| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Methods, Techniques, and Materials Discovery of Irradiation Effect Using In-situ Microscopy
|
| Presentation Title |
Deep Learning Defect Detection in Electron Microscopy of Radiation Damage in Metals |
| Author(s) |
Dane Morgan, Ryan Jacobs, Mingren Shen, Priyam Patki, Matthew Lynch, Kevin Field |
| On-Site Speaker (Planned) |
Dane Morgan |
| Abstract Scope |
In this talk we discuss our recent work on automating detection of defects in electron microscopy images of irradiated metals. We demonstrate the capabilities of deep learning machine learning approaches to find the location and geometry of different defects in irradiated alloys, such as dislocation loops, black dot interstitial clusters, and cavities. We show that performance comparable to human analysis can be achieved with relatively small training data sets consisting of order one thousand labeled defects. We explore multiple avenues of assessment and our results suggest that averaging over many images can reduce the impact of errors. We explore convergence of the results with number of training samples, finding that certain defect types are significantly less well detected, likely due both to their having reduced sampling and greater variability. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, Nuclear Materials, Characterization |