PREDICTION OF THE FORMATION ENERGY OF LI-BASED COMPOUNDS USING MACHINE LEARNING METHODS
Keywords:
machine learning, XGBoost, Materials Project, formation energy, lithium compounds, DFT, regressionAbstract
In this study, a machine learning model was developed to predict the formation energy of lithium-based compounds using density functional theory (DFT) calculation results obtained from the Materials Project database, comprising 21,764 compounds. The XGBoost algorithm was employed for the prediction task. Trained on twenty distinct features, the model achieved a coefficient of determination of R² = 0.8932, with a mean absolute error of 0.1584 eV/atom. These results confirm the effectiveness of machine learning methods in materials science for the rapid and accurate evaluation of the properties of novel compounds.
References
Jain A., Ong S. P., Hautier G., Chen W., Richards W. D., Dacek S., et al. Commentary: The Materials Project: A materials genome approach to accelerating materials innovation // APL Materials. — 2013. — Vol. 1, № 1. — P. 011002.
Faber F. A., Lindmaa A., von Lilienfeld O. A., Armiento R. Machine Learning Energies of 2 Million Elpasolite (ABC₂D₆) Crystals // Physical Review Letters. — 2016. — Vol. 117, № 13. — P. 135502.
Ward L., Dunn A., Faghaninia A., Zimmermann N. E. R., Bajaj S., Wang Q., et al. Matminer: An open source toolkit for materials data mining // Computational Materials Science. — 2018. — Vol. 152. — P. 60–69.
Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. — San Francisco: ACM, 2016. — P. 785–794.
Schmidt J., Marques M. R. G., Botti S., Marques M. A. L. Recent advances and applications of machine learning in solid-state materials science // npj Computational Materials. — 2019. — Vol. 5, № 1. — P. 83.
Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., et al. Scikit-learn: Machine Learning in Python // Journal of Machine Learning Research. — 2011. — Vol. 12. — P. 2825–2830.
Ong S. P., Richards W. D., Jain A., Hautier G., Kocher M., Cholia S., et al. Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis // Computational Materials Science. — 2013. — Vol. 68. — P. 314–319.
Butler K. T., Davies D. W., Cartwright H., Isayev O., Walsh A. Machine learning for molecular and materials science // Nature. — 2018. — Vol. 559, № 7715. — P. 547–555.
Xie T., Grossman J. C. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties // Physical Review Letters. — 2018. — Vol. 120, № 14. — P. 145301.
Chen C., Ye W., Zuo Y., Zheng C., Ong S. P. Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals // Chemistry of Materials. — 2019. — Vol. 31, № 9. — P. 3564–3572.
Saal J. E., Kirklin S., Aykol M., Meredig B., Wolverton C. Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD) // JOM. — 2013. — Vol. 65, № 11. — P. 1501–1509.
Ward L., Agrawal A., Choudhary A., Wolverton C. A general-purpose machine learning framework for predicting properties of inorganic materials // npj Computational Materials. — 2016. — Vol. 2, № 1. — P. 16028.
Sendek A. D., Yang Q., Cubuk E. D., Duerloo K. A. N., Cui Y., Reed E. J. Holistic computational structure screening of more than 12000 candidates for solid lithium-ion conductor materials // Energy & Environmental Science. — 2017. — Vol. 10, № 1. — P. 306–320.
Ramprasad R., Batra R., Pilania G., Mannodi-Kanakkithodi A., Kim C. Machine learning in materials informatics: recent applications and prospects // npj Computational Materials. — 2017. — Vol. 3, № 1. — P. 54.
Curtarolo S., Hart G. L. W., Nardelli M. B., Mingo N., Sanvito S., Levy O. The high-throughput highway to computational materials design // Nature Materials. — 2013. — Vol. 12, № 3. — P. 191–201.





