哈密顿量(控制论)
从头算
量子
计算机科学
统计物理学
物理
人工神经网络
量子动力学
放松(心理学)
图形
QM/毫米
分子动力学
皮秒
积分器
势能面
从头算量子化学方法
量子力学
概括性
算法
势能
哈密顿力学
量子计算机
参数空间
量子退相干
电子
人工智能
作者
Kong Meng,Haoran Lu,Xuhui Xu,Oleg V. Prezhdo,Run Long
标识
DOI:10.1021/acs.jctc.5c02178
摘要
An electron-vibrational Hamiltonian fully encodes corresponding quantum dynamics; however, extracting the dynamics still relies on time and memory-consuming trajectory-based nonadiabatic molecular dynamics (NAMD) simulations, typically stochastic surface hopping. Here, we develop a general graph neural network, artificial intelligence ab initio NAMD (AI 2 NAMD) that establishes an end-to-end mapping from Hamiltonian to hot carrier relaxation dynamics. We validated the generality of AI 2 NAMD across multiple materials, including a zero-dimensional Si quantum dot (QD), a one-dimensional carbon nanotube (CNT), a two-dimensional twisted MoS 2 /WS 2 bilayer, and a three-dimensional soft-lattice MAPbI 3 perovskite. With only 10% training data, AI 2 NAMD can rapidly and accurately generate picosecond energy decay curves for hot electron and hot hole relaxation for the remaining 90% Hamiltonians, while delivering a computational speed-up of more than 6 orders of magnitude compared to standard CPU-based NAMD simulations. Moreover, AI 2 NAMD can also map directly the Hamiltonian to the carrier relaxation time, bypassing generation of the energy decay curves and demonstrating the ability to handle complex NAMD tasks. Further, by projecting high-dimensional Hamiltonian encoding features into a two-dimensional space with unsupervised learning, we demonstrate that AI 2 NAMD can effectively distinguish Hamiltonian types, verifying its ability to identify a particular system (QD, CNT, MoS 2 /WS 2 and MAPbI 3 ) and a charge carrier (electron or hole). Overall, the developed AI 2 NAMD approach provides a novel computational methodology and a conceptual framework for accelerating NAMD simulations with machine learning by many orders of magnitude.
科研通智能强力驱动
Strongly Powered by AbleSci AI