New Research in Physics

Efficient machine learning method, Stacking, to improvement of material band gaps prediction

Authors

Anoshirvan Ghaffaripour
Behrooz Vaseghi

Yasouj University

Abstract
In this research, energy band gap of specific materials has been predicted using machine learning approach. We try by using mixing some usual machine learning methods to presenting an efficient machine learning method to improve material band gap prediction. Based on Gradient Boosting Decision Tree, Light Gradient Boosting, Random Forest and Extreme Gradient Boosting, we presented Stacking method by mixing all mentioned methods as an efficient machine learning method.

Keywords

Machine Learning
Energy Band Gap
XGBoost
Stacking
Regression Coefficient
[1] Y. Zhuo, A. Mansouri Tehrani, J. Brgoch, "Predicting the Band Gaps of Inorganic Solids by Machine Learning", Journal of Physical Chemistry Letters Vol 9, 1668-1673, 2018. [DOI:10.1021/acs.jpclett.8b00124] [PMID]
[1] Y. Zhuo, A. Mansouri Tehrani, J. Brgoch, "Predicting the Band Gaps of Inorganic Solids by Machine Learning", Journal of Physical Chemistry Letters Vol 9, 1668-1673, 2018. [DOI:10.1021/acs.jpclett.8b00124] [PMID]
[2] A. Sabagh Moeini, F. Shariatmadar Tehrani, A. Naeimi-Sadigh "Machine learning-enhanced band gaps prediction for low-symmetry double and layered perovskites", Scientific Reports Vol. 14, 26736, 2024. [DOI:10.1038/s41598-024-77081-7] [PMID]
[2] A. Sabagh Moeini, F. Shariatmadar Tehrani, A. Naeimi-Sadigh "Machine learning-enhanced band gaps prediction for low-symmetry double and layered perovskites", Scientific Reports Vol. 14, 26736, 2024. [DOI:10.1038/s41598-024-77081-7] [PMID]
[3] S.G. Jung, G. Jung, J.M. Cole, "Automatic Prediction of Band Gaps of Inorganic Materials Using a Gradient Boosted and Statistical Feature Selection Workflow", Journal of Chemical Information and Modeling Vol. 64, 1187-1200, 2024. [DOI:10.1021/acs.jcim.3c01897] [PMID]
[3] S.G. Jung, G. Jung, J.M. Cole, "Automatic Prediction of Band Gaps of Inorganic Materials Using a Gradient Boosted and Statistical Feature Selection Workflow", Journal of Chemical Information and Modeling Vol. 64, 1187-1200, 2024. [DOI:10.1021/acs.jcim.3c01897] [PMID]
[4] E. Ogoshi et al., "Learning from machine learning: the case of band gap directness in semiconductors", Discover Materials Vol. 4, 6, 2024. [DOI:10.1007/s43939-024-00073-x]
[4] E. Ogoshi et al., "Learning from machine learning: the case of band gap directness in semiconductors", Discover Materials Vol. 4, 6, 2024. [DOI:10.1007/s43939-024-00073-x]
[5] A.Ch. Rajan et al., "Machine-Learning Assisted Accurate Band Gap Predictions of Functionalized MXene" Chemistry of Materials Vol. 4, 112, 2018.
[5] A.Ch. Rajan et al., "Machine-Learning Assisted Accurate Band Gap Predictions of Functionalized MXene" Chemistry of Materials Vol. 4, 112, 2018.
[6] T. Wang, K. Zhang, J. The, H. Yu, "Accurate prediction of band gap of materials using stacking machine learning model" Computational Materials Science Vol. 201, 110899, 2022. [DOI:10.1016/j.commatsci.2021.110899]
[6] T. Wang, K. Zhang, J. The, H. Yu, "Accurate prediction of band gap of materials using stacking machine learning model" Computational Materials Science Vol. 201, 110899, 2022. [DOI:10.1016/j.commatsci.2021.110899]
[7] S. Priyanga et al., "Prediction of nature of band gap of perovskite oxides (ABO3) using a machine learning approach", Journal of Materiomics Vol. 8, 937e948, 2022. [DOI:10.1016/j.jmat.2022.04.006]
[7] S. Priyanga et al., "Prediction of nature of band gap of perovskite oxides (ABO3) using a machine learning approach", Journal of Materiomics Vol. 8, 937e948, 2022. [DOI:10.1016/j.jmat.2022.04.006]
[8] J. Xu et al., "Machine learning predictions of band gap and band edge for (GaN)1-x(ZnO)x solid solution using crystal structure information" Journal of Material Sciences Vol. 58, 7986-7994, 2023. [DOI:10.1007/s10853-023-08557-6]
[8] J. Xu et al., "Machine learning predictions of band gap and band edge for (GaN)1-x(ZnO)x solid solution using crystal structure information" Journal of Material Sciences Vol. 58, 7986-7994, 2023. [DOI:10.1007/s10853-023-08557-6]

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us