arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.09744physics.ins-detcs.LGphysics.data-an
收藏

用于液氩探测器低能物理的少击中机器学习分类算法评估

Assessment of few-hits machine learning classification algorithms for low energy physics in liquid argon detectors

Università di Milano - Bicocca(米兰比可卡大学);Istituto Nazionale di Fisica Nucleare (INFN)(国家核物理研究所);European Organization for Nuclear Research (CERN)(欧洲核子研究组织);Università degli Studi di Milano(米兰大学)

Roberto Moretti, Marco Rossi, Matteo Biassoni, Andrea Giachero, Michele Grossi, Daniele Guffanti, Danilo Labranca, Francesco Terranova, Sofia Vallecorsa

AI总结:

针对液氩TPC低能少击中事件传统分类算法效果不佳的问题,评估了CNN和Transformer-Encoder两类ML算法,证实其在单/双β事件分类中优于确定性算法,并用于优化DUNE二期探测器参数。

摘要:

大型液氩时间投影室(TPC)在低能区间的物理潜力仍有待充分挖掘,因为少击中事件所携带的信息难以通过传统分类算法加以利用。机器学习(ML)技术在这类分类问题中表现优异。本文中,我们将其与传统(确定性)算法的性能进行了对比评估。我们证明,在低能物理最具挑战性的分类问题之一(单β事件与双β事件的区分)中,卷积神经网络(CNN)和Transformer-Encoder方法的表现均优于确定性算法。我们讨论了Transformer-Encoder方法相较于CNN的优势与缺陷,并利用这些方法优化探测器参数,重点关注DUNE二期探测器(“机遇模块”)。

英文摘要:

The physics potential of massive liquid argon TPCs in the low-energy regime is still to be fully reaped because few-hits events encode information that can hardly be exploited by conventional classification algorithms. Machine learning (ML) techniques give their best in these types of classification problems. In this paper, we evaluate their performance against conventional (deterministic) algorithms. We demonstrate that both Convolutional Neural Networks (CNN) and Transformer-Encoder methods outperform deterministic algorithms in one of the most challenging classification problems of low-energy physics (single- versus double-beta events). We discuss the advantages and pitfalls of Transformer-Encoder methods versus CNN and employ these methods to optimize the detector parameters, with an emphasis on the DUNE Phase II detectors ("Module of Opportunity").

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