期刊
MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
卷 454, 期 2, 页码 2026-2038出版社
OXFORD UNIV PRESS
DOI: 10.1093/mnras/stv2041
关键词
methods: data analysis; methods: observational; methods: statistical; techniques: image processing; techniques: photometric; surveys
资金
- South African Square Kilometre Array (SKA) Project postgraduate scholarship
- Claude Leon Foundation
- South African National Research Foundation (NRF)
- SKA
- South African SKA Project
- NRF
- UK Science & Technology Facilities Council (STFC)
- Alfred P. Sloan Foundation
- National Science Foundation
- US Department of Energy
- National Aeronautics and Space Administration
- Japanese Monbukagakusho
- Max Planck Society
- Higher Education Funding Council for England
- American Museum of Natural History
- Astrophysical Institute Potsdam
- University of Basel
- Cambridge University
- Case Western Reserve University
- University of Chicago
- Drexel University
- Fermilab
- Institute for Advanced Study
- Japan Participation Group
- Johns Hopkins University
- Joint Institute for Nuclear Astrophysics
- Kavli Institute for Particle Astrophysics and Cosmology
- Korean Scientist Group
- Chinese Academy of Sciences (LAMOST), Los Alamos National Laboratory
- Max-Planck-Institute for Astronomy (MPIA)
- Max-Planck-Institute for Astrophysics (MPA)
- New Mexico State University
- Ohio State University
- University of Pittsburgh
- University of Portsmouth
- Princeton University
- United States Naval Observatory
- University of Washington
We show that multiple machine learning algorithms can match human performance in classifying transient imaging data from the Sloan Digital Sky Survey (SDSS) supernova survey into real objects and artefacts. This is a first step in any transient science pipeline and is currently still done by humans, but future surveys such as the Large Synoptic Survey Telescope (LSST) will necessitate fully machine-enabled solutions. Using features trained from eigenimage analysis (principal component analysis, PCA) of single-epoch g, r and i difference images, we can reach a completeness (recall) of 96 per cent, while only incorrectly classifying at most 18 per cent of artefacts as real objects, corresponding to a precision (purity) of 84 per cent. In general, random forests performed best, followed by the k-nearest neighbour and the SkyNet artificial neural net algorithms, compared to other methods such as naive Bayes and kernel support vector machine. Our results show that PCA-based machine learning can match human success levels and can naturally be extended by including multiple epochs of data, transient colours and host galaxy information which should allow for significant further improvements, especially at low signal-to-noise.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据