Optimization of deep learning method on track reconstruction for X-ray polarimetry with gas pixel detectors

IF 2.7 3区物理与天体物理 Q2 ASTRONOMY & ASTROPHYSICS

Experimental Astronomy Pub Date : 2025-05-08 DOI:10.1007/s10686-025-10003-1

Yang Jiao, Weichun Jiang, Jiechen Jiang, Huilin He, Hua Feng, Xiaohua Liu, Hong Li, Liming Song, Yuanyuan Du, Liang Sun, Xiaojing Liu, Qiong Wu, Jiawei Yang, Zipeng Song, Hangyu Chen, Yongqi Zhao, Yupeng Xu, Congzhan Liu, Shuangnan Zhang

{"title":"Optimization of deep learning method on track reconstruction for X-ray polarimetry with gas pixel detectors","authors":"Yang Jiao, Weichun Jiang, Jiechen Jiang, Huilin He, Hua Feng, Xiaohua Liu, Hong Li, Liming Song, Yuanyuan Du, Liang Sun, Xiaojing Liu, Qiong Wu, Jiawei Yang, Zipeng Song, Hangyu Chen, Yongqi Zhao, Yupeng Xu, Congzhan Liu, Shuangnan Zhang","doi":"10.1007/s10686-025-10003-1","DOIUrl":null,"url":null,"abstract":"<div><p>The reconstruction of the photoelectron tracks in X-ray polarimetric detectors based on Gas Pixel Detectors (GPD) is crucial for polarization detection. In addition to traditional moment analysis methods, the convolutional neural network (CNN) is also a noteworthy approach. However, most existing CNN methods for polarization detection have only been effectively validated on simulated data, and the few methods validated on experimental data have not yielded satisfactory results. We have improved the CNN algorithm for reconstructing the emission direction of photoelectron tracks in X-ray polarimetric detectors. We tested this algorithm using calibration data from the detectors of the PolarLight mission and the Polarimetry Focusing Array (PFA) onboard the enhanced X-ray Timing and Polarimetry (eXTP) mission. The results indicate that the optimized deep learning model increased the modulation factor by approximately 0.02 over the 2-8 keV energy range and only introduced a small systematic error. This can enhance the sensitivity of polarization detector in the low-energy range. Additionally, the computational resources required for the model are much lower than the previous CNN models.</p></div>","PeriodicalId":551,"journal":{"name":"Experimental Astronomy","volume":"59 3","pages":""},"PeriodicalIF":2.7000,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Experimental Astronomy","FirstCategoryId":"101","ListUrlMain":"https://link.springer.com/article/10.1007/s10686-025-10003-1","RegionNum":3,"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 reconstruction of the photoelectron tracks in X-ray polarimetric detectors based on Gas Pixel Detectors (GPD) is crucial for polarization detection. In addition to traditional moment analysis methods, the convolutional neural network (CNN) is also a noteworthy approach. However, most existing CNN methods for polarization detection have only been effectively validated on simulated data, and the few methods validated on experimental data have not yielded satisfactory results. We have improved the CNN algorithm for reconstructing the emission direction of photoelectron tracks in X-ray polarimetric detectors. We tested this algorithm using calibration data from the detectors of the PolarLight mission and the Polarimetry Focusing Array (PFA) onboard the enhanced X-ray Timing and Polarimetry (eXTP) mission. The results indicate that the optimized deep learning model increased the modulation factor by approximately 0.02 over the 2-8 keV energy range and only introduced a small systematic error. This can enhance the sensitivity of polarization detector in the low-energy range. Additionally, the computational resources required for the model are much lower than the previous CNN models.

查看原文本刊更多论文

气体像元x射线偏振仪轨道重建的深度学习方法优化

基于气体像素探测器（GPD）的x射线偏振探测器中光电子轨迹的重建是偏振探测的关键。除了传统的矩分析方法外，卷积神经网络（CNN）也是一种值得关注的方法。然而，现有的CNN偏振检测方法大多只在模拟数据上进行了有效的验证，少数在实验数据上进行了验证的方法并没有取得令人满意的结果。我们改进了CNN算法，用于重建x射线偏振探测器中光电子轨迹的发射方向。我们使用来自polpollight任务探测器和增强x射线计时和偏振测量（eXTP）任务上的偏振聚焦阵列（PFA）的校准数据对该算法进行了测试。结果表明，优化后的深度学习模型在2-8 keV能量范围内的调制因子提高了约0.02，并且只引入了很小的系统误差。这可以提高偏振探测器在低能范围内的灵敏度。此外，该模型所需的计算资源远低于之前的CNN模型。

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

Experimental Astronomy 地学天文-天文与天体物理

CiteScore

5.30

自引率

3.30%

发文量

审稿时长

6-12 weeks

期刊介绍： Many new instruments for observing astronomical objects at a variety of wavelengths have been and are continually being developed. Furthermore, a vast amount of effort is being put into the development of new techniques for data analysis in order to cope with great streams of data collected by these instruments. Experimental Astronomy acts as a medium for the publication of papers of contemporary scientific interest on astrophysical instrumentation and methods necessary for the conduct of astronomy at all wavelength fields. Experimental Astronomy publishes full-length articles, research letters and reviews on developments in detection techniques, instruments, and data analysis and image processing techniques. Occasional special issues are published, giving an in-depth presentation of the instrumentation and/or analysis connected with specific projects, such as satellite experiments or ground-based telescopes, or of specialized techniques.