skip to main content

DOE PAGESDOE PAGES

Title: Multi-fidelity machine learning models for accurate bandgap predictions of solids

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.
Authors:
ORCiD logo [1] ; ORCiD logo [2] ; ORCiD logo [2]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Materials Science and Technology Division
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Theoretical Division
Publication Date:
Report Number(s):
LA-UR-16-29228
Journal ID: ISSN 0927-0256; TRN: US1700513
Grant/Contract Number:
AC52-06NA25396
Type:
Accepted Manuscript
Journal Name:
Computational Materials Science
Additional Journal Information:
Journal Volume: 129; Journal Issue: C; Journal ID: ISSN 0927-0256
Publisher:
Elsevier
Research Org:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org:
USDOE
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; Double perovskites; Elpasolites; Materials informatics; Information fusion
OSTI Identifier:
1352377
Alternate Identifier(s):
OSTI ID: 1397619