中国物理B ›› 2026, Vol. 35 ›› Issue (1): 17101-017101.doi: 10.1088/1674-1056/ae15ef

• • 上一篇    

Review of machine learning tight-binding models: Route to accurate and scalable electronic simulations

Jijie Zou(邹暨捷)2,3, Zhanghao Zhouyin(周寅张皓)4, Shishir Kumar Pandey5,6, and Qiangqiang Gu(顾强强)1,2,7,8,†   

  1. 1 School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei 230026, China;
    2 AI for Science Institute, Beijing 100080, China;
    3 Center for Nanoscale Science and Technology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China;
    4 Department of Physics, McGill University, Montreal, Quebec H3A2T8, Canada;
    5 Department of General Sciences, Birla Institute of Technology and Science, Pilani, Dubai Campus, Dubai International Academic City, Dubai, United Arab Emirates;
    6 Department of Physics, Birla Institute of Technology and Science, Pilani, Hyderabad Campus, Jawahar Nagar, Kapra Mandal, Medchal District, Telangana 500078, India;
    7 Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou 215123, China;
    8 Suzhou Big Data & AI Research and Engineering Center, Suzhou 215123, China
  • 收稿日期:2025-07-30 修回日期:2025-10-10 接受日期:2025-10-22 发布日期:2025-12-29
  • 通讯作者: Qiangqiang Gu E-mail:guqq@ustc.edu.cn
  • 基金资助:
    This work is supported by the Advanced MaterialsNational Science and Technology Major Project (Grant No. 2025ZD0618401) and the National Natural Science Foundation of China (Grant No. 12504285), and the Natural Science Foundation of Jiangsu Province (Grant No. BK20250472).

Review of machine learning tight-binding models: Route to accurate and scalable electronic simulations

Jijie Zou(邹暨捷)2,3, Zhanghao Zhouyin(周寅张皓)4, Shishir Kumar Pandey5,6, and Qiangqiang Gu(顾强强)1,2,7,8,†   

  1. 1 School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei 230026, China;
    2 AI for Science Institute, Beijing 100080, China;
    3 Center for Nanoscale Science and Technology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China;
    4 Department of Physics, McGill University, Montreal, Quebec H3A2T8, Canada;
    5 Department of General Sciences, Birla Institute of Technology and Science, Pilani, Dubai Campus, Dubai International Academic City, Dubai, United Arab Emirates;
    6 Department of Physics, Birla Institute of Technology and Science, Pilani, Hyderabad Campus, Jawahar Nagar, Kapra Mandal, Medchal District, Telangana 500078, India;
    7 Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou 215123, China;
    8 Suzhou Big Data & AI Research and Engineering Center, Suzhou 215123, China
  • Received:2025-07-30 Revised:2025-10-10 Accepted:2025-10-22 Published:2025-12-29
  • Contact: Qiangqiang Gu E-mail:guqq@ustc.edu.cn
  • Supported by:
    This work is supported by the Advanced MaterialsNational Science and Technology Major Project (Grant No. 2025ZD0618401) and the National Natural Science Foundation of China (Grant No. 12504285), and the Natural Science Foundation of Jiangsu Province (Grant No. BK20250472).

PDF (PC)

7

赞

摘要： The rapid advancement of machine learning based tight-binding Hamiltonian (MLTB) methods has opened new avenues for efficient and accurate electronic structure simulations, particularly in large-scale systems and long-time scenarios. This review begins with a concise overview of traditional tight-binding (TB) models, including both (semi-)empirical and first-principles approaches, establishing the foundation for understanding MLTB developments. We then present a systematic classification of existing MLTB methodologies, grouped into two major categories: direct prediction of TB Hamiltonian elements and inference of empirical parameters. A comparative analysis with other ML-based electronic structure models is also provided, highlighting the advancement of MLTB approaches. Finally, we explore the emerging MLTB application ecosystem, highlighting how the integration of MLTB models with a diverse suite of post-processing tools from linear-scaling solvers to quantum transport frameworks and molecular dynamics interfaces is essential for tackling complex scientific problems across different domains. The continued advancement of this integrated paradigm promises to accelerate materials discovery and open new frontiers in the predictive simulation of complex quantum phenomena.

关键词: machine learning, tight-binding model, electronic simulations

Abstract: The rapid advancement of machine learning based tight-binding Hamiltonian (MLTB) methods has opened new avenues for efficient and accurate electronic structure simulations, particularly in large-scale systems and long-time scenarios. This review begins with a concise overview of traditional tight-binding (TB) models, including both (semi-)empirical and first-principles approaches, establishing the foundation for understanding MLTB developments. We then present a systematic classification of existing MLTB methodologies, grouped into two major categories: direct prediction of TB Hamiltonian elements and inference of empirical parameters. A comparative analysis with other ML-based electronic structure models is also provided, highlighting the advancement of MLTB approaches. Finally, we explore the emerging MLTB application ecosystem, highlighting how the integration of MLTB models with a diverse suite of post-processing tools from linear-scaling solvers to quantum transport frameworks and molecular dynamics interfaces is essential for tackling complex scientific problems across different domains. The continued advancement of this integrated paradigm promises to accelerate materials discovery and open new frontiers in the predictive simulation of complex quantum phenomena.

Key words: machine learning, tight-binding model, electronic simulations

中图分类号:  (Methods of electronic structure calculations)

  • 71.15.-m
31.15.A- (Ab initio calculations) 31.15.E (Density-functional theory) 31.15.es (Applications of density-functional theory (e.g., to electronic structure and stability; defect formation; dielectric properties, susceptibilities; viscoelastic coefficients; Rydberg transition frequencies))