| CONDENSED MATTER: ELECTRONIC STRUCTURE, ELECTRICAL, MAGNETIC, AND OPTICAL PROPERTIES |
|
|
|
|
Universal Machine Learning Kohn–Sham Hamiltonian for Materials |
| Yang Zhong1,2, Hongyu Yu1,2, Jihui Yang1,2, Xingyu Guo1,2, Hongjun Xiang1,2*, and Xingao Gong1,2 |
1Key Laboratory of Computational Physical Sciences (Ministry of Education), Institute of Computational Physical Sciences, State Key Laboratory of Surface Physics, and Department of Physics, Fudan University, Shanghai 200433, China
2Shanghai Qi Zhi Institute, Shanghai 200030, China
|
|
| Cite this article: |
|
Yang Zhong, Hongyu Yu, Jihui Yang et al 2024 Chin. Phys. Lett. 41 077103 |
|
|
|
|
Abstract While density functional theory (DFT) serves as a prevalent computational approach in electronic structure calculations, its computational demands and scalability limitations persist. Recently, leveraging neural networks to parameterize the Kohn–Sham DFT Hamiltonian has emerged as a promising avenue for accelerating electronic structure computations. Despite advancements, challenges such as the necessity for computing extensive DFT training data to explore each new system and the complexity of establishing accurate machine learning models for multi-elemental materials still exist. Addressing these hurdles, this study introduces a universal electronic Hamiltonian model trained on Hamiltonian matrices obtained from first-principles DFT calculations of nearly all crystal structures on the Materials Project. We demonstrate its generality in predicting electronic structures across the whole periodic table, including complex multi-elemental systems, solid-state electrolytes, Moiré twisted bilayer heterostructure, and metal-organic frameworks. Moreover, we utilize the universal model to conduct high-throughput calculations of electronic structures for crystals in GNoME datasets, identifying 3940 crystals with direct band gaps and 5109 crystals with flat bands. By offering a reliable efficient framework for computing electronic properties, this universal Hamiltonian model lays the groundwork for advancements in diverse fields, such as easily providing a huge data set of electronic structures and also making the materials design across the whole periodic table possible.
|
|
Received: 04 June 2024
Express Letter
Published: 15 June 2024
|
|
| PACS: |
71.15.-m
|
(Methods of electronic structure calculations)
|
|
|
|
|
|
| [1] | Marzari N, Ferretti A, and Wolverton C 2021 Nat. Mater. 20 736 |
| [2] | McCardle K 2023 Nat. Comput. Sci. 3 915 |
| [3] | Chen Z X, Li W Q, Sabuj M A et al. 2021 Nat. Commun. 12 5889 |
| [4] | Dzade N Y 2021 Sci. Rep. 11 4755 |
| [5] | Reidy K, Varnavides G, Thomsen J D et al. 2021 Nat. Commun. 12 1290 |
| [6] | Pederson R, Kalita B, and Burke K 2022 Nat. Rev. Phys. 4 357 |
| [7] | Schleder G R, Padilha A C M, Acosta C M, Costa M, and Fazzio A 2019 J. Phys.: Mater. 2 032001 |
| [8] | Makkar P and Ghosh N N 2021 RSC Adv. 11 27897 |
| [9] | Jones R O 2015 Rev. Mod. Phys. 87 897 |
| [10] | Hegde G and Bowen R C 2017 Sci. Rep. 7 42669 |
| [11] | Li H C, Collins C, Tanha M, Gordon G J, and Yaron D J 2018 J. Chem. Theory Comput. 14 5764 |
| [12] | Schütt K T, Gastegger M, Tkatchenko A, Müller K R, and Maurer R J 2019 Nat. Commun. 10 5024 |
| [13] | Gastegger M, McSloy A, Luya M, Schütt K T, and Maurer R J 2020 J. Chem. Phys. 153 044123 |
| [14] | Unke O T, Bogojeski M, Gastegger M et al. 2021 arXiv:2106.02347 [physics.chem-ph] |
| [15] | Wang Z F, Ye S Z, Wang H et al. 2021 npj Comput. Mater. 7 11 |
| [16] | Westermayr J and Maurer R J 2021 Chem. Sci. 12 10755 |
| [17] | Li H, Wang Z, Zou N L et al. 2022 Nat. Comput. Sci. 2 367 |
| [18] | Nigam J, Willatt M J, and Ceriotti M 2022 J. Chem. Phys. 156 014115 |
