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 16, 2026

Laser-induced Forward Transfer of Ag Nanopaste
08:07

Laser-induced Forward Transfer of Ag Nanopaste

Published on: March 31, 2016

Deep-Learning Inversion Maps Arbitrary Design Images to Low-Cost, Efficient Nanofabrication.

Jinglan Zhang1, Xinyi Chen1, Anh Tu Ngo2

  • 1School of Microelectronics and Communication Engineering, Chongqing Key Laboratory of Bio-Perception & Intelligent Information Processing, Chongqing University, Chongqing 401331, P. R. China.

ACS Nano
|May 14, 2026
PubMed
Summary

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

A case of <i>CDC73</i> mutation-related primary hyperparathyroidism with ectopic parathyroid hyperplasia.

Proceedings (Baylor University. Medical Center)·2026
Same author

Targeting POLRMT-driven epigenetic remodeling of Wnt/β-catenin to eradicate colorectal cancer stem cell proliferation.

Cell death and differentiation·2026
Same author

High-flow nasal cannula oxygen versus Venturi facemask in women with cardiovascular disease undergoing cesarean delivery under neuraxial anesthesia: a randomized controlled trial.

Journal of thoracic disease·2026
Same author

Twin-Boundary Cu<sub>2</sub>-Pair Pockets Drive Spatial Proximity of Key Intermediates for Efficient Urea Electrosynthesis.

Angewandte Chemie (International ed. in English)·2026
Same author

Coronamicroparticle Arrays with Stable Superamphiphobicity.

Small methods·2026
Same author

Effects of Chlorogenic Acid on Deoxynivalenol (DON)-Induced Ferroptosis in Porcine Alveolar Macrophages.

Toxins·2026

Deep learning accelerates nanoscale pattern fabrication using shadow sphere lithography (SSL). This AI-driven approach translates desired nanostructures into precise fabrication recipes, enabling rapid, cost-effective prototyping for advanced technologies.

Area of Science:

  • Materials Science
  • Nanotechnology
  • Artificial Intelligence

Background:

  • Nanoscale patterning is crucial for energy, biomedical, and information technologies.
  • Traditional lithography methods are expensive, and self-assembly lacks design flexibility.
  • Shadow Sphere Lithography (SSL) offers wafer-scale patterning but requires extensive trial-and-error for parameter optimization.

Purpose of the Study:

  • To develop an automated, deep learning-based framework for translating desired nanoscale patterns into fabrication recipes for SSL.
  • To overcome the limitations of manual parameter tuning in SSL, reducing cost and time.

Main Methods:

  • Reformulated the image-to-recipe translation problem for SSL as a deep learning task.
  • Generated over 4.5 million synthetic patterns and parameter pairs using analytic shadow projection equations.
Keywords:
Attention MechanismDeep LearningInverse DesignNanofabricationShadow Sphere Lithography

More Related Videos

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

Related Experiment Videos

Last Updated: May 16, 2026

Laser-induced Forward Transfer of Ag Nanopaste
08:07

Laser-induced Forward Transfer of Ag Nanopaste

Published on: March 31, 2016

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

  • Trained a bidirectional convolutional block attention network with a redesigned loss function.

    • Main Results:

    • The deep learning model achieved 91% parameter accuracy and a Pearson correlation of 0.95 ± 0.01 for unseen designs.
    • The framework generates a full fabrication recipe in under one second on a consumer GPU.
    • A deployed web application successfully guided the fabrication of diverse nanoscale patterns.

    Conclusions:

    • The developed AI framework significantly accelerates and democratizes nanoscale pattern fabrication using SSL.
    • It transforms a weeks-long, high-cost workflow into an automated, one-click operation.
    • Enables fast, on-demand, and cost-efficient nanomanufacturing for diverse applications.