Prediction of electrical properties of GAAFET based on integrated learning model

Abstract As device feature sizes continue to decrease and fin field effect transistors reach their physical limits, gate all around field effect transistors (GAAFETs) have emerged with larger gate control areas and stackable characteristics for better suppression of second-order effects such as short-channel effects due to their gate encircling characteristics. Traditional methods for studying the electrical characteristics of devices are mostly based on the technology computer-aided design. Still, it is not conducive to developing new devices due to its time-consuming and inefficient drawbacks. Deep learning (DL) and machine learning (ML) have been well-used in recent years in many fields. In this paper, we propose an integrated learning model that integrates the advantages of DL and ML to solve many problems in traditional methods. This integrated learning model predicts the direct current characteristics, capacitance characteristics, and electrical parameters of GAAFET better than those predicted by DL or ML methods alone, with a linear regression factor (R ²) greater than 0.99 and very small root mean square error. The proposed integrated learning model achieves fast and accurate prediction of GAAFET electrical characteristics, which provides a new idea for device and circuit simulation and characteristics prediction in microelectronics.