标题： 基于六边形卷积神经网络的X射线偏振分解方法研究 显示英文标题

标题： Research on the X-Ray Polarization Deconstruction Method Based on Hexagonal Convolutional Neural Network

摘要： 轨迹重建算法对于极化测量至关重要。 除了传统的基于矩的轨迹重建方法，卷积神经网络（CNN）是一种有前景的替代方法。 然而，气体像素探测器（GPD）中为了更好的各向异性而使用的六边形网格轨迹图像并不符合经典的基于矩形的CNN，将轨迹图像从六边形转换为方形会导致信息丢失。 我们开发了一种新的六边形CNN算法，用于X射线偏振计中的轨迹重建和极化估计，该算法用于从光电子轨迹图像中提取发射角度和吸收点，并预测预测发射角度的不确定性。 使用PolarLight测试的模拟数据来训练和测试六边形CNN模型。 对于单个能量，与矩分析方法相比，六边形CNN算法在100%极化的数据中实现了15-30%的调制因子改进，其性能与IXPE团队新开发的基于矩形的CNN算法相当，但计算成本要低得多。 显示英文摘要

摘要： Track reconstruction algorithms are critical for polarization measurements. In addition to traditional moment-based track reconstruction approaches, convolutional neural networks (CNN) are a promising alternative. However, hexagonal grid track images in gas pixel detectors (GPD) for better anisotropy do not match the classical rectangle-based CNN, and converting the track images from hexagonal to square results in loss of information. We developed a new hexagonal CNN algorithm for track reconstruction and polarization estimation in X-ray polarimeters, which was used to extract emission angles and absorption points from photoelectron track images and predict the uncertainty of the predicted emission angles. The simulated data of PolarLight test were used to train and test the hexagonal CNN models. For individual energies, the hexagonal CNN algorithm produced 15-30% improvements in modulation factor compared to moment analysis method for 100% polarized data, and its performance was comparable to rectangle-based CNN algorithm newly developed by IXPE team, but at a much less computational cost.