Navigating materials design spaces with efficient Bayesian optimization: a case study in functionalized nanoporous materials
Bayesian optimization with non-random initialization, coupled with an XGBoost regressor trained on BO-acquired samples, reduces experimental cost while efficiently identifying top-performing instances in large design spaces.
Authors
- George Giannakopoulos (ORCID: https://orcid.org/0000-0003-2459-589X)
- J. Theocharis
- Panagiotis Krokidas (ORCID: https://orcid.org/0000-0002-2445-6059)
- Vassilis Gkatsis
Institutions
- National and Kapodistrian University of Athens (GR)
- National Centre of Scientific Research "Demokritos" (GR)
- SciFY (GR)
- Institute of Informatics of the Slovak Academy of Sciences (SK)
Publication Details
- Journal
- Digital Discovery
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5dd00237k
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- European Commission
- HORIZON EUROPE Framework Programme