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 Videos

Deep Learning for Flow Sculpting: Insights into Efficient Learning using Scientific Simulation Data.

Daniel Stoecklein1, Kin Gwn Lore1, Michael Davies1

  • 1Iowa State University, Mechanical Engineering, Ames, 50011, USA.

Scientific Reports
|April 13, 2017
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

Dual-degenerate TCRs target multiple KRAS hotspot and HLA-A3 family combinations.

Research square·2026
Same author

Congenital Heart Defects, Special Needs, and Developmental Vulnerability in Singleton Children at School Age: A Population-Based Data Linkage Study.

Journal of the American Heart Association·2026
Same author

When Timing Matters: Evaluating Temporal Leakage in Machine Learning Models of Football Pass Turnovers.

Research quarterly for exercise and sport·2026
Same author

In-context adaptation of VLMs for few-shot cell detection in optical microscopy.

Frontiers in artificial intelligence·2026
Same author

Steroid-responsive delayed multifocal encephalopathy following vasculotoxic snakebite with serial MRI evolution: a case report.

Toxicon : official journal of the International Society on Toxinology·2026
Same author

Large-scale association study identifies lung cancer susceptibility copy number variants and their potential functional role in genetic instability.

medRxiv : the preprint server for health sciences·2026
Same journal

Correction: A method for supervoxel-wise association studies of age and other non-imaging variables from coronary computed tomography angiograms.

Scientific reports·2026
Same journal

Poly(bromophenol blue)/CoSn(OH)<sub>6</sub> cubic particles modified pencil graphite electrode for electrochemical determination of diphenhydramine.

Scientific reports·2026
Same journal

Dietary Chlorella, Spirulina, and acidifier modulate jejunal cytokine-related gene expression in broiler chickens.

Scientific reports·2026
Same journal

Perceived physical activity barriers in university students: associations with fatigue and eating behaviours.

Scientific reports·2026
Same journal

Refuge limitation structures habitat use in agricultural landscapes: evidence from Sunda pangolins.

Scientific reports·2026
Same journal

Lightweight stateless transaction verification with outsourced witness updates for UTXO blockchains.

Scientific reports·2026
See all related articles

Deep learning offers a faster solution for designing microfluidic flow sculpting devices. This approach overcomes limitations of current methods, enabling efficient control of fluid flow for research and manufacturing.

Area of Science:

  • Microfluidics
  • Computational Science
  • Applied Physics

Background:

  • Flow sculpting enables precise passive control of microfluidic flows, crucial for microscale manufacturing, biology, and chemistry.
  • Designing flow sculpting devices involves solving an inverse problem, which is challenging due to a complex, many-to-one design space and reliance on user intuition.

Purpose of the Study:

  • To investigate the efficacy of deep learning methods in solving the inverse design problem for flow sculpting devices.
  • To demonstrate that deep learning can outperform traditional methods in speed and design quality for scientific inverse problems.

Main Methods:

  • Utilizing deep learning as a function approximation technique for high-dimensional design spaces.
  • Implementing intelligent sampling strategies to optimize the accuracy and efficiency of deep learning models.

Related Experiment Videos

  • Evaluating the generalization capability of deep learning models for predicting out-of-sample designs.

    • Main Results:

    • Deep learning methods show potential to significantly accelerate the design process compared to existing approaches.
    • Intelligent sampling enhances the accuracy of deep learning models, making them competitive with traditional methods.
    • The study demonstrates the generalization ability of deep learning for novel flow sculpting device designs.

    Conclusions:

    • Deep learning presents a powerful and efficient solution for the inverse design problem in flow sculpting.
    • This approach can reduce the time and resources required for designing microfluidic devices.
    • Further exploration of deep learning in scientific inverse problems is warranted.