A transient search using combined human and machine classifications
A transient search using combined human and machine classifications
复制标题
DOI：
10.1093/mnras/stx1812
复制
发表时间：
2017-07
影响因子：
4.8
通讯作者：
D. Wright;C. Lintott;S. Smartt;Kenneth W. Smith;L. Fortson;L. Trouille;Campbell Allen;Melanie Beck;Mark C. Bouslog;Amy Boyer;K. Chambers;H. Flewelling;Will Granger;E. Magnier;Adam McMaster;G. Miller;J. O’Donnell;Helen Spiers;J. Tonry;Marten Veldthuis;R. Wainscoat;C. Waters;M. Willman;Zach Wolfenbarger;D. O. D. O. Physics-D.-O.;University of Oxford Astrophysics Research Centre;S. O. Mathematics;Physics;Queen's University Belfast Minnesota Institute for Astrophysics-Queen's-University-Belfast-Minnesota-Institute-for-1422183721;U. D. O. Physics;Astronomy;University of Minnesota Center for Interdisciplinary Exploration-University-of-Minnesota-Center-for-Exploration-1422184500;Research in Astrophysics;D. Physics;Northwestern University Citizen Science Department;The Netherlands Institute for Radio Astronomy;U. Hawaii
中科院分区：
文献类型：
--
作者：
D. Wright;C. Lintott;S. Smartt;Kenneth W. Smith;L. Fortson;L. Trouille;Campbell Allen;Melanie Beck;Mark C. Bouslog;Amy Boyer;K. Chambers;H. Flewelling;Will Granger;E. Magnier;Adam McMaster;G. Miller;J. O’Donnell;Helen Spiers;J. Tonry;Marten Veldthuis;R. Wainscoat;C. Waters;M. Willman;Zach Wolfenbarger;D. O. D. O. Physics-D.-O.;University of Oxford Astrophysics Research Centre;S. O. Mathematics;Physics;Queen's University Belfast Minnesota Institute for Astrophysics-Queen's-University-Belfast-Minnesota-Institute-for-1422183721;U. D. O. Physics;Astronomy;University of Minnesota Center for Interdisciplinary Exploration-University-of-Minnesota-Center-for-Exploration-1422184500;Research in Astrophysics;D. Physics;Northwestern University Citizen Science Department;The Netherlands Institute for Radio Astronomy;U. Hawaii
大型现代测量需要有效地审查数据，以便找到超新星等瞬变源，并将这些源与人工制品和噪音区分开来。人们已经在自动算法的开发上投入了大量精力，但调查仍然依赖于人类对目标的审查。本文提出了一个综合系统，用于识别Pan-STARRS 1数据中的超新星，将参与公民科学项目的志愿者的分类与卷积神经网络的分类相结合。这项工作的独特之处在于，结合人类和机器分类，在天文项目中进行近实时发现。我们表明，这两种方法的组合优于单独使用的任何一个。这一结果对瞬变搜索的未来发展具有重要意义，特别是在大型综合巡天望远镜和其他大通量巡天的时代。
Large modern surveys require efficient review of data in order to find transient sources such as supernovae, and to distinguish such sources from artefacts and noise. Much effort has been put into the development of automatic algorithms, but surveys still rely on human review of targets. This paper presents an integrated system for the identification of supernovae in data from Pan-STARRS1, combining classifications from volunteers participating in a citizen science project with those from a convolutional neural network. The unique aspect of this work is the deployment, in combination, of both human and machine classifications for near real-time discovery in an astronomical project. We show that the combination of the two methods outperforms either one used individually. This result has important implications for the future development of transient searches, especially in the era of Large Synoptic Survey Telescope and other large-throughput surveys.