| About this Abstract |
| Meeting |
2022 TMS Annual Meeting & Exhibition
|
| Symposium
|
Grain Boundaries and Interfaces: Metastability, Disorder, and Non-Equilibrium Behavior
|
| Presentation Title |
Integration of Microscopy and Deep Learning to Define Localized Grain Boundary Sink Efficiency |
| Author(s) |
Emily H. Mang, Emma Liu, Ryan Jacobs, Priyam Patki, James Nathaniel, Kevin Field, Dane Morgan, Mitra Taheri |
| On-Site Speaker (Planned) |
Emily H. Mang |
| Abstract Scope |
Achieving radiation tolerance in crystalline materials will require a thorough understanding of defect evolution and corresponding grain boundary sink efficiency. Defect denuded zones have been widely accepted as descriptors of grain boundary sinks. However, recent studies have shown that denuded zone measurement may omit critical nuances illustrating the behavioral response of grain boundaries given regions of varying absorption rates and localized strain complexes. In this study, we explore the automated use of the object detection model YOLO to probe sink efficiency in regions of fluctuating grain boundary strain. Used in combination with in situ transmission electron microscopy, we can work toward a deeper understanding of point defect absorption and grain boundary sink behavior through the quantitative visualization of temporal defect evolution under irradiation. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Nuclear Materials, Characterization, Machine Learning |