Wallace Austin M, Sherrill C David
Center for Computational Molecular Science and Technology and School of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, Georgia 30332-0400, USA.
Center for Computational Molecular Science and Technology, School of Chemistry and Biochemistry, and School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332-0400, USA.
J Chem Phys. 2024 Sep 21;161(11). doi: 10.1063/5.0219185.
Symmetry-adapted perturbation theory (SAPT) directly computes intermolecular interaction energy in terms of electrostatics, exchange-repulsion, induction/polarization, and London dispersion components. In SAPT based on Hartree-Fock ("SAPT0") or based on density functional theory, the most time-consuming step is the computation of the dispersion terms. Previous work has explored the replacement of these expensive dispersion terms with simple damped asymptotic models. We recently examined [Schriber et al. J. Chem. Phys. 154, 234107 (2021)] the accuracy of SAPT0 when replacing its dispersion term with Grimme's popular -D3 correction, reducing the computational cost scaling from O(N5) to O(N3). That work optimized damping function parameters for SAPT0-D3/jun-cc-pVDZ using estimates of the coupled-cluster complete basis set limit [CCSD(T)/CBS] on a 8299 dimer dataset. Here, we explore the accuracy of SAPT0-D3 with additional basis sets, along with an analogous model using -D4. Damping parameters are rather insensitive to basis sets, and the resulting SAPT0-D models are more accurate on average for total interaction energies than SAPT0. Our results are surprising in several respects: (1) improvement of -D4 over -D3 is negligible for these systems, even charged systems where -D4 should, in principle, be more accurate; (2) addition of Axilrod-Teller-Muto terms for three-body dispersion does not improve error statistics for this test set; and (3) SAPT0-D is even more accurate on average for total interaction energies than the much more computationally costly density functional theory based SAPT [SAPT(DFT)] in an aug-cc-pVDZ basis. However, SAPT0 and SAPT0-D3/D4 interaction energies benefit from significant error cancellation between exchange and dispersion terms.
对称适配微扰理论（SAPT）直接根据静电作用、交换排斥、诱导/极化以及伦敦色散分量来计算分子间相互作用能。在基于哈特里 - 福克（“SAPT0”）或基于密度泛函理论的SAPT中，最耗时的步骤是色散项的计算。先前的工作已经探索了用简单的阻尼渐近模型来替代这些昂贵的色散项。我们最近研究了[施里伯等人，《化学物理杂志》154, 234107 (2021)]当用格林姆流行的-D3校正替代其色散项时SAPT0的准确性，将计算成本标度从O(N5)降低到了O(N3)。该工作在一个包含8299个二聚体的数据集上，使用耦合簇完全基组极限[CCSD(T)/CBS]的估计值，对SAPT0-D3/jun-cc-pVDZ的阻尼函数参数进行了优化。在此，我们探索了使用其他基组时SAPT0-D3的准确性，以及使用-D4的类似模型。阻尼参数对基组相当不敏感，并且由此得到的SAPT0-D模型对于总相互作用能而言，平均比SAPT0更准确。我们的结果在几个方面令人惊讶：（1）对于这些体系，甚至是原则上-D4应该更准确的带电体系，-D4相对于-D3的改进可以忽略不计；（2）添加用于三体色散的阿西洛德 - 泰勒 - 武藤项并没有改善该测试集的误差统计；（3）对于总相互作用能而言，在aug-cc-pVDZ基组中，SAPT0-D平均甚至比计算成本高得多的基于密度泛函理论的SAPT [SAPT(DFT)]更准确。然而，SAPT0和SAPT0-D3/D4的相互作用能受益于交换项和色散项之间显著的误差抵消。
