arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.08565physics.chem-phcond-mat.mtrl-sciphysics.atm-clusphysics.comp-phphysics.data-an
收藏

构建具有量子化学精度的机器学习力场:应用和化学见解

Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights

Huziel E. Sauceda, Stefan Chmiela, Igor Poltavsky, Klaus-Robert Müller, Alexandre Tkatchenko

摘要:

高度精确的力场是生成预测模拟的强制性要求。在这里,我们通过讨论从生成参考计算数据集到构建机器学习模型的分层路径,以及验证模型生成的物理过程,提出了构建机器学习分子力场的路径。我们将使用对称梯度域机器学习(sGDML)框架,因为它能够以高精度重建复杂的高维势能面(PES),即使只使用几百个分子构象进行训练。sGDML模型的数据效率允许使用用基于高水平波函数的方法计算的参考原子力,例如具有单、双和微扰三重激发的$gold$ $standard$耦合簇方法(CCSD(T))。我们证明了sGDML框架的灵活性捕获本地和非本地的电子相互作用(例如氢键,孤对,空间排斥,杂交状态的变化(例如$sp^2 \rightleftharpoons sp^3$),$n\toπ^*$相互作用和质子转移),而不施加任何限制的性质原子间的潜力。在不同理论水平(例如密度泛函理论和CCSD(T))下针对不同分子结构训练的sGDML模型的分析提供了更高理论水平产生更平滑PES的经验证据。此外,仔细分析分子动力学模拟产生新的定性的见解接近光谱精度的小分子的动力学和振动光谱。

英文摘要:

Highly accurate force fields are a mandatory requirement to generate predictive simulations. Here we present the path for the construction of machine learned molecular force fields by discussing the hierarchical pathway from generating the dataset of reference calculations to the construction of the machine learning model, and the validation of the physics generated by the model. We will use the symmetrized gradient-domain machine learning (sGDML) framework due to its ability to reconstruct complex high-dimensional potential-energy surfaces (PES) with high precision even when using just a few hundreds of molecular conformations for training. The data efficiency of the sGDML model allows using reference atomic forces computed with high-level wavefunction-based approaches, such as the $gold$ $standard$ coupled cluster method with single, double, and perturbative triple excitations (CCSD(T)). We demonstrate that the flexible nature of the sGDML framework captures local and non-local electronic interactions (e.g. H-bonding, lone pairs, steric repulsion, changes in hybridization states (e.g. $sp^2 \rightleftharpoons sp^3$), $n\toπ^*$ interactions, and proton transfer) without imposing any restriction on the nature of interatomic potentials. The analysis of sGDML models trained for different molecular structures at different levels of theory (e.g. density functional theory and CCSD(T)) provides empirical evidence that a higher level of theory generates a smoother PES. Additionally, a careful analysis of molecular dynamics simulations yields new qualitative insights into dynamics and vibrational spectroscopy of small molecules close to spectroscopic accuracy.

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。

↑