Search

Shale oil has become a crucial unconventional resource, bolstering energy supply security, and it is important to accurately predict shale oil production dynamics. However, traditional prediction methods are faced with the challenges of large data fluctuations and numerous interference factors, which make accurate prediction difficult. This paper introduces a deep learning approach, specifically a physical constraint-based convolutional neural network combined with long short-term memory and attention mechanism (CNN-LSTM-AM), to predict shale oil production dynamics. Initially, the correlation analysis method is used to analyze the correlation strengths of features with the prediction target, and the data that are most strongly correlated with the daily oil production are screened out and preprocessed. Key features are then extracted; that is, the CNN layer's output is fed into the LSTM layer, the output of which informs a fully connected layer for time-series production predictions. The model integrates an AM to concentrate on vital data aspects. In the "five-linear flow" formula, the imbibition is hard-coded into the shale oil production prediction model. Physical constraints are introduced into the model. Data driven and empirical formulas are used to introduce a loss function as a constraint condition in the training process of a machine learning model to improve the interpretability and predictive ability of the model. During the tuning phase, Bayesian optimization is used to fine-tune the model's hyperparameters. Shapley additive explanation and accumulated local effects analyses are used to further assess and quantify the significance of the essential parameters, thus optimizing the prediction effectiveness. [ABSTRACT FROM AUTHOR]

This paper reviews the basic research means for oilfield development and also the researches and tests of enhanced oil recovery (EOR) methods for mature oilfields and continental shale oil development, analyzes the problems of EOR methods, and proposes the relevant research prospects. The basic research means for oilfield development include in-situ acquisition of formation rock/fluid samples and non-destructive testing. The EOR methods for conventional and shale oil development are classified as improved water flooding (e.g. nano-water flooding), chemical flooding (e.g. low-concentration middle-phase micro- emulsion flooding), gas flooding (e.g. micro/nano bubble flooding), thermal recovery (e.g. air injection thermal-aided miscible flooding), and multi-cluster uniform fracturing/water-free fracturing, which are discussed in this paper for their mechanisms, approaches, and key technique researches and field tests. These methods have been studied with remarkable progress, and some achieved ideal results in field tests. Nonetheless, some problems still exist, such as inadequate research on mechanisms, imperfect matching technologies, and incomplete industrial chains. It is proposed to further strengthen the basic researches and expand the field tests, thereby driving the formation, promotion and application of new technologies. [ABSTRACT FROM AUTHOR]

Molecular diffusion is critical for enhanced oil recovery (EOR) in shale oil reservoirs with complex fracture networks. Understanding the influence of fractures on diffusive mass transfer is crucial for predicting oil recovery and remaining oil distribution. Diffusive mass transfer between fractures and matrix is critical in comprehensively and effectively simulating molecular diffusion. Resolution of matrix cells significantly affects diffusion accuracy at the fracture–matrix interface. Low resolution results in multiple fractures in the same matrix cell, leading to decreased precision in calculating mass transfer by conventional methods. To address this, a novel multiphase and multicomponent model is proposed. The new model integrating the consideration of fracture spacing modifies molecular diffusion transmissibility between fracture and matrix in an embedded discrete fracture model. The discretization employs the two-point flux approximation in the finite-volume method. Validation compares the coarser mesh to the finest grid as a reliable reference. Results show the proposed model accurately captures diffusive mass transfer in a coarser mesh. Modified models study molecular diffusion's effects on EOR in shale oil reservoirs with complex fracture networks by CO2 huff and puff. Results indicate that increasing injection rates cannot improve oil recovery under extremely low porosity and permeability. Molecular diffusion facilitates CO2 penetration into the formation. This expands the swept CO2 volume and increases both volume expansion and formation energy. In addition, the light and heavy components of the crude oil are diffused into the fractures and eventually produced, which reduces gas production in the case of diffusion. [ABSTRACT FROM AUTHOR]

Gulong shale oil is found in a typical continental shale oil reservoir, which is different from marine shale oil reservoirs. The Gulong shale oil reservoir is a pure shale-type oil reservoir with abundantly developed nanoscale pores, making it extremely difficult to unlock fluids. Pressure drive does not easily achieve fluid unlock conditions; thus, it is necessary to utilize imbibition to unlock nanoscale pore fluids. In this study, experiments were conducted on oil displacement by high-speed centrifugal pressure and imbibition under different conditions, respectively, and simulations were used to evaluate the effects of pressure differential drive and imbibition efficiency on the utilization of crude oil following fracturing. Combined with the mixed wettability of the reservoir, the imbibition efficiency was analyzed, and the imbibition efficiency at different soaking stages was evaluated. When the fracturing pressure was higher than the matrix pore pressure, the imbibition efficiency was the most obvious, which was 27.9%. Spontaneous imbibition depending solely on capillary force had poor efficiency, at 16.8%. When the fracturing pressure was lower than the matrix pore pressure, the imbibition efficiency was the lowest, at only 1.3%. It is proposed that strengthening fracture pressure and promoting pressurized imbibition are the keys to improving shale oil development. [ABSTRACT FROM AUTHOR]

