Machine Learning Based Forward Solver: An Automatic Framework in gprMax

Utsav Akhaury; Iraklis Giannakis; Craig Warren; Antonios Giannopoulos

doi:10.1109/IWAGPR50767.2021.9843172

Machine Learning Based Forward Solver: An Automatic Framework in gprMax

Utsav Akhaury, Iraklis Giannakis, Craig Warren, Antonios Giannopoulos

School of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

General full-wave electromagnetic solvers, such as those utilizing the finite-difference time-domain (FDTD) method, are computationally demanding for simulating practical GPR problems. We explore the performance of a near-real-time, forward modeling approach for GPR that is based on a machine learning (ML) architecture. To ease the process, we have developed a framework that is capable of generating these ML-based forward solvers automatically. The framework uses an innovative training method that combines a predictive dimensionality reduction technique and a large data set of modeled GPR responses from our FDTD simulation software, gprMax. The forward solver is parameterized for a specific GPR application, but the framework can be extended in a straightforward manner to different electromagnetic problems.

Original language	English
Title of host publication	2021 11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021
Publisher	Institute of Electrical and Electronics Engineers
ISBN (Electronic)	9781665422536
DOIs	https://doi.org/10.1109/IWAGPR50767.2021.9843172
Publication status	Published - 2 Aug 2022
Event	11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021 - Valletta, Malta Duration: 1 Dec 2021 → 4 Dec 2021

Conference

Conference	11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021
Country/Territory	Malta
City	Valletta
Period	1/12/21 → 4/12/21

Keywords / Materials (for Non-textual outputs)

Full-Waveform Inversion (FWI)
Machine Learning (ML)
Principle Component Analysis (PCA)
Random Forest
Singular Value Decomposition (SVD)
XGBoost (Extreme Gradient Boosting)

Access to Document

10.1109/IWAGPR50767.2021.9843172

https://arxiv.org/abs/2111.12148Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{f469d811ae87450ea7d7ccd470b8c984,

title = "Machine Learning Based Forward Solver: An Automatic Framework in gprMax",

abstract = "General full-wave electromagnetic solvers, such as those utilizing the finite-difference time-domain (FDTD) method, are computationally demanding for simulating practical GPR problems. We explore the performance of a near-real-time, forward modeling approach for GPR that is based on a machine learning (ML) architecture. To ease the process, we have developed a framework that is capable of generating these ML-based forward solvers automatically. The framework uses an innovative training method that combines a predictive dimensionality reduction technique and a large data set of modeled GPR responses from our FDTD simulation software, gprMax. The forward solver is parameterized for a specific GPR application, but the framework can be extended in a straightforward manner to different electromagnetic problems.",

keywords = "Full-Waveform Inversion (FWI), Machine Learning (ML), Principle Component Analysis (PCA), Random Forest, Singular Value Decomposition (SVD), XGBoost (Extreme Gradient Boosting)",

author = "Utsav Akhaury and Iraklis Giannakis and Craig Warren and Antonios Giannopoulos",

note = "Funding Information: The project was funded via the Google Summer of Code (GSoC) 2021 programme. GSoC initiative is a global program focused on bringing student developers into open source software development. The source code for this project can be found at https://github.com/gprMax/gprMax/pull/294. Publisher Copyright: {\textcopyright} 2021 IEEE.; 11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021 ; Conference date: 01-12-2021 Through 04-12-2021",

year = "2022",

month = aug,

day = "2",

doi = "10.1109/IWAGPR50767.2021.9843172",

language = "English",

booktitle = "2021 11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Akhaury, U, Giannakis, I, Warren, C & Giannopoulos, A 2022, Machine Learning Based Forward Solver: An Automatic Framework in gprMax. in 2021 11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021. Institute of Electrical and Electronics Engineers, 11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021, Valletta, Malta, 1/12/21. https://doi.org/10.1109/IWAGPR50767.2021.9843172

TY - GEN

T1 - Machine Learning Based Forward Solver

T2 - 11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021

AU - Akhaury, Utsav

AU - Giannakis, Iraklis

AU - Warren, Craig

AU - Giannopoulos, Antonios

N1 - Funding Information: The project was funded via the Google Summer of Code (GSoC) 2021 programme. GSoC initiative is a global program focused on bringing student developers into open source software development. The source code for this project can be found at https://github.com/gprMax/gprMax/pull/294. Publisher Copyright: © 2021 IEEE.

PY - 2022/8/2

Y1 - 2022/8/2

N2 - General full-wave electromagnetic solvers, such as those utilizing the finite-difference time-domain (FDTD) method, are computationally demanding for simulating practical GPR problems. We explore the performance of a near-real-time, forward modeling approach for GPR that is based on a machine learning (ML) architecture. To ease the process, we have developed a framework that is capable of generating these ML-based forward solvers automatically. The framework uses an innovative training method that combines a predictive dimensionality reduction technique and a large data set of modeled GPR responses from our FDTD simulation software, gprMax. The forward solver is parameterized for a specific GPR application, but the framework can be extended in a straightforward manner to different electromagnetic problems.

AB - General full-wave electromagnetic solvers, such as those utilizing the finite-difference time-domain (FDTD) method, are computationally demanding for simulating practical GPR problems. We explore the performance of a near-real-time, forward modeling approach for GPR that is based on a machine learning (ML) architecture. To ease the process, we have developed a framework that is capable of generating these ML-based forward solvers automatically. The framework uses an innovative training method that combines a predictive dimensionality reduction technique and a large data set of modeled GPR responses from our FDTD simulation software, gprMax. The forward solver is parameterized for a specific GPR application, but the framework can be extended in a straightforward manner to different electromagnetic problems.

KW - Full-Waveform Inversion (FWI)

KW - Machine Learning (ML)

KW - Principle Component Analysis (PCA)

KW - Random Forest

KW - Singular Value Decomposition (SVD)

KW - XGBoost (Extreme Gradient Boosting)

UR - https://www.scopus.com/pages/publications/85136302918

UR - https://researchportal.northumbria.ac.uk/en/publications/machine-learning-based-forward-solver-an-automatic-framework-in-g

U2 - 10.1109/IWAGPR50767.2021.9843172

DO - 10.1109/IWAGPR50767.2021.9843172

M3 - Conference contribution

AN - SCOPUS:85136302918

BT - 2021 11th International Workshop on Advanced Ground Penetrating Radar, IWAGPR 2021

PB - Institute of Electrical and Electronics Engineers

Y2 - 1 December 2021 through 4 December 2021

ER -

Machine Learning Based Forward Solver: An Automatic Framework in gprMax

Abstract

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Cite this