Improved Oil Viscosity Characterization by Low-Field NMR Using Feature Engineering and Supervised Learning Algorithms

Conventional methods for determining and monitoring the viscosity of oils are time-consuming, expensive, and in some instances, technically unfeasible. These limitations can be avoided using low-field nuclear magnetic resonance (LF-NMR) relaxometry. However, due to the chemical dissimilarity of oils...

Full description

Bibliographic Details
Main Authors: Markovic, Strahinja, Bryan, J.L., Ishimtsev, V., Turakhanov, A., Rezaee, Reza, Cheremisin, A., Kantzas, A., Koroteev, D., Mehta, S.A.
Format: Journal Article
Language:English
Published: AMER CHEMICAL SOC 2020
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/89559
_version_ 1848765245354409984
author Markovic, Strahinja
Bryan, J.L.
Ishimtsev, V.
Turakhanov, A.
Rezaee, Reza
Cheremisin, A.
Kantzas, A.
Koroteev, D.
Mehta, S.A.
author_facet Markovic, Strahinja
Bryan, J.L.
Ishimtsev, V.
Turakhanov, A.
Rezaee, Reza
Cheremisin, A.
Kantzas, A.
Koroteev, D.
Mehta, S.A.
author_sort Markovic, Strahinja
building Curtin Institutional Repository
collection Online Access
description Conventional methods for determining and monitoring the viscosity of oils are time-consuming, expensive, and in some instances, technically unfeasible. These limitations can be avoided using low-field nuclear magnetic resonance (LF-NMR) relaxometry. However, due to the chemical dissimilarity of oils and various temperatures these oils are exposed to, as well as LF-NMR equipment limitations, the commonly used models fail to perform at a satisfactory level, making them impractical for use in heavy oil and bitumen reservoirs and in environments with large temperature oscillations (e.g., mechanical systems). We present a framework that combines supervised learning algorithms with domain knowledge for synthesizing new features to improve model forecasts using only one NMR parameter - T2 geometric mean. Two principal methods were considered, support vector regression (SVR) and gradient boosted trees (GBRT). Models were trained using the experimental data from our previous studies and literature data combining conventional oils, heavy oils, and bitumens from various reservoirs in Canada and United States. The models' performance was compared against four other intelligent algorithms and four well-known empirical NMR models against which the SVR- and GBRT-based models achieved the highest statistical scores. These two models can be used for oil viscosity prediction in conventional and heavy oil reservoirs with a wide range of oil viscosities and in situations where high precision is needed, such as in the determination of viscosity of petroleum distillates or for monitoring of oil viscosity in mechanical systems. The proposed framework can also be applied to determine other physicochemical properties of oils by LF-NMR, where the application of supervised learning is usually impractical due to the limited volume of experimental data.
first_indexed 2025-11-14T11:32:11Z
format Journal Article
id curtin-20.500.11937-89559
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:32:11Z
publishDate 2020
publisher AMER CHEMICAL SOC
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-895592023-01-16T06:34:00Z Improved Oil Viscosity Characterization by Low-Field NMR Using Feature Engineering and Supervised Learning Algorithms Markovic, Strahinja Bryan, J.L. Ishimtsev, V. Turakhanov, A. Rezaee, Reza Cheremisin, A. Kantzas, A. Koroteev, D. Mehta, S.A. Science & Technology Technology Energy & Fuels Engineering, Chemical Engineering HEAVY-OIL PHYSICOCHEMICAL PROPERTIES REGRESSION BIODIESEL SELECTION BITUMEN ERROR Conventional methods for determining and monitoring the viscosity of oils are time-consuming, expensive, and in some instances, technically unfeasible. These limitations can be avoided using low-field nuclear magnetic resonance (LF-NMR) relaxometry. However, due to the chemical dissimilarity of oils and various temperatures these oils are exposed to, as well as LF-NMR equipment limitations, the commonly used models fail to perform at a satisfactory level, making them impractical for use in heavy oil and bitumen reservoirs and in environments with large temperature oscillations (e.g., mechanical systems). We present a framework that combines supervised learning algorithms with domain knowledge for synthesizing new features to improve model forecasts using only one NMR parameter - T2 geometric mean. Two principal methods were considered, support vector regression (SVR) and gradient boosted trees (GBRT). Models were trained using the experimental data from our previous studies and literature data combining conventional oils, heavy oils, and bitumens from various reservoirs in Canada and United States. The models' performance was compared against four other intelligent algorithms and four well-known empirical NMR models against which the SVR- and GBRT-based models achieved the highest statistical scores. These two models can be used for oil viscosity prediction in conventional and heavy oil reservoirs with a wide range of oil viscosities and in situations where high precision is needed, such as in the determination of viscosity of petroleum distillates or for monitoring of oil viscosity in mechanical systems. The proposed framework can also be applied to determine other physicochemical properties of oils by LF-NMR, where the application of supervised learning is usually impractical due to the limited volume of experimental data. 2020 Journal Article http://hdl.handle.net/20.500.11937/89559 10.1021/acs.energyfuels.0c02565 English AMER CHEMICAL SOC restricted
spellingShingle Science & Technology
Technology
Energy & Fuels
Engineering, Chemical
Engineering
HEAVY-OIL
PHYSICOCHEMICAL PROPERTIES
REGRESSION
BIODIESEL
SELECTION
BITUMEN
ERROR
Markovic, Strahinja
Bryan, J.L.
Ishimtsev, V.
Turakhanov, A.
Rezaee, Reza
Cheremisin, A.
Kantzas, A.
Koroteev, D.
Mehta, S.A.
Improved Oil Viscosity Characterization by Low-Field NMR Using Feature Engineering and Supervised Learning Algorithms
title Improved Oil Viscosity Characterization by Low-Field NMR Using Feature Engineering and Supervised Learning Algorithms
title_full Improved Oil Viscosity Characterization by Low-Field NMR Using Feature Engineering and Supervised Learning Algorithms
title_fullStr Improved Oil Viscosity Characterization by Low-Field NMR Using Feature Engineering and Supervised Learning Algorithms
title_full_unstemmed Improved Oil Viscosity Characterization by Low-Field NMR Using Feature Engineering and Supervised Learning Algorithms
title_short Improved Oil Viscosity Characterization by Low-Field NMR Using Feature Engineering and Supervised Learning Algorithms
title_sort improved oil viscosity characterization by low-field nmr using feature engineering and supervised learning algorithms
topic Science & Technology
Technology
Energy & Fuels
Engineering, Chemical
Engineering
HEAVY-OIL
PHYSICOCHEMICAL PROPERTIES
REGRESSION
BIODIESEL
SELECTION
BITUMEN
ERROR
url http://hdl.handle.net/20.500.11937/89559