About this Abstract |
Meeting |
2024 TMS Annual Meeting & Exhibition
|
Symposium
|
Local Ordering in Materials and Its Impacts on Mechanical Behaviors, Radiation Damage, and Corrosion
|
Presentation Title |
Bridging the Gap between Quantum Materials Modeling and Experiments with Machine Learning Under Extreme Environments |
Author(s) |
Wissam Saidi |
On-Site Speaker (Planned) |
Wissam Saidi |
Abstract Scope |
“Computational experiments” have emerged as a powerful complement to experiments in the design of new materials. The development of statistical tools based on machine learning (ML) and deep networks in conjunction with database construction and data mining have been demonstrated to significantly boost traditional quantum mechanical approaches, thus enabling rapid development of structure-property relationships. Recent progress in utilizing ML for computational design and the discovery of high entropy alloy catalysts will be reviewed, highlighting the need to utilize well-designed hierarchical ML architecture to obtain a higher prediction fidelity. Further, I will describe our recent efforts in generating ML potentials for elemental and complex alloy systems under different extreme environments, which enables the broad community to adapt and expand corresponding datasets towards material discovery and optimization applications. |
Proceedings Inclusion? |
Planned: |
Keywords |
Computational Materials Science & Engineering, High-Entropy Alloys, Machine Learning |