论文标题
从Instanton计算中的负担得起和高质量的隧道分裂的转移学习
Transfer learning for affordable and high quality tunneling splittings from instanton calculations
论文作者
论文摘要
转移学习（TL）的组合探索并应用于丙二醛。 RPI方法提供了隧穿分裂的半经典近似，并敏感地取决于PES的准确性。以二阶Møller-plesset扰动理论（MP2）为低级模型以及来自耦合群集单打，双打和扰动三元组（CCSD（t））的能量和力量，并作为高级（HL）模型，这证明了CCSD（T）的构成（T），并与50 ccsd（T）相同，并涉及50层的信息。 HL准确性用于隧道分裂。此外，对于高于最低能量结构的能量，HL-PES的全球质量是通过平均平均误差为0.3 kcal/mol的平均误差（比TL期间使用的能量高2倍）和与计算挑战的正常模式计算（cccccccc cccccccccccccccccccccccccccccccccccccccccs相比，均高2倍）和$ <2 $ cm $^{ - 1} $。
The combination of transfer learning (TL) a low level potential energy surface (PES) to a higher level of electronic structure theory together with ring-polymer instanton (RPI) theory is explored and applied to malonaldehyde. The RPI approach provides a semiclassical approximation of the tunneling splitting and depends sensitively on the accuracy of the PES. With second order Møller-Plesset perturbation theory (MP2) as the low-level (LL) model and energies and forces from coupled cluster singles, doubles and perturbative triples (CCSD(T)) as the high-level (HL) model, it is demonstrated that CCSD(T) information from only 25 to 50 judiciously selected structures along and around the instanton path suffice to reach HL-accuracy for the tunneling splitting. In addition, the global quality of the HL-PES is demonstrated through a mean average error of 0.3 kcal/mol for energies up to 40 kcal/mol above the minimum energy structure (a factor of 2 higher than the energies employed during TL) and $< 2 $ cm$^{-1}$ for harmonic frequencies compared with computationally challenging normal mode calculations at the CCSD(T) level.
