Scientific Machine Learning for Elastic and Acoustic Wave Propagation: Neural Operator and Physics-Guided Neural Network

Scientific machine learning (SciML) offers an emerging alternative to the traditional modeling approaches for wave propagation. These physics-based models rely on computationally demanding numerical techniques. However, SciML extends artificial neural network-based wave models with the capability of...

Full description

Saved in:
Bibliographic Details
Main Authors: Nafisa Mehtaj, Sourav Banerjee
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/12/3588
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849425994983669760
author Nafisa Mehtaj
Sourav Banerjee
author_facet Nafisa Mehtaj
Sourav Banerjee
author_sort Nafisa Mehtaj
collection DOAJ
description Scientific machine learning (SciML) offers an emerging alternative to the traditional modeling approaches for wave propagation. These physics-based models rely on computationally demanding numerical techniques. However, SciML extends artificial neural network-based wave models with the capability of learning wave physics. Contrary to the physics-intensive methods, particularly physics-informed neural networks (PINNs) presented earlier, this study presents data-driven frameworks of physics-guided neural networks (PgNNs) and neural operators (NOs). Unlike PINNs and PgNNs, which focus on specific PDEs with respective boundary conditions, NOs solve a family of PDEs and hold the potential to easily solve different boundary conditions. Hence, NOs provide a more generalized SciML approach. NOs extend neural networks to map between functions rather than vectors, enhancing their applicability. This review highlights the potential of NOs in wave propagation modeling, aiming to advance wave-based structural health monitoring (SHM). Through comparative analysis of existing NO algorithms applied across different engineering fields, this study demonstrates how NOs improve generalization, accelerate inference, and enhance scalability for practical wave modeling scenarios. Lastly, this article identifies current limitations and suggests promising directions for future research on NO-based methods within computational wave mechanics.
format Article
id doaj-art-6faa643d61fe44d4b9a20d2b55d79c05
institution Kabale University
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-6faa643d61fe44d4b9a20d2b55d79c052025-08-20T03:29:35ZengMDPI AGSensors1424-82202025-06-012512358810.3390/s25123588Scientific Machine Learning for Elastic and Acoustic Wave Propagation: Neural Operator and Physics-Guided Neural NetworkNafisa Mehtaj0Sourav Banerjee1Integrated Material Assessment and Predictive Simulation Laboratory (iMAPS), Department of Mechanical Engineering, Molinaroli College of Engineering and Computing, University of South Carolina, Columbia, SC 29201, USAIntegrated Material Assessment and Predictive Simulation Laboratory (iMAPS), Department of Mechanical Engineering, Molinaroli College of Engineering and Computing, University of South Carolina, Columbia, SC 29201, USAScientific machine learning (SciML) offers an emerging alternative to the traditional modeling approaches for wave propagation. These physics-based models rely on computationally demanding numerical techniques. However, SciML extends artificial neural network-based wave models with the capability of learning wave physics. Contrary to the physics-intensive methods, particularly physics-informed neural networks (PINNs) presented earlier, this study presents data-driven frameworks of physics-guided neural networks (PgNNs) and neural operators (NOs). Unlike PINNs and PgNNs, which focus on specific PDEs with respective boundary conditions, NOs solve a family of PDEs and hold the potential to easily solve different boundary conditions. Hence, NOs provide a more generalized SciML approach. NOs extend neural networks to map between functions rather than vectors, enhancing their applicability. This review highlights the potential of NOs in wave propagation modeling, aiming to advance wave-based structural health monitoring (SHM). Through comparative analysis of existing NO algorithms applied across different engineering fields, this study demonstrates how NOs improve generalization, accelerate inference, and enhance scalability for practical wave modeling scenarios. Lastly, this article identifies current limitations and suggests promising directions for future research on NO-based methods within computational wave mechanics.https://www.mdpi.com/1424-8220/25/12/3588scientific machine learningwave propagationphysics-guided neural networkneural operatordeep operator networkFourier neural operator
spellingShingle Nafisa Mehtaj
Sourav Banerjee
Scientific Machine Learning for Elastic and Acoustic Wave Propagation: Neural Operator and Physics-Guided Neural Network
Sensors
scientific machine learning
wave propagation
physics-guided neural network
neural operator
deep operator network
Fourier neural operator
title Scientific Machine Learning for Elastic and Acoustic Wave Propagation: Neural Operator and Physics-Guided Neural Network
title_full Scientific Machine Learning for Elastic and Acoustic Wave Propagation: Neural Operator and Physics-Guided Neural Network
title_fullStr Scientific Machine Learning for Elastic and Acoustic Wave Propagation: Neural Operator and Physics-Guided Neural Network
title_full_unstemmed Scientific Machine Learning for Elastic and Acoustic Wave Propagation: Neural Operator and Physics-Guided Neural Network
title_short Scientific Machine Learning for Elastic and Acoustic Wave Propagation: Neural Operator and Physics-Guided Neural Network
title_sort scientific machine learning for elastic and acoustic wave propagation neural operator and physics guided neural network
topic scientific machine learning
wave propagation
physics-guided neural network
neural operator
deep operator network
Fourier neural operator
url https://www.mdpi.com/1424-8220/25/12/3588
work_keys_str_mv AT nafisamehtaj scientificmachinelearningforelasticandacousticwavepropagationneuraloperatorandphysicsguidedneuralnetwork
AT souravbanerjee scientificmachinelearningforelasticandacousticwavepropagationneuraloperatorandphysicsguidedneuralnetwork