DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 – Reservoir oil minimum miscibility pressure prediction

Abstract

Carbon dioxide (CO2) injection into oil reservoirs is considered a mature enhanced oil recovery (EOR) technique for conventional reservoirs. The local displacement efficiency of the CO2-EOR process is highly dependent on the minimum miscibility pressure (MMP), estimating this parameter is critical to design of the CO2 injection process. Traditional empirical methods to test the CO2-oil MMP are time consuming and expensive; derived correlations are fast but not accurate. Therefore, an efficient and reliable method to determine MMP is beneficial. Here in this study, a mixed kernels function (MKF) based support vector regression (SVR) model was developed and used to predict the MMP for both pure and impure CO2 injection cases. Four parameters were chosen as input parameters: (1) reservoir temperature; (2) average critical temperature; (3) molecular weight of pentane plus (C5+) fraction of crude oil, and; (4) the ratio of volatile components to intermediate components in crude oil. MMP was selected as the desired output parameter to train and test this newly developed model. The performance of basic kernels function based SVR model is compared with that of this newly developed MKF-SVR model. The well-trained MFK-SVR was compared with three well-established published correlations, demonstrated the highest correlation coefficient (R ofmore » 0.9381), lowest root mean square error (RMSE of 1.9151), smallest average absolute error (AAE of 1.1406) and maximum absolute error (MAE of 4.6291). We believe that the proposed MFK-SVM model is a more reliable and stable regression model to predict MMP. In addition, a sensitivity analysis was conducted to evaluate the physical correctness. It indicates that the predicted results from the newly developed model are in excellent agreement with previous empirical work.« less

Authors:
 [1];  [1]
  1. West Virginia University, Morgantown, WV (United States)
Publication Date:
Research Org.:
West Virginia Univ., Morgantown, WV (United States)
Sponsoring Org.:
USDOE Office of Policy and International Affairs (PO); USDOE
OSTI Identifier:
1533789
Alternate Identifier(s):
OSTI ID: 1399037
Grant/Contract Number:  
PI0000017
Resource Type:
Accepted Manuscript
Journal Name:
Fuel
Additional Journal Information:
Journal Volume: 184; Journal Issue: C; Journal ID: ISSN 0016-2361
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; 42 ENGINEERING; CO2-oil minimum miscibility pressure; CO2 enhanced oil recovery; support vector regression; mixed kernels function; particle swarm optimization algorithm

Citation Formats

Zhong, Zhi, and Carr, Timothy R. Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 – Reservoir oil minimum miscibility pressure prediction. United States: N. p., 2016. Web. doi:10.1016/j.fuel.2016.07.030.
Zhong, Zhi, & Carr, Timothy R. Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 – Reservoir oil minimum miscibility pressure prediction. United States. https://doi.org/10.1016/j.fuel.2016.07.030
Zhong, Zhi, and Carr, Timothy R. Thu . "Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 – Reservoir oil minimum miscibility pressure prediction". United States. https://doi.org/10.1016/j.fuel.2016.07.030. https://www.osti.gov/servlets/purl/1533789.
@article{osti_1533789,
title = {Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 – Reservoir oil minimum miscibility pressure prediction},
author = {Zhong, Zhi and Carr, Timothy R.},
abstractNote = {Carbon dioxide (CO2) injection into oil reservoirs is considered a mature enhanced oil recovery (EOR) technique for conventional reservoirs. The local displacement efficiency of the CO2-EOR process is highly dependent on the minimum miscibility pressure (MMP), estimating this parameter is critical to design of the CO2 injection process. Traditional empirical methods to test the CO2-oil MMP are time consuming and expensive; derived correlations are fast but not accurate. Therefore, an efficient and reliable method to determine MMP is beneficial. Here in this study, a mixed kernels function (MKF) based support vector regression (SVR) model was developed and used to predict the MMP for both pure and impure CO2 injection cases. Four parameters were chosen as input parameters: (1) reservoir temperature; (2) average critical temperature; (3) molecular weight of pentane plus (C5+) fraction of crude oil, and; (4) the ratio of volatile components to intermediate components in crude oil. MMP was selected as the desired output parameter to train and test this newly developed model. The performance of basic kernels function based SVR model is compared with that of this newly developed MKF-SVR model. The well-trained MFK-SVR was compared with three well-established published correlations, demonstrated the highest correlation coefficient (R of 0.9381), lowest root mean square error (RMSE of 1.9151), smallest average absolute error (AAE of 1.1406) and maximum absolute error (MAE of 4.6291). We believe that the proposed MFK-SVM model is a more reliable and stable regression model to predict MMP. In addition, a sensitivity analysis was conducted to evaluate the physical correctness. It indicates that the predicted results from the newly developed model are in excellent agreement with previous empirical work.},
doi = {10.1016/j.fuel.2016.07.030},
journal = {Fuel},
number = C,
volume = 184,
place = {United States},
year = {Thu Jul 21 00:00:00 EDT 2016},
month = {Thu Jul 21 00:00:00 EDT 2016}
}

