Machine learning generalised DFT+ <i>U</i> projectors in a numerical atom-centred orbital framework
We present machine learning-based workflows using symbolic regression and support vector machines to simultaneously optimise Hubbard U values and projectors, enabling accurate and efficient simulations of defects and polarons in complex metal oxides.
Authors
- Kushagra Agrawal (ORCID: https://orcid.org/0000-0002-9749-1031)
- Amit Chaudhari (ORCID: https://orcid.org/0009-0003-9782-9332)
- Andrew J. Logsdail (ORCID: https://orcid.org/0000-0002-2277-415X)
Institutions
- Cardiff University (GB)
- Cardiff Metropolitan University (GB)
Publication Details
- Journal
- Digital Discovery
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5dd00292c
- Citations
- 2
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 1.04