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

Gao, Ming; Liu, Zhaoxia; Qian, Shihao; Liu, Wanlu; Li, Weirong; Yin, Hengfei; Cao, Jinhong

doi:10.3390/en16176149

Cited by 5 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various statistical methods [38] 2021; ADP approximate dynamic programming [39] 2021; XGBoost-PSO [40] 2023…”

Section: Designing Flooding Planmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning in Reservoir Engineering: A Review

Zhou,

Liu,

Liu

et al. 2024

Processes

View full text Add to dashboard Cite

With the rapid progress of big data and artificial intelligence, machine learning technologies such as learning and adaptive control have emerged as a research focus in petroleum engineering. They have various applications in oilfield development, such as parameter prediction, optimization scheme deployment, and performance evaluation. This paper provides a comprehensive review of these applications in three key scenarios of petroleum engineering, namely hydraulic fracturing and acidizing, chemical flooding and gas flooding, and water injection. This article first introduces the steps and methods of machine learning processing in these scenarios, then discusses the advantages, disadvantages, existing challenges, and future prospects of these machine learning methods. Furthermore, this article compares and contrasts the strengths and weaknesses of these machine learning methods, aiming to help researchers select and improve their methods. Finally, this paper identifies some potential development trends and research directions of machine learning in petroleum engineering based on the current issues.

show abstract

“…Various statistical methods [38] 2021; ADP approximate dynamic programming [39] 2021; XGBoost-PSO [40] 2023…”

Section: Designing Flooding Planmentioning

confidence: 99%

“…The SVM-based prediction model proposed by Hao Chen [38], which utilizes multiple statistical methods to screen the main control factors, works well. Gao M. [40] and others designed the XGBoost-PSO method, which, in comparison with eight types of methods, is a very good way to carry out CO 2 flooding parameter design.…”

Section: Design Of Flooding Planmentioning

confidence: 99%

Machine Learning in Reservoir Engineering: A Review

Zhou,

Liu,

Liu

et al. 2024

Processes

View full text Add to dashboard Cite

show abstract

“…To achieve this, the study gathered a large dataset through the definition of uncertainty variables and the application of Latin hypercube sampling, guided by previous sensitivity analyses that highlighted key factors in the EOR-CO 2 process [1,[42][43][44][45]. Consequently, nine parameters were selected for detailed analysis: porosity (Por), permeability (Perm), reservoir thickness (Thickness), fracture half-length (FHL), bottom hole flowing pressure (BHP), injection rate of CO 2 (CO 2 -INJ), cumulative injected CO 2 mass (CO 2 -CMASS), soaking time (SOAK-T), and number of fractures (Numfrac).…”

Section: Obtaining Numerical Simulation Datamentioning

confidence: 99%

Prediction of ORF for Optimized CO2 Flooding in Fractured Tight Oil Reservoirs via Machine Learning

Yue,

Dai,

Liao

et al. 2024

Energies

View full text Add to dashboard Cite

Tight reservoirs characterized by complex physical properties pose significant challenges for extraction. CO2 flooding, as an EOR technique, offers both economic and environmental advantages. Accurate prediction of recovery rate plays a crucial role in the development of tight oil and gas reservoirs. But the recovery rate is influenced by a complex array of factors. Traditional methods are time-consuming and costly and cannot predict the recovery rate quickly and accurately, necessitating advanced multi-factor analysis-based prediction models. This study uses machine learning models to rapidly predict the recovery of CO2 flooding for tight oil reservoir development, establishes a numerical model for CO2 flooding for low-permeability tight reservoir development based on actual blocks, studies the effects of reservoir parameters, horizontal well parameters, and injection-production parameters on CO2 flooding recovery rate, and constructs a prediction model based on machine learning for the recovery. Using simulated datasets, three models, random forest (RF), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM), were trained and tested for accuracy evaluation. Different levels of noise were added to the dataset and denoised, and the effects of data noise and denoising techniques on oil recovery factor prediction were studied. The results showed that the LightGBM model was superior to other models, with R2 values of 0.995, 0.961, 0.921, and 0.877 for predicting EOR for the original dataset, 5% noise dataset, 10% noise dataset, and 15% noise dataset, respectively. Finally, based on the optimized model, the key control factors for CO2 flooding for tight oil reservoirs to enhance oil recovery were analyzed. The novelty of this study is the development of a machine-learning-based method that can provide accurate and cost-effective ORF predictions for CO2 flooding for tight oil reservoir development, optimize the development process in a timely manner, significantly reduce the required costs, and make it a more feasible carbon utilization and EOR strategy.

show abstract

“…Simultaneously implementing both pressure retention and water-alternating-gas (WAG) flooding is costly but can significantly increase oil recovery [22][23][24][25][26][27]. Pure CO 2 offers higher oil recovery and net present value compared to impure CO 2 [28][29][30][31].…”

Section: Introductionmentioning

confidence: 99%

Comprehensive Study of Development Strategies for High-Pressure, Low-Permeability Reservoirs

Nan,

Xin,

et al. 2023

Processes

View full text Add to dashboard Cite

Currently, there is no well-established framework for studying development patterns in high-pressure, low-permeability reservoirs. The key factors influencing development effect typically include the reservoir properties, well pattern, well spacing, and the rate of oil production. Reservoir A is a representative of this type of reservoir. Starting from its physical properties, a study of the development mechanism was conducted using the tNavigator (22.1) software. A total of 168 sets of numerical experiments were conducted, and 3D maps were innovatively created to optimize the development mode. Building upon the preferred mode, an exploration was carried out for the applicability of gas flooding and the optimization of water flooding schemes for such reservoirs. All experimental results were reasonably validated through Reservoir A. Furthermore, due to the high original pressure in such reservoirs, the injection of displacement media was challenging. Considering economic benefits simultaneously, a study was conducted to explore the rational utilization of natural energy. The research proved that for a reservoir with a permeability of about 10 mD, the suitable development scheme was five-point well pattern, a well spacing of 350 m, water–gas alternating flooding, and an initial oil production rate of 2%. When the reservoir underwent 8 months of depleted development, corresponding to a reduction in the reservoir pressure coefficient to 1.09, the development efficiency was relatively favorable. Over a 15-year production period, the oil recovery reached 29.98%, the water cut was 10.31%, and the reservoir pressure was maintained at around 67.18%. The geology of the newly discovered reservoir is not specific in the early stage of oilfield construction, and this research can help to determine a suitable development scheme.

show abstract

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

Cited by 5 publications

References 43 publications

Machine Learning in Reservoir Engineering: A Review

Machine Learning in Reservoir Engineering: A Review

Prediction of ORF for Optimized CO2 Flooding in Fractured Tight Oil Reservoirs via Machine Learning

Comprehensive Study of Development Strategies for High-Pressure, Low-Permeability Reservoirs

Contact Info

Product

Resources

About