Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase-Mapping
| dc.contributor.author | Kusne, A. Gilad | |
| dc.contributor.author | McDannald, Austin | |
| dc.contributor.author | DeCost, Brian | |
| dc.contributor.author | Oses, Corey | |
| dc.contributor.author | Toher, Cormac | |
| dc.contributor.author | Curtarolo, Stefano | |
| dc.contributor.author | Mehta, Apurva | |
| dc.contributor.author | Takeuchi, Ichiro | |
| dc.date.accessioned | 2022-06-14T20:06:34Z | |
| dc.date.available | 2022-06-14T20:06:34Z | |
| dc.date.issued | 2022-02-16 | |
| dc.description | Partial funding for Open Access provided by the UMD Libraries' Open Access Publishing Fund. | en_US |
| dc.description.abstract | Application of artificial intelligence (AI), and more specifically machine learning, to the physical sciences has expanded significantly over the past decades. In particular, science-informed AI, also known as scientific AI or inductive bias AI, has grown from a focus on data analysis to now controlling experiment design, simulation, execution and analysis in closed-loop autonomous systems. The CAMEO (closed-loop autonomous materials exploration and optimization) algorithm employs scientific AI to address two tasks: learning a material system’s composition-structure relationship and identifying materials compositions with optimal functional properties. By integrating these, accelerated materials screening across compositional phase diagrams was demonstrated, resulting in the discovery of a best-in-class phase change memory material. Key to this success is the ability to guide subsequent measurements to maximize knowledge of the composition-structure relationship, or phase map. In this work we investigate the benefits of incorporating varying levels of prior physical knowledge into CAMEO’s autonomous phase-mapping. This includes the use of ab-initio phase boundary data from the AFLOW repositories, which has been shown to optimize CAMEO’s search when used as a prior. | en_US |
| dc.description.uri | https://doi.org/10.3389/fphy.2022.815863 | |
| dc.identifier | https://doi.org/10.13016/rqdd-apb3 | |
| dc.identifier.citation | Kusne AG, McDannald A, DeCost B, Oses C, Toher C, Curtarolo S, Mehta A and Takeuchi I (2022) Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase- Mapping. Front. Phys. 10:815863. | en_US |
| dc.identifier.uri | http://hdl.handle.net/1903/28681 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Frontiers | en_US |
| dc.relation.isAvailableAt | A. James Clark School of Engineering | en_us |
| dc.relation.isAvailableAt | Materials Science & Engineering | en_us |
| dc.relation.isAvailableAt | Digital Repository at the University of Maryland | en_us |
| dc.relation.isAvailableAt | University of Maryland (College Park, MD) | en_us |
| dc.title | Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase-Mapping | en_US |
| dc.type | Article | en_US |