PSO-SVR Algorithm for Accurate ZnO Energy Band Gap Prediction

An artificial algorithm using a machine learning approach could be used to determine the energy band gap, E g which would simply the process of synthesizing ZnO properties. This paper proposes to develop machine learning models that can accurately predict the energy band gap of ZnO. This study used PSO-SVR model utilizing three kernel functions: linear, polynomial, and RBF. The PSO-SVR with RBF resulted in the lowest RMSE of 0.0395eV. This analysis also showed that the combination of lattice constant a and c , crystallite size, D and grain size of ZnO datasets had contributed to high accuracy of predicting E g .