OFET Informatics: Observing the impact of organic transistor's design parameters on the device output performance using a machine learning algorithm

Organic field effect transistors (OFETs), used in the fabrication of nano-sensors, are one of the most promising devices in organic electronics because of their lightweight, flexible, and low fabrication cost. However, the numerical modeling of such OFETs is still in an early stage due to the minimal analytical as well as numerical models presented in the literature. This research aims to demonstrate an experimentally verified machine-learning model by investigating an OFET with polyaniline as a p-type organic semiconductor. OFET's threshold voltage, on/off current ratio, subthreshold swing, and device mobilities are studied as the primary output chiasmatic parameters. The random-forest machine learning model has shown the criticality of the doping effect on turning the OFET to depletion mode, with positive threshold voltage, under doping higher than 5x10(14) cm(-3). Additionally, the study highlights the effectiveness of the gate oxide thickness in controlling the OFET threshold voltage. A 50 nm oxide thickness showed sufficiency to have a non-depleted OFET operation.