Journal Article:

Citation Metrics:
Cited by: 49 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Laboratory Investigation of Weyburn CO2 Miscible Flooding
journal, February 2000

  • Srivastava, R. K.; Huang, S. S.; Dong, M.
  • Journal of Canadian Petroleum Technology, Vol. 39, Issue 02
  • DOI: 10.2118/00-02-04

A study on the minimum miscibility pressure for miscible flooding systems
journal, January 1993

  • Zuo, You-xiang; Chu, Ji-zheng; Ke, Shui-lin
  • Journal of Petroleum Science and Engineering, Vol. 8, Issue 4
  • DOI: 10.1016/0920-4105(93)90008-3

Intelligent model for prediction of CO2 – Reservoir oil minimum miscibility pressure
journal, October 2013


CO2–oil minimum miscibility pressure model for impure and pure CO2 streams
journal, August 2007


Miscible Drive - Its Theory and Application
journal, June 1958

  • Clark, Norman J.; Shearin, H. M.; Schultz, W. P.
  • Journal of Petroleum Technology, Vol. 10, Issue 06
  • DOI: 10.2118/1036-G

Application of the new vanishing interfacial tension technique to evaluate miscibility conditions for the Terra Nova Offshore Project
journal, August 2002


A tutorial on support vector regression
journal, August 2004


Mechanisms of Oil Displacement By Carbon Dioxide
journal, December 1974

  • Holm, L. W.; Josendal, V. A.
  • Journal of Petroleum Technology, Vol. 26, Issue 12
  • DOI: 10.2118/4736-PA

A new technique of vanishing interfacial tension for miscibility determination
journal, December 1997


Support vector regression for porosity prediction in a heterogeneous reservoir: A comparative study
journal, December 2010


Simplified Method for Calculation of Minimum Miscibility Pressure or Enrichment
journal, December 2005

  • Yuan, Hua; Johns, Russell T.
  • SPE Journal, Vol. 10, Issue 04
  • DOI: 10.2118/77381-PA

Effects of Impurities on Minimum Miscibility Pressures and Minimum Enrichment Levels for CO2 and Rich-Gas Displacements
journal, April 1982

  • Metcalfe, R. S.
  • Society of Petroleum Engineers Journal, Vol. 22, Issue 02
  • DOI: 10.2118/9230-PA

An analysis of the vanishing interfacial tension technique for determination of minimum miscibility pressure
journal, July 2007


An Improved CO2-Crude Oil Minimum Miscibility Pressure Correlation
journal, January 2015


Carbon Dioxide Solubility in Water
journal, January 1956

  • Dodds, W. S.; Stutzman, L. F.; Sollami, B. J.
  • Industrial & Engineering Chemistry Chemical & Engineering Data Series, Vol. 1, Issue 1
  • DOI: 10.1021/i460001a018

Support-Vector Regression for Permeability Prediction in a Heterogeneous Reservoir: A Comparative Study
journal, June 2010

  • Al-anazi, Ammal F.; Gates, Ian D.
  • SPE Reservoir Evaluation & Engineering, Vol. 13, Issue 03
  • DOI: 10.2118/126339-PA

Carbon Dioxide Flooding-fundamentals
journal, January 1981

  • Mungan, Necmettin
  • Journal of Canadian Petroleum Technology, Vol. 20, Issue 01
  • DOI: 10.2118/81-01-03

Generalized Minimum Miscibility Pressure Correlation (includes associated papers 15845 and 16287 )
journal, December 1985

  • Glaso, O.
  • Society of Petroleum Engineers Journal, Vol. 25, Issue 06
  • DOI: 10.2118/12893-PA

