Epistemic uncertainty as a diagnostic probe for deep learning Hamiltonians
= 10.85 meV). These results establish ensemble variance as a practical reliability indicator and underscore the critical need for pre-establishing applicability boundaries before deploying machine learning models in computational research workflows.
Authors
- Shunbo Hu (ORCID: https://orcid.org/0000-0003-0472-0999)
- Zeyun Gao (ORCID: https://orcid.org/0009-0006-8174-4192)
- Tongyi Zhang (ORCID: https://orcid.org/0000-0002-7908-8046)
- Tianhao Su
Institutions
- Shanghai University (CN)
Publication Details
- Journal
- Nanoscale
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1039/d6nr02280d
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Key Research and Development Program of China