About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Environmental Degradation of Multiple Principal Component Materials
|
| Presentation Title |
Data-Driven Prediction of Materials Electrochemical Stability |
| Author(s) |
Seda Oturak, Ismaila Dabo |
| On-Site Speaker (Planned) |
Seda Oturak |
| Abstract Scope |
Predicting corrosion resistance under operating conditions is critical to materials design, notably for the development of durable electrocatalysts. While high-entropy oxides are among the strongest candidates for applications in electrocatalysis, predicting the electrochemical stability of multi-component materials as a function of the applied electrode potential and pH conditions is challenging. In this study, we leverage available online databases to develop a model to predict electrochemical decomposition energy from crystal structure characteristics and atomic properties. To do this, data-analysis and dimensionality reduction methods are used to examine the latent space, and a graph-neural-network model is developed to estimate electrochemical stability. The proposed model provides an effective approach with a relative accuracy to generalized-gradient density-functional theory predictions. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, High-Entropy Alloys, Computational Materials Science & Engineering |