Quantum Chemistry-Informed Active Learning to Accelerate the Design and Discovery of Sustainable Energy Storage Materials

Hieu A. Doan, Garvit Agarwal, Hai Qian, Michael J. Counihan, Joaquín Rodríguez-López, Jeffrey S. Moore, Rajeev S. Assary

Research output: Contribution to journalArticlepeer-review

Abstract

We employed density functional theory (DFT) to compute oxidation potentials of 1400 homobenzylic ether molecules to search for the ideal sustainable redoxmer design. The generated data were used to construct an active learning model based on Bayesian optimization (BO) that targets candidates with desired oxidation potentials utilizing only a minimal number of DFT calculations. The active learning model demonstrated not only significant efficiency improvement over the random selection approach but also robust capability in identifying desired candidates in an untested set of 112 »000 homobenzylic ether molecules. Our findings highlight the efficacy of quantum chemistry-informed active learning to accelerate the discovery of materials with desired properties from a vast chemical space.

Original languageEnglish (US)
Pages (from-to)6338-6346
Number of pages9
JournalChemistry of Materials
Volume32
Issue number15
DOIs
StatePublished - Aug 11 2020

ASJC Scopus subject areas

  • Chemistry(all)
  • Chemical Engineering(all)
  • Materials Chemistry

Fingerprint Dive into the research topics of 'Quantum Chemistry-Informed Active Learning to Accelerate the Design and Discovery of Sustainable Energy Storage Materials'. Together they form a unique fingerprint.

Cite this