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

Title: Co-optimizing water-alternating-carbon dioxide injection projects using a machine learning assisted computational framework

Abstract

In this report, a robust machine-learning-based computational framework that couples multi-layer neural network (MLNN) proxies and a multi-objective particle swarm optimizer (MOPSO) to design water-alternating-carbon dioxide injection (CO2-WAG) projects is presented. The proposed optimization protocol considers various objectives, including oil recovery and CO2 storage volume. Expert MLNN systems are trained and employed as surrogate models of the high-fidelity compositional simulator in the optimization workflow. When multiple objective functions are considered, two approaches are employed to treat the objectives: the weighted sum method and the Pareto-front-based scheme. A field-scale implementation focusing on tertiary recovery in the Morrow B formation at Farnsworth Unit (FWU) is presented. The developed Pareto-optimal solutions indicate the maximal available oil production can be 1.64 × 107 barrels and maximal carbon storage can achieve 2.35 × 107 tons. Trade-offs factor is defined to divide the constructed Pareto front into 4 sections with the trade-off factors’ value ranges from 0.35 to 49.9. This work also compares the optimum solution found by the aggregative objective function and the solution repository covered by the Pareto front that considers the physical and operational constraints and reduces uncertainties involved by the multi-objective optimization process. Our comparison indicates multiple solutions exist to satisfy themore » objective criteria of the WAG design, and these results cannot be found using the traditional weighted sum method. The Pareto front solution can provide more options for project designers, but decisions regarding necessary trade-offs must be made using the solution repository to balance the project economics and CO2 storage amount.« less

Authors:
 [1];  [1];  [1]
  1. New Mexico Tech, Socorro NM (United States). Petroleum Recovery Research Center
Publication Date:
Research Org.:
New Mexico Institute of Mining and Technology, Socorro, NM (United States)
Sponsoring Org.:
USDOE Office of Fossil Energy (FE)
OSTI Identifier:
1849087
Alternate Identifier(s):
OSTI ID: 1759140
Grant/Contract Number:  
FC26-05NT42591
Resource Type:
Accepted Manuscript
Journal Name:
Applied Energy
Additional Journal Information:
Journal Volume: 279; Journal Issue: C; Journal ID: ISSN 0306-2619
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
10 SYNTHETIC FUELS; Energy & Fuels; Engineering; Carbon dioxide sequestration; CO2-EOR; Multi-objective optimization; Artificial neural network

Citation Formats

You, Junyu, Ampomah, William, and Sun, Qian. Co-optimizing water-alternating-carbon dioxide injection projects using a machine learning assisted computational framework. United States: N. p., 2020. Web. doi:10.1016/j.apenergy.2020.115695.
You, Junyu, Ampomah, William, & Sun, Qian. Co-optimizing water-alternating-carbon dioxide injection projects using a machine learning assisted computational framework. United States. https://doi.org/10.1016/j.apenergy.2020.115695
You, Junyu, Ampomah, William, and Sun, Qian. Sun . "Co-optimizing water-alternating-carbon dioxide injection projects using a machine learning assisted computational framework". United States. https://doi.org/10.1016/j.apenergy.2020.115695. https://www.osti.gov/servlets/purl/1849087.
@article{osti_1849087,
title = {Co-optimizing water-alternating-carbon dioxide injection projects using a machine learning assisted computational framework},
author = {You, Junyu and Ampomah, William and Sun, Qian},
abstractNote = {In this report, a robust machine-learning-based computational framework that couples multi-layer neural network (MLNN) proxies and a multi-objective particle swarm optimizer (MOPSO) to design water-alternating-carbon dioxide injection (CO2-WAG) projects is presented. The proposed optimization protocol considers various objectives, including oil recovery and CO2 storage volume. Expert MLNN systems are trained and employed as surrogate models of the high-fidelity compositional simulator in the optimization workflow. When multiple objective functions are considered, two approaches are employed to treat the objectives: the weighted sum method and the Pareto-front-based scheme. A field-scale implementation focusing on tertiary recovery in the Morrow B formation at Farnsworth Unit (FWU) is presented. The developed Pareto-optimal solutions indicate the maximal available oil production can be 1.64 × 107 barrels and maximal carbon storage can achieve 2.35 × 107 tons. Trade-offs factor is defined to divide the constructed Pareto front into 4 sections with the trade-off factors’ value ranges from 0.35 to 49.9. This work also compares the optimum solution found by the aggregative objective function and the solution repository covered by the Pareto front that considers the physical and operational constraints and reduces uncertainties involved by the multi-objective optimization process. Our comparison indicates multiple solutions exist to satisfy the objective criteria of the WAG design, and these results cannot be found using the traditional weighted sum method. The Pareto front solution can provide more options for project designers, but decisions regarding necessary trade-offs must be made using the solution repository to balance the project economics and CO2 storage amount.},
doi = {10.1016/j.apenergy.2020.115695},
journal = {Applied Energy},
number = C,
volume = 279,
place = {United States},
year = {Sun Sep 06 00:00:00 EDT 2020},
month = {Sun Sep 06 00:00:00 EDT 2020}
}

