Analysis of Interpretable Data Representations for 4D-STEM Using Unsupervised Learning
Analysis of Interpretable Data Representations for 4D-STEM Using Unsupervised Learning
复制标题
DOI：
10.1017/s1431927622012259
复制
发表时间：
2022-09
影响因子：
2.8
通讯作者：
Alexandra Bruefach;C. Ophus;M. Scott
中科院分区：
文献类型：
--
作者：
Alexandra Bruefach;C. Ophus;M. Scott
摘要了解材料的结构对于提高材料和工程器件的性能至关重要。四维扫描透射电子显微镜（4D-STEM）能够在微米级视场上映射纳米级局部晶体结构。然而，4D-STEM数据集可能包含来自各种材料结构的数万张图像，这使得结构的自动检测和分类变得困难。传统的4D-STEM自动分析管道专注于监督方法，这需要材料结构的先验知识，并且无法描述异常或异常结构。在这篇文章中，介绍了一种使用非负矩阵分解（NMF）为无监督聚类设计4D-STEM特征表示的管道。每个功能使用NMF和结果进行评估，模拟和实验数据。结果表明，一些数据表示更可靠地识别重叠的晶粒。此外，应用真实的空间细化来识别空间上不同的样品区域，从而允许执行尺寸和形状分析。这项工作为使用4D-STEM改进对偏离预期晶体学排列的材料中纳米级结构特征的分析奠定了基础。
Abstract Understanding the structure of materials is crucial for engineering devices and materials with enhanced performance. Four-dimensional scanning transmission electron microscopy (4D-STEM) is capable of mapping nanometer-scale local crystallographic structure over micron-scale field of views. However, 4D-STEM datasets can contain tens of thousands of images from a wide variety of material structures, making it difficult to automate detection and classification of structures. Traditional automated analysis pipelines for 4D-STEM focus on supervised approaches, which require prior knowledge of the material structure and cannot describe anomalous or deviant structures. In this article, a pipeline for engineering 4D-STEM feature representations for unsupervised clustering using non-negative matrix factorization (NMF) is introduced. Each feature is evaluated using NMF and results are presented for both simulated and experimental data. It is shown that some data representations more reliably identify overlapping grains. Additionally, real space refinement is applied to identify spatially distinct sample regions, allowing for size and shape analysis to be performed. This work lays the foundation for improved analysis of nanoscale structural features in materials that deviate from expected crystallographic arrangement using 4D-STEM.