Achieving Vibrational Energies of Diatomic Systems with High Quality by Machine Learning Improved DFT Method

Overview

Journal RSC Adv

Publisher Royal Society of Chemistry

Specialty Chemistry

Date 2022 Dec 22

PMID 36545113

Authors

Zhangzhang Yang

Zhitao Wan

Li Liu

Jia Fu

Qunchao Fan

Feng Xie

Yi Zhang

Jie Ma

Affiliations

Soon will be listed here.

Abstract

When using 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 CO, MgO and NaCl 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.

References

Onate C, Okon I, Onyeaju M, Ebomwonyi O . Vibrational energies of some diatomic molecules for a modified and deformed potential. Sci Rep. 2021; 11(1):22498. PMC: 8602305. DOI: 10.1038/s41598-021-01998-6. View

Zhang Y, Xu X, Goddard 3rd W . Doubly hybrid density functional for accurate descriptions of nonbond interactions, thermochemistry, and thermochemical kinetics. Proc Natl Acad Sci U S A. 2009; 106(13):4963-8. PMC: 2664054. DOI: 10.1073/pnas.0901093106. View

Zhao J, Tian G, Qiu Y, Qu H . Rapid quantification of active pharmaceutical ingredient for sugar-free Yangwei granules in commercial production using FT-NIR spectroscopy based on machine learning techniques. Spectrochim Acta A Mol Biomol Spectrosc. 2020; 245:118878. DOI: 10.1016/j.saa.2020.118878. View

Shayesteh A, Henderson R, Le Roy R, Bernath P . Ground state potential energy curve and dissociation energy of MgH. J Phys Chem A. 2007; 111(49):12495-505. DOI: 10.1021/jp075704a. View

Ram , Dulick , Guo , Zhang , Bernath . Fourier Transform Infrared Emission Spectroscopy of NaCl and KCl. J Mol Spectrosc. 1997; 183(2):360-73. DOI: 10.1006/jmsp.1997.7292. View

Fu J, Long S, Jian J, Fan Z, Fan Q, Xie F . A joint data and model driven method for study diatomic vibrational spectra including dissociation behavior. Spectrochim Acta A Mol Biomol Spectrosc. 2020; 239:118363. DOI: 10.1016/j.saa.2020.118363. View

Mohr S, Ratcliff L, Genovese L, Caliste D, Boulanger P, Goedecker S . Accurate and efficient linear scaling DFT calculations with universal applicability. Phys Chem Chem Phys. 2015; 17(47):31360-70. DOI: 10.1039/c5cp00437c. View

Baiz C, Blasiak B, Bredenbeck J, Cho M, Choi J, Corcelli S . Vibrational Spectroscopic Map, Vibrational Spectroscopy, and Intermolecular Interaction. Chem Rev. 2020; 120(15):7152-7218. PMC: 7710120. DOI: 10.1021/acs.chemrev.9b00813. View

Bubin S, Pavanello M, Tung W, Sharkey K, Adamowicz L . Born-Oppenheimer and non-Born-Oppenheimer, atomic and molecular calculations with explicitly correlated Gaussians. Chem Rev. 2012; 113(1):36-79. DOI: 10.1021/cr200419d. View

10.

Fink D, Myers E . Deuteron-to-Proton Mass Ratio from Simultaneous Measurement of the Cyclotron Frequencies of H_{2}^{+} and D^{+}. Phys Rev Lett. 2021; 127(24):243001. DOI: 10.1103/PhysRevLett.127.243001. View

11.

Chen M, Dixon D . Low-lying electronic states of Ir(n) clusters with n = 2-8 predicted at the DFT, CASSCF, and CCSD(T) levels. J Phys Chem A. 2013; 117(17):3676-88. DOI: 10.1021/jp4014465. View

12.

Fu J, Jian J, Long S, Fan Z, Fan Q, Xie F . Study on potential energy curves and ro-vibrational energies of DT, HT and T molecules. Spectrochim Acta A Mol Biomol Spectrosc. 2021; 260:119913. DOI: 10.1016/j.saa.2021.119913. View

13.

Cohen A, Mori-Sanchez P, Yang W . Insights into current limitations of density functional theory. Science. 2008; 321(5890):792-4. DOI: 10.1126/science.1158722. View

14.

Lischka H, Nachtigallova D, Aquino A, Szalay P, Plasser F, Machado F . Multireference Approaches for Excited States of Molecules. Chem Rev. 2018; 118(15):7293-7361. DOI: 10.1021/acs.chemrev.8b00244. View

15.

Erba A, Baima J, Bush I, Orlando R, Dovesi R . Large-Scale Condensed Matter DFT Simulations: Performance and Capabilities of the CRYSTAL Code. J Chem Theory Comput. 2017; 13(10):5019-5027. DOI: 10.1021/acs.jctc.7b00687. View

16.

Coxon , Hajigeorgiou . The Radial Hamiltonians for the X(1)Sigma(+) and B(1)Sigma(+) States of HCl. J Mol Spectrosc. 2000; 203(1):49-64. DOI: 10.1006/jmsp.2000.8155. View

17.

Speth , Braatz , Tiemann . REMPI Spectroscopy of SO Singlet States. J Mol Spectrosc. 1998; 192(1):69-74. DOI: 10.1006/jmsp.1998.7670. View

18.

Fortes F, Moros J, Lucena P, Cabalin L, Laserna J . Laser-induced breakdown spectroscopy. Anal Chem. 2012; 85(2):640-69. DOI: 10.1021/ac303220r. View

19.

Abiodun O, Jantan A, Omolara A, Dada K, Mohamed N, Arshad H . State-of-the-art in artificial neural network applications: A survey. Heliyon. 2018; 4(11):e00938. PMC: 6260436. DOI: 10.1016/j.heliyon.2018.e00938. View