Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

A machine learning model for predicting the minimum miscibility pressure of CO2 and crude oil system based on a support vector machine algorithm approach

Journal Article · · Fuel
 [1];  [2];  [3];  [4];  [2];  [3]
  1. State Key Lab of Petroleum Resources and Prospecting, Beijing (China); China Univ. of Petroleum, Beijing (China); State Key Lab of Petroleum Resources and Prospecting, Beijing (China)
  2. State Key Lab of Petroleum Resources and Prospecting, Beijing (China); China Univ. of Petroleum, Beijing (China)
  3. PetroChina Research Inst. of Petroleum Exploration and Development, Beijing (China)
  4. Univ. of Texas, Austin, TX (United States). Bureau of Economic Geology
+ Show Author Affiliations
CO2 enhanced oil recovery (EOR) is a potential way for carbon capture, utilization and storage (CCUS). Though, the effect of CO2 injection is greatly influenced by the reservoir conditions. Typically, Minimum miscible pressure (MMP) is selected as one of the key parameters for the screening and evaluation of prospective CO2 flooding. Conventional slim tube test is both accurate and widely accepted but it is inefficient. Existing empirical formulas for MMPs are easy to be used but have been proved inaccurate and unreliable. Machine learning-based methods have great advantages in predicting MMP. However, only predication accuracy is discussed for most models without the screening of the main control factors and further validation of the model reliability. In this paper, a new prediction model based on support vector machine (SVM) was developed for pure/impure CO2 and crude oil system. This study was based on 147 sets of MMP data from the literature with full information on reservoir temperature, oil composition and gas composition. The main control factors were screened by several statistical methods. Unlike the conventional prediction models that verified by only prediction accuracy, learning curve and single factor control variable analysis are further validated to obtain the optimum model.
Research Organization:
Univ. of Texas, Austin, TX (United States)
Sponsoring Organization:
China Natural Science Foundation; USDOE Office of Fossil Energy (FE)
Grant/Contract Number:
FE0024375
OSTI ID:
1849150
Journal Information:
Fuel, Journal Name: Fuel Journal Issue: C Vol. 290; ISSN 0016-2361
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (34)

Efficient Learning Machines book January 2015
Support-vector networks journal September 1995
Development of an artificial neural network model for predicting minimum miscibility pressure in CO2 flooding journal February 2003
A self-adaptive deep learning algorithm for accelerating multi-component flash calculation journal September 2020
CO2 storage in depleted oil fields: The worldwide potential for carbon dioxide enhanced oil recovery journal January 2011
Machine learning for predicting thermodynamic properties of pure fluids and their mixtures journal December 2019
Intelligent model for prediction of CO2 – Reservoir oil minimum miscibility pressure journal October 2013
Application of hybrid neural particle swarm optimization algorithm for prediction of MMP journal January 2014
The genetic algorithm based back propagation neural network for MMP prediction in CO2-EOR process journal June 2014
Prediction of nitrogen diluted CO 2 minimum miscibility pressure for EOR and storage in depleted oil reservoirs journal December 2015
Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 – Reservoir oil minimum miscibility pressure prediction journal November 2016
Empirical correlations for prediction of minimum miscible pressure and near-miscible pressure interval for oil and CO2 systems journal October 2020
A molecular dynamics simulation study of PVT properties for H2O/H2/CO2 mixtures in near-critical and supercritical regions of water journal June 2018
Thermodynamic models for H2O–CO2–H2 mixtures in near-critical and supercritical regions of water journal February 2020
Diffusion coefficients of supercritical CO 2 in oil-saturated cores under low permeability reservoir conditions journal June 2016
The effect of permeability on supercritical CO2 diffusion coefficient and determination of diffusive tortuosity of porous media under reservoir conditions journal December 2018
Accelerating flash calculation through deep learning methods journal October 2019
Use of genetic algorithm to estimate CO2–oil minimum miscibility pressure—a key parameter in design of CO2 miscible flood journal February 2005
Study on pressure interval of near-miscible flooding by production gas Re-injection in QHD offshore oilfield journal August 2017
Effect of gas contamination and well depth on pressure interval of CO2 near-miscible flooding journal May 2019
Accelerating flash calculations in unconventional reservoirs considering capillary pressure using an optimized deep learning algorithm journal December 2020
Measuring CO 2 Minimum Miscibility Pressures:  Slim-Tube or Rising-Bubble Method? journal January 1996
A Tutorial on Support Vector Machines for Pattern Recognition journal January 1998
Tests for rank Correlation Coefficients. i journal December 1957
Classification of Petroleum Well Drilling Operations Using Support Vector Machine (SVM)
  • S. Serapiao, Adriane; Tavares, Rogerio; P. Mendes, Jose
  • 2006 International Conference on Computational Inteligence for Modelling Control and Automation and International Conference on Intelligent Agents Web Technologies and International Commerce (CIMCA'06) https://doi.org/10.1109/CIMCA.2006.66
conference November 2006
A Hybrid of Functional Networks and Support Vector Machine models for the prediction of petroleum reservoir properties
  • Anifowose, Fatai; Labadin, Jane; Abdulraheem, Abdulazeez
  • 2011 11th International Conference on Hybrid Intelligent Systems (HIS 2011), 2011 11th International Conference on Hybrid Intelligent Systems (HIS) https://doi.org/10.1109/HIS.2011.6122085
conference December 2011
Prediction of Hydrocarbon Reservoirs Permeability Using Support Vector Machine journal January 2012
World Carbon Dioxide Emissions: 1950–2050 journal February 1998
CO2 Capture and Storage journal September 2006
Equation-of-State-Based Downhole Fluid Characterization journal October 2010
Effect of Oil Composition on Minimum Miscibility Pressure—Part 1: Solubility of Hydrocarbons in Dense CO2 journal November 1987
Determining Diffusion Coefficients for Carbon Dioxide Injection in Oil-Saturated Chalk by Use of a Constant-Volume-Diffusion Method journal December 2016
Determination and Prediction of CO2 Minimum Miscibility Pressures (includes associated paper 8876 ) journal January 1980
Application of an integrated support vector regression method in prediction of financial returns journal June 2011

Similar Records

Related Subjects

02 PETROLEUM
42 ENGINEERING
97 MATHEMATICS AND COMPUTING
Energy & Fuels
Engineering
Machine learning
Minimum miscible pressure
Prediction model
Support vector machine
The impure CO2