Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application

Many inversion codes in marine controlled-source electromagnetic (CSEM) inverse problems use numerical partial differential equation (PDE) solvers as the forward solutions modelers. These codes perform well only when handling limited observations, as solving the governing equations in the forward mo...

Full description

Bibliographic Details
Main Authors: Muhammad Naeim, Mohd Aris, Hanita, Daud, Dass, Sarat Chandra, Nagaratnam, Shalini, Noryanti, Muhammad, Evizal, Abdul Kadir, Maharani, Warih
Format: Article
Language:English
Published: IEEE 2024
Subjects:
Online Access:https://umpir.ump.edu.my/id/eprint/44234/
_version_ 1848827318492987392
author Muhammad Naeim, Mohd Aris
Hanita, Daud
Dass, Sarat Chandra
Nagaratnam, Shalini
Noryanti, Muhammad
Evizal, Abdul Kadir
Maharani, Warih
author_facet Muhammad Naeim, Mohd Aris
Hanita, Daud
Dass, Sarat Chandra
Nagaratnam, Shalini
Noryanti, Muhammad
Evizal, Abdul Kadir
Maharani, Warih
author_sort Muhammad Naeim, Mohd Aris
building UMP Institutional Repository
collection Online Access
description Many inversion codes in marine controlled-source electromagnetic (CSEM) inverse problems use numerical partial differential equation (PDE) solvers as the forward solutions modelers. These codes perform well only when handling limited observations, as solving the governing equations in the forward modeling is very challenging, and quantifying uncertainties is not the strength of these solvers. A Gaussian process (GP)-based inversion was proposed to allow for greater flexibility in modeling numerous forward solutions by calibrating the stochastic process with computer experiment responses to estimate hydrocarbon parameters (i.e., depth and electrical resistivity) in marine CSEM application. Here, GP was used to evaluate electromagnetic (EM) responses at untried input specifications with uncertainty quantification, and gradient decent was employed for optimization in the inversion algorithm. The developed forward and inverse models were assessed against the true values through computing deviations. Hypothesis testing was also conducted to quantify the uncertainty of the estimation function as per its corresponding estimator. This research also compared the predictive performance of the proposed inversion methodology and existing framework. The calibration enabled GP to provide numerous reliable EM responses for the inversion. All the EM responses significantly fell within the GP predictive variance at α = 0.05. The resulting deviations and Bland-Altman plots demonstrated that GP-based inversion was capable of efficiently estimating the hydrocarbon input parameters in the marine CSEM inverse problems.
first_indexed 2025-11-15T03:58:49Z
format Article
id ump-44234
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:58:49Z
publishDate 2024
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling ump-442342025-09-23T03:42:57Z https://umpir.ump.edu.my/id/eprint/44234/ Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application Muhammad Naeim, Mohd Aris Hanita, Daud Dass, Sarat Chandra Nagaratnam, Shalini Noryanti, Muhammad Evizal, Abdul Kadir Maharani, Warih Q Science (General) QD Chemistry TP Chemical technology Many inversion codes in marine controlled-source electromagnetic (CSEM) inverse problems use numerical partial differential equation (PDE) solvers as the forward solutions modelers. These codes perform well only when handling limited observations, as solving the governing equations in the forward modeling is very challenging, and quantifying uncertainties is not the strength of these solvers. A Gaussian process (GP)-based inversion was proposed to allow for greater flexibility in modeling numerous forward solutions by calibrating the stochastic process with computer experiment responses to estimate hydrocarbon parameters (i.e., depth and electrical resistivity) in marine CSEM application. Here, GP was used to evaluate electromagnetic (EM) responses at untried input specifications with uncertainty quantification, and gradient decent was employed for optimization in the inversion algorithm. The developed forward and inverse models were assessed against the true values through computing deviations. Hypothesis testing was also conducted to quantify the uncertainty of the estimation function as per its corresponding estimator. This research also compared the predictive performance of the proposed inversion methodology and existing framework. The calibration enabled GP to provide numerous reliable EM responses for the inversion. All the EM responses significantly fell within the GP predictive variance at α = 0.05. The resulting deviations and Bland-Altman plots demonstrated that GP-based inversion was capable of efficiently estimating the hydrocarbon input parameters in the marine CSEM inverse problems. IEEE 2024 Article PeerReviewed pdf en cc_by_4 https://umpir.ump.edu.my/id/eprint/44234/1/Gaussian%20process-based%20inversion-A%20new%20approach%20for%20estimating%20hydrocarbon.pdf Muhammad Naeim, Mohd Aris and Hanita, Daud and Dass, Sarat Chandra and Nagaratnam, Shalini and Noryanti, Muhammad and Evizal, Abdul Kadir and Maharani, Warih (2024) Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application. IEEE Access, 12. pp. 1-25. ISSN 2169-3536. (Published) https://doi.org/10.1109/ACCESS.2024.3510481 https://doi.org/10.1109/ACCESS.2024.3510481 https://doi.org/10.1109/ACCESS.2024.3510481
spellingShingle Q Science (General)
QD Chemistry
TP Chemical technology
Muhammad Naeim, Mohd Aris
Hanita, Daud
Dass, Sarat Chandra
Nagaratnam, Shalini
Noryanti, Muhammad
Evizal, Abdul Kadir
Maharani, Warih
Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application
title Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application
title_full Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application
title_fullStr Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application
title_full_unstemmed Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application
title_short Gaussian process-based inversion: A new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application
title_sort gaussian process-based inversion: a new approach for estimating hydrocarbon parameters in controlled-source electromagnetic application
topic Q Science (General)
QD Chemistry
TP Chemical technology
url https://umpir.ump.edu.my/id/eprint/44234/
https://umpir.ump.edu.my/id/eprint/44234/
https://umpir.ump.edu.my/id/eprint/44234/