Importance of input data normalization for the application of neural networks to complex industrial problems
journal, June 1997

  • Sola, J.; Sevilla, J.
  • IEEE Transactions on Nuclear Science, Vol. 44, Issue 3
  • DOI: 10.1109/23.589532

Minimum miscibility pressure prediction based on a hybrid neural genetic algorithm
journal, February 2008

  • Dehghani, S. A. Mousavi; Sefti, M. Vafaie; Ameri, A.
  • Chemical Engineering Research and Design, Vol. 86, Issue 2
  • DOI: 10.1016/j.cherd.2007.10.011

Correlation of Minimum Miscibility Pressure for Impure CO2 Streams
journal, November 1985

  • Sebastian, H. M.; Wenger, R. S.; Renner, T. A.
  • Journal of Petroleum Technology, Vol. 37, Issue 11
  • DOI: 10.2118/12648-PA

Fuzzy Modeling and Experimental Investigation of Minimum Miscible Pressure in Gas Injection Process
journal, September 2014


Use of genetic algorithm to estimate CO2–oil minimum miscibility pressure—a key parameter in design of CO2 miscible flood
journal, February 2005


Determination and Prediction of CO2 Minimum Miscibility Pressures (includes associated paper 8876 )
journal, January 1980

  • Yellig, W. F.; Metcalfe, R. S.
  • Journal of Petroleum Technology, Vol. 32, Issue 01
  • DOI: 10.2118/7477-PA

Implementing Radial Basis Function Networks for modeling CO2-reservoir oil minimum miscibility pressure
journal, November 2013

  • Tatar, Afshin; Shokrollahi, Amin; Mesbah, Mohammad
  • Journal of Natural Gas Science and Engineering, Vol. 15
  • DOI: 10.1016/j.jngse.2013.09.008

What is a support vector machine?
journal, December 2006


Interpretation of Pressure-Composition Phase Diagrams for CO2/Crude-Oil Systems
journal, October 1984

  • Orr, F. M.; Jensen, C. M.
  • Society of Petroleum Engineers Journal, Vol. 24, Issue 05
  • DOI: 10.2118/11125-PA

Comparative studies of metamodelling techniques under multiple modelling criteria
journal, December 2001

  • Jin, R.; Chen, W.; Simpson, T. W.
  • Structural and Multidisciplinary Optimization, Vol. 23, Issue 1
  • DOI: 10.1007/s00158-001-0160-4

Experimental Determination of Interfacial Tension and Miscibility of the CO2–Crude Oil System; Temperature, Pressure, and Composition Effects
journal, December 2013

  • Hemmati-Sarapardeh, Abdolhossein; Ayatollahi, Shahab; Ghazanfari, Mohammad-Hossein
  • Journal of Chemical & Engineering Data, Vol. 59, Issue 1
  • DOI: 10.1021/je400811h

A comparison of CO2 minimum miscibility pressure determinations for Weyburn crude oil
journal, October 2001


Identifying organic-rich Marcellus Shale lithofacies by support vector machine classifier in the Appalachian basin
journal, March 2014


Study of a Possible CO2 Flood in Rangely Field
journal, July 1981

  • Graue, Dennis J.; Zana, E. T.
  • Journal of Petroleum Technology, Vol. 33, Issue 07
  • DOI: 10.2118/7060-PA

Status of Miscible Displacement
journal, April 1983

  • Stalkup, Fred I.
  • Journal of Petroleum Technology, Vol. 35, Issue 04
  • DOI: 10.2118/9992-PA

Prediction of minimum miscibility pressure in oil reservoirs using a modified SAFT equation of state
journal, June 2013


Evaluation and Design of a CO2 Miscible Flood Project-SACROC Unit, Kelly-Snyder Field
journal, November 1973

  • Dicharry, Roy M.; Perryman, T. L.; Ronquille, J. D.
  • Journal of Petroleum Technology, Vol. 25, Issue 11
  • DOI: 10.2118/4083-PA

Rapid method to estimate the minimum miscibility pressure (MMP) in live reservoir oil systems during CO 2 flooding
journal, August 2015


An Improved CO 2 –Oil Minimum Miscibility Pressure Correlation for Live and Dead Crude Oils
journal, February 2012

