arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.06189physics.chem-ph
收藏

基于量子力学与机器学习方法的Python面跳跃动力学MLatom软件生态系统

MLatom software ecosystem for surface hopping dynamics in Python with quantum mechanical and machine learning methods

Lina Zhang, Sebastian V. Pios, Mikołaj Martyka, Fuchun Ge, Yi-Fan Hou, Yuxinxin Chen, Lipeng Chen, Joanna Jankowska, Mario Barbatti, Pavlo O. Dral

AI总结:

本文提出开源MLatom@XACS软件生态系统,通过Python API结合量子力学与机器学习方法实现基于LZBL算法的实时面跳跃非绝热动力学,并提供AIQM1模型和自动化脚本,以低成本高效模拟光化学过程。

摘要:

我们提出了一个开源的MLatom@XACS软件生态系统,用于基于Landau-Zener-Belyaev-Lebedev(LZBL)算法的实时面跳跃非绝热动力学。该动力学可通过Python API执行,支持广泛的量子力学(QM)和机器学习(ML)方法,包括从头算QM(CASSCF和ADC(2))、半经验QM方法(如AM1、PM3、OMx和ODMx)以及多种类型的机器学习势(如KREG、ANI和MACE)。QM和ML方法的组合也可以使用。虽然用户可以构建自己的组合,但我们提供了基于Δ-learning的AIQM1,可开箱即用。我们展示了AIQM1如何以低成本重现反式偶氮苯的异构化量子产率。我们提供了示例脚本,仅需十几行代码,用户只需提供分子的初始几何结构即可获得最终的布居数图。因此,这些脚本执行几何优化、简正模式计算、初始条件采样、并行轨迹传播、布居数分析和最终结果绘图。鉴于MLatom可用于训练不同ML模型的能力,该生态系统可以无缝集成到为非绝热动力学构建ML模型的流程中。未来,MLatom与Newton-X的更深入、更高效的集成将为面跳跃动力学提供广泛的功能,例如最少切换面跳跃,从而通过Python API促进类似的工作流程。

英文摘要:

We present an open-source MLatom@XACS software ecosystem for on-the-fly surface hopping nonadiabatic dynamics based on the Landau-Zener-Belyaev-Lebedev (LZBL) algorithm. The dynamics can be performed via Python API with a wide range of quantum mechanical (QM) and machine learning (ML) methods, including ab initio QM (CASSCF and ADC(2)), semi-empirical QM methods (e.g., AM1, PM3, OMx, and ODMx), and many types of machine learning potentials (e.g., KREG, ANI, and MACE). Combinations of QM and ML methods can also be used. While the user can build their own combinations, we provide AIQM1, which is based on Δ-learning and can be used out of the box. We showcase how AIQM1 reproduces the isomerization quantum yield of trans-azobenzene at a low cost. We provide example scripts that, in a dozen lines, enable the user to obtain the final population plots by simply providing the initial geometry of a molecule. Thus, those scripts perform geometry optimization, normal mode calculations, initial condition sampling, parallel trajectories propagation, population analysis, and final result plotting. Given the capabilities of MLatom to be used for training different ML models, this ecosystem can be seamlessly integrated into the protocols building ML models for nonadiabatic dynamics. In the future, a deeper and more efficient integration of MLatom with Newton-X will enable vast range of functionalities for surface hopping dynamics, such as fewest-switches surface hopping, to facilitate similar workflows via the Python API.

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。

↑