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

Typical Model Studies01:30

Typical Model Studies

344
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
344
Uniform Depth Channel Flow01:27

Uniform Depth Channel Flow

63
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
63
Rapidly Varying Flow01:24

Rapidly Varying Flow

56
Rapidly varying flow (RVF) in open channels is characterized by abrupt changes in flow depth over a short distance, with the rate of depth change relative to distance often approaching unity. These flows are inherently complex due to their transient and multi-dimensional nature, making exact analysis difficult. However, approximate solutions using simplified models provide valuable insights into their behavior.Key Features of Rapidly Varying FlowRVF is commonly observed in scenarios involving...
56
Design Example: Creating a Hydraulic Model of a Dam Spillway01:21

Design Example: Creating a Hydraulic Model of a Dam Spillway

135
Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.
135
Gradually Varying Flow01:29

Gradually Varying Flow

36
Gradually varying flow (GVF) in open channels describes situations where water depth changes slowly along the channel due to factors like non-uniform bed slope, channel shape variations, or obstructions. This flow type occurs when the depth adjusts gradually to balance gravitational forces, shear forces, and energy requirements, resulting in a low rate of depth change.Characteristics of Gradually Varying FlowGVF is commonly observed in natural streams, rivers, and canals, where flow depth...
36
Introduction to Types of Flows01:23

Introduction to Types of Flows

964
Fluid flows are categorized by dimensionality and behavior, with one-dimensional flow being the simplest form, where properties like velocity and pressure change only along a single axis. Water moving through straight pipes exemplifies this flow type, as variations in other directions are minimal. One-dimensional analysis helps simplify understanding such flows, focusing solely on changes along the pipe's length.
Two-dimensional flow involves changes in both length and height, as seen in...
964

You might also read

Related Articles

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

Sort by
Same author

A Comparative Analysis of Explainable AI (XAI) Techniques for Transparent and Reliable Image Classification.

Entropy (Basel, Switzerland)·2026
Same author

Interpretable Machine Learning to Understand Wildfire Toxicity: Bridging Chemicals, Omics, and Toxicological Outcomes via Symbolic Regression with Novel Feature Scoring.

Chemical research in toxicology·2026
Same author

PMMoTo: A Porous Media Morphology and Topology Toolkit.

Journal of open source software·2026
Same author

Thermodynamically Constrained Averaging Theory: Why Bother?

ARC geophysical research·2025
Same author

A survey on deep learning for drug-target binding prediction: models, benchmarks, evaluation, and case studies.

Briefings in bioinformatics·2025
Same author

Temporal fluctuations of non-equilibrium water accessible pathways in polyamide reverse osmosis active layers.

Journal of membrane science letters·2025

Related Experiment Video

Updated: Jun 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

483

A scalable convolutional neural network approach to fluid flow prediction in complex environments.

Pratip Rana1, Timothy M Weigand2,3, Kevin R Pilkiewicz3

  • 1Bennett Aerospace, Vicksburg, 39180, USA.

Scientific Reports
|October 4, 2024
PubMed
Summary

Convolutional neural networks (CNNs) can predict fluid flow velocity fields. A novel domain decomposition method enhances efficiency for complex obstacle configurations in computational fluid dynamics (CFD).

Keywords:
Computational fluid dynamicsConvolutional neural networksDeep learning

More Related Videos

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature
09:39

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Published on: November 18, 2019

5.8K
Meso-Scale Particle Image Velocimetry Studies of Neurovascular Flows In Vitro
08:00

Meso-Scale Particle Image Velocimetry Studies of Neurovascular Flows In Vitro

Published on: December 3, 2018

8.3K

Related Experiment Videos

Last Updated: Jun 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

483
Spatial Temporal Analysis of Fieldwise Flow in Microvasculature
09:39

Spatial Temporal Analysis of Fieldwise Flow in Microvasculature

Published on: November 18, 2019

5.8K
Meso-Scale Particle Image Velocimetry Studies of Neurovascular Flows In Vitro
08:00

Meso-Scale Particle Image Velocimetry Studies of Neurovascular Flows In Vitro

Published on: December 3, 2018

8.3K

Area of Science:

  • Fluid dynamics
  • Computational fluid dynamics (CFD)
  • Machine learning
  • Deep learning

Background:

  • Accurate prediction of fluid flow velocity fields is crucial for many engineering applications.
  • Traditional computational fluid dynamics (CFD) methods can be computationally expensive, especially for complex geometries and large domains.
  • Deep learning models, specifically convolutional neural networks (CNNs), show promise in accelerating these predictions.

Purpose of the Study:

  • To evaluate the capability of CNNs in predicting velocity fields for fluid flow around obstacles.
  • To develop and assess a domain decomposition method for handling larger and more complex flow domains than those used in training.
  • To introduce a novel metric for domain decomposition and analyze error propagation.

Main Methods:

  • Utilized a gated residual U-Net architecture for CNN model.
  • Trained the network on velocity fields generated from CFD simulations.
  • Developed a piecewise, semicontinuous approach by decomposing domains into subdomains.
  • Introduced a local orientational vector field entropy (LOVE) metric for domain decomposition strategy.
  • Applied smoothness and continuity constraints for velocity field reconstruction.

Main Results:

  • The CNN model accurately predicts steady fluid flow velocity fields for unseen inlet speeds and obstacle configurations.
  • The proposed domain decomposition method offers a computationally efficient alternative to retraining models on larger datasets.
  • The LOVE metric effectively guides the decomposition of complex domains into weakly interacting subsets.
  • Error propagation was assessed across modeled domains of increasing size.

Conclusions:

  • CNNs are capable of accurately predicting fluid flow velocity fields.
  • The domain decomposition strategy significantly enhances computational efficiency for complex fluid flow problems.
  • The LOVE metric provides a robust method for optimizing domain decomposition in fluid dynamics.
  • This approach offers a promising pathway for efficient and accurate fluid flow prediction in real-world applications.