| TOPICAL REVIEW — AI + Physical Science |
Prev
|
|
|
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 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 |
|
|
|
|
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.
|
Received: 30 July 2025
Revised: 10 October 2025
Accepted manuscript online: 22 October 2025
|
|
PACS:
|
71.15.-m
|
(Methods of electronic structure calculations)
|
| |
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))
|
|
| Fund: 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). |
Corresponding Authors:
Qiangqiang Gu
E-mail: guqq@ustc.edu.cn
|
Cite this article:
Jijie Zou(邹暨捷), Zhanghao Zhouyin(周寅张皓), Shishir Kumar Pandey, and Qiangqiang Gu(顾强强) Review of machine learning tight-binding models: Route to accurate and scalable electronic simulations 2026 Chin. Phys. B 35 017101
|
[1] Hohenberg P and Kohn W 1964 Phys. Rev. 136 B864
[2] Kohn W and Sham L J 1965 Phys. Rev. 140 A1133
[3] Harrison W 2012 Electronic Structure and the Properties of Solids: The Physics of the Chemical Bond Dover Books on Physics (Dover Publications)
[4] Slater J C and Koster G F 1954 Phys. Rev. 94 1498
[5] Li H, Collins C, Tanha M, Gordon G J and Yaron D J 2018 Journal of Chemical Theory and Computation 14 5764
[6] Nakhaee M, Ketabi S A and Peeters F M 2020 J. Appl. Phys. 128 215107
[7] Wang Z, Ye S, Wang H, He J, Huang Q and Chang S 2021 npj Computational Materials 7 11
[8] Schattauer C, Todorovic M, Ghosh K, Rinke P and Libisch F 2022 npj Computational Materials 8 116
[9] Gu Q, Zhang L and Feng J 2022 Science Bulletin 67 29
[10] Fan G, McSloy A, Aradi B, Yam C Y and Frauenheim T 2022 The Journal of Physical Chemistry Letters 13 10132
[11] Wang Z, Dong J, Qiu J and Wang L 2022 ACS Applied Materials & Interfaces 14 22929
[12] Sun W, Fan G, van der Heide T, McSloy A, Frauenheim T and Aradi B 2023 Journal of Chemical Theory and Computation 19 3877
[13] Gu Q, Zhouyin Z, Pandey S K, Zhang P, Zhang L and E W 2024 Nat. Commun. 15 6772
[14] Qi Y, Gong W and Yan Q 2025 npj Computational Materials 11 177
[15] Fried H P, Barragan-Yani D, Libisch F and Wirtz L 2025 npj Computational Materials 11 176
[16] Cao B, Dong J, Wang Z and Wang L 2025 The Journal of Physical Chemistry Letters 16 4907
[17] Zou J, Zhouyin Z, Lin D, Huang Y, Zhang L, Hou S and Gu Q 2025 npj Comput. Mater. 11 375
[18] Gu Q, Pandey S K and Zhouyin Z 2025 Preprint 2502.00798
[19] Seifert G, Porezag D and Frauenheim T 1996 International Journal of Quantum Chemistry 58 185
[20] Porezag D, Frauenheim T, Kohler T, Seifert G and Kaschner R 1995 Phys. Rev. B 51 12947
[21] Elstner M, Porezag D, Jungnickel G, Elsner J, Haugk M, Frauenheim T, Suhai S and Seifert G 1998 Phys. Rev. B 58 7260
[22] Grimme S, Bannwarth C and Shushkov P 2017 Journal of Chemical Theory and Computation 13 1989
[23] Yang Y, Yu H, York D, Cui Q and Elstner M 2007 The Journal of Physical Chemistry A 111 10861
[24] Gaus M, Cui Q and Elstner M 2011 Journal of Chemical Theory and Computation 7 931
[25] Gaus M, Goez A and Elstner M 2013 Journal of Chemical Theory and Computation 9 338
[26] Bannwarth C, Ehlert S and Grimme S 2019 Journal of Chemical Theory and Computation 15 1652
[27] Marzari N, Mostofi A A, Yates J R, Souza I and Vanderbilt D 2012 Rev. Mod. Phys. 84 1419
[28] Papaconstantopoulos D and Mehl M 2003 J. Phys.: Condens. Matter 15 R413
[29] Cohen R E, Mehl M J and Papaconstantopoulos D A 1994 Phys. Rev. B 50 14694
