Interpolating Nonadiabatic Molecular Dynamics Hamiltonian with Artificial Neural Networks

被引:33
|
作者
Wang, Bipeng [1 ]
Chu, Weibin [2 ]
Tkatchenko, Alexandre [3 ]
Prezhdo, Oleg, V [1 ,2 ]
机构
[1] Univ Southern Calif, Dept Chem Engn, Los Angeles, CA 90089 USA
[2] Univ Southern Calif, Dept Chem, Los Angeles, CA 90089 USA
[3] Univ Luxembourg, Dept Phys & Mat Sci, L-1511 Luxembourg, Luxembourg
来源
JOURNAL OF PHYSICAL CHEMISTRY LETTERS | 2021年 / 12卷 / 26期
基金
美国国家科学基金会;
关键词
AB-INITIO; CHARGE SEPARATION; SOLAR-CELLS; FORCE-FIELD; RECOMBINATION; LOCALIZATION; TRANSITION;
D O I
10.1021/acs.jpclett.1c01645
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
Nonadiabatic (NA) molecular dynamics (MD) allows one to study far-from-equilibrium processes involving excited electronic states coupled to atomic motions. While NAMD involves expensive calculations of excitation energies and NA couplings (NACs), ground-state properties require much less effort and can be obtained with machine learning (ML) at a fraction of the ab initio cost. Application of ML to excited states and NACs is more challenging, due to costly reference methods, many states, and complex geometry dependence. We developed a NAMD methodology that avoids time extrapolation of excitation energies and NACs. Instead, under the classical path approximation that employs a precomputed ground-state trajectory, we use a small fraction (2%) of the geometries to train neural networks and obtain excited-state energies and NACs for the remaining 98% of the geometries by interpolation. Demonstrated with metal halide perovskites that exhibit complex MD, the method provides nearly two orders of computational savings while generating accurate NAMD results.
引用
收藏
页码:6070 / 6077
页数:8
相关论文
共 50 条
  • [1] Interpolating Nonadiabatic Molecular Dynamics Hamiltonian with Bidirectional Long Short-Term Memory Networks
    Wang, Bipeng
    Winkler, Ludwig
    Wu, Yifan
    Muller, Klaus-Robert
    Sauceda, Huziel E.
    Prezhdo, Oleg V.
    JOURNAL OF PHYSICAL CHEMISTRY LETTERS, 2023, 14 (31): : 7092 - 7099
  • [2] Interpolating Nonadiabatic Molecular Dynamics Hamiltonian with Inverse Fast Fourier Transform
    Wang, Bipeng
    Chu, Weibin
    Prezhdo, Oleg, V
    JOURNAL OF PHYSICAL CHEMISTRY LETTERS, 2022, 13 (01): : 331 - 338
  • [3] BAYESIAN OPTIMIZATION USING HAMILTONIAN DYNAMICS FOR SPARSE ARTIFICIAL NEURAL NETWORKS
    Fakhfakh, Mohamed
    Bouaziz, Bassem
    Gargouri, Faiez
    Chaari, Lotfi
    2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022), 2022,
  • [4] HAMILTONIAN-DYNAMICS OF NEURAL NETWORKS
    RAMACHER, U
    NEURAL NETWORKS, 1993, 6 (04) : 547 - 557
  • [5] Increasing Efficiency of Nonadiabatic Molecular Dynamics by Hamiltonian Interpolation with Kernel Ridge Regression
    Wu, Yifan
    Prezhdo, Natalie
    Chu, Weibin
    JOURNAL OF PHYSICAL CHEMISTRY A, 2021, 125 (41): : 9191 - 9200
  • [6] Benchmarking Quasiclassical Mapping Hamiltonian Methods for Simulating Electronically Nonadiabatic Molecular Dynamics
    Gao, Xing
    Saller, Maximilian A. C.
    Liu, Yudan
    Kelly, Aaron
    Richardson, Jeremy O.
    Geva, Eitan
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2020, 16 (05) : 2883 - 2895
  • [7] Gradient and Hamiltonian dynamics applied to learning in neural networks
    Howse, JW
    Abdallah, CT
    Heileman, GL
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 8: PROCEEDINGS OF THE 1995 CONFERENCE, 1996, 8 : 274 - 280
  • [8] Machine-Learned Kohn-Sham Hamiltonian Mapping for Nonadiabatic Molecular Dynamics
    Shakiba, Mohammad
    Akimov, Alexey V.
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2024, 20 (08) : 2992 - 3007
  • [9] Dynamics of Biomimetic Electronic Artificial Neural Networks
    Hastings, Harold M.
    Hernandez, Oscar I.
    Jiang, Lucy
    Lai, Boqiao
    Tensen, Lindsey
    Yang, June
    PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON APPLICATIONS IN NONLINEAR DYNAMICS (ICAND 2016), 2017, 6 : 195 - 207
  • [10] A dynamics of the Hough transform and artificial neural networks
    Imiya, A
    Kawamoto, K
    MACHINE LEARNING AND DATA MINING IN PATTERN RECOGNITION, 1999, 1715 : 36 - 50