arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16962physics.chem-ph
收藏

利用机器学习代理实现高效瞬子速率计算

A Machine-Learning Framework for Efficient Ring-Polymer Instanton Rate Calculations

Pacific Northwest National Laboratory(太平洋西北国家实验室);University of Washington(华盛顿大学);Princeton University(普林斯顿大学)

Chenghao Zhang, Amke Nimmrich, Axel Gomez, Munira Khalil, Niranjan Govind

AI总结:

提出高斯过程回归增强线积分弦方法,加速分子质子转移反应中隧穿速率的环聚合物瞬子计算,通过代理模型的不确定性估计使力评估次数与离散化珠子数无关,并采用高效训练策略实现数量级加速。

摘要:

我们开发了一种高斯过程回归增强线积分弦方法,用于加速分子质子转移反应中隧穿速率的环聚合物瞬子计算。通过利用代理建模的不确定性估计,我们表明收敛瞬子路径所需的力评估次数实际上与用于离散化路径的珠子数无关。为了减少与训练相关的计算开销,特别是在包含Hessian信息时,我们通过结合物理GPR先验、无Hessian GPR训练和图形处理单元加速的黑盒矩阵乘法,实现了一种高效的训练策略,相对于标准实现获得了数量级的加速。对于速率计算,我们引入了一种选择性Hessian训练策略,将强耦合于转移质子的柔性模式与弱耦合于反应坐标的刚性模式区分开来。这使得能够通过减少Hessian评估来构建准确的代理势能面。我们应用三次样条插值方法和高斯过程回归来近似典型系统(丙二醛、Z-3-氨基丙烯醛和7,9-二硝基-10-羟基苯并[h]喹啉)的瞬子速率。在我们的数值测试中,样条插值成为瞬子速率计算的一种简单且计算高效的方法。

英文摘要:

We develop an efficient machine-learning framework for ring-polymer instanton rate calculations that combines Gaussian process regression (GPR)-enhanced line integral string optimization with scalable surrogate modeling of the fluctuation prefactor. By exploiting uncertainty estimates from the surrogate modeling, we show that the number of force evaluations required to converge an instanton path becomes effectively independent of the number of beads used to discretize the pathway. To improve the efficiency of GPR model training, we introduce a strategy combining a physics-informed kernel prior, Hessian-free hyperparameter optimization, and GPU-accelerated Blackbox Matrix-Matrix Multiplication (BBMM), reducing model-training costs by more than an order of magnitude. For rate calculations, we develop adaptive regression, selective Hessian training, and cubic-spline interpolation strategies that substantially reduce the number of explicit Hessian evaluations while maintaining accurate tunneling rates. We apply and compare both cubic spline interpolation and GPR methods to approximate the instanton rate for representative proton transfer systems such as malonaldehyde, Z-3-aminopropenal, and 7,9-dinitro-10-hydroxybenzo[h]quinoline (dinitro-HBQ). Both approaches perform well for the smaller systems, whereas the dinitro-HBQ results expose limitations of the GPR model and demonstrate the greater robustness of the cubic spline interpolation method. These developments provide a practical workflow for reducing the computational cost of instanton rate calculations in complex molecular systems.

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。

↑