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

Linear Differential Equations01:27

Linear Differential Equations

262
The integrating factor method provides a systematic way to solve first-order linear differential equations, especially those that cannot be handled by separation of variables. This method is particularly useful in modeling time-dependent physical systems influenced by both constant inputs and resistive forces. A common example is the motion of a car subjected to a constant engine force while experiencing air resistance proportional to its velocity.In such scenarios, Newton’s second law...
262
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

433
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
433
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

415
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
415
Modeling with Differential Equations01:25

Modeling with Differential Equations

294
Population dynamics can be described mathematically by considering the population size P(t) as a function of time. The rate of change of the population is then represented by the derivative of P(t). A simple assumption is that the rate of growth is proportional to the size of the population itself. This leads to an exponential growth model, where the population increases rapidly without bound. While this is a useful first approximation, it does not reflect realistic long-term...
294
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

457
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
457
Newton’s Method01:30

Newton’s Method

185
Newton’s Method is a powerful iterative technique for approximating the roots of real-valued, differentiable functions, particularly when analytical solutions are impractical. This approach is widely used in scientific computing, engineering, and finance, where equations may be too complex for traditional algebraic methods to handle. The method relies on an iterative process that refines an initial estimate using the function’s derivative to approach the true solution progressively.
185

You might also read

Related Articles

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

Sort by
Same author

Isolation and characterisation of virulent bacteriophage targeting canola rhizosphere bacteria Klebsiella grimontii and Bacillus sp.

Virology·2026
Same author

Active cooling device: A flexible, lab-scale experimental unit to develop spatio-temporal temperature control strategies.

HardwareX·2026
Same author

Kirigami-inspired parachutes with programmable reconfiguration.

Nature·2025
Same author

Mechanical interactions between tissue layers underlie plant morphogenesis.

Nature plants·2025
Same author

Co-Existence Slows Diversification in Experimental Populations of E. coli and P. fluorescens.

Environmental microbiology·2025
Same author

Evolutionary shift of a tipping point can precipitate, or forestall, collapse in a microbial community.

Nature ecology & evolution·2024

Related Experiment Video

Updated: Apr 20, 2026

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

2.3K

The finite element neural network method to simulate two dimensional partial differential equations and perform

Mohammed Abda1, Lucas Berthet1, Mohsen Hamedi1

  • 1Laboratory for Multi-scale Mechanics (LM2) of the Department of Mechanical Engineering, Polytechnique Montréal, Montréal, Canada.

Scientific Reports
|April 18, 2026
PubMed
Summary

The novel Finite Element Neural Network Method (FENNM) merges neural networks with finite elements for solving partial differential equations (PDEs). FENNM enhances training stability and adaptability for complex engineering problems.

More Related Videos

Lumped-Parameter and Finite Element Modeling of Heart Failure with Preserved Ejection Fraction
09:20

Lumped-Parameter and Finite Element Modeling of Heart Failure with Preserved Ejection Fraction

Published on: February 13, 2021

7.2K
A Modeling and Simulation Method for Preliminary Design of an Electro-Variable Displacement Pump
09:04

A Modeling and Simulation Method for Preliminary Design of an Electro-Variable Displacement Pump

Published on: June 1, 2022

3.8K

Related Experiment Videos

Last Updated: Apr 20, 2026

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

2.3K
Lumped-Parameter and Finite Element Modeling of Heart Failure with Preserved Ejection Fraction
09:20

Lumped-Parameter and Finite Element Modeling of Heart Failure with Preserved Ejection Fraction

Published on: February 13, 2021

7.2K
A Modeling and Simulation Method for Preliminary Design of an Electro-Variable Displacement Pump
09:04

A Modeling and Simulation Method for Preliminary Design of an Electro-Variable Displacement Pump

Published on: June 1, 2022

3.8K

Area of Science:

  • Computational Engineering and Applied Mathematics
  • Artificial Intelligence in Scientific Computing

Background:

  • Neural networks (NNs) offer powerful data assimilation for complex systems.
  • Classical numerical methods like finite elements provide benchmark accuracy and reliability.
  • Physics-informed neural networks (PINNs) integrate physical laws into NNs for solving PDEs.

Purpose of the Study:

  • To introduce the Finite Element Neural Network Method (FENNM) for approximating partial differential equations (PDEs).
  • To enhance the capabilities of PINNs by integrating them with the finite element framework.
  • To improve training stability and adaptability for real-world engineering applications.

Main Methods:

  • FENNM utilizes a Petrov-Galerkin framework, with NNs providing the solution space and Lagrange shape functions as test functions.
  • The weak-form formulation explicitly incorporates flux terms at element interfaces.
  • Neumann boundary conditions are naturally integrated into the residual loss function.

Main Results:

  • FENNM demonstrates improved training stability and adaptability compared to existing PINN variants (VPINN, hp-VPINN, cv-PINN, FastVPINN).
  • The method is extended to 2D domains, accommodating space, time, or parameter dimensions.
  • FENNM showcases capabilities in local mesh refinement, handling vector-valued PDEs, inverse problems, and complex geometries.

Conclusions:

  • FENNM offers a robust and versatile approach for solving PDEs, merging the strengths of NNs and finite elements.
  • The method provides advantages for design optimization and handling complex physical phenomena.
  • FENNM represents a significant advancement in the application of neural networks for scientific and engineering challenges.