A convolutional neural network approach for reconstructing polarization information of photoelectric X-ray polarimeters
A convolutional neural network approach for reconstructing polarization information of photoelectric X-ray polarimeters
复制标题
DOI：
10.1016/j.nima.2019.162389
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
T. Kitaguchi;K. Black;T. Enoto;A. Hayato;J. Hill;W. Iwakiri;P. Kaaret;T. Mizuno;T. Tamagawa
中科院分区：
文献类型：
--
作者：
T. Kitaguchi;K. Black;T. Enoto;A. Hayato;J. Hill;W. Iwakiri;P. Kaaret;T. Mizuno;T. Tamagawa
提出了一种基于机器学习的X射线光电子径迹图像偏振提取和同相轴选择的数据处理算法。该方法使用卷积神经网络（CNN）分类来从沿X射线入射方向沿着投影的2-D轨迹图像预测初始光电子发射的方位角和2-D位置。用Monte Carlo模拟生成的数据集演示了两种CNN模型：一种具有由交叉熵计算的常用损失函数，另一种具有额外的损失项，以基于H检验的非偏振调制曲线的非均匀性，该H检验用于X射线/γ射线天文学中的周期信号搜索。利用非极化数据计算得到的调制曲线存在一些不规则的特征，这些特征可以通过展开角响应或模拟探测器旋转来消除。另一方面，后一种模型可以预测平坦的调制曲线，其残余系统调制下降到101%。两个模型显示出几乎相同的调制因子和小于2像素（或240 μ m）的所有四个测试能量为2.7，4.5，6.4，和8.0 keV的位置精度。此外，基于来自CNN的概率来执行事件选择，以考虑调制因子和信号接受度之间的权衡来最大化偏振灵敏度。与先前开发的图像矩方法相比，所开发的机器学习方法将偏振灵敏度提高了10%-20%。
This paper presents a data processing algorithm with machine learning for polarization extraction and event selection applied to photoelectron track images taken with X-ray polarimeters. The method uses a convolutional neural network (CNN) classification to predict the azimuthal angle and 2-D position of the initial photoelectron emission from a 2-D track image projected along the X-ray incident direction. Two CNN models are demonstrated with data sets generated by a Monte Carlo simulation: one has a commonly used loss function calculated by the cross entropy and the other has an additional loss term to penalize nonuniformity for an unpolarized modulation curve based on the H-test, which is used for periodic signal search in X-ray/γ-ray astronomy. The modulation curve calculated by the former model with unpolarized data has several irregular features, which can be canceled out by unfolding the angular response or simulating the detector rotation. On the other hand, the latter model can predict a flat modulation curve with a residual systematic modulation down to≲ 1%. Both models show almost the same modulation factors and position accuracy of less than 2 pixel (or 240 μ m) for all four test energies of 2.7, 4.5, 6.4, and 8.0 keV. In addition, event selection is performed based on probabilities from the CNN to maximize the polarization sensitivity considering a trade-off between the modulation factor and signal acceptance. The developed method with machine learning improves the polarization sensitivity by 10%–20%, compared to that determined with the image moment method developed previously.