Multi-fidelity machine learning models for accurate bandgap predictions of solids [electronic resource].
- Published:
- Washington, D.C. : United States. Dept. of Energy, 2016.
Oak Ridge, Tenn. : Distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy - Physical Description:
- 156-163 : digital, PDF file
- Additional Creators:
- Los Alamos National Laboratory
United States. Department of Energy
United States. Department of Energy. Office of Scientific and Technical Information - Access Online:
- www.osti.gov
- Summary:
- Here, we present a multi-fidelity co-kriging statistical learning framework that combines variable-fidelity quantum mechanical calculations of bandgaps to generate a machine-learned model that enables low-cost accurate predictions of the bandgaps at the highest fidelity level. Additionally, the adopted Gaussian process regression formulation allows us to predict the underlying uncertainties as a measure of our confidence in the predictions. In using a set of 600 elpasolite compounds as an example dataset and using semi-local and hybrid exchange correlation functionals within density functional theory as two levels of fidelities, we demonstrate the excellent learning performance of the method against actual high fidelity quantum mechanical calculations of the bandgaps. The presented statistical learning method is not restricted to bandgaps or electronic structure methods and extends the utility of high throughput property predictions in a significant way.
- Subject(s):
- Note:
- Published through SciTech Connect.
12/28/2016.
"la-ur-16-29228"
Computational Materials Science 129 C ISSN 0927-0256 AM
Ghanshyam Pilania; James E. Gubernatis; Turab Lookman. - Funding Information:
- AC52-06NA25396
View MARC record | catkey: 24057298