Charge reconstruction of HERD silicon charge detectors based on MLP

IF 1.9 4区物理与天体物理 Q2 ASTRONOMY & ASTROPHYSICS

Astronomy and Computing Pub Date : 2025-07-11 DOI:10.1016/j.ascom.2025.100986

Longkun Yu , Jing Wang , Rui Qiao , Ke Gong , Wenxi Peng , Jiaju Wei , Bing Lu , Dongya Guo , Yaqing Liu , Xuan Liu , Chenxing Zhang , Ming Xu , Zhigang Wang , Ruijie Wang , Tianwei Bao , Yongwei Dong , Oscar Adriani , Eugenio Berti , Pietro Betti , Jorge Casaus , Nicola Zampa

{"title":"Charge reconstruction of HERD silicon charge detectors based on MLP","authors":"Longkun Yu , Jing Wang , Rui Qiao , Ke Gong , Wenxi Peng , Jiaju Wei , Bing Lu , Dongya Guo , Yaqing Liu , Xuan Liu , Chenxing Zhang , Ming Xu , Zhigang Wang , Ruijie Wang , Tianwei Bao , Yongwei Dong , Oscar Adriani , Eugenio Berti , Pietro Betti , Jorge Casaus , Nicola Zampa","doi":"10.1016/j.ascom.2025.100986","DOIUrl":null,"url":null,"abstract":"<div><div>The High Energy Cosmic-Radiation Detection (HERD) is an experimental facility designed for the study of space astronomy and particle astrophysics. The Silicon Charge Detector (SCD), as the outermost detector of HERD, has the primary objective of precisely measuring cosmic rays ranging from hydrogen to nickel. To enhance the charge resolution of the silicon charge detector by fully utilizing multi-channel information, this study employed Support Vector Machines (SVM) and Multi-Layer Perceptron (MLP) for charge reconstruction. Given the challenge of low statistics in high-<span><math><mi>Z</mi></math></span> data, we also introduced transfer learning to improve charge reconstruction for high-<span><math><mi>Z</mi></math></span> samples. Compared to our previous results (Zhanget al., 2024), the machine learning algorithm achieved an average improvement of approximately 9.8% in charge resolution for heavy nuclei with <span><math><mi>Z</mi></math></span> = 10 to <span><math><mi>Z</mi></math></span> = 28.</div></div>","PeriodicalId":48757,"journal":{"name":"Astronomy and Computing","volume":"53 ","pages":"Article 100986"},"PeriodicalIF":1.9000,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Astronomy and Computing","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2213133725000599","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}

引用次数: 0

Abstract

The High Energy Cosmic-Radiation Detection (HERD) is an experimental facility designed for the study of space astronomy and particle astrophysics. The Silicon Charge Detector (SCD), as the outermost detector of HERD, has the primary objective of precisely measuring cosmic rays ranging from hydrogen to nickel. To enhance the charge resolution of the silicon charge detector by fully utilizing multi-channel information, this study employed Support Vector Machines (SVM) and Multi-Layer Perceptron (MLP) for charge reconstruction. Given the challenge of low statistics in high-

Z

data, we also introduced transfer learning to improve charge reconstruction for high-

Z

samples. Compared to our previous results (Zhanget al., 2024), the machine learning algorithm achieved an average improvement of approximately 9.8% in charge resolution for heavy nuclei with

Z

= 10 to

Z

= 28.

查看原文本刊更多论文

基于MLP的HERD硅电荷探测器的电荷重构

高能宇宙辐射探测（HERD）是为研究空间天文学和粒子天体物理学而设计的实验设备。硅电荷探测器（SCD）作为HERD最外层的探测器，其主要目标是精确测量从氢到镍的宇宙射线。为了充分利用多通道信息，提高硅电荷探测器的电荷分辨率，本研究采用支持向量机（SVM）和多层感知器（MLP）进行电荷重构。考虑到高z数据的低统计量的挑战，我们还引入了迁移学习来改进高z样本的电荷重建。与我们之前的结果（Zhanget al., 2024）相比，机器学习算法在Z = 10到Z = 28的重核电荷分辨率上平均提高了约9.8%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Astronomy and Computing ASTRONOMY & ASTROPHYSICSCOMPUTER SCIENCE,-COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

CiteScore

4.10

自引率

8.00%

发文量

期刊介绍： Astronomy and Computing is a peer-reviewed journal that focuses on the broad area between astronomy, computer science and information technology. The journal aims to publish the work of scientists and (software) engineers in all aspects of astronomical computing, including the collection, analysis, reduction, visualisation, preservation and dissemination of data, and the development of astronomical software and simulations. The journal covers applications for academic computer science techniques to astronomy, as well as novel applications of information technologies within astronomy.