arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.24329hep-ex
收藏

基于深度神经网络的时间投影室域自适应位置重建方法

A Domain Adaptive Position Reconstruction Method for Time Projection Chamber based on Deep Neural Network

State Key Laboratory of Particle Detection and Electronics, University of Science and Technology of China(粒子探测与电子学国家重点实验室,中国科学技术大学);Department of Modern Physics, University of Science and Technology of China(近代物理系,中国科学技术大学);Deep Space Exploration Laboratory(深空探测实验室);School of Physics, Sun Yat-Sen University(物理学院,中山大学)

Xiaoran Guo, Fei Gao, Kaihang Li, Qing Lin, Jiajun Liu, Lijun Tong, Xiang Xiao, Lingfeng Xie, Yifei Zhao

AI总结:

针对时间投影室横向位置重建中真实与模拟数据不匹配导致的偏差和分辨率有限问题,提出基于循环一致性生成对抗网络的域自适应方法,在原型探测器和模拟50-kg TPC中均实现显著性能提升。

摘要:

时间投影室(TPC)的横向位置重建对精准的粒子径迹测量与粒子分类至关重要,通常借助机器学习技术实现。然而,由于真实实验数据与模拟训练样本之间存在不匹配,这类方法常存在偏差且分辨率有限。为缓解该问题,本文提出一种基于循环一致性生成对抗网络的域自适应重建方法。在原型探测器中应用该方法后,重建的径向边界提升了60.6%。将该方法扩展至模拟的50千克TPC中,通过评估模拟事例的分辨率,可实现至少27%的额外提升。

英文摘要:

Transverse position reconstruction in a Time Projection Chamber (TPC) is crucial for accurate particle tracking and classification, and is typically accomplished using machine learning techniques. However, these methods often exhibit biases and limited resolution due to incompatibility between real experimental data and simulated training samples. To mitigate this issue, we present a domain-adaptive reconstruction approach based on a cycle-consistent generative adversarial network. In the prototype detector, the application of this method led to a 60.6% increase in the reconstructed radial boundary. Scaling this method to a simulated 50-kg TPC, by evaluating the resolution of simulated events, an additional improvement of at least 27% is achieved.

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。

↑