Manchev Yulian T, Popelier Paul L A
Department of Chemistry, The University of Manchester, Manchester M13 9PL, U.K.
J Phys Chem A. 2024 Oct 24;128(42):9345-9351. doi: 10.1021/acs.jpca.4c05873. Epub 2024 Oct 11.
We report a first-principles water dimer potential that captures many-body interactions through Gaussian process regression (GPR). Modeling is upgraded from previous work by using a custom kernel function implemented through the KeOps library, allowing for much larger GPR models to be constructed and interfaced with the next-generation machine learning force field FFLUX. A new synthetic water dimer data set, called WD24, is used for model training. The resulting models can predict 90% of dimer geometries within chemical accuracy for a test set and in a simulation. The curvature of the potential energy surface is captured by the models, and a successful geometry optimization is completed with a total energy error of just 2.6 kJ mol, from a starting structure where water molecules are separated by nearly 4.3 Å. Dimeric modeling of a flexible, noncrystalline system with FFLUX is shown for the first time.
我们报告了一种通过高斯过程回归（GPR）捕捉多体相互作用的第一性原理水二聚体势。通过使用通过KeOps库实现的自定义核函数，建模比之前的工作有所升级，这使得能够构建更大的GPR模型，并与下一代机器学习力场FFLUX接口。一个名为WD24的新的合成水二聚体数据集用于模型训练。所得模型在测试集和模拟中能够在化学精度范围内预测90%的二聚体几何结构。模型捕捉到了势能面的曲率，并且从水分子相距近4.3 Å的起始结构开始，成功完成了几何优化，总能量误差仅为2.6 kJ/mol。首次展示了使用FFLUX对柔性非晶系统进行二聚体建模。
