【Device Papers】Ga₂O₃ TCAD Mobility Parameter Calibration Using Simulation Augmented Machine Learning With Physics-Informed Neural Network

      Researchers from the San Jose State University have published a dissertation titled "Ga₂O₃ TCAD Mobility Parameter Calibration Using Simulation Augmented Machine Learning With Physics-Informed Neural Network" in IEEE Transactions on Electron Devices.

Abstract

      In this article, we demonstrate the feasibility of performing automatic technology computer-aided-design (TCAD) parameter calibration and extraction using machine learning (ML), with the machine trained solely by TCAD-simulation data. The methodology is validated using experimental data. Schottky barrier diodes (SBDs) with different effective anode workfunctions (WF) are fabricated with emerging ultrawide bandgap material, Gallium Oxide (Ga₂O₃), and are measured at various temperatures (T). Their current-voltage (I–V) curves are used for automatic Ga₂O₃ Philips unified mobility (PhuMob) model parameters calibration. Five critical PhuMob parameters (μ_max,μ_min,N_ref,α, and θ) were calibrated. The machine consists of an autoencoder (AE) and a neural network (NN) and is trained solely by TCAD simulation data with variations in WF, T, and the five PhuMob parameters (seven variations in total). Then, Ga₂O₃ PhuMob parameters are extracted from the noisy experimental curves. Subsequent TCAD simulation using the extracted parameters shows that the quality of the parameters is as good as an expert’s calibration at the preturned-on regime, but not in the on-state regime. By using a simple physics-informed NN (PINN), the machine performs as well as the human expert in all regimes.

DOI：

https://doi.org/10.1109/TED.2025.3648986