用机器学习势能模型替代量子力学计算，高效模拟溶剂中激发态非绝热过程。
Excited-state nonadiabatic dynamics in explicit solvent using machine learned interatomic potentials
- 用机器学习势能替代传统量子力学嵌入，降低计算成本。
- 在水中呋喃五重激发态体系中，结果与量子力学方法高度一致。
- 提供可解释的性能指标，验证模型准确性，适合化学动力学研究者。
基于量子力学/分子力学（QM/MM）的激发态非绝热模拟对理解明光诱导过程至关重要，但其高昂的量子化学计算成本限制了与轨迹表面跳跃方法的结合。本文采用FieldSchNet——一种能将电场效应纳入电子态的机器学习原子间势能模型，取代传统QM/MM中的静电嵌入，构建了机器学习/MM（ML/MM）方法用于激发态非绝热轨迹模拟。该方法应用于水相中的呋喃体系，包含五个耦合单重态。结果表明，在训练数据充分且精心筛选的前提下，ML/MM模型能够准确再现QM/MM表面跳跃参考模拟的电子动力学和结构重构。此外，我们提出了可量化且可解释的性能评估指标，以验证模型精度。
原文摘要 · Abstract (English)
Excited-state nonadiabatic simulations with quantum mechanics/molecular mechanics (QM/MM) are essential to understand photoinduced processes in explicit environments. However, the high computational cost of the underlying quantum chemical calculations limits its application in combination with trajectory surface hopping methods. Here, we use FieldSchNet, a machine-learned interatomic potential capable of incorporating electric field effects into the electronic states, to replace traditional QM/MM electrostatic embedding with its ML/MM counterpart for nonadiabatic excited state trajectories. The developed method is applied to furan in water, including five coupled singlet states. Our results demonstrate that with sufficiently curated training data, the ML/MM model reproduces the electronic kinetics and structural rearrangements of QM/MM surface hopping reference simulations. Furthermore, we identify performance metrics that provide robust and interpretable validation of model accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。