[30] Mehl M J and Papaconstantopoulos D A 1996 Phys. Rev. B 54 4519
[31] Hourahine B, Aradi B, Blum V, Bonafe F, Buccheri A, Camacho C, Cevallos C, Deshaye M, Dumitrica T, Dominguez A et al. 2020 J. Chem. Phys. 152 124101
[32] Bannwarth C, Caldeweyher E, Ehlert S, Hansen A, Pracht P, Seibert J, Spicher S and Grimme S 2021 Wiley Interdisciplinary Reviews: Computational Molecular Science 11 e1493
[33] Wahiduzzaman M, Oliveira A F, Philipsen P, Zhechkov L, van Lenthe E, Witek H A and Heine T 2013 Journal of Chemical Theory and Computation 9 4006
[34] Cui M, Reuter K and Margraf J T 2024 Journal of Chemical Theory and Computation 20 5276
[35] Lu W C, Wang C Z, Chan T L, Ruedenberg K and Ho K M 2004 Phys. Rev. B 70 041101
[36] Qian X, Li J, Qi L, Wang C Z, Chan T L, Yao Y X, Ho K M and Yip S 2008 Phys. Rev. B 78 245112
[37] Marrazzo A, Beck S, Margine E R, Marzari N, Mostofi A A, Qiao J, Souza I, Tsirkin S S, Yates J R and Pizzi G 2024 Rev. Mod. Phys. 96 045008
[38] Andersen O and Saha-Dasgupta T 2000 Phys. Rev. B 62 R16219
[39] Agapito L A, Ferretti A, Calzolari A, Curtarolo S and Buongiorno Nardelli M 2013 Phys. Rev. B 88 165127
[40] Zhang L, Han J, Wang H, Car R and E W 2018 Phys. Rev. Lett. 120 143001
[41] Hegde G and Bowen R C 2017 Scientific Reports 7 42669
[42] Schutt K T, Gastegger M, Tkatchenko A, M uller K R and Maurer R J 2019 Nat. Commun. 10 5024
[43] Schutt K T, Arbabzadah F, Chmiela S, M uller K R and Tkatchenko A 2017 Nat. Commun. 8 13890
[44] Li H, Wang Z, Zou N, Ye M, Xu R, Gong X, Duan W and Xu Y 2022 Nature Computational Science 2 367
[45] Yu H, Xu Z, Qian X, Qian X and Ji S 2023 Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research vol. 202) ed Krause A, Brunskill E, Cho K, Engelhardt B, Sabato S and Scarlett J (PMLR) pp. 40412–40424
[46] Gong X, Li H, Zou N, Xu R, Duan W and Xu Y 2023 Nat. Commun. 14 2848
[47] Zhong Y, Yu H, Su M, Gong X and Xiang H 2023 npj Computational Materials 9 1
[48] Zhouyin Z H, Gan Z X, Pandey S K, Zhang L F and Gu Q Q 2025 Learning local equivariant representations for quantum operators in The Thirteenth International Conference on Learning Representations
[49] Yin S, Pan X Y, Wang F Y and He L X 2025 Tracegrad: a framework learning expressive SO(3)-equivariant non-linear representations for electronic-structure hamiltonian prediction in Proceedings of the 42nd International Conference on Machine Learning (ICML)
[50] McSloy A, Fan G, Sun W, Holzer C, Friede M, Ehlert S, Sch utte N E, Grimme S, Frauenheim T and Aradi B 2023 The Journal of Chemical Physics 158 034801
[51] Fung V, Ganesh P and Sumpter B G 2022 Chemistry of Materials 34 4848
[52] Kong S, Ricci F, Guevarra D, Neaton J B, Gomes C P and Gregoire J M 2022 Nat. Commun. 13 949
[53] Zhuo Y, Mansouri Tehrani A and Brgoch J 2018 The Journal of Physical Chemistry Letters 9 1668
[54] Burkle M, Perera U, Gimbert F, Nakamura H, Kawata M and Asai Y 2021 Phys. Rev. Lett. 126 177701
[55] Lin D, Zou J, Dong Y, Wang Y, Wang Y, Sanvito S and Hou S 2025 Phys. Chem. Chem. Phys. 27 7728
[56] Zhou G, Gao Z, Ding Q, Zheng H, Xu H, Wei Z, Zhang L and Ke G 2023 Uni-mol: A universal 3d molecular representation learning framework in The Eleventh International Conference on Learning Representations
[57] Unke O, Bogojeski M, Gastegger M, Geiger M, Smidt T and Muller K R 2021 Advances in Neural Information Processing Systems Vol. 34 ed. Ranzato M, Beygelzimer A, Dauphin Y, Liang P and Vaughan J W (Curran Associates, Inc.) pp. 14434–14447
