arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.12860cs.CVphysics.ins-det
收藏

机器学习在CLAS12探测器粒子径迹识别中的应用

Using Machine Learning for Particle Track Identification in the CLAS12 Detector

Old Dominion University(奥尔多明尼苏大学);Jefferson Lab(杰斐逊实验室)

Polykarpos Thomadakis, Angelos Angelopoulos, Gagik Gavalian, Nikos Chrisochoides

摘要:

粒子径迹重建是核物理实验中计算量最大的过程。传统算法使用组合方法,该方法详尽地测试轨道测量("命中")以识别形成实际粒子轨迹的那些。在这篇文章中,我们描述了四个机器学习(ML)模型,协助跟踪算法,从漂移室的测量识别有效的轨道候选人的发展。测试了几种类型的机器学习模型,包括:卷积神经网络(CNN),多层感知器(MLP),极端随机树(ERT)和递归神经网络(RNN)。作为这项工作的结果,一个MLP网络分类器被实现为CLAS12重建软件的一部分,以提供跟踪代码与推荐的候选轨道。所得到的软件实现了大于99%的准确性,并导致了35%的端到端的加速比相比,现有的算法。

英文摘要:

Particle track reconstruction is the most computationally intensive process in nuclear physics experiments. Traditional algorithms use a combinatorial approach that exhaustively tests track measurements ("hits") to identify those that form an actual particle trajectory. In this article, we describe the development of four machine learning (ML) models that assist the tracking algorithm by identifying valid track candidates from the measurements in drift chambers. Several types of machine learning models were tested, including: Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), Extremely Randomized Trees (ERT) and Recurrent Neural Networks (RNN). As a result of this work, an MLP network classifier was implemented as part of the CLAS12 reconstruction software to provide the tracking code with recommended track candidates. The resulting software achieved accuracy of greater than 99\% and resulted in an end-to-end speedup of 35\% compared to existing algorithms.

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。

↑