About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
Computational Discovery and Design of Materials
|
Presentation Title |
Applying Data-driven Models in Materials Science: Unraveling Hidden Relationships between Structures and Properties |
Author(s) |
Mingjie Liu |
On-Site Speaker (Planned) |
Mingjie Liu |
Abstract Scope |
Designing materials at atomic scale is promising to develop new materials for energy applications. However, we are still facing the challenges from huge materials space to explore, mismatch between simulations and experiments, and multiobjective design requirements. Data science and machine learnings are demonstrated as useful tools to tackle those challenges. In this talk, I will introduce the work of applying data-driven models in carbon materials design with examples of single-atom catalysts and ion-selective membrane. From those examples, I will show how the data-driven models can be used to accelerate the exploration of the materials space from atomic scale. |
Proceedings Inclusion? |
Planned: |
Keywords |
Computational Materials Science & Engineering, Machine Learning, Modeling and Simulation |