ProgramMaster Logo
Conference Tools for 2021 TMS Annual Meeting & Exhibition
Register as a New User
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting 2021 TMS Annual Meeting & Exhibition
Symposium Characterization of Materials through High Resolution Imaging
Presentation Title Ptychographic Inversion with Deep Learning Network and Automatic Differentiation
Author(s) Tao Zhou, Mathew Cherukara, Saugat Kandel, Stephan Hruszkewycz, Alexander Hexemer, Ross Harder, Pablo Enfedaque, Martin Holt
On-Site Speaker (Planned) Tao Zhou
Abstract Scope In this work, we demonstrate how machine learning and its related optimization tools can be used to replace conventional phase retrieval methods in X-ray transmission and Bragg ptychography. X-ray transmission ptychography has become a well-established technique for high resolution imaging and phase retrieval. We present PtychoNN, a novel approach to solve the ptychography problem based on deep convolutional neural networks. Once trained, PtychoNN is capable of generating high quality reconstructions up to hundreds of times faster compared to conventional iterative methods, essential for implementing on-the-fly phase retrieval. Moreover, by surpassing the numerical constraints of iterative methods, the sampling condition can also be significantly relaxed. The counterpart of transmission ptychography in diffraction condition is known as Bragg ptychography. The technique itself is less mature, as limited by the more complex diffraction geometry and data quality. Here we describe the forward propagation in Bragg ptychography using the Takagi-Taupin Equations (TTE). We show that, when combined with Automatic Differentiation (AD), TTE can be used as a general formalism for 3D phase retrieval, applicable to both Bragg ptychography and Bragg Coherent Diffraction Imaging. Compared to conventional Fourier Transform based methods, our approach accounts for additionally refraction, absorption, interference, dynamical effects, and is applicable to any kind of weakly strained material system.
Proceedings Inclusion? Planned:
Keywords Characterization, Machine Learning, Other


Adaptive Machine Learning for 3D Bragg Coherent Diffraction Imaging Reconstructions
Confocal Bragg Ptychography for 3D Mapping of Bulk Specimens
Evaluation of TATB Crystal Morphology for Predicting Sensitivity Using X-ray Computed Tomography
Exploiting Machine Learning Techniques in X-ray Ptychography
High Speed, High Resolution, High Temperature 3D Imaging of Spacecraft Materials during Atmospheric Entry Conditions
ID01 in Light of the ESRF-EBS
Image-based Simulation of Permeability and Image-to-Mesh Conversion of X-ray Tomographic Images of a Nickel Foam
Imaging Materials on the Run: Shedding Light on Fast Structural Processes Using Time-resolved Synchrotron X-ray Tomographic Microscopy
Imaging Phase Transitions of Quantum Materials with Bragg Coherent X-ray Diffraction
Improve Phase Retrieval Performance in Bragg CDI by Simultaneous Reconstruction of Multiple Diffraction Peaks
In Situ and Operando 3D Nano-imaging for Materials Science at the ESRF
Indexing Grains: A Comparison between Three-dimensional Synchrotron X-ray Diffraction and Electron Backscatter Diffraction Techniques
Investigating the Early Life on Earth with Nanoscale X-ray Coherent Imaging
Laboratory and Synchrotron-based X-ray Tomographic Imaging during In Situ Loading of Materials
Magnetic Correlations and Time Fluctuations in Assemblies of Fe3O4 Nanoparticles Probed via X-rays
Megahertz X-ray Microscopy for Imaging High-speed Phenomena in Opaque Materials
Mesoscale Defect Dynamics in the Bulk with Time-resolved Dark-field X-ray Microscopy
Microstructural Characterization and Mechanical Behavior of a Meteorite Using Correlative Microscopy
Multi-peak Phase Retrieval for Coherent X-ray Diffraction Imaging at High Energies
Near-surface Optical Characterisation of Ion Implantation in Titanium Oxide Thin Films
Optimization Based Approach for 3D Alignment in X-ray Nano-tomography
Ptychographic Inversion with Deep Learning Network and Automatic Differentiation
Quantitative Data Analysis of Dynamic Tomography Data with Motion Artifacts
Retrieving the Full 3D Strain Tensor for Nanoscale Materials Science Applications at 34-ID-C
Study of Structure of Beam-sensitive Supported Nanoparticle Catalysts by Low-dose High Resolution Phase Contrast Imaging
The Fourth is Strong in These Ones!
Using Phase Field Simulations to Train Convolutional Neural Networks for Segmentation of Experimental Materials Imaging Datasets
Using the Rotation Vector Base Line Electron Back Scatter Diffraction (RVB-EBSD) Method to Characterize Single Crystal Cast Microstructures
X-ray Based Nanodiffraction to Study Strain in Materials for Nuclear Energy
X-ray Imaging of Three-dimensional Magnetic Systems and Their Dynamics

Questions about ProgramMaster? Contact