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

Saved in:
Bibliographic Details
Published in:Scientific reports 2022-08, Vol.12 (1), p.13984-13984, Article 13984
Main Authors: Markovic, Strahinja, Bryan, Jonathan L., Rezaee, Reza, Turakhanov, Aman, Cheremisin, Alexey, Kantzas, Apostolos, Koroteev, Dmitry
Format: Article
Language:English
Subjects:
639/4077/4082/4061
639/705/531
639/766/930/12
704/2151/2809
Decision making
Humanities and Social Sciences
multidisciplinary
NMR
Nuclear magnetic resonance
Oil
Oil sands
Science
Science (multidisciplinary)
Water content
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 (T 2 ) 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 T 2 relaxation distribution analysis domain and mutual information feature extraction technique, while the second model considers whole samples’ NMR T 2 -relaxation distribution. The NMR T 2 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% (R 2  = 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.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-022-17886-6