The excellent transmission characteristics of graphene surface plasmon polaritons in mid-infrared band were analyzed and verified effectively through theoretical derivation and soft simulation in this paper. Meanwhile, a sandwich waveguide structure of dielectric–graphene–substrate–dielectric based on graphene surface plasmon polaritons (SPPs) was presented. Simulation results indicate that graphene SPPs show unique properties in the mid-infrared region including ultra-compact mode confinement and dynamic tunability, which allow these SPPs to overcome the defects of metal SPPs and traditional silicon-based optoelectronic devices. Thus, they can be used to manufacture subwavelength devices. The work in this paper lays a theoretical foundation for the application of graphene SPPs in the mid-infrared region.
This work employs a deep learning method to develop a high-precision model for predicting the breakdown voltage (Vbr) and forward I-V characteristics of silicon carbide Schottky barrier diodes (SiC SBDs). The model significantly reduces the testing costs associated with destructive experiments, such as breakdown voltage testing. Although the model requires a certain amount of time to establish itself, it supports linear variations in related variables once developed. A predicted model for Vbr with an accuracy of up to 99% was successfully developed using 600 sets of input data after 200 epochs of training. After training for 1000 epochs, the deep learning-based model could predict not only point values like Vbr but also curves, such as forward I-V characteristics, with a mean squared error (MSE) of less than 10−3. Our research shows the applicability and high efficiency of introducing deep learning into device characteristic prediction.