logo
ResearchBunny Logo
Machine learning the Hubbard *U* parameter in DFT+*U* using Bayesian optimization

Engineering and Technology

Machine learning the Hubbard *U* parameter in DFT+*U* using Bayesian optimization

M. Yu, S. Yang, et al.

Explore a novel machine learning approach that employs Bayesian optimization to pinpoint optimal Hubbard *U* parameters in DFT+*U* calculations, achieving band structures on par with, or even superior to, traditional linear response methods. This exciting research was conducted by Maituo Yu, Shuyang Yang, Chunzhi Wu, and Noa Marom.... show more
Abstract
Within density functional theory (DFT), adding a Hubbard U correction can mitigate some of the deficiencies of local and semi-local exchange-correlation functionals, while maintaining computational efficiency. However, the accuracy of DFT+U largely depends on the chosen Hubbard U values. We propose an approach to determining the optimal U parameters for a given material by machine learning. The Bayesian optimization (BO) algorithm is used with an objective function formulated to reproduce the band structures produced by more accurate hybrid functionals. This approach is demonstrated for transition metal oxides, europium chalcogenides, and narrow-gap semiconductors. The band structures obtained using the BO U values are in agreement with hybrid functional results. Additionally, comparison to the linear response (LR) approach to determining U demonstrates that the BO method is superior.
Publisher
npj Computational Materials
Published On
Nov 27, 2020
Authors
Maituo Yu, Shuyang Yang, Chunzhi Wu, Noa Marom
DOI
https://doi.org/10.1038/s41524-020-00446-9
Tags
Bayesian optimization
Hubbard U parameters
DFT+U calculations
band structures
transition metal oxides
computational efficiency
hybrid functionals

Related Publications

Explore these studies to deepen your understanding of the subject.

Recent Advancements and Perspectives in the Diagnosis of Skin Diseases Using Machine Learning and Deep Learning: A Review
Medicine and Health

Recent Advancements and Perspectives in the Diagnosis of Skin Diseases Using Machine Learning and Deep Learning: A Review

J. Zhang, F. Zhong, et al.

Accelerating the prediction of CO2 capture at low partial pressures in metal-organic frameworks using new machine learning descriptors
Chemistry

Accelerating the prediction of CO2 capture at low partial pressures in metal-organic frameworks using new machine learning descriptors

I. B. Orhan, T. C. Le, et al.

Decoding consumer purchase decisions: exploring the predictive power of EEG features in online shopping environments using machine learning
Business

Decoding consumer purchase decisions: exploring the predictive power of EEG features in online shopping environments using machine learning

Z. Xu and S. Liu

Building machine learning prediction models for well-being using predictors from the exposome and genome in a population cohort
Psychology

Building machine learning prediction models for well-being using predictors from the exposome and genome in a population cohort

D. H. M. Pelt, P. C. Habets, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny