The Photometric LSST Astronomical Time-series Classification Challenge PLAsTiCC: Selection of a Performance Metric for Classification Probabilities Balancing Diverse Science Goals-猫眼课题宝

DOI：

10.3847/1538-3881/ab3a2f

发表时间：

2018-09

期刊：

The Astronomical Journal

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

A. Malz;R. Hložek;T. Allam;A. Bahmanyar;R. Biswas;M. Dai;L. Galbany;E. Ishida;S. Jha;D. Jones;R. Kessler;M. Lochner;A. Mahabal;K. Mandel;J. R. Martínez-Galarza;J. McEwen;D. Muthukrishna;G. Narayan;H. Peiris;C. Peters;K. Ponder;C. Setzer

对瞬变光曲线和可变光曲线进行分类是利用天文观测发展对产生瞬变光曲线的基本物理过程的理解的重要步骤。然而，即将到来的深部光度测量，包括大型天气观测望远镜(LSST)，将产生大量低信噪比数据，传统的类型估计程序不适合这些数据。概率分类更适合于这类数据，但与用于确定性分类的传统指标不兼容。此外，像LSST这样的大型调查合作打算将结果分类概率用于不同的科学目标，这表明需要一种平衡各种目标的衡量标准。我们描述了用于为开放分类挑战开发最佳性能度量的过程，该挑战寻求识别可以服务于许多科学兴趣的概率分类器。光度学LSST天文时间序列分类挑战(PLAsTiCC)旨在通过参与天文学以外的更广泛的社区，确定获得瞬变和可变物体的分类概率的有前途的技术。使用模拟的分类概率提交，模拟PLAsTiCC预期的真实复杂原型，我们比较了不同加权方案下两种分类概率度量的敏感度，发现两者产生的结果与分类性能的直观概念定性一致。因此，我们选择交叉熵的加权修正作为PLAsTiCC的度量，因为它可以根据信息量进行有意义的解释。最后，我们建议将我们的方法扩展到更复杂的挑战目标，并提出一些指导原则，以接近概率数据产品度量的选择。

Classification of transient and variable light curves is an essential step in using astronomical observations to develop an understanding of the underlying physical processes from which they arise. However, upcoming deep photometric surveys, including the Large Synoptic Survey Telescope (LSST), will produce a deluge of low signal-to-noise data for which traditional type estimation procedures are inappropriate. Probabilistic classification is more appropriate for such data but is incompatible with the traditional metrics used on deterministic classifications. Furthermore, large survey collaborations like LSST intend to use the resulting classification probabilities for diverse science objectives, indicating a need for a metric that balances a variety of goals. We describe the process used to develop an optimal performance metric for an open classification challenge that seeks to identify probabilistic classifiers that can serve many scientific interests. The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC) aims to identify promising techniques for obtaining classification probabilities of transient and variable objects by engaging a broader community beyond astronomy. Using mock classification probability submissions emulating realistically complex archetypes of those anticipated of PLAsTiCC, we compare the sensitivity of two metrics of classification probabilities under various weighting schemes, finding that both yield results that are qualitatively consistent with intuitive notions of classification performance. We thus choose as a metric for PLAsTiCC a weighted modification of the cross-entropy because it can be meaningfully interpreted in terms of information content. Finally, we propose extensions of our methodology to ever more complex challenge goals and suggest some guiding principles for approaching the choice of a metric of probabilistic data products.

The Photometric LSST Astronomical Time-series Classification Challenge PLAsTiCC: Selection of a Performance Metric for Classification Probabilities Balancing Diverse Science Goals

文献摘要

相似文献