A deep convolutional neural network to analyze position averaged convergent beam electron diffraction patterns
A deep convolutional neural network to analyze position averaged convergent beam electron diffraction patterns
复制标题
DOI：
10.1016/j.ultramic.2018.03.004
复制
发表时间：
2018-05-01
期刊：
影响因子：
2.2
通讯作者：
LeBeau, J. M.
中科院分区：
文献类型：
--
作者：
Xu, W.;LeBeau, J. M.
我们建立了一系列深度卷积神经网络来自动分析位置平均会聚束电子衍射图。网络首先校准零阶磁盘大小、中心位置和旋转，而不需要预处理数据。有了对齐的数据，额外的网络然后测量样本的厚度和倾斜。网络的性能是作为一个函数的各种变量，包括厚度，倾斜和剂量进行探索。本文还提出了一种探索神经网络对各种模式特征响应的方法。该网络以类似于0.1秒/模式的速度处理模式，在保持准确性的同时，比暴力破解方法要快几个数量级。因此，该方法适用于自动处理大的4D STEM数据。我们还讨论了该方法对其他材料/方向的通用性，以及将神经网络的特征与最小二乘拟合相结合的混合方法，以便进行更稳健的分析。源代码可从https://github.com/subangstrom/DeepDiffraction获得。(C) 2018 Elsevier B.V.版权所有
We establish a series of deep convolutional neural networks to automatically analyze position averaged convergent beam electron diffraction patterns. The networks first calibrate the zero-order disk size, center position, and rotation without the need for pretreating the data. With the aligned data, additional networks then measure the sample thickness and tilt. The performance of the network is explored as a function of a variety of variables including thickness, tilt, and dose. A methodology to explore the response of the neural network to various pattern features is also presented. Processing patterns at a rate of similar to 0.1 s/pattern, the network is shown to be orders of magnitude faster than a brute force method while maintaining accuracy. The approach is thus suitable for automatically processing big, 4D STEM data. We also discuss the generality of the method to other materials/orientations as well as a hybrid approach that combines the features of the neural network with least squares fitting for even more robust analysis. The source code is available at https://github.com/subangstrom/DeepDiffraction. (C) 2018 Elsevier B.V. All rights reserved.