Aquifer Matching With Material Balance Using Particle Swarm Optimization Algorithm – PSO

Ottah, D. G.; Ikiensikimama, S. S.; Matemilola, S.A.

doi:10.2118/178319-ms

Cited by 4 publications

(1 citation statement)

References 11 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the prediction accuracy of the machine learning models, the coefficient of determination (R 2 ) was selected as the metric [43]. The R 2 value ranges from 0 to 1, with a higher value indicating a better fit of the model.…”

Section: Machine Learning Model Buildingmentioning

confidence: 99%

Machine-Learning-Based Approach to Optimize CO2-WAG Flooding in Low Permeability Oil Reservoirs

Gao,

Liu,

Qian

et al. 2023

Energies

View full text Add to dashboard Cite

One of the main applications of carbon capture, utilization, and storage (CCUS) technology in the industry is carbon-dioxide-enhanced oil recovery (CO2-EOR). However, accurately and rapidly assessing their application potential remains a major challenge. In this study, a numerical model of the CO2-WAG technique was developed using the reservoir numerical simulation software CMG (Version 2021), which is widely used in the field of reservoir engineering. Then, 10,000 different reservoir models were randomly generated using the Monte Carlo method for numerical simulations, with each having different formation physical parameters, fluid parameters, initial conditions, and injection and production parameters. Among them, 70% were used as the training set and 30% as the test set. A comprehensive analysis was conducted using eight different machine learning regression methods to train and evaluate the dataset. After evaluation, the XGBoost algorithm emerged as the top-performing method and was selected as the optimal approach for the prediction and optimization. By integrating the production prediction model with a particle swarm optimizer (PSO), a workflow for optimizing the CO2-EOR parameters was developed. This process enables the rapid optimization of the CO2-EOR parameters and the prediction of the production for each period based on cumulative production under different geological conditions. The proposed XGBoost-PSO proxy model accurately, reliably, and efficiently predicts production, thereby making it an important tool for optimizing CO2-EOR design.

show abstract

Section: Machine Learning Model Buildingmentioning

confidence: 99%

Machine-Learning-Based Approach to Optimize CO2-WAG Flooding in Low Permeability Oil Reservoirs

Gao,

Liu,

Qian

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

Reservoir Production Optimal Control Using Parameterization Method and General Upscaling Stochastic Approximation Algorithm

Lei

Zeng

Wang

et al. 2021

Springer Series in Geomechanics and Geoengineering

View full text Add to dashboard Cite

A Stochastic Optimization Approach for Profit Maximization Using Alkaline-Surfactant-Polymer Flooding in Complex Reservoirs

et al. 2018

View full text Add to dashboard Cite

In heterogeneous reservoir formations, water tends to have early breakthrough due to the overriding and viscous fingering during secondary recovery. The overall hydrocarbon recovery efficiency remains very low in gas and water flooding projects because of less viscosity and higher mobility of water and gas. Therefore, there is an underlying need for improving recovery through a suitable chemical enhanced oil recovery (EOR) method. After investigating the feasibility of alkaline, polymer, surfactant, surfactant-polymer, alkaline-polymer and alkaline-surfactant-polymer (ASP) flood, ASP was selected as a chemical EOR method in low permeability heterogeneous reservoirs. However, the performance of the ASP flooding was highly dependent on operational parameters. Thus, it was important to select these parameters with extensive care to increase the recovery along with the profitability. The relationship between the ASP flooding operational parameters and profitability (NPV) has not been yet understood fully. In this research, the new stochastic optimization approach to optimize the ASP flooding operational parameters has been proposed. To gain the objective of this research, a numerical simulation study was carried out and Particle Swarm Optimization (PSO) was implemented as an optimization algorithm. The net present value (NPV) served as the objective function that has to be maximized among the compared flooding processes. The used operational parameters were location of production and injection well, number of injection cycles, oil production rate, ASP injection time, ASP injection rate, alkaline-surfactant and polymer concentrations, surfactant and polymer viscosities. Sensitivity study of these parameters shows significant impact on net present value and ultimate oil recovery. Results also confirm that NPV is increased significantly after the optimization of all flooding parameters by using Particle Swarm Optimizer. The new optimized model was developed for designing the ASP as a chemical EOR method in low permeability heterogeneous reservoir. It can be served as a handy tool for reservoir engineer to select the best ASP flood parameters to achieve maximum NPV.

show abstract

Aquifer Matching With Material Balance Using Particle Swarm Optimization Algorithm – PSO

Cited by 4 publications

References 11 publications

Machine-Learning-Based Approach to Optimize CO2-WAG Flooding in Low Permeability Oil Reservoirs

Machine-Learning-Based Approach to Optimize CO2-WAG Flooding in Low Permeability Oil Reservoirs

Reservoir Production Optimal Control Using Parameterization Method and General Upscaling Stochastic Approximation Algorithm

A Stochastic Optimization Approach for Profit Maximization Using Alkaline-Surfactant-Polymer Flooding in Complex Reservoirs

Contact Info

Product

Resources

About