A convolutional neural network for defect classification in Bragg coherent X-ray diffraction

Bruce Lim,Steven Leake,Alessandro Coati,Michael Sprung,Andrea Resta,Eugen Rabkin,Ehud Almog,Ewen Bellec,Tobias Schulli,Maxime Dupraz,Marie-Ingrid Richard

doi:10.1038/s41524-021-00583-9

Abstract

Coherent diffraction imaging enables the imaging of individual defects, such as dislocations or stacking faults, in materials. These defects and their surrounding elastic strain fields have a critical influence on the macroscopic properties and functionality of materials. However, their identification in Bragg coherent diffraction imaging remains a challenge and requires significant data mining. The ability to identify defects from the diffraction pattern alone would be a significant advantage when targeting specific defect types and accelerates experiment design and execution. Here, we exploit a computational tool based on a three-dimensional (3D) parametric atomistic model and a convolutional neural network to predict dislocations in a crystal from its 3D coherent diffraction pattern. Simulated diffraction patterns from several thousands of relaxed atomistic configurations of nanocrystals are used to train the neural network and to predict the presence or absence of dislocations as well as their type (screw or edge). Our study paves the way for defect-recognition in 3D coherent diffraction patterns for material science.

Highlights

Defect detection and classification are important issues in material science, as defects strongly influence the properties of materials[1,2,3,4]
Twins and stacking faults can improve the catalytic efficiency of nanoparticles[8], and more generally the strain generated by defects can affect the catalytic activity[9]
With the exponential advancements in computational resources[30] and the possibility of ultra-fast atomistic relaxation and computation of diffraction patterns with massive parallelism or graphical processing units (GPUs), it is straightforward to calculate the 3D Coherent X-ray diffraction patterns (CXDPs) of single nanocrystals from their atomistic configurations

Summary

INTRODUCTION

Defect detection and classification are important issues in material science, as defects strongly influence the properties of materials[1,2,3,4]. With the exponential advancements in computational resources[30] and the possibility of ultra-fast atomistic relaxation and computation of diffraction patterns with massive parallelism or graphical processing units (GPUs), it is straightforward to calculate the 3D CXDPs of single nanocrystals from their atomistic configurations These configurations can be generated by varying the type and location of the crystal defects and relaxed by energy minimization. Several papers proposed to use deeplearning models trained on simulated CXDPs to perform phase retrieval[32,33,34,35,36] which is commonly carried out using iterative algorithms This demonstrates the emergence of deep learning in the field of CXD and BCDI. This work paves the way for automated defect detection and its reliable recognition from 3D CXDPs

RESULTS AND DISCUSSION

Lim et al 3

METHODS