A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations

TL;DR

This paper presents an automated TEM video analysis system using YOLO for defect detection, enabling scalable, human-comparable microstructural analysis and defect tracking in in-situ ion irradiation experiments.

Contribution

The work introduces a YOLO-based automated defect detection and tracking framework for TEM videos, achieving high accuracy and enabling detailed defect evolution analysis.

Findings

F1 score of 0.89 for defect detection

Automated tracking of defect growth rates

Scalable analysis comparable to human performance

Abstract

Videos captured using Transmission Electron Microscopy (TEM) can encode details regarding the morphological and temporal evolution of a material by taking snapshots of the microstructure sequentially. However, manual analysis of such video is tedious, error-prone, unreliable, and prohibitively time-consuming if one wishes to analyze a significant fraction of frames for even videos of modest length. In this work, we developed an automated TEM video analysis system for microstructural features based on the advanced object detection model called YOLO and tested the system on an in-situ ion irradiation TEM video of dislocation loops formed in a FeCrAl alloy. The system provides analysis of features observed in TEM including both static and dynamic properties using the YOLO-based defect detection module coupled to a geometry analysis module and a dynamic tracking module. Results show that the system can achieve human comparable performance with an F1 score of 0.89 for fast, consistent, and scalable frame-level defect analysis. This result is obtained on a real but exceptionally clean and stable data set and more challenging data sets may not achieve this performance. The dynamic tracking also enabled evaluation of individual defect evolution like per defect growth rate at a fidelity never before achieved using common human analysis methods. Our work shows that automatically detecting and tracking interesting microstructures and properties contained in TEM videos is viable and opens new doors for evaluating materials dynamics.