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 2406.09191hep-exphysics.comp-phphysics.data-anphysics.ins-det
收藏

粒子相互作用产生的切伦科夫光与闪烁光分离的机器学习模型综合比较

Comprehensive Machine Learning Model Comparison for Cherenkov and Scintillation Light Separation due to Particle Interactions

Emrah Tiras, Merve Tas, Dilara Kizilkaya, Muhammet Anil Yagiz, Mustafa Kandemir

AI总结:

针对WbLS探测器中切伦科夫光与闪烁光的分离问题,本文比较20余种机器学习模型,发现XGBoost、Light GBM、Random Forest及其集成模型在平衡与非平衡数据上准确率均超过95%。

摘要:

在过去几十年中,对水基液体闪烁体(Water-based Liquid Scintillator,WbLS)等新型探测器介质的需求不断增长,因为它们既能处理低能粒子相互作用,又具有更高的光产额。近年来,机器学习(ML)方法在高能物理中的应用也不断增加。ML和AI方法被用于该领域的许多物理项目,因为它们能够给出有效且灵敏的结果。在本研究中,我们旨在对水切伦科夫探测器开展综合分析,并利用来自WbLS探测器环境的数据,通过ML算法进行物理分析,以高效分离切伦科夫光子和闪烁光子。本研究的主要目标是通过将ML技术应用于模拟数据和实验数据,为信号分类等物理问题给出更精确的解决方案。在此,我们训练了20多个ML模型,结果表明,XGBoost、Light GBM和Random Forest三种机器学习模型及其集成模型,在平衡和非平衡数据集上分离切伦科夫光子和闪烁光子时均取得了超过95%的准确率。与采用简单时间截断的经典方法结果相比,这是效率上的显著提升。

英文摘要:

The demand for novel detector mediums such as Water-based Liquid Scintillator (WbLS) has increased over the last few decades due to their capability for both low energy particle interactions and higher light yield. Recently, the usage of machine learning (ML) methods in high-energy physics has also been increasing. The ML and AI methods are used in many physics projects in the field since they provide effective and sensitive results. In this study, we aimed to develop a comprehensive analysis of water Cherenkov detectors and perform physics analyses to efficiently separate Cherenkov and scintillation photons with ML algorithms using the data from the WbLS detector environment. The main goal of this study was to produce more precise solutions to physics problems, such as signal classification, by applying ML techniques to the simulation and experimental data. Here, we trained more than 20 ML models, and our results revealed that three machine learning models, XGBoost, Light GBM, and Random Forest models, and their ensemble model gave us more than 95\% accuracy for separating Cherenkov and scintillation photons with balanced and unbalanced datasets. This is a significant increase in efficiency as compared with the results of the classical method by applying simple time cuts.

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。

↑