Prediction of phonon mode frequencies in chalcopyrites using a graph neural network | Izvestiya vuzov. Fizika. 2025. № 11. DOI: 10.17223/00213411/68/11/11

Prediction of phonon mode frequencies in chalcopyrites using a graph neural network

Quantum-chemical calculations of phonon mode frequencies in optical nonlinear crystals are computationally expensive. In this work, we propose a predictive model based on a graph neural network for estimating phonon mode frequencies in «chalcopyrite» type optical crystals. The neural network was trained using structural data of «chalcopyrite» type crystals and corresponding phonon mode frequencies from the «Computational Raman Database». The developed model achieves a coefficient of determination of 0.922 for predicting phonon mode frequencies.

Download file

Counter downloads: 1

Keywords

phonon modes, graph neural network, optical crystals, chalcopyrite, predictive model, quantum-chemical calculations

Authors

Name	Organization	E-mail
Snegerev Mikhail S.	Tomsk State University	snegerev@mail.tsu.ru
Knyazkova Anastasia I.	V.E. Zuev Institute of Atmospheric Optics of the Siberian Branch of the Russian Academy of Sciences	knyazkova@iao.ru
Vrazhnov Denis A.	V.E. Zuev Institute of Atmospheric Optics of the Siberian Branch of the Russian Academy of Sciences	vda@iao.ru
Raspopin Georgy K.	V.E. Zuev Institute of Atmospheric Optics of the Siberian Branch of the Russian Academy of Sciences	RaspopinGK@mail.tsu.ru
Kistenev Yury V.	V.E. Zuev Institute of Atmospheric Optics of the Siberian Branch of the Russian Academy of Sciences	yuk@iao.ru

Всего: 5

References

Murray Sandroni M. et al. // ACS Energy Lett. - 2017. - V. 2. - No. 5. - P. 1076-1088. - DOI: 10.1021/acsenergylett.7b00003-9.

Thomas S.R. et al. // RSC Advances. - 2016. - V. 6. - No. 65. - P. 60643-60656. - DOI: 10.1039/c6ra05502h.

Wada T. // Jpn. J. Appl. Phys. - 2021. - V. 60. - No. 8. - P. 080101. - DOI: 10.35848/1347-4065/ac08ac.

Kittel C., McEuen P.Introduction to Solid State Physics. - John Wiley & Sons, 2018.

Kohn W., Sham L.J. // Phys. Rev. - 1965. - V. 140. - No. 4A. - P. A1133. - DOI: 10.1103/PhysRev.140.A1133.

Baroni S., Giannozzi P., Testa A. // Phys. Rev. Lett. - 1987. - V. 58. - No. 18. - P. 1861. - DOI: 10.1103/PhysRevLett.58.1861.

Schmidt J. et al. // NPJ Comput. Mater. - 2019. - V. 5. - No. 1. - P. 83. - DOI: 10.1038/s41524-019-0221-0.

Cheng J., Zhang C., Dong L. // Commun. Mater. - 2021. - V. 2. - No. 1. - P. 92. - DOI: 10.1038/s43246-021-00194-3.

Wei L. et al. // J. Appl. Phys. - 2013. - V. 114. - No. 23. - DOI: 10.1063/1.4847935.

Continenza A. et al. // Phys. Rev. B. - 1992. - V. 46. - No. 16. - P. 10070. - DOI: 10.1103/PhysRevB.46.10070.

Yu Y. et al. // Chalcogenide Lett. - 2019. - V. 16. - No. 11. - P. 513-522.

Xie T. et al. // arXiv preprint arXiv:2110.06197. - 2021. - DOI: 10.48550/arXiv.2110.06197.

Das K. et al. // Proceedings of the AAAI Conference on Artificial Intelligence. - 2023. - V. 37. - No. 6. - P. 7323-7331. - DOI: 10.1609/aaai.v37i6.25892.

Bagheri M., Komsa H.P. // Sci. Data. - 2023. - V. 10. - No. 1. - P. 80. - DOI: 10.1038/s41597-023-01988-5.

Zhang S.L. Raman Spectroscopy and its Application in Nanostructures. - John Wiley & Sons, 2012.

Gilmer J. et al. // Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, PMLR 70, 2017. - P. 1263-1272.

Elfwing S., Uchibe E., Doya K. // Neural Networks. - 2018. - V. 107. - P. 3-11. - DOI: 10.1016/j.neunet.2017.12.012.