Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks
Suppression of cosmic muon spallation backgrounds in liquid scintillator detectors using convolutional neural networks
复制标题
DOI：
10.1016/j.nima.2019.162604
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
A. Li;A. Elagin;S. Fraker;C. Grant;L. Winslow
中科院分区：
文献类型：
--
作者：
A. Li;A. Elagin;S. Fraker;C. Grant;L. Winslow
宇宙μ介子散射背景在低本底实验中是普遍存在的。对于寻找无中微子双β衰变的基于液体蒸发器的实验，spiral产物10 C是2-3 MeV之间感兴趣区域的重要背景，并决定了实验的深度要求。我们开发了一种基于卷积神经网络（CNN）的算法，该算法使用光发射中的时间和空间相关性来识别10 C背景事件。使用一个简单的Monte Carlo模拟的单片液体闪烁体探测器，如KamLAND，我们发现，该算法是能够识别61.6%的10 C在90%的信号接受度，总的不确定度为2.7%。具有完美光收集的检测器可以在90%的信号接受度下识别98.2%。该算法不依赖于顶点和能量重建，与其他常用方法互补，可推广到其他背景源。这项工作为更深入地研究检测器相关效应和更先进的基于CNN的算法奠定了基础。
Cosmic muon spallation backgrounds are ubiquitous in low-background experiments. For liquid scintillator-based experiments searching for neutrinoless double-beta decay, the spallation product10C is an important background in the region of interest between 2–3 MeV and determines the depth requirement for the experiment. We have developed an algorithm based on a convolutional neural network (CNN) that uses the temporal and spatial correlations in light emissions to identify10C background events. Using a simple Monte Carlo simulation of a monolithic liquid scintillator detector like KamLAND, we find that the algorithm is capable of identifying 61.6% of the10C at 90% signal acceptance, with a total uncertainty of 2.7%. A detector with perfect light collection can identify 98.2% at 90% signal acceptance. The algorithm is independent of vertex and energy reconstruction, so it is complementary to other frequently-used methods and can be expanded to other background sources. This work forms the foundation for more in depth studies of detector-dependent effects and more advanced CNN-based algorithms.