Transformer-Based Neural-Network Quantum State Method for Electronic Band Structures of Real Solids

被引:3
作者
Fu, Lizhong [1 ]
Wu, Yangjun [1 ]
Shang, Honghui [1 ]
Yang, Jinlong [1 ,2 ]
机构
[1] Univ Sci & Technol China, Key Lab Precis & Intelligent Chem, Hefei 230026, Anhui, Peoples R China
[2] Univ Sci & Technol China, Hefei Natl Lab, Hefei 230088, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1021/acs.jctc.4c00567
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Recent advancements in neural networks have led to significant progress in addressing many-body electron correlations in small molecules and various physical models. In this work, we propose QiankunNet-Solid, which incorporates periodic boundary conditions into the neural network quantum state (NNQS) framework based on generative Transformer architecture along with a batched autoregressive sampling (BAS) method, enabling the effective ab initio calculation of real solid materials. The accuracy of this method is demonstrated in one-, two-, and three-dimensional periodic systems, with results comparable to those of full configuration interaction and coupled-cluster method, even in the strongly correlated regime. Furthermore, we compute the band structures and density of states for silicon crystal. The successful incorporation of periodic boundary conditions into the NNQS framework through QiankunNet-Solid opens up new possibilities for the accurate and efficient study of electronic structure properties in solid-state physics.
引用
收藏
页码:6218 / 6226
页数:9
相关论文
共 32 条
  • [1] Autoregressive neural-network wavefunctions for ab initio quantum chemistry
    Barrett, Thomas D.
    Malyshev, Aleksei
    Lvovsky, A., I
    [J]. NATURE MACHINE INTELLIGENCE, 2022, 4 (04) : 351 - 358
  • [2] Beeler C., 2023, ARXIV
  • [3] Solving the quantum many-body problem with artificial neural networks
    Carleo, Giuseppe
    Troyer, Matthias
    [J]. SCIENCE, 2017, 355 (6325) : 602 - 605
  • [4] Discovering Quantum Phase Transitions with Fermionic Neural Networks
    Cassella, Gino
    Sutterud, Halvard
    Azadi, Sam
    Drummond, N. D.
    Pfau, David
    Spencer, James S.
    Foulkes, W. M. C.
    [J]. PHYSICAL REVIEW LETTERS, 2023, 130 (03)
  • [5] Finite-size error in many-body simulations with long-range interactions
    Chiesa, Simone
    Ceperley, David M.
    Martin, Richard M.
    Holzmann, Markus
    [J]. PHYSICAL REVIEW LETTERS, 2006, 97 (07)
  • [6] Fermionic neural-network states for ab-initio electronic structure
    Choo, Kenny
    Mezzacapo, Antonio
    Carleo, Giuseppe
    [J]. NATURE COMMUNICATIONS, 2020, 11 (01)
  • [7] Two-dimensional frustrated J1-J2 model studied with neural network quantum states
    Choo, Kenny
    Neupert, Titus
    Carleo, Giuseppe
    [J]. PHYSICAL REVIEW B, 2019, 100 (12)
  • [8] Das S., 2023, Proceedings of the International Conference for HighPerformance Computing, Networking, Storage and Analysis
  • [9] Quantum Entanglement in Neural Network States
    Deng, Dong-Ling
    Li, Xiaopeng
    Das Sarma, S.
    [J]. PHYSICAL REVIEW X, 2017, 7 (02):
  • [10] Equation-of-Motion Theory to Calculate Accurate Band Structures with a Quantum Computer
    Fan, Yi
    Liu, Jie
    Li, Zhenyu
    Yang, Jinlong
    [J]. JOURNAL OF PHYSICAL CHEMISTRY LETTERS, 2021, 12 (36): : 8833 - 8840