共 74 条
Two-Step Machine Learning Approach for Charge-Transfer Coupling with Structurally Diverse Data
被引:0
作者:
Lin, Hung-Hsuan
[1
,5
]
Wang, Chun-, I
[1
,6
]
Yang, Chou-Hsun
[1
]
Secario, Muhammad Khari
[1
,2
,3
]
Hsu, Chao-Ping
[1
,4
]
机构:
[1] Acad Sinica, Inst Chem, Taipei 115, Taiwan
[2] Acad Sinica, Taiwan Int Grad Program Sustainable Chem Sci & Tec, Inst Chem, Taipei 115, Taiwan
[3] Natl Yang Ming Chiao Tung Univ, Dept Appl Chem, Hsinchu 300, Taiwan
[4] Natl Ctr Theoret Sci, Div Phys, Taipei 106, Taiwan
[5] Yuan Ze Univ, Dept Comp Sci & Engn, Innovat Ctr Big Data & Digital Convergence, 135 Yuan Tung Rd, Taoyuan, Taiwan
[6] Univ Illinois, Dept Chem, Urbana, IL 61801 USA
关键词:
POTENTIAL-ENERGY SURFACES;
KERNEL RIDGE-REGRESSION;
ELECTRON-TRANSFER;
MOLECULAR-DYNAMICS;
TRANSPORT;
SCATTERING;
DNA;
D O I:
10.1021/acs.jpca.3c04524
中图分类号:
O64 [物理化学(理论化学)、化学物理学];
学科分类号:
070304 ;
081704 ;
摘要:
Electronic coupling is important in determining charge-transfer rates and dynamics. Coupling strength is sensitive to both intermolecular, e.g., orientation or distance, and intramolecular degrees of freedom. Hence, it is challenging to build an accurate machine learning model to predict electronic coupling of molecular pairs, especially for those derived from the amorphous phase, for which intermolecular configurations are much more diverse than those derived from crystals. In this work, we devise a new prediction algorithm that employs two consecutive KRR models. The first model predicts molecular orbitals (MOs) from structural variation for each fragment, and coupling is further predicted by using the overlap integral included in a second model. With our two-step procedure, we achieved mean absolute errors of 0.27 meV for an ethylene dimer and 1.99 meV for a naphthalene pair, much improved accuracy amounting to 14-fold and 3-fold error reductions, respectively. In addition, MOs from the first model can also be the starting point to obtain other quantum chemical properties from atomistic structures. This approach is also compatible with a MO predictor with sufficient accuracy.
引用
收藏
页码:271 / 280
页数:10
相关论文