K2 variable catalogue – II. Machine learning classification of variable stars and eclipsing binaries in K2 fields 0–4
K2 variable catalogue – II. Machine learning classification of variable stars and eclipsing binaries in K2 fields 0–4
复制标题
DOI：
10.1093/mnras/stv2836
复制
发表时间：
2015-12
影响因子：
4.8
通讯作者：
David J Armstrong;J. Kirk;K. Lam;J. McCormac;H. Osborn;J. Spake;S. Walker;D. Brown;M. Kristiansen;D. Pollacco;R. West;P. Wheatley
中科院分区：
文献类型：
--
作者：
David J Armstrong;J. Kirk;K. Lam;J. McCormac;H. Osborn;J. Spake;S. Walker;D. Brown;M. Kristiansen;D. Pollacco;R. West;P. Wheatley
我们正在进入一个由现有和计划中的巡天望远镜提供的数据量空前的时代。为了最大限度地发挥此类调查的潜力，需要自动化数据分析技术。在这里，我们通过 Kohonen 自组织映射（SOM，一种无监督机器学习算法）和更常见的随机森林 (RF) 监督机器学习技术的结合，实现了一种新的变星分类方法。我们将此方法应用于 K2 任务场 0-4 的数据，发现 154 个 ab 型 RR 天琴座（10 个新发现）、377 个 δ Scuti 脉动星、133 个 γ Doradus 脉动星、183 个分离食双星、290 个半分离或接触食双星和 9399 个其他周期性（主要是点调制）源，一旦分类考虑了显着性削减。我们展示了所有 K2 恒星目标的光曲线特征，包括它们的三个最强的检测到的频率，这些频率可用于研究恒星自转周期，其中观察到的变化是由点调制引起的。由此产生的变星、类和相关数据特征的目录可在线获取。我们在 PYTHON 中发布 SOM 代码，作为开源 PYMVPA 包的一部分，它与现有的 RF 模块相结合，可以轻松地用于重新创建该方法。
We are entering an era of unprecedented quantities of data from current and planned survey telescopes. To maximize the potential of such surveys, automated data analysis techniques are required. Here we implement a new methodology for variable star classification, through the combination of Kohonen Self-Organizing Maps (SOMs, an unsupervised machine learning algorithm) and the more common Random Forest (RF) supervised machine learning technique. We apply this method to data from the K2 mission fields 0–4, finding 154 ab-type RR Lyraes (10 newly discovered), 377 δ Scuti pulsators, 133 γ Doradus pulsators, 183 detached eclipsing binaries, 290 semidetached or contact eclipsing binaries and 9399 other periodic (mostly spot-modulated) sources, once class significance cuts are taken into account. We present light-curve features for all K2 stellar targets, including their three strongest detected frequencies, which can be used to study stellar rotation periods where the observed variability arises from spot modulation. The resulting catalogue of variable stars, classes, and associated data features are made available online. We publish our SOM code in PYTHON as part of the open source PYMVPA package, which in combination with already available RF modules can be easily used to recreate the method.