Physics-Informed Neural Network for Predicting Out-of-Training-Range TCAD Solution with Minimized Domain Expertise
Publication Date
1-1-2025
Document Type
Conference Proceeding
Publication Title
9th IEEE Electron Devices Technology and Manufacturing Conference Shaping the Future with Innovations in Devices and Manufacturing Edtm 2025
DOI
10.1109/EDTM61175.2025.11040268
Abstract
In this paper, a Si nanowire transistor is used to demonstrate the possibility of using a physics-informed neural network to predict out-of-training-range TCAD solutions without accessing internal solvers and with minimal domain expertise. The machine can predict a 10 times larger range than the training data and also predict the inversion region behavior with only subthreshold region training data. The physics-informed module is trained without human-coded differential equations making this extendable to more sophisticated systems.
Funding Number
2046220
Funding Sponsor
National Science Foundation
Keywords
ML, Nanowire, Out-of-training-range prediction, Physics Informed Neural Networks (PINN), TCAD
Department
Electrical Engineering
Recommended Citation
Albert Lu, Yu Foon Chau, and Hiu Yung Wong. "Physics-Informed Neural Network for Predicting Out-of-Training-Range TCAD Solution with Minimized Domain Expertise" 9th IEEE Electron Devices Technology and Manufacturing Conference Shaping the Future with Innovations in Devices and Manufacturing Edtm 2025 (2025). https://doi.org/10.1109/EDTM61175.2025.11040268
