Cookies ussage consent
Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.I agree, do not show this message again.
YUEYU ZHOU1, JING GAO1, YITING GUI1, JUN WEN1,* , YAN WANG1, QUANJIN LIU1, GUISHENG JIANG1, XIAOXIAO HUANG1, QIANG WANG1, CHENLONG WEI1
- School of Electronic Engineering and Intelligent Manufacturing, Anqing Normal University, Anqing 246133, China
The prediction of the properties of inorganic compounds by data-driven machine learning methods has gradually become a research hotspot in the field of materials science. In this work, the machine learning models of the least absolute shrinkage and selection operator (Lasso), kernel ridge regression (KRR), Gaussian process regression (GPR), random forests regression (RFR), support vector regression (SVR) and gradient boosting regression (GBR) were utilized to predict band gaps of ternary oxides for phosphor hosts. The results show that the GBR is a robust and feasible model with higher performance. Besides, the importance of each feature is analyzed quantificationally based on the GBR model. It indicates that two features (i.e., the average of molar heat capacity and the range of metallic valence) play a great role in affecting the predictive performance of band gaps. Besides, the Shapley additive explanation (SHAP) is used to elaborate the results from the GBR model. This work not only demonstrates the feasibility of machine learning to predict band gaps based only on the chemical composition but also contributes to the prediction of the other properties of inorganic materials..
Machine learning methods, Band gaps, Inorganic compounds, Materials science.
Submitted at: May 2, 2022
Accepted at: Dec. 6, 2022
YUEYU ZHOU, JING GAO, YITING GUI, JUN WEN, YAN WANG, QUANJIN LIU, GUISHENG JIANG, XIAOXIAO HUANG, QIANG WANG, CHENLONG WEI, Predicting band gaps of ternary oxides for phosphor hosts from machine learning, Journal of Optoelectronics and Advanced Materials Vol. 24, Iss. 11-12, pp. 548-557 (2022)
- Download Fulltext
- Downloads: 1 (from 1 distinct Internet Addresses ).