About this Abstract |
| Meeting |
2027 TMS Annual Meeting & Exhibition
|
| Symposium
|
Hume-Rothery Symposium: Data-Driven Materials Discovery and Phase Stability
|
| Presentation Title |
AI in the Wild: Autonomous laboratories for materials synthesis |
| Author(s) |
Gerbrand Ceder |
| On-Site Speaker (Planned) |
Gerbrand Ceder |
| Abstract Scope |
A-lab is an autonomous facility for the closed-loop synthesis of inorganic materials from powder precursors and a test bed for the interaction of AI and the physical world of materials experimenting. All synthesis and characterization actions in A-lab and all sample transfers between them are fully automated, leading to a lab that can synthesize and structurally characterize compounds within 10-20 hrs of initiation. The lab can be flexibly organized into workflows to satisfy the varying need of distinct research projects.
Autonomous decision making in an automated lab can be challenging as experimental is often noisy, incomplete, or ambiguous. I will show examples of how efficacy of decision making may require statistical priors that are based on chemical or human experience in order to produce reasonable data interpretation. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Ceramics, Machine Learning, |