A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain Media

Soil materials can exhibit strongly dispersive properties in the operating frequency range of a physical system, and the uncertain parameters of the dispersive materials introduce uncertainties in the simulation result of propagating waves. It is essential to quantify the uncertainty in the simulati...

Full description

Bibliographic Details
Main Authors:	Xi Cheng, Zhi-Yong Zhang, Wei Shao
Format:	Article
Language:	English
Published:	IEEE 2020-01-01
Series:	IEEE Access
Subjects:	Artificial neural network (ANN) ground penetrating radar (GPR) surrogate model
Online Access:	https://ieeexplore.ieee.org/document/9277512/

id	doaj-85281c849273416eb4372b48bd3b9863
record_format	Article
spelling	doaj-85281c849273416eb4372b48bd3b98632021-03-30T03:30:54ZengIEEEIEEE Access2169-35362020-01-01821832321833010.1109/ACCESS.2020.30420009277512A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain MediaXi Cheng0Zhi-Yong Zhang1Wei Shao2https://orcid.org/0000-0001-9515-7091School of Physics, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi, ChinaSchool of Physics, University of Electronic Science and Technology of China, Chengdu, ChinaSoil materials can exhibit strongly dispersive properties in the operating frequency range of a physical system, and the uncertain parameters of the dispersive materials introduce uncertainties in the simulation result of propagating waves. It is essential to quantify the uncertainty in the simulation result when the acceptability of these calculation results is considered. To avoid performing thousands of full-wave simulations, an efficient surrogate model based on artificial neural networks (ANNs) is proposed in this paper, to imitate the concerned ground penetrating radar (GPR) calculation. With the autoencoder neural network to reduce the dimensionality of data, the surrogate model successfully predicts the outputs of the GPR calculation using a small number of training samples. The finite-difference time-domain method with the uniaxial perfectly matched layer is used to collect sampling data for the surrogate model. The process of constructing the surrogate model is presented in detail in this paper. The proposed surrogate model is demonstrated to be an attractive alternative to the full-wave GPR calculation due to its considerable advantage in terms of computational expense and speed.https://ieeexplore.ieee.org/document/9277512/Artificial neural network (ANN)ground penetrating radar (GPR)surrogate model
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Xi Cheng Zhi-Yong Zhang Wei Shao
spellingShingle	Xi Cheng Zhi-Yong Zhang Wei Shao A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain Media IEEE Access Artificial neural network (ANN) ground penetrating radar (GPR) surrogate model
author_facet	Xi Cheng Zhi-Yong Zhang Wei Shao
author_sort	Xi Cheng
title	A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain Media
title_short	A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain Media
title_full	A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain Media
title_fullStr	A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain Media
title_full_unstemmed	A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain Media
title_sort	surrogate model based on artificial neural networks for wave propagation in uncertain media
publisher	IEEE
series	IEEE Access
issn	2169-3536
publishDate	2020-01-01
description	Soil materials can exhibit strongly dispersive properties in the operating frequency range of a physical system, and the uncertain parameters of the dispersive materials introduce uncertainties in the simulation result of propagating waves. It is essential to quantify the uncertainty in the simulation result when the acceptability of these calculation results is considered. To avoid performing thousands of full-wave simulations, an efficient surrogate model based on artificial neural networks (ANNs) is proposed in this paper, to imitate the concerned ground penetrating radar (GPR) calculation. With the autoencoder neural network to reduce the dimensionality of data, the surrogate model successfully predicts the outputs of the GPR calculation using a small number of training samples. The finite-difference time-domain method with the uniaxial perfectly matched layer is used to collect sampling data for the surrogate model. The process of constructing the surrogate model is presented in detail in this paper. The proposed surrogate model is demonstrated to be an attractive alternative to the full-wave GPR calculation due to its considerable advantage in terms of computational expense and speed.
topic	Artificial neural network (ANN) ground penetrating radar (GPR) surrogate model
url	https://ieeexplore.ieee.org/document/9277512/
work_keys_str_mv	AT xicheng asurrogatemodelbasedonartificialneuralnetworksforwavepropagationinuncertainmedia AT zhiyongzhang asurrogatemodelbasedonartificialneuralnetworksforwavepropagationinuncertainmedia AT weishao asurrogatemodelbasedonartificialneuralnetworksforwavepropagationinuncertainmedia AT xicheng surrogatemodelbasedonartificialneuralnetworksforwavepropagationinuncertainmedia AT zhiyongzhang surrogatemodelbasedonartificialneuralnetworksforwavepropagationinuncertainmedia AT weishao surrogatemodelbasedonartificialneuralnetworksforwavepropagationinuncertainmedia
_version_	1724183305666953216

A Surrogate Model Based on Artificial Neural Networks for Wave Propagation in Uncertain Media

Similar Items