当前位置: X-MOL 学术Appl. Phys. Rev. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Rapid 3D nanoscale coherent imaging via physics-aware deep learning
Applied Physics Reviews ( IF 11.9 ) Pub Date : 2021-05-17 , DOI: 10.1063/5.0031486
Henry Chan 1, 2 , Youssef S. G. Nashed 3 , Saugat Kandel 4 , Stephan O. Hruszkewycz 5 , Subramanian K. R. S. Sankaranarayanan 1, 2 , Ross J. Harder 6 , Mathew J. Cherukara 1, 6
Affiliation  

Phase retrieval, the problem of recovering lost phase information from measured intensity alone, is an inverse problem that is widely faced in various imaging modalities ranging from astronomy to nanoscale imaging. The current process of phase recovery is iterative in nature. As a result, the image formation is time consuming and computationally expensive, precluding real-time imaging. Here, we use 3D nanoscale X-ray imaging as a representative example to develop a deep learning model to address this phase retrieval problem. We introduce 3D-CDI-NN, a deep convolutional neural network and differential programing framework trained to predict 3D structure and strain, solely from input 3D X-ray coherent scattering data. Our networks are designed to be “physics-aware” in multiple aspects; in that the physics of the X-ray scattering process is explicitly enforced in the training of the network, and the training data are drawn from atomistic simulations that are representative of the physics of the material. We further refine the neural network prediction through a physics-based optimization procedure to enable maximum accuracy at lowest computational cost. 3D-CDI-NN can invert a 3D coherent diffraction pattern to real-space structure and strain hundreds of times faster than traditional iterative phase retrieval methods. Our integrated machine learning and differential programing solution to the phase retrieval problem is broadly applicable across inverse problems in other application areas.

中文翻译:

通过物理感知深度学习实现快速 3D 纳米级相干成像

相位检索,即仅从测量强度中恢复丢失的相位信息的问题,是在从天文学到纳米级成像的各种成像模式中广泛面临的逆问题。当前的相位恢复过程本质上是迭代的。结果,图像形成耗时且计算成本高,妨碍了实时成像。在这里,我们使用 3D 纳米级 X 射线成像作为代表性示例来开发深度学习模型来解决这个相位检索问题。我们介绍了 3D-CDI-NN,这是一种深度卷积神经网络和差分编程框架,训练用于预测 3D 结构和应变,仅从输入的 3D X 射线相干散射数据。我们的网络被设计为在多个方面具有“物理意识”;因为 X 射线散射过程的物理特性在网络训练中被明确执行,并且训练数据来自代表材料物理特性的原子模拟。我们通过基于物理的优化程序进一步细化神经网络预测,以最低的计算成本实现最大的准确性。3D-CDI-NN 可以将 3D 相干衍射图案反转为真实空间结构,并且比传统的迭代相位检索方法快数百倍。我们针对相位检索问题的集成机器学习和差分编程解决方案广泛适用于其他应用领域的逆问题。训练数据来自代表材料物理特性的原子模拟。我们通过基于物理的优化程序进一步细化神经网络预测,以最低的计算成本实现最大的准确性。3D-CDI-NN 可以将 3D 相干衍射图案反转为真实空间结构,并且比传统的迭代相位检索方法快数百倍。我们针对相位检索问题的集成机器学习和差分编程解决方案广泛适用于其他应用领域的逆问题。训练数据来自代表材料物理特性的原子模拟。我们通过基于物理的优化程序进一步细化神经网络预测,以最低的计算成本实现最大的准确性。3D-CDI-NN 可以将 3D 相干衍射图案反转为真实空间结构,并且比传统的迭代相位检索方法快数百倍。我们针对相位检索问题的集成机器学习和差分编程解决方案广泛适用于其他应用领域的逆问题。3D-CDI-NN 可以将 3D 相干衍射图案反转为真实空间结构,并且比传统的迭代相位检索方法快数百倍。我们针对相位检索问题的集成机器学习和差分编程解决方案广泛适用于其他应用领域的逆问题。3D-CDI-NN 可以将 3D 相干衍射图案反转为真实空间结构,并且比传统的迭代相位检索方法快数百倍。我们针对相位检索问题的集成机器学习和差分编程解决方案广泛适用于其他应用领域的逆问题。
更新日期:2021-07-26
down
wechat
bug