Works referenced in this record:

What Can History Teach Us? A Retrospective Examination of Long-Term Energy Forecasts for the United States
journal, November 2002


Optimization using surrogate models and partially converged computational fluid dynamics simulations
journal, February 2006

  • Forrester, Alexander I. J.; Bressloff, Neil W.; Keane, Andy J.
  • Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 462, Issue 2071
  • DOI: 10.1098/rspa.2006.1679

Global optimization of multiphase flow networks using spline surrogate models
journal, January 2016


Factors That Control Condensate Production From Shales: Surrogate Reservoir Models and Uncertainty Analysis
journal, December 2015

  • Panja, Palash; Deo, Milind
  • SPE Reservoir Evaluation & Engineering, Vol. 19, Issue 01
  • DOI: 10.2118/179720-PA

Recurrent neural networks and robust time series prediction
journal, March 1994

  • Connor, J. T.; Martin, R. D.; Atlas, L. E.
  • IEEE Transactions on Neural Networks, Vol. 5, Issue 2
  • DOI: 10.1109/72.279188

The role of CO2 capture and utilization in mitigating climate change
journal, April 2017

  • Mac Dowell, Niall; Fennell, Paul S.; Shah, Nilay
  • Nature Climate Change, Vol. 7, Issue 4
  • DOI: 10.1038/nclimate3231

Support Vector Machines Framework for Predicting the PVT Properties of Crude Oil Systems
conference, March 2007

  • El-Sebakhy, Emad Ahmed; Sheltami, Tarek; Al-Bokhitan, Said Y.
  • SPE Middle East Oil and Gas Show and Conference, All Days
  • DOI: 10.2118/105698-MS

Determinants of carbon dioxide emissions: Empirical evidence from 69 countries
journal, January 2011


Co-optimization of enhanced oil recovery and carbon sequestration
journal, November 2011


A multi-objective optimization for green supply chain network design
journal, May 2011


IEA World Energy Outlook 2011—A comment
journal, September 2012


Handling multiple objectives with particle swarm optimization
journal, June 2004

  • Coello, C. A. C.; Pulido, G. T.; Lechuga, M. S.
  • IEEE Transactions on Evolutionary Computation, Vol. 8, Issue 3
  • DOI: 10.1109/TEVC.2004.826067

Neural network based swarm concept for prediction asphaltene precipitation due to natural depletion
journal, November 2012


An algorithm for the use of surrogate models in modular flowsheet optimization
journal, October 2008

  • Caballero, José A.; Grossmann, Ignacio E.
  • AIChE Journal, Vol. 54, Issue 10
  • DOI: 10.1002/aic.11579

Optimum design of CO2 storage and oil recovery under geological uncertainty
journal, June 2017


Prediction of storage efficiency on CO2 sequestration in deep saline aquifers using artificial neural network
journal, January 2017


Energy consumption and greenhouse gas emissions in the recovery and extraction of crude bitumen from Canada’s oil sands
journal, April 2015


The weighted sum method for multi-objective optimization: new insights
journal, December 2009

  • Marler, R. Timothy; Arora, Jasbir S.
  • Structural and Multidisciplinary Optimization, Vol. 41, Issue 6
  • DOI: 10.1007/s00158-009-0460-7

Opportunities for Using Anthropogenic CO 2 for Enhanced Oil Recovery and CO 2 Storage
journal, March 2013

  • Godec, Michael L.; Kuuskraa, Vello A.; Dipietro, Phil
  • Energy & Fuels, Vol. 27, Issue 8
  • DOI: 10.1021/ef302040u

Multiobjective Optimization of Industrial Petroleum Processing Units Using Genetic Algorithms
journal, January 2014


Energy consumption and CO2 emissions in Turkey: Empirical analysis and future projection based on an economic growth
journal, December 2006


The ghost of unbalanced species distribution data in geographical model predictions
journal, September 2006


Heterogeneity-assisted carbon dioxide storage in marine sediments
journal, September 2018


Review: Multi-objective optimization methods and application in energy saving
journal, April 2017


