用深度学习提升超新基多诺实验的低能中微子触发效率
Deep-learning-based low-energy trigger algorithms for the Hyper-Kamiokande experiment
- 设计神经网络分类器与异常检测模型，识别低能中微子信号
- 3MeV电子信号识别率达76.7%，远超传统方法的26.4%
- 模型推理延迟低于毫秒级，适合实时数据采集
现代机器学习在粒子物理中日益重要，尤其在实时数据获取中展现强大模式识别能力。本文针对大型水切伦科夫探测器超新基多诺（Hyper-Kamiokande）的低能中微子事件（低于7 MeV），评估基于深度学习的触发算法性能。对比了定制的监督式神经网络分类器与两种仅由探测器噪声训练的异常检测方法：纯自编码器和基于流形投影-扩散恢复（MPDR）的能量模型。监督模型对3 MeV动能单电子信号的识别效率达76.7%，显著优于传统基于击中计数的触发方法（26.4%），MPDR方法也达到31.8%。GPU运行测试显示，每窗口推理延迟远低于毫秒级，表明实时运行可行。
原文摘要 · Abstract (English)
Modern machine learning techniques have become increasingly important in particle physics because of their powerful pattern-recognition capabilities, including in real-time data acquisition where stringent runtime constraints apply. This paper details the performance of deep-learning-based trigger algorithms for a large water Cherenkov detector such as Hyper-Kamiokande aimed at low-energy neutrino events (below 7 MeV). The performance of custom neural-network supervised classifiers is shown alongside two anomaly-detection approaches trained solely on detector noise: a pure autoencoder and an energy-based model based on Manifold Projection--Diffusion Recovery (MPDR). The supervised model shows signal identification efficiencies of 76.7% for single electrons of 3 MeV kinetic energy, significantly exceeding signal efficiencies obtained from a traditional hit-count-based trigger of 26.4%, as does the MPDR approach with 31.8%. Runtime evaluations on GPU yield per-window inference latencies well below the millisecond scale, indicating that real-time operation is feasible.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。