Wang Bipeng, Winkler Ludwig, Wu Yifan, Müller Klaus-Robert, Sauceda Huziel E, Prezhdo Oleg V
Department of Chemical Engineering, University of Southern California, Los Angeles, California 90089, United States.
Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany.
J Phys Chem Lett. 2023 Aug 10;14(31):7092-7099. doi: 10.1021/acs.jpclett.3c01723. Epub 2023 Aug 2.
Essential for understanding far-from-equilibrium processes, nonadiabatic (NA) molecular dynamics (MD) requires expensive calculations of the excitation energies and NA couplings. Machine learning (ML) can simplify computation; however, the NA Hamiltonian requires complex ML models due to its intricate relationship to atomic geometry. Working directly in the time domain, we employ bidirectional long short-term memory networks (Bi-LSTM) to interpolate the Hamiltonian. Applying this multiscale approach to three metal-halide perovskite systems, we achieve two orders of magnitude computational savings compared to direct ab initio calculation. Reasonable charge trapping and recombination times are obtained with NA Hamiltonian sampling every half a picosecond. The Bi-LSTM-NAMD method outperforms earlier models and captures both slow and fast time scales. In combination with ML force fields, the methodology extends NAMD simulation times from picoseconds to nanoseconds, comparable to charge carrier lifetimes in many materials. Nanosecond sampling is particularly important in systems containing defects, boundaries, interfaces, etc. that can undergo slow rearrangements.
非绝热（NA）分子动力学（MD）对于理解远离平衡的过程至关重要，但需要对激发能和NA耦合进行昂贵的计算。机器学习（ML）可以简化计算；然而，由于NA哈密顿量与原子几何结构的复杂关系，它需要复杂的ML模型。我们直接在时域中工作，采用双向长短期记忆网络（Bi-LSTM）对哈密顿量进行插值。将这种多尺度方法应用于三种金属卤化物钙钛矿体系，与直接从头计算相比，我们实现了两个数量级的计算量节省。通过每皮秒对NA哈密顿量进行采样，获得了合理的电荷俘获和复合时间。Bi-LSTM-NAMD方法优于早期模型，能够捕捉慢速和快速时间尺度。与ML力场相结合，该方法将NAMD模拟时间从皮秒扩展到纳秒，与许多材料中的电荷载流子寿命相当。纳秒采样在包含可能经历缓慢重排的缺陷、边界、界面等的系统中尤为重要。