Multi-objective global optimization for hydrologic models
journal, January 1998


Forecasting of CO2 emissions from fuel combustion using trend analysis
journal, December 2010


Non-Dominated Ranked Based Genetic Algorithm Multi-Objective Well Placement Optimization
conference, January 2019


Gradient-based multi-objective optimization with applications to waterflooding optimization
journal, September 2015


Surrogate modeling-based optimization for the integration of static and dynamic data into a reservoir description
journal, August 2002

  • Queipo, Nestor V.; Pintos, Salvador; Rincón, Néstor
  • Journal of Petroleum Science and Engineering, Vol. 35, Issue 3-4
  • DOI: 10.1016/S0920-4105(02)00238-3

Building Surrogate Models Based on Detailed and Approximate Simulations
journal, June 2005

  • Qian, Zhiguang; Seepersad, Carolyn Conner; Joseph, V. Roshan
  • Journal of Mechanical Design, Vol. 128, Issue 4
  • DOI: 10.1115/1.2179459

Geologic Carbon Storage Through Enhanced Oil Recovery
journal, January 2013


Scenario analysis of CO2 emissions from China’s civil aviation industry through 2030
journal, August 2016


Prospects of carbon capture and storage (CCS) in India’s power sector – An integrated assessment
journal, March 2014


Generation of a Pareto front for a bi-objective water flooding optimization problem using approximate ensemble gradients
journal, November 2016

  • Fonseca, Rahul M.; Reynolds, Albert C.; Jansen, Jan Dirk
  • Journal of Petroleum Science and Engineering, Vol. 147
  • DOI: 10.1016/j.petrol.2016.06.009

Assessment of Enhanced Oil Recovery and CO2 Storage Capacity Using Machine Learning and Optimization Framework
conference, June 2019

  • You, Junyu; Ampomah, William; Kutsienyo, Eusebius Junior
  • SPE Europec featured at 81st EAGE Conference and Exhibition, Day 4 Thu, June 06, 2019
  • DOI: 10.2118/195490-MS

Numerical Simulation of Carbon Dioxide Injection in the Western Section of the Farnsworth Unit
journal, January 2014


Experimental investigation of miscible and immiscible Water-Alternating-Gas (WAG) process performance
journal, July 2005


The Modeling and Projection of Primary Energy Consumption by the Sources
journal, July 2014


Ensemble-Based Optimization of the Water-Alternating-Gas-Injection Process
journal, June 2016

  • Chen, Bailian; Reynolds, Albert C.
  • SPE Journal, Vol. 21, Issue 03
  • DOI: 10.2118/173217-PA

Evaluation of CO2-EOR Performance and Storage Mechanisms in an Active Partially Depleted Oil Reservoir
conference, June 2019

  • Kutsienyo, Eusebius Junior; Ampomah, William; Sun, Qian
  • SPE Europec featured at 81st EAGE Conference and Exhibition, Day 4 Thu, June 06, 2019
  • DOI: 10.2118/195534-MS

Production Modeling in the Oil and Natural Gas Industry: An Application of Trend Analysis
journal, January 2014


Handling conflicting multiple objectives using Pareto-based evolutionary algorithm during history matching of reservoir performance
journal, January 2015

  • Park, Han-Young; Datta-Gupta, Akhil; King, Michael J.
  • Journal of Petroleum Science and Engineering, Vol. 125
  • DOI: 10.1016/j.petrol.2014.11.006

Optimization of petroleum production networks – Through proxy models and structural constraints
journal, January 2012


A study on the impact of SO2 on CO2 injectivity for CO2 storage in a Canadian saline aquifer
journal, December 2016


Scenario analysis of urban energy saving and carbon abatement policies: A case study of Beijing city, China
journal, January 2012


The Development and Validation of Regression Models to Predict Energy-related CO 2 Emissions in Turkey
journal, September 2014


CO 2 Accounting and Risk Analysis for CO 2 Sequestration at Enhanced Oil Recovery Sites
journal, June 2016

  • Dai, Zhenxue; Viswanathan, Hari; Middleton, Richard
  • Environmental Science & Technology, Vol. 50, Issue 14
  • DOI: 10.1021/acs.est.6b01744

Co-optimization of CO 2 -EOR and storage processes in mature oil reservoirs : Original Research Article: Co-optimization of CO
journal, August 2016

  • Ampomah, William; Balch, Robert S.; Grigg, Reid B.
  • Greenhouse Gases: Science and Technology, Vol. 7, Issue 1
  • DOI: 10.1002/ghg.1618