| [19] | Schattauer C, Todorović M, Ghosh K, Rinke P, and Libisch F 2022 npj Comput. Mater. 8 116 |
| [20] | Zhang L W, Onat B, Dusson G et al. 2022 npj Comput. Mater. 8 158 |
| [21] | Gong X X, Li H, Zou N L et al. 2023 Nat. Commun. 14 2848 |
| [22] | Zhong Y, Yu H, Su M, Gong X, and Xiang H 2023 npj Comput. Mater. 9 182 |
| [23] | Ye Y F, Wang Q, Lu J, Liu C T, and Yang Y 2016 Mater. Today 19 349 |
| [24] | Feng R, Zhang C, Gao M C et al. 2021 Nat. Commun. 12 4329 |
| [25] | George E P, Raabe D, and Ritchie R O 2019 Nat. Rev. Mater. 4 515 |
| [26] | Zhang R Z and Reece M J 2019 J. Mater. Chem. A 7 22148 |
| [27] | Oses C, Toher C, and Curtarolo S 2020 Nat. Rev. Mater. 5 295 |
| [28] | Zhao P, Xiao C, and Yao W 2021 npj 2D Mater. Appl. 5 38 |
| [29] | Chen C 2022 Nat. Comput. Sci. 2 703 |
| [30] | Chen C and Ong S P 2022 Nat. Comput. Sci. 2 718 |
| [31] | Takamoto S, Shinagawa C, Motoki D et al. 2022 Nat. Commun. 13 2991 |
| [32] | Deng B W, Zhong P C, Jun K et al. 2023 Nat. Mach. Intell. 5 1031 |
| [33] | Batatia I, Benner P, Chiang Y et al. 2023 arXiv:2401.00096 [physics.chem-ph] |
| [34] | Jain A, Ong S P, Hautier G et al. 2013 APL Mater. 1 011002 |
| [35] | Jain A, Montoya J, Dwaraknath S et al. 2018 Handbook of Materials Modeling (Berlin: Springer) p 1 |
| [36] | Wang H, Zhang L F, Han J Q, and E W N 2018 Comput. Phys. Commun. 228 178 |
| [37] | Behler J 2011 J. Chem. Phys. 134 074106 |
| [38] | Pinheiro M, Ge F C, Ferré N, Dral P O, and Barbatti M 2021 Chem. Sci. 12 14396 |
| [39] | Xie T and Grossman J C 2018 Phys. Rev. Lett. 120 145301 |
| [40] | Chmiela S, Tkatchenko A, Sauceda H E et al. 2017 Sci. Adv. 3 e1603015 |
| [41] | Glielmo A, Sollich P, and De Vita A 2017 Phys. Rev. B 95 214302 |
| [42] | Ozaki T and Kino H 2004 Phys. Rev. B 69 195113 |
| [43] | Ozaki T 2003 Phys. Rev. B 67 155108 |
| [44] | Weinert U 1980 Arch. Ration. Mech. Anal. 74 165 |
| [45] | Morrison M A and Parker G A 1987 Aust. J. Phys. 40 465 |
| [46] | Grisafi A, Wilkins D M, Csányi G, and Ceriotti M 2018 Phys. Rev. Lett. 120 036002 |
| [47] | Thomas N, Smidt T, Kearnes S et al. 2018 arXiv:1802.08219 [cs.LG] |
| [48] | Naveed H, Khan A U, Qiu S et al. 2023 arXiv:2307.06435 [cs.CL] |
| [49] | Zhao W X, Zhou K, Li J Y et al. 2023 arXiv:2303.18223 [cs.CL] |
| [50] | Zeng L Y, Hu X W, Zhou Y Z et al. 2023 Innovat. Mater. 1 100042 |
| [51] | Zeng L Y, Hu X W, Zhou Y Z et al. 2024 Adv. Sci. 11 2305054 |
| [52] | Zeng L Y, Wang Z Q, Song J et al. 2023 Adv. Funct. Mater. 33 2301929 |
| [53] | Zhao S G, Kang L, Shen Y G et al. 2016 J. Am. Chem. Soc. 138 2961 |
| [54] | Zhang J W, Wang W H, Xie M X et al. 2023 Electrochim. Acta 461 142691 |
| [55] | Baumann A E, Burns D A, Liu B, and Thoi V S 2019 Commun. Chem. 2 86 |
| [56] | Felix Sahayaraj A, Joy Prabu H, Maniraj J et al. 2023 J. Inorg. Organomet. Polym. Mater. 33 1757 |
| [57] | Mancuso J L, Mroz A M, Le K N, and Hendon C H 2020 Chem. Rev. 120 8641 |
| [58] | Rosen A S, Fung V, Huck P et al. 2022 npj Comput. Mater. 8 112 |
| [59] | Rosen A S, Iyer S M, Ray D et al. 2021 Matter 4 1578 |
| [60] | Stassen I, Burtch N, Talin A et al. 2017 Chem. Soc. Rev. 46 3185 |
| [61] | Chung Y G, Camp J, Haranczyk M et al. 2014 Chem. Mater. 26 6185 |
| [62] | Chung Y G, Haldoupis E, Bucior B J et al. 2019 J. Chem. Eng. Data 64 5985 |
| [63] | Merchant A, Batzner S, Schoenholz S S et al. 2023 Nature 624 80 |
| [64] | He C Y, Liao Y J, Ouyang T et al. 2023 Fundam. Res. |
| [65] | Bhattacharya A, Timokhin I, Chatterjee R, Yang Q, and Mishchenko A 2023 npj Comput. Mater. 9 101 |
| [66] | Huber S D and Altman E 2010 Phys. Rev. B 82 184502 |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
