Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches
Abstract
Machine-learning technologies have exhibited robust competences in solving many petroleum engineering problems. The accurate predictivity and fast computational speed enable a large volume of time-consuming engineering processes such as history-matching and field development optimization. The Southwest Regional Partnership on Carbon Sequestration (SWP) project desires rigorous history-matching and multi-objective optimization processes, which fits the superiorities of the machine-learning approaches. Although the machine-learning proxy models are trained and validated before imposing to solve practical problems, the error margin would essentially introduce uncertainties to the results. In this paper, a hybrid numerical machine-learning workflow solving various optimization problems is presented. By coupling the expert machine-learning proxies with a global optimizer, the workflow successfully solves the history-matching and CO2 water alternative gas (WAG) design problem with low computational overheads. The history-matching work considers the heterogeneities of multiphase relative characteristics, and the CO2-WAG injection design takes multiple techno-economic objective functions into accounts. This work trained an expert response surface, a support vector machine, and a multi-layer neural network as proxy models to effectively learn the high-dimensional nonlinear data structure. The proposed workflow suggests revisiting the high-fidelity numerical simulator for validation purposes. The experience gained from this work would provide valuable guiding insights to similar CO2more »
- Authors:
- 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:
- 1766084
- Alternate Identifier(s):
- OSTI ID: 1849090
- Grant/Contract Number:
- FC26-05NT42591
- Resource Type:
- Published Article
- Journal Name:
- Energies
- Additional Journal Information:
- Journal Name: Energies Journal Volume: 14 Journal Issue: 4; Journal ID: ISSN 1996-1073
- Publisher:
- MDPI AG
- Country of Publication:
- Switzerland
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 29 ENERGY PLANNING, POLICY, AND ECONOMY; Energy & Fuels; multi-objective optimization; CO2-WAG; machine learning; numerical modeling; hybrid workflows
Citation Formats
Sun, Qian, Ampomah, William, You, Junyu, Cather, Martha, and Balch, Robert. Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches. Switzerland: N. p., 2021.
Web. doi:10.3390/en14041055.
Sun, Qian, Ampomah, William, You, Junyu, Cather, Martha, & Balch, Robert. Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches. Switzerland. https://doi.org/10.3390/en14041055
Sun, Qian, Ampomah, William, You, Junyu, Cather, Martha, and Balch, Robert. Wed .
"Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches". Switzerland. https://doi.org/10.3390/en14041055.
@article{osti_1766084,
title = {Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches},
author = {Sun, Qian and Ampomah, William and You, Junyu and Cather, Martha and Balch, Robert},
abstractNote = {Machine-learning technologies have exhibited robust competences in solving many petroleum engineering problems. The accurate predictivity and fast computational speed enable a large volume of time-consuming engineering processes such as history-matching and field development optimization. The Southwest Regional Partnership on Carbon Sequestration (SWP) project desires rigorous history-matching and multi-objective optimization processes, which fits the superiorities of the machine-learning approaches. Although the machine-learning proxy models are trained and validated before imposing to solve practical problems, the error margin would essentially introduce uncertainties to the results. In this paper, a hybrid numerical machine-learning workflow solving various optimization problems is presented. By coupling the expert machine-learning proxies with a global optimizer, the workflow successfully solves the history-matching and CO2 water alternative gas (WAG) design problem with low computational overheads. The history-matching work considers the heterogeneities of multiphase relative characteristics, and the CO2-WAG injection design takes multiple techno-economic objective functions into accounts. This work trained an expert response surface, a support vector machine, and a multi-layer neural network as proxy models to effectively learn the high-dimensional nonlinear data structure. The proposed workflow suggests revisiting the high-fidelity numerical simulator for validation purposes. The experience gained from this work would provide valuable guiding insights to similar CO2 enhanced oil recovery (EOR) projects.},
doi = {10.3390/en14041055},
journal = {Energies},
number = 4,
volume = 14,
place = {Switzerland},
year = {Wed Feb 17 00:00:00 EST 2021},
month = {Wed Feb 17 00:00:00 EST 2021}
}
https://doi.org/10.3390/en14041055
Works referenced in this record:
Study of Gas/Condensate Reservoir Exploitation Using Neurosimulation
journal, April 2007
- Ayala, Luis Felipe; Ertekin, Turgay; Adewumi, Michael A.
- SPE Reservoir Evaluation & Engineering, Vol. 10, Issue 02
Performance assessment of CO2-enhanced oil recovery and storage in the Morrow reservoir
journal, April 2017
- Ampomah, W.; Balch, R.; Grigg, R. B.
- Geomechanics and Geophysics for Geo-Energy and Geo-Resources, Vol. 3, Issue 3
Integration of seismic attributes and production data for infill drilling strategies — A virtual intelligence approach
journal, December 2008
- Thararoop, P.; Karpyn, Z.; Gitman, A.
- Journal of Petroleum Science and Engineering, Vol. 63, Issue 1-4
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
Optimum design of CO2 storage and oil recovery under geological uncertainty
journal, June 2017
- Ampomah, W.; Balch, R. S.; Cather, M.
- Applied Energy, Vol. 195
Application of artificial intelligence to forecast hydrocarbon production from shales
journal, March 2018
- Panja, Palash; Velasco, Raul; Pathak, Manas
- Petroleum, Vol. 4, Issue 1
A tutorial on support vector regression
journal, August 2004
- Smola, Alex J.; Schölkopf, Bernhard
- Statistics and Computing, Vol. 14, Issue 3
Chemical effects of carbon dioxide sequestration in the Upper Morrow Sandstone in the Farnsworth, Texas, hydrocarbon unit
journal, March 2016
- Ahmmed, Bulbul; Appold, Martin S.; Fan, Tianguang
- Environmental Geosciences, Vol. 23, Issue 1
Machine learning based co-optimization of carbon dioxide sequestration and oil recovery in CO2-EOR project
journal, July 2020
- You, Junyu; Ampomah, William; Sun, Qian
- Journal of Cleaner Production, Vol. 260
Recent progress in augmenting turbulence models with physics-informed machine learning
journal, December 2019
- Zhang, Xinlei; Wu, Jinlong; Coutier-Delgosha, Olivier
- Journal of Hydrodynamics, Vol. 31, Issue 6
Development and application of a machine learning based multi-objective optimization workflow for CO2-EOR projects
journal, March 2020
- You, Junyu; Ampomah, William; Sun, Qian
- Fuel, Vol. 264
Carbon Storage and Enhanced Oil Recovery in Pennsylvanian Morrow Formation Clastic Reservoirs: Controls on Oil–Brine and Oil–CO2 Relative Permeability from Diagenetic Heterogeneity and Evolving Wettability
journal, September 2019
- Rasmussen, Lindsey; Fan, Tianguang; Rinehart, Alex
- Energies, Vol. 12, Issue 19
Acceleration of the NVT Flash Calculation for Multicomponent Mixtures Using Deep Neural Network Models
journal, June 2019
- Li, Yiteng; Zhang, Tao; Sun, Shuyu
- Industrial & Engineering Chemistry Research, Vol. 58, Issue 27
Uncertainty analysis of carbon sequestration in an active CO2-EOR field
journal, August 2016
- Pan, Feng; McPherson, Brian J.; Dai, Zhenxue
- International Journal of Greenhouse Gas Control, Vol. 51
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
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