  • Li, Huazhou; Qin, Jishun; Yang, Daoyong
  • Industrial & Engineering Chemistry Research, Vol. 51, Issue 8
  • DOI: 10.1021/ie202339g

Development of an artificial neural network model for predicting minimum miscibility pressure in CO2 flooding
journal, February 2003


Application of hybrid neural particle swarm optimization algorithm for prediction of MMP
journal, January 2014


Rapid Measurement of Minimum Miscibility Pressure With the Rising-Bubble Apparatus
journal, November 1987

  • Christiansen, Richard L.; Haines, Hiemi Kim
  • SPE Reservoir Engineering, Vol. 2, Issue 04
  • DOI: 10.2118/13114-PA

First-Contact-Miscible and Multicontact-Miscible Gas Injection within a Channeling Heterogeneity System
journal, February 2010


Oil-CO2MMP Determination in Competition of Neural Network, Support Vector Regression, and Committee Machine
journal, March 2014

  • Asoodeh, Mojtaba; Gholami, Amin; Bagheripour, Parisa
  • Journal of Dispersion Science and Technology, Vol. 35, Issue 4
  • DOI: 10.1080/01932691.2013.803255

Chaotic particle swarm optimization algorithm in a support vector regression electric load forecasting model
journal, January 2009


Carbon Dioxide Flooding Evaluation of High-Pour-Point, Paraffinic Red Wash Reservoir Oil
journal, August 1983

  • Frimodig, James P.; Reese, Norman A.; Williams, Craig A.
  • Society of Petroleum Engineers Journal, Vol. 23, Issue 04
  • DOI: 10.2118/10272-PA

Robust linear programming discrimination of two linearly inseparable sets
journal, January 1992


Support-vector networks
journal, September 1995

  • Cortes, Corinna; Vapnik, Vladimir
  • Machine Learning, Vol. 20, Issue 3
  • DOI: 10.1007/BF00994018

Precise model for estimating CO2—oil minimum miscibility pressure
journal, September 2007


Multiple Phase Behavior in Porous Media During CO2 or Rich-Gas Flooding
journal, September 1977

  • Shelton, J. L.; Yarborough, L.
  • Journal of Petroleum Technology, Vol. 29, Issue 09
  • DOI: 10.2118/5827-PA

A support vector machine algorithm to classify lithofacies and model permeability in heterogeneous reservoirs
journal, August 2010


Phase relations of miscible displacement in oil recovery
journal, March 1961


Improved MMP Correlation for CO2 Floods Using Analytical Theory
journal, October 2005

  • Yuan, Hua; Johns, Russell T.; Egwuenu, Azubuike M.
  • SPE Reservoir Evaluation & Engineering, Vol. 8, Issue 05
  • DOI: 10.2118/89359-PA

Acid Gases And Their Contribution to Miscibility
journal, April 1972

  • Jacobson, H. A.
  • Journal of Canadian Petroleum Technology, Vol. 11, Issue 02
  • DOI: 10.2118/72-02-03

Phase Equilibria in CO2—Multicomponent Hydrocarbon Systems: Experimental Data and an Improved Prediction Technique
journal, June 1984

  • Turek, Edward A.; Metcalfe, Robert S.; Yarborough, Lyman
  • Society of Petroleum Engineers Journal, Vol. 24, Issue 03
  • DOI: 10.2118/9231-PA

A crude oil data bank containing more than 5000 PVT and gas injection data
journal, June 2002

  • Jaubert, Jean-Noël; Avaullee, Laurent; Souvay, Jean-François
  • Journal of Petroleum Science and Engineering, Vol. 34, Issue 1-4
  • DOI: 10.1016/S0920-4105(02)00153-5

CO2 Minimum Miscibility Pressure: A Correlation for Impure CO2 Streams and Live Oil Systems
journal, April 1985

  • Alston, R. B.; Kokolis, G. P.; James, C. F.
  • Society of Petroleum Engineers Journal, Vol. 25, Issue 02
  • DOI: 10.2118/11959-PA

The genetic algorithm based back propagation neural network for MMP prediction in CO2-EOR process
journal, June 2014


Multiple-Phase Generation During Carbon Dioxide Flooding
journal, August 1983

  • Henry, Richard L.; Metcalfe, Robert S.
  • Society of Petroleum Engineers Journal, Vol. 23, Issue 04
  • DOI: 10.2118/8812-PA