arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.21703physics.chem-ph
收藏

最少切换面跳跃结合深度学习势与长短期记忆网络传播子模拟真实光化学过程

Fewest-Switches Surface Hopping with Combined Deep Learning Potential and Long Short-Term Memory Network Propagator for Simulating Realistic Photochemical Processes

Key Laboratory of Theoretical and Computational Photochemistry of Ministry of Education, College of Chemistry, Beijing Normal University(教育部理论计算光化学重点实验室,北京师范大学化学学院);Department of Chemistry, University of Washington(华盛顿大学化学系)

Zhenxing Zhu, Diandong Tang, Lin Shen, Wei-Hai Fang

AI总结:

本文提出扩展的LSTM-FSSH框架,通过重新设计LSTM输入特征和训练过程,结合等变神经网络构建势能面,高效模拟真实光化学反应,准确再现激发态寿命和产物产率。

摘要:

最少切换面跳跃(FSSH)是模拟分子系统光化学过程最流行的方法。最近,我们构建了长短期记忆(LSTM)网络作为FSSH动力学模拟中电子子系统的传播子。Tully三个模型的集体结果已得到满意复现。在本工作中,我们开发了一个扩展的LSTM-FSSH框架来模拟真实光化学反应。重新设计了LSTM的输入特征以及训练过程,以有效表示高维核自由度。等变神经网络与LSTM集成,用于构建基态和激发态的绝热势能面。模拟了$\mathrm{CH_2NH}$和偶氮苯的光异构化,结果表明,与传统FSSH模拟作为参考相比,我们新提出的LSTM-FSSH方法能够准确产生激发态寿命和产物产率。训练LSTM网络仅需10条参考轨迹,然后可以通过非常高效的LSTM-FSSH动力学模拟生成轨迹系综,以获得集体结果。

英文摘要:

Fewest-switches surface hopping (FSSH) is the most popular method for simulating photochemical processes of molecular systems. Recently, we have constructed long short-term memory (LSTM) networks as a propagator for electronic subsystems in FSSH dynamics simulations. The collective results on Tully's three models have been reproduced satisfactorily. In the present work, we develop an extended LSTM-FSSH framework to simulate realistic photochemical reactions. The input features of LSTM as well as the training procedure are redesigned to represent high-dimensional nuclear degrees of freedom in an effective way. Equivariant neural networks are integrated with LSTM to build adiabatic potential energy surfaces in ground and excited states. Photoisomerizations of $\mathrm{CH_2NH}$ and azobenzene are simulated, showing that our new proposed LSTM-FSSH method can produce excited-state lifetimes and product yields accurately in comparison with conventional FSSH simulations as reference. Only 10 reference trajectories are required for training LSTM networks, and then a trajectory ensemble can be generated with very efficient LSTM-FSSH dynamics simulations to obtain collective results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