FURI | Spring 2025

TCAD Modeling Aided by Physics-informed Neural Networks

Technology-Computer-Aided-Design (TCAD) solvers are highly accurate yet computationally expensive tools to simulate electronic device behavior. Photoconductive Semiconductor Switches (PCSS) are optoelectronic devices used in high-frequency amplification and power applications. This research project aims to train a physics-informed neural network (PINN) model to simulate device behavior and compare to the speed and accuracy of the TCAD solvers. By implementing a PINN model, this research aims to improve the efficiency of device-technology co-optimization (DTCO).