic, Dragana … 展开作者

Đorđe V. Savić, Isidora Jankov, Weixiang Yu, Vincenzo Petrecca, Matthew J. Temple, Qingling Ni, Raphael Shirley, Andjelka B. Kovacevic, Mladen Nikolic, Dragana Ilic, Luka C. Popovic, Maurizio Paolillo, Swayamtrupta Panda, Aleksandra Ciprijanovic, Gordon T. Richards

AI总结:

本文介绍 LSST AGN 数据挑战,系统比较监督、无监督及经典方法对恒星、星系和 AGN 的分类性能,并发现光变特征与多波段相关性分析可显著提升类星体候选体选择效率。

摘要:

鲁宾天文台时空遗产巡天(LSST)的开发包括一系列由各个 LSST 科学合作组织(SC)在项目预运行阶段安排的数据挑战(DC)。AGN 科学合作组织数据挑战(AGNSCDC)是预期 LSST AGN 数据的部分原型,旨在验证在 LSST 等大型巡天中进行 AGN 选择与表征的机器学习方法。AGNSC-DC 于 2021 年开展,重点关注准确性、鲁棒性和可扩展性。训练数据集和盲测数据集利用斯隆数字巡天 Stripe 82 区域和 XMM-牛顿大尺度结构巡天区域的数据构建,以模拟未来的 LSST 发布星表。数据特征分为天体测量、测光、颜色、形态、红移和类别标签,并附加了光变特征和图像。我们展示了四个 DC 提交解决方案的结果,这些方案同时使用了经典方法和机器学习方法。我们系统测试了监督模型(支持向量机、随机森林、极端梯度提升、人工神经网络、卷积神经网络)和无监督模型(深度嵌入聚类)在将源分类/聚类为恒星、星系或 AGN 这一问题上的性能。我们在盲测数据集上获得了监督模型 97.5% 的分类准确率、无监督模型 96.0% 的聚类准确率,以及经典方法 95.0% 的准确率。我们发现光变特征显著提高了训练模型的准确率,并且不同波段之间的相关性分析能够实现快速且低成本的类星体候选体一阶选择。

英文摘要:

Development of the Rubin Observatory Legacy Survey of Space and Time (LSST) includes a series of Data Challenges (DC) arranged by various LSST Scientific Collaborations (SC) that are taking place during the projects preoperational phase. The AGN Science Collaboration Data Challenge (AGNSCDC) is a partial prototype of the expected LSST AGN data, aimed at validating machine learning approaches for AGN selection and characterization in large surveys like LSST. The AGNSC-DC took part in 2021 focusing on accuracy, robustness, and scalability. The training and the blinded datasets were constructed to mimic the future LSST release catalogs using the data from the Sloan Digital Sky Survey Stripe 82 region and the XMM-Newton Large Scale Structure Survey region. Data features were divided into astrometry, photometry, color, morphology, redshift and class label with the addition of variability features and images. We present the results of four DC submitted solutions using both classical and machine learning methods. We systematically test the performance of supervised (support vector machine, random forest, extreme gradient boosting, artificial neural network, convolutional neural network) and unsupervised (deep embedding clustering) models when applied to the problem of classifying/clustering sources as stars, galaxies or AGNs. We obtained classification accuracy 97.5% for supervised and clustering accuracy 96.0% for unsupervised models and 95.0% with a classic approach for a blinded dataset. We find that variability features significantly improve the accuracy of the trained models and correlation analysis among different bands enables a fast and inexpensive first order selection of quasar candidates

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。

↑