Artificial Neural Network-Based Approach to Modeling Energy Bands of GaN-Based Heterojunction Materials

This work reports a preliminary investigation of energy bands of AlxGal-xN/GaN heterojunction based on the use of artificial neural networks (ANN). Numerical energy bands simulations were used to generate training and testing dataset for ANN model. The input parameters of the ANN are the Al content, the thicknesses of AlxGal-xN barrier layer and position description of two-Layer Materials, respectively. The outputs of the ANN are the conduction band energy profile of the AlxGal_xN/GaN heterojunction and the channel Two-dimensional electron gas (2DEG) concentration distributions. The results show that trained ANN model can effectively predict the energy bands structure. The model achieved a mean squared error of 7.94×10 6 on the testing dataset, with an average relative L2 error of 4.44×10 ³ for electron concentration prediction and 2.57×10 ³ for conduction band energy prediction.