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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

98
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...
98
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.8K
Ampere-Maxwell's Law: Problem-Solving01:17

Ampere-Maxwell's Law: Problem-Solving

728
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
728
Maxwell-Boltzmann Distribution: Problem Solving01:20

Maxwell-Boltzmann Distribution: Problem Solving

1.7K
Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
1.7K
Mechanistic Models: Overview of Compartment Models01:21

Mechanistic Models: Overview of Compartment Models

143
Mechanistic models, a category encompassing both physiological and compartmental modeling, differ from empirical models' approaches to incorporating known factors about the systems being modeled. Empirical models describe data with minimal assumptions, while mechanistic models aim to provide a robust description of available data by specifying assumptions and integrating known factors about the system. Compartmental analysis is a key example of a mechanistic model in pharmacokinetics and...
143
Typical Model Studies01:30

Typical Model Studies

425
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.
425

You might also read

Related Articles

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

Sort by
Same author

Simulation-assisted multimodal deep learning (Sim-MDL) fusion models for the evaluation of thermal barrier coatings using infrared thermography and Terahertz imaging.

Scientific reports·2025
Same author

Development of bulk wave EMAT sensors with enhanced Lorentz force through magnetic field concentration in eddy current regions.

Ultrasonics·2025
Same author

An experimental investigation on the combined effect of plastic deformation and grain size variation on the acoustic nonlinearity parameter.

The Review of scientific instruments·2023
Same author

Smart Graphene Nanoplatelet Strain Sensor for Natural Frequency Sensing of Stainless Steel (SS304) and Human Health Monitoring.

Materials (Basel, Switzerland)·2022
Same author

DPAI: A Data-driven simulation-assisted-Physics learned AI model for transient ultrasonic wave propagation.

Ultrasonics·2022
Same author

Observing dual-mode second-harmonic generation in an isotropic nonlinear elastic plate.

Ultrasonics·2021
Same journal

CFREE-uPIV: A contrast-free resolution-enhanced ultrasound particle image velocimetry for rapid microvascular flow imaging.

Ultrasonics·2026
Same journal

Ultrasonic-induced nucleation kinetics in directed energy deposition.

Ultrasonics·2026
Same journal

Grain size evaluation in polycrystalline materials using the interference effect of bounded ultrasonic beams at the Rayleigh critical angle.

Ultrasonics·2026
Same journal

Ultrasonic characterization of functionally graded materials using a continuously graded model and spectral inversion.

Ultrasonics·2026
Same journal

Frequency-wavenumber domain inversion for arterial viscoelasticity.

Ultrasonics·2026
Same journal

Pressure- and frequency-dependent acoustic behavior of second-generation acoustic reporter genes-expressing bacteria for optimized ultrasound imaging.

Ultrasonics·2026
See all related articles

Related Experiment Video

Updated: Aug 24, 2025

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption
10:36

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption

Published on: November 3, 2023

1.7K

Optimizing hyperparameters of Data-driven simulation-assisted-Physics learned AI (DPAI) model to reduce compounding

Thulsiram Gantala1, Krishnan Balasubramaniam1

  • 1Centre for Non-Destructive Evaluation, Department of Mechanical Engineering, Indian Institute of Technology Madras, Chennai, 600036, India.

Ultrasonics
|October 21, 2022
PubMed
Summary
This summary is machine-generated.

Optimizing hyperparameters for the Data-driven simulation-assisted-Physics learned AI (DPAI) model reduced errors in simulating ultrasonic wave propagation. This AI approach accurately models deeper wave phenomena with lower compounding error.

Keywords:
Convolutional LSTMDeep learningError propagationFinite elementUltrasonic wave propagation

More Related Videos

Design and Optimization Strategies of a High-Performance Vented Box
14:23

Design and Optimization Strategies of a High-Performance Vented Box

Published on: June 9, 2023

1.2K
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

3.2K

Related Experiment Videos

Last Updated: Aug 24, 2025

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption
10:36

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption

Published on: November 3, 2023

1.7K
Design and Optimization Strategies of a High-Performance Vented Box
14:23

Design and Optimization Strategies of a High-Performance Vented Box

Published on: June 9, 2023

1.2K
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

3.2K

Area of Science:

  • Computational Physics
  • Artificial Intelligence in Engineering
  • Wave Propagation Modeling

Background:

  • Simulating ultrasonic wave propagation is crucial for various engineering applications.
  • Traditional methods like finite element (FE) simulations can be computationally intensive, especially for extended depths.
  • Data-driven approaches offer a potential alternative for efficient and accurate wave propagation modeling.

Purpose of the Study:

  • To optimize hyperparameters of a deep learning Data-driven simulation-assisted-Physics learned AI (DPAI) model.
  • To enhance the accuracy of simulating ultrasonic wave propagation for extended depths.
  • To reduce the compounding error in AI-based wave propagation simulations.

Main Methods:

  • Developed a DPAI model with an encoder-decoder structure and modified convolutional long short-term memory (ConvLSTM) layers.
  • Trained the DPAI model using a dataset from finite element (FE) simulations of ultrasonic wave propagation.
  • Investigated six different hyperparameter combinations (hidden dimensions, kernel size, batch size) for model optimization.

Main Results:

  • Optimized DPAI models demonstrated reduced compounding error in simulating deeper wave propagation scenarios.
  • The model effectively captured wave propagation from both single-point and multi-point excitation sources.
  • Achieved a maximum Mean Absolute Error (MAE) of 5.0×10-2 on amplitude and 2.64% Mean Absolute Percentage Error (MAPE) on time of flight (TOF) compared to FE simulations.

Conclusions:

  • Hyperparameter optimization is effective in improving the accuracy of DPAI models for ultrasonic wave propagation.
  • The DPAI model provides a data-driven approach to understanding the physics of elastodynamic wave propagation.
  • The optimized DPAI model shows significant potential for accurate and efficient simulation of complex wave phenomena.