Prediction of global Raman spectral features in minerals from structure and composition
= 0.33), and leave-one-family-out validation showed substantial losses in transfer performance. These results quantify both the predictive content and the extrapolation limits of static structure- and composition-derived descriptors.
Authors
- Chunguang Dong (ORCID: https://orcid.org/0009-0008-4643-9218)
- Zhao Liu (ORCID: https://orcid.org/0009-0008-0757-1398)
- Yihao Chen (ORCID: https://orcid.org/0009-0001-6870-6232)
- Meijie Zhang (ORCID: https://orcid.org/0000-0003-3630-819X)
Institutions
- Southern University of Science and Technology (CN)
- Wuhan University of Science and Technology (CN)
Publication Details
- Journal
- Physical Chemistry Chemical Physics
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1039/d6cp03858a
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00