The pore structure of shale oil reservoirs is complex, and the microscale and nanoscale effect is obvious in the development of shale oil reservoirs. Understanding the oil flow mechanism in shale reservoirs is essential for optimizing the development plan and enhancing the recovery rate of shale oil reservoirs. In this review, we briefly introduce the occurrence status of shale oil and shale oil flow in the inorganic matrix and the organic matrix (including the shrinkage of kerogen, oil diffusion in kerogen, oil transport in the organic pore channels, coupling of diffusion, and fluid transport in the organic matrix). Then, the shale oil microflow simulation and a coupling model of double-porous media for microflow and macroflow in the production process of shale oil are discussed. Finally, we summarize the main conclusions and perspectives on the oil flow mechanism and numerical simulations in shale oil reservoirs. An accurate description of shale oil occurrence status and shale oil flow in the inorganic and organic matrices is crucial for the numerical simulation of shale oil reservoirs. It can provide a basis and reference for the future directions of shale oil flow and numerical simulations during the development of shale oil reservoirs. [ABSTRACT FROM AUTHOR]

In recent years, CO2 huff and puff has become one of the most important methods developed for unconventional shale oil reservoirs and has been widely used in all major shale oil fields. However, the microscopic mechanism of CO2 contacting with crude oil is complex, and the change law of the residual oil occurrence after CO2 injection is unclear. In this paper, a micro visualization fluid flow simulation experiment (microfluidic experiment) under high temperatures and high pressure of a shale reservoir was conducted to reveal the micro mechanism of CO2 and crude oil after contact at the microscale. This allows conclusion of more precise results than any experiment conducted in a room environment. Combined with gas–oil two-phase micro flow characteristics, the production mechanisms of crude oil by CO2 huff and puff at the pore scale are clarified, and the change characteristics of the remaining oil occurrence state after CO2 injection are quantified. The results show that CO2 mainly produces crude oil in macropores and microfractures in the injection stage of huff and puff, improves the mobility of crude oil through diffusion dissolution in the soaking stage, and that the driving of dissolved gas is dominant in depressurization production. The major micro-mechanisms for CO2 to improve shale oil are extraction and dissolution expansion, accompanied by a variety of secondary mechanisms, such as the miscibility effect, oil expansion, viscosity reduction and other contact effects, as well as the improvement of crude oil properties. The simulation results of huff and puff development show that soaking is an important stage to enhance oil recovery. With increasing soaking time or the soaking pressure, the recovery degree of crude oil will increase positively. [ABSTRACT FROM AUTHOR]

For shale oil reservoirs, the horizontal well multistage fracturing technique is mostly used to reform the reservoir in order to achieve economic and effective development. The size of the reservoir reconstruction volume and the quantitative characterization of the fracture system are of great significance to accurately predict the productivity of shale oil wells. There are few flowback models for shale oil reservoirs. To solve this problem, first, a physical model of the simultaneous production of oil, gas, and water in the early flowback stage of shale oil development is established using the material balance equation for a fracture system. Second, the physical model of the underground fracture system is simplified, which is approximately regarded as a thin cylindrical body with a circular section. The flow of the fluid in the fracture system is approximately regarded as radial flow. In this model, the expansion of the fluid and the closure of the fracture are defined as integrated storage coefficients to characterize the storage capacity of the fracture system. Then, the curves illustrating the relationships between the oil-water ratio and the cumulative oil production and between the gas-water ratio and the cumulative gas production are drawn, and the curves are used to divide the flowback stage into an early stage and a late stage because the flowback process of shale oil wells exhibits obvious stage characteristics. Finally, the reservoir reconstruction volume and the related hydraulic fracture parameters are estimated based on the material balance method, and the rationality of the model is verified via numerical simulation. The interpretation results of this novel model are more accurate, making it an effective way to evaluate the hydraulic fracture parameters and transformation effect, and it has guiding significance for the evaluation of the hydraulic fracturing effect in the field. [ABSTRACT FROM AUTHOR]