About this Abstract |
Meeting |
2024 TMS Annual Meeting & Exhibition
|
Symposium
|
Chemistry and Physics of Interfaces
|
Presentation Title |
Prediction of Solute Segregation at Metal/Oxide Interfaces Using Machine Learning Approach |
Author(s) |
Yizhou Lu, Blas Uberuaga , Samrat Choudhury |
On-Site Speaker (Planned) |
Yizhou Lu |
Abstract Scope |
The atomic structure and chemistry at metal/oxide interfaces are known to affect the properties of these interfaces. However, investigation of semi-coherent metal/oxide interfaces containing misfit dislocations using density functional theory (DFT) is often computationally intensive or prohibitive as it involves several hundreds to thousands of atoms. In this research we have investigated the solute segregation behavior at the Fe/Y2O3 interface, a model interface for cladding applications in nuclear fission reactors, using a combination of DFT calculations and machine learning (ML) approach. ML models were trained on DFT calculated segregation energy to identify the key chemical and geometric features that govern the solute segregation behavior at metal/oxide interfaces. Moreover, it was observed that ML models can predict the solute segregation behavior at a different Fe/Y2O3 interface with new orientation relationship at a computational cost less than 1/1000 of the cost needed for similar DFT calculations. |
Proceedings Inclusion? |
Planned: |
Keywords |
Computational Materials Science & Engineering, Thin Films and Interfaces, Machine Learning |