Machine learning based co-optimization of carbon dioxide sequestration and oil recovery in CO2-EOR project

You, Jane; Ampomah, William; Sun, Qing; Kutsienyo, Eusebius Junior; Balch, Robert; Dai, Zhenxue; Cather, Martha; Zhang, Xiaoying

doi:10.1016/j.jclepro.2020.120866

Cited by 76 publications

(28 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…History matching error: The history-matching error is a significant objective function to measure the misfit of the numerical model results with the field historical data. In this work, the square error was used to account for the differences between the results generated by the simulator with the field historical measurement for oil, water, gas production data, water, gas injection data, and pressure data via Equation (14) through Equation ( 19), respectively.…”

Section: Technical Objective Functionsmentioning

confidence: 99%

“…The optimization studies in this work considered more than one objective function, which are called multi-objective optimization problems (MOO). For instance, the historymatching work needs to minimize the error functions defined by Equation (14) through Equation ( 19) simultaneously, and the CO2-WAG design problem aims at maximizing the NPV, oil recovery, and CO2 storage volume in the meantime. There were two different ways employed in this work to treat the MOO problems:…”

Section: Treatment Of Multiple-objective Optimizationsmentioning

confidence: 99%

“…A facies model was developed to populate the petrophysical property distributions with assistance from the HFU. There are numerous history-matching studies imposed on reservoir models considering the field historical injection and production data in the primary, secondary, and tertiary recovery period [14]. The history-matched model can be used to assess various CO2 water-alternative-gas (WAG) forecasting scenarios and more importantly, optimize the project design strategies.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches

et al. 2021

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Technical Objective Functionsmentioning

confidence: 99%

Section: Treatment Of Multiple-objective Optimizationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Independent component analysis has been used for fault diagnosis and detection in industrial processes [23,24], and data clustering was used in chemical processes to detect faults on a separation tower [25]. In the oil industry, machine learning techniques were used to predict pressure, volume, and temperature (PVT) properties of crude oil [26,27], crude oil price [28,29], and enhanced oil recovery [30,31]. In oil sands operations, machine learning methods were applied to analyse incident reports and increase process safety [32,33], and predict crude oil production from in situ oil sands extraction [34,35].…”

Section: Introductionmentioning

confidence: 99%

Discovering Energy Consumption Patterns with Unsupervised Machine Learning for Canadian In Situ Oil Sands Operations

Bai²,

2021

Sustainability

View full text Add to dashboard Cite

Canada’s in situ oil sands can help meet the global oil demand. Because of the energy-intensive extraction processes, in situ oil sands operations also play a critical role in meeting the global carbon budget. The steam oil ratio (SOR) is an indicator used to measure energy efficiency and assess greenhouse gas (GHG) emissions in the in situ oil sands industry. A low SOR indicates an extraction process that is more energy efficient and less carbon intensive. In this study, we applied machine learning methods for data-driven discovery to a public database⁠, Petrinex⁠, containing operating data from 2015 to 2019 extracted from over 35 million records for 20 in situ oil sands extraction operations. Two unsupervised machine learning methods, including clustering and association rules, showed that the cyclic steam stimulation (CSS) recovery method was less efficient than the steam-assisted gravity drainage (SAGD) recovery method. Chi-square tests showed a statistically significant association between the CSS recovery method and high SOR (p <0.005). Two association rules suggested that the occurrence of non-condensable gas (NCG) co-injection produced a low SOR. Chi-square tests on the two rules identified a statistically significant relationship between gas co-injection and low SOR (p < 0.005). Association rules also indicated that there was no association between the production regions and SORs. For future in situ oil sands development, decision-makers should consider SAGD as the preferred method because it is less carbon intensive. Existing in situ oil sands projects and future development should explore the possibility of NCG co-injection with steam to reduce steam consumption and consequently reduce GHG emissions from the extraction processes.

show abstract

“…Furthermore, several studies were employed ANN-based proxies models for EOR projects 38 , 39 . These authors stated that the ANN expert system could propose the fast technical and economic assessment for EOR projects.…”

Section: Introductionmentioning

confidence: 99%

Application of artificial neural network for predicting the performance of CO2 enhanced oil recovery and storage in residual oil zones

Thanh

Sugai

Sasaki

2020

Sci Rep

100

View full text Add to dashboard Cite

Residual Oil Zones (ROZs) become potential formations for Carbon Capture, Utilization, and Storage (CCUS). Although the growing attention in ROZs, there is a lack of studies to propose the fast tool for evaluating the performance of a CO2 injection process. In this paper, we introduce the application of artificial neural network (ANN) for predicting the oil recovery and CO2 storage capacity in ROZs. The uncertainties parameters, including the geological factors and well operations, were used for generating the training database. Then, a total of 351 numerical samples were simulated and created the Cumulative oil production, Cumulative CO2 storage, and Cumulative CO2 retained. The results indicated that the developed ANN model had an excellent prediction performance with a high correlation coefficient (R2) was over 0.98 on comparing with objective values, and the total root mean square error of less than 2%. Also, the accuracy and stability of ANN models were validated for five real ROZs in the Permian Basin. The predictive results were an excellent agreement between ANN predictions and field report data. These results indicated that the ANN model could predict the CO2 storage and oil recovery with high accuracy, and it can be applied as a robust tool to determine the feasibility in the early stage of CCUS in ROZs. Finally, the prospective application of the developed ANN model was assessed by optimization CO2-EOR and storage projects. The developed ANN models reduced the computational time for the optimization process in ROZs.

show abstract

Machine learning based co-optimization of carbon dioxide sequestration and oil recovery in CO2-EOR project

Cited by 76 publications

References 32 publications

Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches

Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches

Discovering Energy Consumption Patterns with Unsupervised Machine Learning for Canadian In Situ Oil Sands Operations

Application of artificial neural network for predicting the performance of CO2 enhanced oil recovery and storage in residual oil zones

Contact Info

Product

Resources

About