Autonomous materials synthesis via hierarchical active learning of nonequilibrium phase diagrams.

Autor: Ament S; Department of Computer Science, Cornell University, Ithaca, NY 14853, USA., Amsler M; Department of Materials Science and Engineering, Cornell University, Ithaca, NY 14853, USA.; Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, CH-3012 Bern, Switzerland., Sutherland DR; Department of Materials Science and Engineering, Cornell University, Ithaca, NY 14853, USA., Chang MC; Department of Materials Science and Engineering, Cornell University, Ithaca, NY 14853, USA., Guevarra D; Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA 91125, USA., Connolly AB; Department of Materials Science and Engineering, Cornell University, Ithaca, NY 14853, USA., Gregoire JM; Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA 91125, USA., Thompson MO; Department of Materials Science and Engineering, Cornell University, Ithaca, NY 14853, USA., Gomes CP; Department of Computer Science, Cornell University, Ithaca, NY 14853, USA., van Dover RB; Department of Materials Science and Engineering, Cornell University, Ithaca, NY 14853, USA.
Jazyk: angličtina
Zdroj: Science advances [Sci Adv] 2021 Dec 17; Vol. 7 (51), pp. eabg4930. Date of Electronic Publication: 2021 Dec 17.
DOI: 10.1126/sciadv.abg4930
Abstrakt: Autonomous experimentation enabled by artificial intelligence offers a new paradigm for accelerating scientific discovery. Nonequilibrium materials synthesis is emblematic of complex, resource-intensive experimentation whose acceleration would be a watershed for materials discovery. We demonstrate accelerated exploration of metastable materials through hierarchical autonomous experimentation governed by the Scientific Autonomous Reasoning Agent (SARA). SARA integrates robotic materials synthesis using lateral gradient laser spike annealing and optical characterization along with a hierarchy of AI methods to map out processing phase diagrams. Efficient exploration of the multidimensional parameter space is achieved with nested active learning cycles built upon advanced machine learning models that incorporate the underlying physics of the experiments and end-to-end uncertainty quantification. We demonstrate SARA’s performance by autonomously mapping synthesis phase boundaries for the Bi 2 O 3 system, leading to orders-of-magnitude acceleration in the establishment of a synthesis phase diagram that includes conditions for stabilizing δ-Bi 2 O 3 at room temperature, a critical development for electrochemical technologies.
Databáze: MEDLINE
Externí odkaz: