| About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
2023 Technical Division Student Poster Contest
|
| Presentation Title |
SPG-46: Automating Selective Area Electron Diffraction Pattern Phase Identification Using Image Analysis and Machine Learning |
| Author(s) |
Mitchell L. Mika, Assel Aitkaliyeva |
| On-Site Speaker (Planned) |
Mitchell L. Mika |
| Abstract Scope |
Selective area electron diffraction (SAED) patterns can provide valuable insight into the structure of a material. For example, SAED patterns can be used to identify phase transformations such as those occurring during constituent redistribution in metallic nuclear fuels. The phase identification is conducted by matching experimentally collected SAED patterns to those simulated using various software. This process is time-intensive when done manually for each diffraction image and can create a bottleneck in the workflow of characterizing materials. In this contribution, we utilize the recent advances in computer vision and machine learning (ML) to automate the indexing of electron diffraction patterns. We utilize image analysis techniques and ML algorithms to introduce an open-source workflow that accelerates the processing of electron diffraction patterns. The phase identification is based on experimentally acquired SAED patterns and is demonstrated on metallic Pu-based alloys. |
| Proceedings Inclusion? |
Undecided |
| Keywords |
Nuclear Materials, Machine Learning, Characterization |