.png){kind=icon}
.png){kind=icon}
Return
STEM diffraction pattern analysis with deep learning networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.matdes.2025.115069.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Machine learning enables fast, high-resolution STEM orientation mapping. • Deep networks trained on experimental 4D-SPED data predict Euler angles. • Swin Transformer yields highest accuracy and intra-grain consistency. • Workflow includes systematic hyperparameter optimisation for ML models. • Approach supports scalable microstructure analysis in energy materials.
Keywords:
STEM
Artificial neural networks
Microstructure analysis
Grain orientation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
M
IF:
7.9
Papers:
1.9W
Citations:
9.8W