Predicting the band gap of ZnO quantum dots via supervised machine learning models

Abstract Developing mathematical models for zinc oxide (ZnO) nanostructures can significantly accelerate the production of ZnO-based devices and applications. Herein, the implementation of supervised machine learning to predict the optical band gap energy of ZnO is presented. Different models such as Kernel Ridge Regression (KRR) and Artificial Neural Network (ANN) were trained with empirical features, including experimental time and temperature conditions during ZnO fabrication. Test results revealed high accuracy of the models (KRR with quadratic features), with root mean squared error = 0.0849 eV, and mean absolute error percentage = 1.7328%. These results show the capabilities of machine learning models for automated prediction of semiconductor properties, which can be used to accelerate materials design and applications.