The search for gravitational-wave signals is limited by non-Gaussian transient noises that mimic astrophysical signals. Temporal coincidence between two or more detectors is used to mitigate contamination by these instrumental glitches. However, when a single detector is in operation, coincidence is impossible, and other strategies have to be used. We explore the possibility of using neural network classifiers and present the results obtained with three types of architectures: convolutional neural network, temporal convolutional network, and inception time. The last two architectures are specifically designed to process time-series data. The classifiers are trained on a month of data from the LIGO Livingston detector during the first observing run (O1) to identify data segments that include the signature of a binary black hole merger. Their performances are assessed and compared. We then apply trained classifiers to the remaining three months of O1 data, focusing specifically on single-detector times. The most promising candidate from our search is 2016-01-04 12:24:17 UTC. Although we are not able to constrain the significance of this event to the level conventionally followed in gravitational-wave searches, we show that the signal is compatible with the merger of two black holes with masses $m_1 = 50.7^{+10.4}_{-8.9}\,M_{\odot}$ and $m_2 = 24.4^{+20.2}_{-9.3}\,M_{\odot}$ at the luminosity distance of $d_L = 564^{+812}_{-338}\,\mathrm{Mpc}$.
A Bayesian method to set upper limits on the strength of a periodic gravitational wave signal from the remnant of SN1987A: possible applications in LIGO searches
Multivariate Classification with Random Forests for Gravitational Wave Searches of Black Hole Binary Coalescence
对总质量为$\gtrsim25\,$ M $_\odot$的合并黑洞双星产生的引力波进行了匹配滤波。引力波探测器数据中的非高斯噪声爆发可以模拟短信号,并限制这些搜索的灵敏度。以前的搜索依赖于经验设计的统计数据,包括信噪比和基于信号的否决,以将引力波候选者与噪声候选者分开。我们报告使用来自监督机器学习算法的多变量候选人排名统计实现的灵敏度改进。我们应用随机森林的袋装决策树技术,在高质量的$\left( \gtrsim25\,\mathrm{M}_\odot \right)$参数空间中进行两次单独的搜索。对于一个搜索是敏感的引力波从螺旋,合并,和振铃(IMR)的二进制黑洞与$25\,$ M $_\odot$和$100\,$ M $_\odot$之间的总质量,我们发现灵敏的体积改善高达$70_{\pm 13}-109_{\pm 11}$ \%相比,以前使用的排名统计。对于振铃只搜索,这是敏感的引力波从所产生的扰动中间质量黑洞与质量大致之间的$10\,$ M $_\odot$和$600\,$ M $_\odot$,我们发现灵敏的体积改善高达$61_{\pm 4}-241_{\pm 12}$ \%相比,以前使用的排名统计。我们还报告了如何灵敏度的改善可以根据质量制度,质量比,和可用的数据质量信息而有所不同。最后,我们描述了用于调整和训练的随机森林分类器,可以推广到它的使用在其他搜索引力波的技…
Astrophysical or Terrestrial: Machine learning classification of gravitational-wave candidates using multiple-search information
University of Minnesota(明尼苏达大学);The University of British Columbia(不列颠哥伦比亚大学);NASA Goddard Space Flight Center(美国国家航空航天局戈达德太空飞行中心);Joint Space-Science Institute, University of Maryland(马里兰大学联合空间科学研究所)