About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Computational Thermodynamics and Kinetics
|
| Presentation Title |
The Largest Ab Initio Amorphous Materials Database and Machine Learning Prediction for Diffusivity |
| Author(s) |
Hui Zheng, Eric Sivonxay, Max Gallant, Ziyao Luo, Matthew McDermott, Kristin Persson |
| On-Site Speaker (Planned) |
Hui Zheng |
| Abstract Scope |
Amorphous materials have unique properties that make them suitable for various applications in industry and technology. However, the absence of a database covering a broad chemical space for amorphous materials hinders the exploration of their design roles and effective screening, particularly regarding superior ionic conductivity. Establishing a comprehensive database is imperative to facilitate the investigation of amorphous materials. We present the largest amorphous database generated from systematic and accurate AIMD calculations. The database covered a total of 4886 distinct compositions, and 3383 of them include Li. We show that the database can be used for different simple machine-learning models to predict Li diffusivity with remarkable speed and good accuracy, offering a cost-effective alternative to expensive density functional theory (DFT) calculations. The database is a valuable resource for developing the universal machine learning potential to accelerate the materials design process. |
| Proceedings Inclusion? |
Planned: |