Mendive-Tapia David, Meyer Hans-Dieter, Vendrell Oriol
Theoretische Chemie, Universität Heidelberg, Im Neuenheimer Feld 229, D-69120Heidelberg, Germany.
J Chem Theory Comput. 2023 Feb 28;19(4):1144-1156. doi: 10.1021/acs.jctc.2c01089. Epub 2023 Jan 30.
The multiconfiguration time-dependent Hartree (MCTDH) method and its multilayer extension (ML-MCTDH) are powerful algorithms for the efficient computation of nuclear quantum dynamics in high-dimensional systems. By providing time-dependent variational orbitals and an optimal choice of layered effective degrees of freedom, one is able to reduce the computational cost to an amenable number of configurations. However, choices related to selecting properly the mode grouping and tensor tree are strongly system dependent and, thus far, subjectively based on intuition and/or experience. Therefore, herein we detail a new protocol based on multivariate statistics─more specifically, factor analysis and hierarchical clustering─for a reliable and convenient guiding in the optimal design of such complex "system-of-systems" tensor-network decompositions. The advantages of employing the new algorithm and its applicability are tested on water and two floppy protonated water clusters with large amplitude motions.
多组态含时 Hartree（MCTDH）方法及其多层扩展（ML-MCTDH）是用于高效计算高维系统中核量子动力学的强大算法。通过提供含时变分轨道以及对分层有效自由度的优化选择，能够将计算成本降低到可处理的组态数量。然而，与正确选择模式分组和张量树相关的选择强烈依赖于系统，并且迄今为止，是基于直觉和/或经验主观做出的。因此，在此我们详细介绍一种基于多元统计——更具体地说是因子分析和层次聚类——的新方案，以便在这种复杂的“系统之系统”张量网络分解的优化设计中进行可靠且便捷的指导。在水以及两个具有大幅运动的松弛质子化水团簇上测试了采用新算法的优势及其适用性。
