Calibrating DFT Formation Enthalpy Calculations by Multifidelity Machine Learning.

Autor:	Gong S; Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States., Wang S; Department of Materials Science and Engineering, University of Maryland, College Park, Maryland 20742, United States., Xie T; Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States., Chae WH; Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States., Liu R; Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States., Shao-Horn Y; Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States., Grossman JC; Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
Jazyk:	angličtina
Zdroj:	JACS Au [JACS Au] 2022 Sep 09; Vol. 2 (9), pp. 1964-1977. Date of Electronic Publication: 2022 Sep 09 (Print Publication: 2022).
DOI:	10.1021/jacsau.2c00235
Abstrakt:	The application of machine learning to predict materials properties measured by experiments are valuable yet difficult due to the limited amount of experimental data. In this work, we use a multifidelity random forest model to learn the experimental formation enthalpy of materials with prediction accuracy higher than the Perdew-Burke-Ernzerhof (PBE) functional with linear correction, PBEsol, and meta-generalized gradient approximation (meta-GGA) functionals (SCAN and r 2 SCAN), and it outperforms the hotly studied deep neural network-based representation learning and transfer learning. We then use the model to calibrate the DFT formation enthalpy in the Materials Project database and discover materials with underestimated stability. The multifidelity model is also used as a data-mining approach to find how DFT deviates from experiments by explaining the model output. Competing Interests: The authors declare no competing financial interest. (© 2022 The Authors. Published by American Chemical Society.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu