KamNet: An integrated spatiotemporal deep neural network for rare event searches in KamLAND-Zen
KamNet: An integrated spatiotemporal deep neural network for rare event searches in KamLAND-Zen
复制标题
DOI：
10.1103/physrevc.107.014323
复制
发表时间：
2022-03
影响因子：
3.1
通讯作者：
A. Li;Z. Fu;C. Grant;H. Ozaki;I. Shimizu;H. Song;A. Takeuchi;L. Winslow
中科院分区：
文献类型：
--
作者：
A. Li;Z. Fu;C. Grant;H. Ozaki;I. Shimizu;H. Song;A. Takeuchi;L. Winslow
罕见事件搜索使我们能够利用专门的大质量探测器在其他手段无法达到的能量尺度上搜索新的物理现象。机器学习提供了一种新的工具，可以最大限度地利用这些检测器提供的信息。信息是稀疏的，这迫使这些算法从最低级别的数据开始，并利用探测器中的所有对称性来产生结果。在这项工作中，我们介绍了KamNet，它利用几何深度学习和时空数据分析方面的突破，最大限度地扩大了KamLAND-Zen的物理范围，这是一种千吨级球形液体闪烁体探测器，用于搜索中微子双β衰变（$0\nu\beta\beta$）。使用KamLAND的简化背景模型，我们表明KamNet在基准MC模拟中表现优于传统CNN，具有更高的鲁棒性。使用模拟数据，我们展示了KamNet提高KamLAND-Zen对$0\nu\beta\beta$和$0\nu\beta\beta$对激发态的敏感性的能力。这项工作的一个关键组成部分是增加了一个注意力机制，以阐明KamNet用于背景拒绝的底层物理。
Rare event searches allow us to search for new physics at energy scales inaccessible with other means by leveraging specialized large-mass detectors. Machine learning provides a new tool to maximize the information provided by these detectors. The information is sparse, which forces these algorithms to start from the lowest level data and exploit all symmetries in the detector to produce results. In this work we present KamNet which harnesses breakthroughs in geometric deep learning and spatiotemporal data analysis to maximize the physics reach of KamLAND-Zen, a kiloton scale spherical liquid scintillator detector searching for neutrinoless double beta decay ($0\nu\beta\beta$). Using a simplified background model for KamLAND we show that KamNet outperforms a conventional CNN on benchmarking MC simulations with an increasing level of robustness. Using simulated data, we then demonstrate KamNet's ability to increase KamLAND-Zen's sensitivity to $0\nu\beta\beta$ and $0\nu\beta\beta$ to excited states. A key component of this work is the addition of an attention mechanism to elucidate the underlying physics KamNet is using for the background rejection.