| About this Abstract |
| Meeting |
TMS Specialty Congress 2024
|
| Symposium
|
Accelerating Discovery for Mechanical Behavior of Materials 2024
|
| Presentation Title |
Advancing Multiscale Materials Characterization Through Machine Learning Integration |
| Author(s) |
Reeju Pokharel, Ashley Lenau |
| On-Site Speaker (Planned) |
Ashley Lenau |
| Abstract Scope |
We address the difficulty of characterizing mesoscale materials behavior across various spatial and temporal scales, emphasizing the need for faster data analysis capability to enable multiscale experiments at light sources. The present bottlenecks in the data inversion process hinder instantaneous feedback, thereby limiting our capability to pinpoint key areas of interest in real-time during experiments for guiding multiscale measurements. In this work, we demonstrate machine learning (ML) techniques to reconstruct crystal orientations from diffraction patterns, the refinement of ML algorithms for superior prediction accuracy, and the integration of physics-based principles to strengthen the robustness of these ML models. The overarching goal is to enable multiscale material characterization studies in beamline settings, ensuring immediate feedback and reducing the time required for data analysis and interpretation. Such integrated approach is anticipated to improve our understanding of mesoscale material dynamics. |
| Proceedings Inclusion? |
Definite: Other |