| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Novel Strategies for Rapid Acquisition and Processing of Large Datasets from Advanced Characterization Techniques
|
| Presentation Title |
Hierarchical Bayesian Data Analysis for Accelerating Structural Materials Characterization |
| Author(s) |
Brian DeCost, Howie Joress, Bruce Ravel, Mitra Taheri |
| On-Site Speaker (Planned) |
Brian DeCost |
| Abstract Scope |
Machine learning systems are being widely deployed to accelerate measurements of the structure and performance of materials. The black-box nature of the models used by these systems can limit the ability to decouple the effects of competing physical phenomena, particularly in the few-sample setting. Our approach blends Bayesian physical modeling and non-parametric machine learning models. Two challenging structural materials characterization tasks highlight this approach: quantitative analysis of multiphase x-ray diffraction (XRD) data and quantification of chemical short range order in multicomponent alloys via EXAFS. We show how to incorporate physical intuition into hierarchical priors, and how to incorporate flexible Gaussian Process modeling components for features without concrete physical models. Our long term goal is automated online analysis that can drive adaptive measurement selection with the aim of enabling comprehensive understanding of the relationship between structure and properties. |
| Proceedings Inclusion? |
Planned: |