About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advanced Materials for Energy Conversion and Storage 2026
|
| Presentation Title |
Machine Learning–Accelerated Design of Oxygen Electrodes for SOECs |
| Author(s) |
Guangchen Liu, Songge Yang, Yu Zhong |
| On-Site Speaker (Planned) |
Yu Zhong |
| Abstract Scope |
We present a machine learning–driven approach to design advanced oxygen electrode materials for solid oxide electrolysis cells (SOECs). First, we investigate LaCoO₃-based perovskites doped with 20 elements, using ML models trained on DFT and thermodynamic data to predict dopant effects on stability and conductivity. Second, we develop an interface construction tool to model perovskite/Ruddlesden-Popper (R-P) phase junctions, optimizing interfacial energy and coherency. Third, we explore high-entropy perovskites with multi-elemental doping on both A and B sites to assess phase stability and transport properties. This integrated framework enables rapid screening and targeted discovery of high-performance oxygen electrode candidates. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Energy Conversion and Storage, Modeling and Simulation, Machine Learning |