A deep equivariant neural network approach for efficient hybrid density functional calculations

Hybrid density functional calculations are essential for accurate description of electronic structure, yet their widespread use is restricted by the substantial computational cost. Here we develop DeepH-hybrid, a deep equivariant neural network method for learning the hybrid-functional Hamiltonian as a function of material structure, which circumvents the time-consuming self-consistent field iterations and enables the study of large-scale materials with hybrid-functional accuracy. Our extensive experiments demonstrate good reliability as well as effective transferability and efficiency of the method. As a notable application, DeepH-hybrid is applied to study large-supercell Moiré-twisted materials, offering the first case study on how the inclusion of exact exchange affects flat bands in magic-angle twisted bilayer graphene. The work generalizes deep-learning electronic structure methods to beyond conventional density functional theory, facilitating the development of deep-learning-based ab initio methods.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2024-10-11
DOI
https://doi.org/10.1038/s41467-024-53028-4
Citations
28
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
3.28

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A deep equivariant neural network approach for efficient hybrid density functional calculations

He Li, Peize Lin, Yong Xu, Wenhui Duan et al.
28 citations
Nature Communications
Machine Learning in Materials Science
3.28
article

A deep equivariant neural network approach for efficient hybrid density functional calculations

He Li, Peize Lin, Yong Xu, Wenhui Duan, Lixin He, Xinguo Ren, Hong Jiang, Xiaoxun Gong, Zechen Tang, Gan Jin
article en
28 citations

Abstract

Hybrid density functional calculations are essential for accurate description of electronic structure, yet their widespread use is restricted by the substantial computational cost. Here we develop DeepH-hybrid, a deep equivariant neural network method for learning the hybrid-functional Hamiltonian as a function of material structure, which circumvents the time-consuming self-consistent field iterations and enables the study of large-scale materials with hybrid-functional accuracy. Our extensive experiments demonstrate good reliability as well as effective transferability and efficiency of the method. As a notable application, DeepH-hybrid is applied to study large-supercell Moiré-twisted materials, offering the first case study on how the inclusion of exact exchange affects flat bands in magic-angle twisted bilayer graphene. The work generalizes deep-learning electronic structure methods to beyond conventional density functional theory, facilitating the development of deep-learning-based ab initio methods.

Nature CommunicationsVol. 15(1)
University of Science and Technology of China (CN), Chinese Academy of Sciences (CN), Peking University (CN), Songshan Lake Materials Laboratory (CN), RIKEN Center for Emergent Matter Science (JP), Beijing Academy of Quantum Information Sciences (CN), Institute of Physics (CN), National Laboratory for Superconductivity (CN), Tsinghua University (CN)
National Natural Science Foundation of China, Beijing Innovation Center for Future Chip, National Science Fund for Distinguished Young Scholars
Affordable and clean energy
Openalex Percentile: Top 4%
Machine Learning in Materials Science
3.28
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.