用于在GRAPES-3缪子望远镜中识别缪子和强子径迹的机器学习管道
Machine learning pipeline for identifying tracks of muons and hadrons at GRAPES-3 muon telescope
AI总结:
研究针对GRAPES-3缪子望远镜中缪子和强子径迹识别问题,利用CORSIKA模拟质子簇射及Geant4探测器模拟,通过单粒子分类和多粒子分类的GNN建模及深度学习回归模型,实现粒子径迹区分与数量估计。
摘要:
GRAPES-3实验是一个地面广延大气簇射阵列,由约400个紧密排列的塑料闪烁体探测器和一个大面积缪子望远镜组成。估算大气簇射中产生的相关缪子数量对理解初级宇宙射线性质至关重要。GRAPES-3缪子望远镜记录这些次级缪子,但穿透强子会引入背景噪声。本研究旨在开发机器学习管道以区分GRAPES-3缪子望远镜中次级缪子和强子的径迹。使用CORSIKA模拟的能量在100 - 158 TeV范围内的质子簇射作为基于Geant4的探测器模拟的输入来分析两种粒子的特征。单粒子分类用决策树、随机森林、神经网络和XGBoost进行,XGBoost准确率最高达88.7%。多粒子分类用图神经网络(GNNs)建模,还开发了深度学习回归模型来估计同时撞击G3MT的粒子和缪子数量。将展示多粒子分类任务的分析细节和结果。
英文摘要:
The GRAPES-3 experiment is a ground-based extensive air shower array which consists of approximately $400$ closely packed plastic scintillator detectors and a large area muon telescope. Estimating the number of associated muons created in an air shower is crucial to understand the properties of primary cosmic rays. The GRAPES-3 muon telescope (G3MT) records these secondary muons, however, the punch-through hadrons can introduce background noise. This study aims to develop a machine learning pipeline to distinguish the tracks of secondary muons and hadrons at G3MT. We have used CORSIKA-simulated proton showers having energy in the range 100-158 TeV as an input for a Geant4-based detector simulation to analyze the signatures of both type of particles. Initially, single-particle classification was performed using decision trees, random forests, neural networks, and XGBoost, with XGBoost achieving the highest accuracy of 88.7\%. For multiparticle classification, we modelled Graph Neural Networks (GNNs) where each event was represented as a graph with detector hits as nodes. A GNN with edge convolution layers was developed to classify each node as a muon or hadron hit. Following this, a deep learning regression model using Dynamic Reduction Network was developed to estimate the number of particles and muons striking G3MT simultaneously. Details of the analysis and results of the multiparticle classification task will be presented.
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。