Achieving vibrational energies of diatomic systems with high quality by machine learning improved DFT method. Issue 55 (15th December 2022)

• Record Type: Journal Article
• Authors: Yang, Zhangzhang; Wan, Zhitao; Liu, Li; Fu, Jia; Fan, Qunchao; Xie, Feng; Zhang, Yi; Ma, Jie
• Is Part Of: RSC advances. Volume 12:Issue 55(2022)
• Page Start: 35950
• Page End: 35958
• Publication Date: 2022-12-15
• Subjects: Chemistry -- Periodicals; 540.5
• DOI: 10.1039/d2ra07613f
• Languages: English
• ISSNs: 2046-2069

Abstract

Abstract : By systematically correcting the calculation errors through machine learning, the accuracy of the diatomic vibrational energy prediction based on typical DFT methods has been improved by order of magnitude. Abstract : When using ab initio methods to obtain high-quality quantum behavior of molecules, it often involves a lot of trial-and-error work in algorithm design and parameter selection, which requires enormous time and computational resource costs. In the study of vibrational energies of diatomic molecules, we found that starting from a low-precision DFT model and then correcting the errors using the high-dimensional function modeling capabilities of machine learning, one can considerably reduce the computational burden and improve the prediction accuracy. Data-driven machine learning is able to capture subtle physical information that is missing from DFT approaches. The results of 12 C 16 O, 24 MgO and Na 35 Cl show that, compared with CCSD(T)/cc-pV5Z calculation, this work improves the prediction accuracy by more than one order of magnitude, and reduces the computation cost by more than one order of magnitude.