Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 28, 2026

Focused Ion Beam Lithography to Etch Nano-architectures into Microelectrodes
13:49

Focused Ion Beam Lithography to Etch Nano-architectures into Microelectrodes

Published on: January 19, 2020

EPreNet: A Condition-Guided Network Accelerates Etching Profile Prediction.

Mengjiao Lu1,2, Zerui Jin3, Wanjun Wang1,2

  • 1School of Computer and Software Engineering, Anhui Institute of Information Technology, Wuhu 241199, China.

Micromachines
|May 27, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

VMESR: Variable Mamba-Enhanced Super-Resolution for Real-Time Road Scene Understanding with Automotive Vision Sensors.

Sensors (Basel, Switzerland)·2026
Same author

Hydrogen promoted mitochondrial autophagy and alleviated CIH-induced vascular endothelial cell senescence by regulating oxidative stress.

European journal of pharmacology·2025
Same author

Response of Patch Characteristics of <i>Carex alatauensis</i> S. R. Zhang to Establishment Age in Artificial Grasslands on the Qinghai-Tibet Plateau, China.

Plants (Basel, Switzerland)·2025
Same author

Mitochondrial DNA-Mediated Intercellular Communication via Extracellular Vesicles Under Hypoxic Stress to Drive HCC Progression.

Cancer science·2025
Same author

Advances in research on severe fever with thrombocytopenia syndrome virus.

Frontiers in microbiology·2025
Same author

Effects of various thermal processing methods on the gel properties of hulless barley β-glucan.

Food chemistry·2025

We developed EPreNet, a novel AI model for predicting plasma etching profiles in semiconductor manufacturing. This tool significantly accelerates process simulation, offering high accuracy and geometric fidelity.

Area of Science:

  • Materials Science
  • Computer Science
  • Chemical Engineering

Background:

  • Plasma etching is crucial for semiconductor fabrication.
  • Current methods for predicting etching profiles are computationally intensive or lack detailed accuracy.
  • Predicting the full profile evolution, not just scalar metrics, is essential for process optimization.

Purpose of the Study:

  • To introduce EPreNet, a condition-guided spatio-temporal network for accurate plasma etching profile prediction.
  • To develop a computationally efficient surrogate model for TCAD simulations.
  • To enable rapid evaluation and exploration of plasma etching processes.

Main Methods:

  • Developed EPreNet, a pixel-level prediction network using historical profile frames and process parameters.
Keywords:
TCAD simulationetching profile predictionplasma etchingsemiconductor manufacturingspatio-temporal modeling

More Related Videos

Precision Milling of Carbon Nanotube Forests Using Low Pressure Scanning Electron Microscopy
08:10

Precision Milling of Carbon Nanotube Forests Using Low Pressure Scanning Electron Microscopy

Published on: February 5, 2017

A Novel Method for In Situ Electromechanical Characterization of Nanoscale Specimens
07:15

A Novel Method for In Situ Electromechanical Characterization of Nanoscale Specimens

Published on: June 2, 2017

Related Experiment Videos

Last Updated: May 28, 2026

Focused Ion Beam Lithography to Etch Nano-architectures into Microelectrodes
13:49

Focused Ion Beam Lithography to Etch Nano-architectures into Microelectrodes

Published on: January 19, 2020

Precision Milling of Carbon Nanotube Forests Using Low Pressure Scanning Electron Microscopy
08:10

Precision Milling of Carbon Nanotube Forests Using Low Pressure Scanning Electron Microscopy

Published on: February 5, 2017

A Novel Method for In Situ Electromechanical Characterization of Nanoscale Specimens
07:15

A Novel Method for In Situ Electromechanical Characterization of Nanoscale Specimens

Published on: June 2, 2017

  • Created a benchmark dataset with 18,360 images from 918 TCAD-simulated process conditions.
  • Established an evaluation framework with image-level and geometry-based metrics.

    • Main Results:

    • EPreNet achieved a 16% reduction in Mean Squared Error (MSE).
    • High image quality metrics (SSIM 0.992, PSNR 30.323 dB) were obtained.
    • Excellent geometric accuracy was demonstrated with 1.4° sidewall angle error and 1.6% depth error.

    Conclusions:

    • EPreNet offers a significant speedup (38.92 ms/frame vs. 1300s for TCAD), enabling accelerated process development.
    • The model demonstrates strong generalization to new initial conditions and potential transferability to experimental SEM images.
    • EPreNet serves as an efficient, high-fidelity surrogate for TCAD-assisted semiconductor manufacturing process development.