About this Abstract |
| Meeting |
2023 TMS Annual Meeting & Exhibition
|
| Symposium
|
Computational Discovery and Design of Materials
|
| Presentation Title |
Closed Loop Computational Materials Discovery |
| Author(s) |
Raymundo Arroyave, Brent Vela, Danial Khatamsaz, Prashant Singh, Duane Johnson, Douglas Allaire |
| On-Site Speaker (Planned) |
Raymundo Arroyave |
| Abstract Scope |
In this talk, I will present some recent efforts toward developing and deploying closed-loop materials discovery frameworks within materials simulation workflows. Specifically, it will be shown how Bayesian Optimization (BO) methods can be used to efficiently explore vast materials spaces. These frameworks incorporate the ability to optimize for multiple objectives at once, and are capable of dealing with multiple constraints. Moreover, the framework is capable of incorporating multiple information sources at different levels of fidelity. While the frameworks have been deployed on structural materials, their application in the discovery of novel functional materials is straightforward. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, Modeling and Simulation, |