Autonomous intelligent agents for accelerated materials discovery

Joseph H. Montoya, Kirsten T. Winther, Raul A. Flores, Thomas Bligaard, Jens S. Hummelshøj, Muratahan Aykol*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

31 Downloads (Pure)

Abstract

We present an end-to-end computational system for autonomous materials discovery. The system aims for cost-effective optimization in large, high-dimensional search spaces of materials by adopting a sequential, agent-based approach to deciding which experiments to carry out. In choosing next experiments, agents can make use of past knowledge, surrogate models, logic, thermodynamic or other physical constructs, heuristic rules, and different exploration-exploitation strategies. We show a series of examples for (i) how the discovery campaigns for finding materials satisfying a relative stability objective can be simulated to design new agents, and (ii) how those agents can be deployed in real discovery campaigns to control experiments run externally, such as the cloud-based density functional theory simulations in this work. In a sample set of 16 campaigns covering a range of binary and ternary chemistries including metal oxides, phosphides, sulfides and alloys, this autonomous platform found 383 new stable or nearly stable materials with no intervention by the researchers. This journal is

Original languageEnglish
JournalChemical Science
Volume11
Issue number32
Pages (from-to)8517-8532
ISSN2041-6520
DOIs
Publication statusPublished - 2020

Cite this

Montoya, J. H., Winther, K. T., Flores, R. A., Bligaard, T., Hummelshøj, J. S., & Aykol, M. (2020). Autonomous intelligent agents for accelerated materials discovery. Chemical Science, 11(32), 8517-8532. https://doi.org/10.1039/d0sc01101k