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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Fast inverse lithography approach based on a model-driven graph convolutional network.

Optics express·2023
Same author

AEMDA: inferring miRNA-disease associations based on deep autoencoder.

Bioinformatics (Oxford, England)·2020
Same author

Mutation analysis, treatment and prenatal diagnosis of Chinese cases of methylmalonic acidemia.

Scientific reports·2020
Same author

[Progress on Mechanism of MET Gene Mutation and Targeted Drugs in Non-small Cell Lung Cancer].

Zhongguo fei ai za zhi = Chinese journal of lung cancer·2020
Same author

Fast inverse lithography based on dual-channel model-driven deep learning.

Optics express·2020
Same author

Oxidative stress response associates with the teratogenic effects of benzyl butyl phthalate (BBP).

Toxicology research·2020

Related Experiment Video

Updated: Jul 22, 2025

Pattern Generation for Micropattern Traction Microscopy
09:26

Pattern Generation for Micropattern Traction Microscopy

Published on: February 17, 2022

2.3K

Fast diffraction model of lithography mask based on improved pixel-to-pixel generative adversarial network.

Junbi Zhang, Xu Ma

    Optics Express
    |July 21, 2023
    PubMed
    Summary

    This study introduces a fast and accurate AI method to calculate mask diffraction near-field (DNF) for extreme ultraviolet (EUV) lithography. The new approach significantly speeds up calculations while maintaining high accuracy, overcoming computational burdens.

    More Related Videos

    Fabrication of Micropatterned Hydrogels for Neural Culture Systems using Dynamic Mask Projection Photolithography
    16:06

    Fabrication of Micropatterned Hydrogels for Neural Culture Systems using Dynamic Mask Projection Photolithography

    Published on: February 11, 2011

    18.9K
    Design and Development of a Three-Dimensionally Printed Microscope Mask Alignment Adapter for the Fabrication of Multilayer Microfluidic Devices
    06:21

    Design and Development of a Three-Dimensionally Printed Microscope Mask Alignment Adapter for the Fabrication of Multilayer Microfluidic Devices

    Published on: January 25, 2021

    2.9K

    Related Experiment Videos

    Last Updated: Jul 22, 2025

    Pattern Generation for Micropattern Traction Microscopy
    09:26

    Pattern Generation for Micropattern Traction Microscopy

    Published on: February 17, 2022

    2.3K
    Fabrication of Micropatterned Hydrogels for Neural Culture Systems using Dynamic Mask Projection Photolithography
    16:06

    Fabrication of Micropatterned Hydrogels for Neural Culture Systems using Dynamic Mask Projection Photolithography

    Published on: February 11, 2011

    18.9K
    Design and Development of a Three-Dimensionally Printed Microscope Mask Alignment Adapter for the Fabrication of Multilayer Microfluidic Devices
    06:21

    Design and Development of a Three-Dimensionally Printed Microscope Mask Alignment Adapter for the Fabrication of Multilayer Microfluidic Devices

    Published on: January 25, 2021

    2.9K

    Area of Science:

    • Semiconductor Manufacturing
    • Computational Physics
    • Optics and Photonics

    Background:

    • The three-dimensional (3D) mask effect is critical for imaging performance in advanced extreme ultraviolet (EUV) lithography.
    • Rigorous 3D mask diffraction modeling presents significant computational challenges and time constraints.

    Purpose of the Study:

    • To develop a computationally efficient and accurate method for calculating the mask diffraction near-field (DNF).
    • To address the limitations of traditional, time-consuming 3D mask diffraction models in EUV lithography.

    Main Methods:

    • An improved pixel-to-pixel generative adversarial network (GAN) was developed for DNF calculation.
    • Deformable convolution was incorporated into the GAN to model crosstalk effects between mask feature edges.
    • A long short-term memory (LSTM) model was integrated into the generator to enhance information fusion between real and imaginary parts of DNF matrices.
    • Subpixel super-resolution was employed during the up-sampling stage to improve simulation accuracy.

    Main Results:

    • The developed method achieved over 50% improvement in calculation accuracy compared to traditional neural networks.
    • Computational efficiency was enhanced by 128-fold compared to rigorous electromagnetic field simulation methods.
    • The integration of deformable convolution and LSTM effectively handled mask feature edge complexities and DNF matrix data.

    Conclusions:

    • The proposed AI-based method offers a significant advancement in calculating EUV lithography mask diffraction near-fields.
    • This approach provides a viable solution for reducing computational burden without sacrificing accuracy in advanced lithography simulations.
    • The enhanced GAN model demonstrates potential for broader applications in computational lithography and optical modeling.