[58] Lv T, Zhong Z, Liang Y, Li F, Huang J and Zheng R 2023 Phys. Rev. B 108 235159
[59] Song F and Feng J 2024 Preprint 2406.15873
[60] Dong X, Gull E and Wang L 2024 Phys. Rev. B 109 075112
[61] Venturella C, Li J, Hillenbrand C, Leyva Peralta X, Liu J and Zhu T 2025 Nature Computational Science 5 502
[62] Gu Q, Pandey S K and Tiwari R 2023 Computational Materials Science 221 112090
[63] Vonsovsky S V and Katsnelson M I 1989 Quantum solid-state physics (Berlin: Springer-Verlag)
[64] Hubbard J and Flowers B H 1963 Proc. Roy. Soc. Lond. Ser. A Math. Phys. Sci. 276 238
[65] Qin M, Schofer T, Andergassen S, Corboz P and Gull E 2022 Annual Review of Condensed Matter Physics 13 275
[66] Li Y, Zhan Z, Kuang X, Li Y and Yuan S 2023 Computer Physics Communications 285 108632
[67] Francis J G 1961 The Computer Journal 4 265
[68] Francis J G F 1962 The Computer Journal 4 332
[69] Kublanovskaya V 1962 USSR Computational Mathematics and Mathematical Physics 1 637
[70] Rutishauser H 1966 Numerische Mathematik 9 1
[71] Cuppen J J M 1980 Numerische Mathematik 36 177
[72] Demmel J W 1997 Applied numerical linear algebra (SIAM)
[73] Lanczos C 1950 Journal of Research of the National Bureau of Standards 45 255
[74] Cullum J K and Willoughby R A 2002 Lanczos algorithms for large symmetric eigenvalue computations: Vol. I: Theory (SIAM)
[75] Roder H and Silver R N 1995 Densities of States and Thermodynamics of Mega-Dimensional Sparse Matrices (Boston: Springer) pp. 301–308
[76] Wang L W 1994 Phys. Rev. B 49 10154
[77] Wang L W and Zunger A 1994 Phys. Rev. Lett. 73 1039
[78] Silver R, Roeder H, Voter A and Kress J 1996 Journal of Computational Physics 124 115
[79] Weiße A, Wellein G, Alvermann A and Fehske H 2006 Rev. Mod. Phys. 78 275
[80] Yuan S, De Raedt H and Katsnelson M I 2010 Phys. Rev. B 82 115448
[81] Hams A and De Raedt H 2000 Phys. Rev. E 62 4365
[82] Yuan S, Roldan R and Katsnelson M I 2011 Phys. Rev. B 84 035439
[83] Fiori G, Iannaccone G and Klimeck G 2006 IEEE Transactions on Electron Devices 53 1782
[84] Marian D, Marin E G, Perucchini M, Iannaccone G and Fiori G 2023 Journal of Computational Electronics 22 1327
[85] Luisier M and Klimeck G 2008 2008 8th IEEE Conference on Nanotechnology pp. 354–357
[86] Pecchia A, Penazzi G, Salvucci L and Carlo A D 2008 New J. Phys. 10 065022
[87] Steiger S, Povolotskyi M, Park H H, Kubis T and Klimeck G 2011 IEEE Transactions on Nanotechnology 10 1464
[88] Fan Z, Uppstu A, Siro T and Harju A 2014 Computer Physics Communications 185 28
[89] Groth C W, Wimmer M, Akhmerov A R and Waintal X 2014 New J. Phys. 16 063065
[90] Joao S M, And-elkovic M, Covaci L, Rappoport T G, Lopes J M V P and Ferreira A 2020 Royal Society Open Science 7 191809
[91] Kubo R 1957 J. Phys. Soc. Jpn. 12 570
[92] Keldysh L V et al. 1965 Sov. Phys. JETP 20 1018
[93] Datta S 1997 Electronic Transport in Mesoscopic Systems (Cambridge University Press)
[94] Yang N and Guo J 2024 Solid-State Electronics 213 108859
[95] Spinazze M and Yoon Y 2025 IEEE Transactions on Electron Devices 72 3287
[96] Franklin A D and Chen Z 2010 Nat. Nanotechnol. 5 858
[97] Franklin A D, Luisier M, Han S J, Tulevski G, Breslin C M, Gignac L, Lundstrom M S and Haensch W 2012 Nano Lett. 12 758
[98] Dong J, Qiu J, Bai X, Wang Z, Xiao B and Wang L 2025 Journal of Chemical Theory and Computation 21 3300 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
