Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Electrostatic Boundary Conditions

Electrostatic Boundary Conditions

Consider an external electric field propagating through a homogeneous medium. When the electric field crosses the surface boundary of the medium, it undergoes a discontinuity. The electric field can be resolved into normal and tangential components. The amount by which the field changes at any boundary is given by the difference between the field components above and below the surface boundary.
The surface integral of an electric field is given by Gauss's law in integral form and is related to...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Variable Resistance Training Improves Velocity and Power Output by Reducing Concentric Deceleration in the Back Squat.

Journal of strength and conditioning research·2026

Same author

"Autism Diagnosis as a Guide": Taiwanese Adolescents' Own Experiences of Receiving Autism Diagnoses.

Autism : the international journal of research and practice·2026

Same author

Parallel micro- and mesophase transitions of thermoplastic polyurethane induced by thermal annealing.

Soft matter·2026

Same author

Endurance Paradox in Hafnium-Oxide-Based Silicon-Channel Ferroelectric Transistors.

ACS applied materials & interfaces·2026

Same author

Vertically stacked immobilized photocatalyst devices towards land-efficient solar hydrogen production.

Nature communications·2026

Same author

Rare case of recurrent respiratory papillomatosis with malignant transformation.

SAGE open medical case reports·2026

Search research articles

Related Experiment Video

Updated: Jun 29, 2025

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

Using U-Net convolutional neural network to model pixel-based electrostatic potential distributions in GaN power

Bang-Ren Chen¹, Yu-Sheng Hsiao², Wei-Cheng Lin¹

¹International College of Semiconductor Technology, National Yang Ming Chiao Tung University, Hsinchu, Taiwan.

Scientific Reports

|April 8, 2024

Summary

This study uses a U-Net convolutional neural network (CNN) to accurately model electrostatic potential in Gallium Nitride (GaN) power devices. This AI approach significantly speeds up simulations for advanced GaN metal-insulator-semiconductor high-electron mobility transistors (MIS-HEMTs).

Keywords:

Electrostatic potential modeling GaN HEMT Machine learning U-Net

More Related Videos

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

Published on: November 26, 2016

Finite Element Modelling of a Cellular Electric Microenvironment

Finite Element Modelling of a Cellular Electric Microenvironment

Published on: May 18, 2021

Related Experiment Videos

Last Updated: Jun 29, 2025

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

High-density Electroencephalographic Acquisition in a Rodent Model Using Low-cost and Open-source Resources

Published on: November 26, 2016

Finite Element Modelling of a Cellular Electric Microenvironment

Finite Element Modelling of a Cellular Electric Microenvironment

Published on: May 18, 2021

Area of Science:

Materials Science
Electrical Engineering
Artificial Intelligence

Background:

Gallium Nitride (GaN) power devices, specifically Metal-Insulator-Semiconductor High-Electron Mobility Transistors (MIS-HEMTs), are crucial for high-power applications.
Accurate modeling of electrostatic potential distributions is essential for optimizing device performance and reliability.
Traditional simulation methods can be computationally intensive and time-consuming.

Purpose of the Study:

To introduce and evaluate a novel application of the U-Net convolutional neural network (CNN) for pixel-based electrostatic potential modeling.
To assess the accuracy and efficiency of the U-Net CNN in simulating potential distributions in GaN MIS-HEMTs.
To explore the potential of U-Net CNN for rapid characterization of GaN power devices.

Main Methods:

Development of a U-Net convolutional neural network (CNN) architecture.
Training the U-Net CNN using data from Technology Computer-Aided Design (TCAD) simulations of GaN MIS-HEMTs.
Validation of the U-Net CNN model against TCAD-simulated electrostatic potential distributions under varying device designs and drain voltages.

Main Results:

The U-Net CNN successfully modeled pixel-based electrostatic potential distributions with an accuracy of less than 1% error compared to TCAD simulations.
The developed U-Net CNN achieved a modeling time of approximately 80 milliseconds for potential distributions.
The model demonstrated robustness across different gate/source field plate designs and drain voltages.

Conclusions:

The U-Net CNN presents a highly efficient and accurate method for modeling electrostatic potential distributions in GaN power devices.
This AI-driven approach offers significant advantages in simulation speed for GaN MIS-HEMTs.
The U-Net CNN is a promising tool for accelerating the design and optimization of next-generation GaN power electronics.