PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING
PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING
复制标题
DOI：
10.3847/0067-0049/225/2/31
复制
发表时间：
2016-08-01
影响因子：
8.7
通讯作者：
Winter, Max K.
中科院分区：
文献类型：
--
作者：
Lochner, Michelle;McEwen, Jason D.;Winter, Max K.
鉴于暗能量巡天（DES）和大型综合巡天望远镜等当前和即将到来的成像巡天，自动光度超新星分类已成为近年来的一个活跃研究领域，因为不可能对所有发现的超新星类型进行光谱确认。在这里，我们结合现有方法和新方法开发了一个多方面的分类管道。我们的流程由两个阶段组成：从光变曲线中提取描述性特征，并使用机器学习算法进行分类。我们的特征提取方法各不相同，从依赖于模型的技术（即 SALT2 拟合）到将参数模型拟合到曲线的更独立的技术，再到完全独立于模型的小波方法。我们涵盖了一系列具有代表性的机器学习算法，包括朴素贝叶斯、k 最近邻、支持向量机、人工神经网络和增强决策树 (BDT)。我们在超新星光度分类挑战赛中的模拟多波段 DES 光曲线上测试了该流程。使用接收者操作特征的常用曲线下面积 (AUC) 作为度量，我们发现 SALT2 拟合和小波方法与 BDT 算法的 AUC 均达到 0.98，其中 1 表示完美分类。我们发现，无论特征集或算法是什么，代表性的训练集对于良好的分类都是至关重要的，这对光谱跟踪具有影响。重要的是，我们发现通过使用 SALT2 或带有 BDT 算法的小波特征集，可以纯粹根据光变曲线数据进行准确分类，而不需要任何红移信息。
Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k-nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.