loading page

Combining ab initio and machine learning method to improve prediction performance of diatomic vibrational energies
  • +5
  • Jia Fu,
  • Zhitao Wan,
  • Zhangzhang Yang,
  • Li Liu,
  • Qunchao Fan,
  • Feng Xie,
  • Yi Zhang,
  • Jie Ma
Jia Fu
Xihua University

Corresponding Author:[email protected]

Author Profile
Zhitao Wan
Xihua University
Author Profile
Zhangzhang Yang
Xihua University
Author Profile
Li Liu
Xihua University
Author Profile
Qunchao Fan
Xihua University
Author Profile
Feng Xie
Tsinghua University
Author Profile
Yi Zhang
National University of Defense Technology
Author Profile
Jie Ma
Shanxi University
Author Profile


Through the comprehensive analysis of ab initio and experimental results of a large number of diatomic systems, the systematic deviation of ab initio method in vibrational energies prediction caused by physical/mathematical simplification is located. A joint ab initio and machine learning method based on information across molecules is proposed to deal with the problem. Starting from an ab initio model, and then systematically modifying it through machine learning, the vibrational energies prediction of many diatomic systems (SiC, HBr, NO, PC, N2, SiO, O2, ClF, etc.) have been improved, and significantly surpassed the more complex ab initio model. In addition to the improvement of accuracy, the new method also greatly reduces the computational expense, and is applicable for the systems without experimental data.
26 Feb 2022Submitted to International Journal of Quantum Chemistry
28 Feb 2022Submission Checks Completed
28 Feb 2022Assigned to Editor
28 Feb 2022Reviewer(s) Assigned
10 Mar 2022Review(s) Completed, Editorial Evaluation Pending
14 Mar 2022Editorial Decision: Revise Major
13 Apr 20221st Revision Received
16 Apr 2022Submission Checks Completed
16 Apr 2022Assigned to Editor
13 May 2022Reviewer(s) Assigned
16 May 2022Review(s) Completed, Editorial Evaluation Pending
17 May 2022Editorial Decision: Accept
15 Sep 2022Published in International Journal of Quantum Chemistry volume 122 issue 18. 10.1002/qua.26953