[论文解读] Paradigm shift in electron-based crystallography via machine learning

Kevin Kaufmann, Chaoyi Zhu+5 more|arXiv (Cornell University)|Feb 10, 2019

X-ray Diffraction in Crystallography参考文献 50被引用 43

一句话总结

本文提出一种深度学习方法，能够在没有先验知识的情况下自动从 EBSD 模式识别晶体结构，性能优于传统的基于 Hough 的 EBSD，并揭示所学习到的晶体学特征。

ABSTRACT

Accurately determining the crystallographic structure of a material, organic or inorganic, is a critical primary step in material development and analysis. The most common practices involve analysis of diffraction patterns produced in laboratory XRD, TEM, and synchrotron X-ray sources. However, these techniques are slow, require careful sample preparation, can be difficult to access, and are prone to human error during analysis. This paper presents a newly developed methodology that represents a paradigm change in electron diffraction-based structure analysis techniques, with the potential to revolutionize multiple crystallography-related fields. A machine learning-based approach for rapid and autonomous identification of the crystal structure of metals and alloys, ceramics, and geological specimens, without any prior knowledge of the sample, is presented and demonstrated utilizing the electron backscatter diffraction (EBSD) technique. Electron backscatter diffraction patterns are collected from materials with well-known crystal structures, then a deep neural network model is constructed for classification to a specific Bravais lattice or point group. The applicability of this approach is evaluated on diffraction patterns from samples unknown to the computer without any human input or data filtering. This is in comparison to traditional Hough transform EBSD, which requires that you have already determined the phases present in your sample. The internal operations of the neural network are elucidated through visualizing the symmetry features learned by the convolutional neural network. It is determined that the model looks for the same features a crystallographer would use, even though it is not explicitly programmed to do so. This study opens the door to fully automated, high-throughput determination of crystal structures via several electron-based diffraction techniques.

研究动机与目标

• 开发一种机器学习工作流程，快速且自动地从金属、合金、陶瓷和地质标本的 EBSD 模式识别晶体结构。
• 在模型未知的样品模式上评估性能，且无人工干预或数据筛选。
• 将 ML 方法与需要先前相位确定的传统 Hough 变换 EBSD 进行比较。
• 对神经网络学习到的内部特征进行可视化和解释，以评估与晶体学家直觉的一致性。
• 展示通过电子衍射技术实现全自动化、高通量晶体结构确定的潜力。

提出的方法

• 构建一个深度神经网络模型，将 EBSD 衍射图样分类到一个特定的 Bravais lattice 或点群。
• 在具有已知晶体结构的材料的衍射图样上训练模型。
• 在计算机未知的样品上评估模型，且无人工输入或数据筛选。
• 可视化卷积神经网络学习到的对称性特征，以解释其决策基础。
• 将性能与需要先前相位知识的传统 Hough-transform EBSD 进行比较。
• 通过 EBSD 展示对多种电子衍射模态的适用性。

实验结果

研究问题

• RQ1 在不事先了解样品的情况下，深度神经网络是否能够将 EBSD 图样分类到正确的 Bravais lattice 或点群？
• RQ2 在需要先前相位信息方面，ML 方法与传统 Hough-transform EBSD 的比较如何？
• RQ3 卷积神经网络中学习到的特征是否与晶体学家所识别的对称特征一致？
• RQ4 在未知样品且不进行数据筛选的情况下，该方法是否具备鲁棒性？
• RQ5 使用该方法实现自动化、高通量晶体结构确定的潜力有多大？

主要发现

• 该模型能够将 EBSD 图样分类到 Bravais lattice 或点群，适用于金属、合金、陶瓷和地质标本。
• 该方法在计算机未知的样品上工作，无需人工输入或数据筛选。
• 与 Hough-transform EBSD 相比，ML 方法不需要先前相位的确定。
• 可视化显示网络学习的对称性特征，类似晶体学家使用的特征。
• 该研究为通过电子衍射实现完全自动化、高通量的晶体结构确定提供了一条途径。