Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data

Water saturation determination is among the most challenging tasks in petrophysical well-logging, which directly impacts the decision-making process in hydrocarbon exploration and production. Low-field nuclear magnetic resonance (LF-NMR) measurements can provide reliable evaluation. However, quantif...

Full description

Bibliographic Details
Main Authors: Markovic, Strahinja, Bryan, J.L., Rezaee, Reza, Turakhanov, A., Cheremisin, A., Kantzas, A., Koroteev, D.
Format: Journal Article
Language:English
Published: 2022
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/89526
_version_ 1848765235960217600
author Markovic, Strahinja
Bryan, J.L.
Rezaee, Reza
Turakhanov, A.
Cheremisin, A.
Kantzas, A.
Koroteev, D.
author_facet Markovic, Strahinja
Bryan, J.L.
Rezaee, Reza
Turakhanov, A.
Cheremisin, A.
Kantzas, A.
Koroteev, D.
author_sort Markovic, Strahinja
building Curtin Institutional Repository
collection Online Access
description Water saturation determination is among the most challenging tasks in petrophysical well-logging, which directly impacts the decision-making process in hydrocarbon exploration and production. Low-field nuclear magnetic resonance (LF-NMR) measurements can provide reliable evaluation. However, quantification of oil and water volumes is problematic when their NMR signals are not distinct. To overcome this, we developed two machine learning frameworks for predicting relative water content in oil-sand samples using LF-NMR spin–spin (T2) relaxation and bulk density data to derive a model based on Extreme Gradient Boosting. The first one facilitates feature engineering based on empirical knowledge from the T2 relaxation distribution analysis domain and mutual information feature extraction technique, while the second model considers whole samples’ NMR T2-relaxation distribution. The NMR T2 distributions were obtained for 82 Canadian oil-sands samples at ambient and reservoir temperatures (164 data points). The true water content was determined by Dean-Stark extraction. The statistical scores confirm the strong generalization ability of the feature engineering LF-NMR model in predicting relative water content by Dean-Stark—root-mean-square error of 0.67% and mean-absolute error of 0.53% (R2 = 0.90). Results indicate that this approach can be extended for the improved in-situ water saturation evaluation by LF-NMR and bulk density measurements.
first_indexed 2025-11-14T11:32:02Z
format Journal Article
id curtin-20.500.11937-89526
institution Curtin University Malaysia
institution_category Local University
language eng
last_indexed 2025-11-14T11:32:02Z
publishDate 2022
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-895262023-01-18T07:12:24Z Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data Markovic, Strahinja Bryan, J.L. Rezaee, Reza Turakhanov, A. Cheremisin, A. Kantzas, A. Koroteev, D. Canada Magnetic Resonance Imaging Magnetic Resonance Spectroscopy Rapeseed Oil Sand Water saturation determination is among the most challenging tasks in petrophysical well-logging, which directly impacts the decision-making process in hydrocarbon exploration and production. Low-field nuclear magnetic resonance (LF-NMR) measurements can provide reliable evaluation. However, quantification of oil and water volumes is problematic when their NMR signals are not distinct. To overcome this, we developed two machine learning frameworks for predicting relative water content in oil-sand samples using LF-NMR spin–spin (T2) relaxation and bulk density data to derive a model based on Extreme Gradient Boosting. The first one facilitates feature engineering based on empirical knowledge from the T2 relaxation distribution analysis domain and mutual information feature extraction technique, while the second model considers whole samples’ NMR T2-relaxation distribution. The NMR T2 distributions were obtained for 82 Canadian oil-sands samples at ambient and reservoir temperatures (164 data points). The true water content was determined by Dean-Stark extraction. The statistical scores confirm the strong generalization ability of the feature engineering LF-NMR model in predicting relative water content by Dean-Stark—root-mean-square error of 0.67% and mean-absolute error of 0.53% (R2 = 0.90). Results indicate that this approach can be extended for the improved in-situ water saturation evaluation by LF-NMR and bulk density measurements. 2022 Journal Article http://hdl.handle.net/20.500.11937/89526 10.1038/s41598-022-17886-6 eng http://creativecommons.org/licenses/by/4.0/ fulltext
spellingShingle Canada
Magnetic Resonance Imaging
Magnetic Resonance Spectroscopy
Rapeseed Oil
Sand
Markovic, Strahinja
Bryan, J.L.
Rezaee, Reza
Turakhanov, A.
Cheremisin, A.
Kantzas, A.
Koroteev, D.
Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data
title Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data
title_full Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data
title_fullStr Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data
title_full_unstemmed Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data
title_short Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data
title_sort application of xgboost model for in-situ water saturation determination in canadian oil-sands by lf-nmr and density data
topic Canada
Magnetic Resonance Imaging
Magnetic Resonance Spectroscopy
Rapeseed Oil
Sand
url http://hdl.handle.net/20.500.11937/89526