Optimization of Water-Alternating-CO2 Injection Field Operations Using a Machine-Learning-Assisted Workflow

Self Cite

The petroleum reservoir represents a complex heterogeneous system that requires thorough characterization prior to the implementation of any incremental recovery technique. One of the most commonly utilized and successful secondary recovery techniques is waterflooding. However, a lack of sufficient investigation into the inherent behavior and characteristics of the reservoir formation in situ can result in failure or suboptimal performance of waterflood operations. Therefore, a comprehensive understanding of the geological history, static and dynamic reservoir characteristics, and petrophysical data is essential for analyzing the mechanisms and causes of waterflood inefficiency and failure. In this study, waterflood inefficiency was observed in the Morrow B reservoir located in the Farnsworth Unit, situated in the northwestern shelf of the Anadarko Basin, Texas. To assess the potential mechanisms behind the inefficiency of waterflooding in the east half, geological, petrophysical, and reservoir engineering data, along with historical information, were integrated, reviewed, and analyzed. The integration and analysis of these datasets revealed that several factors contributed to the waterflood inefficiency. Firstly, the presence of abundant dispersed authigenic clays within the reservoir, worsened by low reservoir quality and high heterogeneity, led to unfavorable conditions for waterflood operations. The use of freshwater for flooding exacerbated the adverse effects of sensitive and migratory clays, further hampering the effectiveness of the waterflood. In addition to these factors, several reservoir engineering issues played a significant role in the inefficiency of waterflooding. These issues included inadequate perforation strategies due to the absence of detailed hydraulic flow units (HFUs) and rock typing, random placement of injectors, and uncontrolled injected fresh water. These external controlling parameters further contributed to the overall inefficiencies observed during waterflood operations in the east half of the reservoir. A detailed understanding of the mechanistic factors of inefficient waterflood operation will provide adequate insights into the development of the improved recovery technique for the field.

Section: Clay Composition/contentmentioning

confidence: 99%

Mechanisms of Waterflood Inefficiency: Analysis of Geological, Petrophysical and Reservoir History, a Field Case Study of FWU (East Section)

Morgan,

Ampomah,

Grigg

et al. 2024

Self Cite

“…Their results confirmed the ANN's suitability for predicting oil recoveries. You et al [149] developed Gaussian kernel SVR (Gaussian-SVR) models integrated with a multi-objective PSO algorithm to obtain optimal results for multi-objective optimization problems in the context of a CO 2 -WAG project. For the optimization, various operational parameters that affect the CO 2 -WAG operation (e.g., water/gas injection duration, producer BHP, water injection rate) were used.…”

Section: Machine Learning Models For Wag-eor Applications Static Mach...mentioning

confidence: 99%

Applications of Machine Learning in Subsurface Reservoir Simulation—A Review—Part II

Samnioti,

Gaganis

2023

In recent years, Machine Learning (ML) has become a buzzword in the petroleum industry, with numerous applications which guide engineers in better decision making. The most powerful tool that most production development decisions rely on is reservoir simulation with applications in multiple modeling procedures, such as individual simulation runs, history matching and production forecast and optimization. However, all of these applications lead to considerable computational time and computer resource-associated costs, rendering reservoir simulators as not fast and robust enough, and thus introducing the need for more time-efficient and intelligent tools, such as ML models which are able to adapt and provide fast and competent results that mimic the simulator’s performance within an acceptable error margin. In a recent paper, the developed ML applications in a subsurface reservoir simulation were reviewed, focusing on improving the speed and accuracy of individual reservoir simulation runs and history matching. This paper consists of the second part of that study, offering a detailed review of ML-based Production Forecast Optimization (PFO). This review can assist engineers as a complete source for applied ML techniques in reservoir simulation since, with the generation of large-scale data in everyday activities, ML is becoming a necessity for future and more efficient applications.

“…Parameters such as the water injection volume, gas injection volume, bottom hole pressure of producing wells, cycle ratio, cycle duration, injected hydrocarbon gas fraction, and total WAG cycle were optimized. You et al [25] combined Gaussian-SVR (support vector regression) with a Gaussian kernel to construct a surrogate model, and the hyperparameters of the surrogate model were optimized using Bayesian optimization. The trained surrogate model was then coupled with a multi-objective particle swarm optimization (MOPSO) protocol.…”

Section: Introductionmentioning

confidence: 99%

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

Gao,

Liu,

Qian

et al. 2023

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.