Polymer flooding is drawing lots of attention because of the technical maturity in some reservoirs. The first commercial polymer flooding in China was performed in the Daqing oilfield and is one of the largest applications in the world. Some laboratory tests from Daqing researchers in China showed that the viscoelasticity of high molecular weight polymers plays a significant role in increasing displacement efficiency. Hence, encouraged by the conventional field applications and new findings on the viscoelasticity effect of polymers on residual oil saturation (ROS), some high-concentration high-molecular-weight (HCHMW) polymer-flooding field tests have been conducted. Although some field tests were well-documented, subsequent progress was seldom reported. It was recently reported that HCHMW has a limited application in Daqing, which does not agree with observations from laboratory core flooding and early field tests. However, the cause of this discrepancy is unclear. Thus, a systematic summary of polymer-flooding mechanisms and field tests in China is necessary. This paper explained why HCHMW is not widely used when considering new understandings of polymer-flooding mechanisms. Different opinions on the viscoelasticity effect of polymers on ROS reduction were critically reviewed. Other mechanisms of polymer flooding, such as wettability change and gravity stability effect, were discussed with regard to widely reported laboratory tests, which were explained in terms of the viscoelasticity effects of polymers on ROS. Recent findings from Chinese field tests were also summarized. Salt-resistance polymers (SRPs) with good economic performance using produced water to prepare polymer solutions were very economically and environmentally promising. Notable progress in SRP flooding and new amphiphilic polymer field tests in China were summarized, and lessons learned were given. Formation blockage, represented by high injection pressure and produced productivity ability, was reported in several oil fields due to misunderstanding of polymers’ injectivity. Although the influence of viscoelastic polymers on reservoir conditions is unknown, the injection of very viscous polymers to displace medium-to-high viscosity oils is not recommended. This is especially important for old wells that could cause damage. This paper clarified misleading notions on polymer-flooding implementations based on theory and practices in China.

Oil production from tight oil reservoirs has become economically feasible because of the combination of horizontal drilling and multistage hydraulic fracturing. Optimal fracture design plays a critical role in successful economical production from a tight oil reservoir. However, many complex parameters such as fracture spacing and fracture half-length make fracturing treatments costly and uncertain. To improve fracture design, it is essential to determine reasonable ranges for these parameters and to evaluate their effects on well performance and economic feasibility. In traditional analytical and numerical simulation methods, many simplifications and assumptions are introduced for artificial fracture characterization and gas percolation mechanisms, and their implementation process remains complicated and computationally inefficient. Most previous studies on big data-driven fracturing parameter optimization have been based on only a single output, such as expected ultimate recovery, and few studies have integrated machine learning with evolutionary algorithms to optimize fracturing parameters based on time-series production prediction and economic objectives. This study proposed a novel approach, combining a data-driven model with evolutionary optimization algorithms to optimize fracturing parameters. We established a significant number of static and dynamic data sets representing the geological and developmental characteristics of tight oil reservoirs from numerical simulation. Four production-prediction models based on machine-learning methods—support vector machine, gradient-boosted decision tree, random forest, and multilayer perception—were constructed as mapping functions between static properties and dynamic production. Then, to optimize the fracturing parameters, the best machine-learning-based production predictive model was coupled with four evolutionary algorithms—genetic algorithm, differential evolution algorithm, simulated annealing algorithm, and particle swarm optimization—to investigate the highest net present value (NPV). The results show that among the four production-prediction models established, multilayer perception (MLP) has the best prediction performance. Among the evolutionary algorithms, particle swarm optimization (PSO) not only has the fastest convergence speed but also the highest net present value. The optimal fracturing parameters for the study area were identified. The hybrid MLP-PSO model represents a robust and convenient method to forecast the time-series production and to optimize fracturing parameters by reducing manual tuning.

Hydraulic fracturing is a crucial method in shale oil development, and predicting production after hydraulic fracturing is one of the challenges in shale oil development. Conventional methods for predicting production include analytical methods and numerical simulation methods, but these methods involve many parameters, have high uncertainty, and are time-consuming and costly. With the development of shale oil development, there are more and more sample data on the geological parameters, engineering parameters, and development parameters of shale oil hydraulic fracturing, making it possible to use machine learning methods to predict production after hydraulic fracturing. This article first analyzes the impact of different parameters on initial production and recoverable reserves based on field data from Chang-7 shale oil in the Ordos Basin of China. Then, using the Particle Swarm Optimization (PSO) algorithm and the Gradient Boosting Decision Tree (GBDT) algorithm, machine learning models for initial production and recoverable reserves are established. The Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) explanation methods are used to explain the models. The study found that initial production is highly correlated with parameters such as the number of fracturing stages and fracturing fluid volume, while recoverable reserves are significantly related to parameters such as well spacing, area, and reserver-controlled. The PSO-GBDT model established in this study has an accuracy of over 85% and can be used for production prediction and subsequent parameter optimization research. By comparing the LIME and SHAP local explanation methods, it is shown that different explanation methods can obtain reasonable and credible local explanation results. This article establishes a high-precision shale oil well production prediction model and two model interpretation methods, which could provide technical support for shale oil well production prediction and production analysis.

Based on a large number of empirical statistics of tertiary oil recovery technology in China, including polymer flooding, chemical flooding, gas flooding, in situ combustion, steam flooding, ect., 22 key reservoir parameters were filterized. Five levels of quantitative screening criteria were developed for different tertiary oil recovery methods. The mean algorithm for the downward approximation and the grey correlation theory were used in this paper to quickly select the appropriate tertiary oil recovery method for the target blocks, which provides a preferred development method for subsequent potential evaluation. In the rapid analogy evaluation method of tertiary oil recovery potential, the total similarity ratio between the target block and the example block is determined. The target block is matched with the appropriate instance block according to the total similarity ratio value, using 80% as the boundary. The ratio of the geological reserves is used to predict the oil recovery interval, the actual annual injection data, and the economic profit, thus quickly predicting the economic potential of the tertiary oil recovery technology in the target block. Currently, our research team has integrated these two methods into the tertiary oil production potential evaluation software EORSYS3.0. The empirical analysis shows that this method is reasonable and the conclusion is reliable. In addition, the actual enhanced recovery value is within the effective range predicted by the method. The method and results of this paper will provide an important decision-making reference for the application and sustainable development of China Petroleum’s main tertiary oil recovery technology in the next 5–10 years.

Gas injection has received increasing attention as one of the key technologies to enhance oil recovery. When gas is dissolved in crude oil, it will accelerate the flow of crude oil by reducing the density, viscosity, interfacial tension (IFT), and other properties of crude oil, so IFT is one of the main factors affecting the recovery of the gas drive. The interfacial properties of CH₄, one of the principal associated hydrocarbon gases, with crude oil remain unclear. In this study, molecular dynamics (MD) simulations were used to determine the IFTs of pure and impure CH₄ with n-decane as well as the IFTs of the ternary systems CH₄ + n-hexane + n-decane and CH₄ + n-decane + n-nonadecane. Additionally, investigating factors including pressure, temperature, gas composition, and crude oil composition reveals the mechanisms affecting the interfacial properties of CH₄ and crude oil. The results demonstrate that CO₂ significantly lowers the IFT of CH₄ + n-decane; the effect of crude oil components on IFT varies with the properties of the crude oil and, generally speaking, IFT is greater for crude oils containing heavy components than for those containing light components; the effect of temperature on the IFT of the CH₄ + n-decane system is more pronounced at low pressure and decreases with increasing pressure. This study contributes to understanding the behavior of CH₄ and oil systems in the formation and could be used to enhance the oil recovery technology.