npj: 神经网络——细探晶体

海归学者发起的公益学术平台

分享信息，整合资源

交流学术，偶尔风月

相形成和演化是固体化学、物理学、电化学和材料科学的关键过程之一，具有基础重要性，但目前尚没有在原子尺度上探索其机制。

近年来，（扫描）透射电子显微镜（（S）TEM）的进步使得人们能够在多个固态过程中观察到原子动力学对电子束辐射的响应。之前，要了解电子束照射下的相转换需要实时绘制结构相及其演变，需要靠手动尝试逐帧分析，不仅困难重重，还耗时费力、单调乏味、极易出错。美国橡树岭国家实验室的Rama Vasudevan等，受计算机视觉启发，猜测神经网络可能有所助益。他们采用深层卷积神经网络（DCNN）计算，自动确定在原子分辨图像中存在的布拉维晶格对称性。在给定输入图像的2D快速傅立叶变换情况下，对DCNN进行训练，识别出布拉维晶格类别；另外采用蒙特卡洛分析来确定预测概率和统计偏差，以展示（S）TEM的模拟图像和真实原子分辨图像的比较结果，他们发现该网络正确而快速地预测了晶格。然后，他们将训练好的网络应用于研究电子轰击下的WS₂结构，发现在此过程中其菱形结构消失，与实际观察的数据一致。可见，这种神经网络有可能是分析实时电子显微镜数据用于材料优化和设计的强大工具。

该文近期发表于npj Computational Materials, 4: 30 (2018) ，英文标题与摘要如下，点击左下角“阅读原文”可以自由获取论文PDF。

Mapping mesoscopic phase evolution during E-beam induced transformations via deep learning of atomically resolved images

Rama K. Vasudevan, Nouamane Laanait, Erik M. Ferragut, Kai Wang, David B. Geohegan, Kai Xiao, Maxim Ziatdinov, Stephen Jesse, Ondrej Dyck & Sergei V. Kalinin 

Understanding transformations under electron beam irradiation requires mapping the structural phases and their evolution in real time. To date, this has mostly been a manual endeavor comprising difficult frame-by-frame analysis that is simultaneously tedious and prone to error. Here, we turn toward the use of deep convolutional neural networks (DCNN) to automatically determine the Bravais lattice symmetry present in atomically resolved images. A DCNN is trained to identify the Bravais lattice class given a 2D fast Fourier transform of the input image. Monte-Carlo dropout is used for determining the prediction probability, and results are shown for both simulated and real atomically resolved images from scanning tunneling microscopy and scanning transmission electron microscopy. A reduced representation of the final layer output allows to visualize the separation of classes in the DCNN and agrees with physical intuition. We then apply the trained network to electron beam-induced transformations in WS2, which allows tracking and determination of growth rate of voids. We highlight two key aspects of these results: (1) it shows that DCNNs can be trained to recognize diffraction patterns, which is markedly different from the typical “real image” cases and (2) it provides a method with in-built uncertainty quantification, allowing the real-time analysis of phases present in atomically resolved images.

扩展阅读

 

npj：高强度难熔复合固溶体合金——通过电子结构筛选

npj: 热导率的计算——天堑变通途

npj: 机器学习——助力高效光谱学测定

npj：金属玻璃变形行为调节——软点的作用

npj：倪勇相场模型——预测位错独特相互作用

本文系网易新闻·网易号“各有态度”特色内容

媒体转载联系授权请看下方