Shale oil resources, noted for their broad distribution and significant reserves, are increasingly recognized as vital supplements to traditional oil resources. In response to the high fracturing costs and swift decline in productivity associated with shale oil horizontal wells, this research introduces a novel approach utilizing CO₂ for enhanced shale oil recovery in radial boreholes. A compositional numerical simulation method is built accounted for component diffusion, adsorption, and non-Darcy flow, to explore the viability of this technique. The study examines how different factors—such as initial reservoir pressure, permeability, numbers of radial boreholes, and their branching patterns—influence oil production and CO₂ storage. Our principal conclusions indicate that with a constant CO₂ injection rate, lower initial reservoir pressures predominantly lead to immiscible oil displacement, hastening the occurrence of CO₂ gas channeling. Therefore, maintaining higher initial or injection pressures is critical for effective miscible displacement in CO₂-enhanced recovery using radial boreholes. Notably, the adsorption of CO₂ in shale oil results in the displacement of lighter hydrocarbons, an effect amplified by competitive adsorption. While CO₂ diffusion tends to prompt earlier gas channeling, its migration towards areas of lower concentration within the reservoir reduces the extent of channeling CO₂. Nonetheless, when reservoir permeability falls below 0.01 mD, the yield from CO₂-enhanced recovery using radial boreholes is markedly low. Hence, selecting high-permeability “sweet spot” regions within shale oil reservoirs for the deployment of this method is advisable. To boost oil production, utilizing longer and broader radial boreholes, increasing the number of boreholes, or setting the phase angle to 0° are effective strategies. Finally, by comparing the production of shale oil enhanced by CO₂ with that of a dual horizontal well fracturing system enhanced by CO₂, it was found that although the former’s oil production is only 50.6% of the latter, its cost is merely 11.1%, thereby proving its economic viability. These findings present a new perspective for the economically efficient extraction of shale oil, offering potential guidance for industrial practices.

The nanoscale pores in shale oil and gas are often filled with external nanomaterials to enhance wellbore stability and improve energy production. And there has been considerable research on discrete element blocking models and simulations related to nanoparticles. In this paper, the pressure transmission experimental platform is used to systematically study the influence law of different water activity salt solutions on shale permeability and borehole stability. In addition, the force model of the particles in the pore space is reconstructed to study the blocking law of the particle parameters and fluid physical properties on the shale pore space based on the discrete element hydrodynamic model. However, the migration and sealing patterns of nanomaterials in shale pores are unknown, as are the effects of changes in particle parameters on nanoscale sealing. The results show that: (1) The salt solution adopts a formate system, and the salt solution is most capable of blocking the pressure transmission in the shale pores when the water activity is 0.092. The drilling fluid does not easily penetrate into the shale pore space, and it is more capable of maintaining the stability of the shale wellbore. (2) For the physical blocking numerical simulation, the nanoparticle concentration is the most critical factor affecting the shale pore blocking efficiency. Particle size has a large impact on the blocking efficiency of shale pores. The particle diameter increases by 30% and the pore-blocking efficiency increases by 13% when the maximum particle size is smaller than the pore exit. (3) Particle density has a small effect on the final sealing effect of pore space. The pore-plugging efficiency is only increased by 4% as the particle density is increased by 60%. (4) Fluid viscosity has a significant effect on shale pore plugging. The increase in viscosity at a nanoparticle concentration of 1 wt% significantly improves the sealing effectiveness, specifically, the sealing efficiency of the 5 mPa-s nanoparticle solution is 16% higher than that of the 1 mPa-s nanoparticle solution. Finally, we present a technical basis for the selection of a water-based drilling fluid system for long horizontal shale gas drilling.

Q-compensated reverse time migration (Q-RTM) is a crucial technique in seismic imaging. However, stability is a prominent concern due to the exponential increase in high-frequency ambient noise during seismic wavefield propagation. The two primary strategies for mitigating instability in Q-RTM are regularization and low-pass filtering. Q-RTM instability can be addressed through regularization. However, determining the appropriate regularization parameters is often an experimental process, leading to challenges in accurately recovering the wavefield. Another approach to control instability is low-pass filtering. Nevertheless, selecting the cutoff frequency for different Q values is a complex task. In situations with low signal-to-noise ratios (SNRs) in seismic data, using low-pass filtering can make Q-RTM highly unstable. The need for a small cutoff frequency for stability can result in a significant loss of high-frequency signals. In this study, we propose a multi-task learning (MTL) framework that leverages data-driven concepts to address the issue of amplitude attenuation in seismic records, particularly when dealing with instability during the Q-RTM (reverse time migration with Q-attenuation) process. Our innovative framework is executed using a convolutional neural network. This network has the capability to both predict and compensate for the missing high-frequency components caused by Q-effects while simultaneously reconstructing the low-frequency information present in seismograms. This approach helps mitigate overwhelming instability phenomena and enhances the overall generalization capacity of the model. Numerical examples demonstrate that our Q-RTM results closely align with the reference images, indicating the effectiveness of our proposed MTL frequency-extension method. This method effectively compensates for the attenuation of high-frequency signals and mitigates the instability issues associated with the traditional Q-RTM process.

Natural fractures serve as important storage spaces and primary flow channels in hydrocarbon reservoirs. However, fracture identification using conventional well logs remains challenging due to complex logging responses and the limited number of fracture samples. Logging responses exhibit two important characteristics: different logging variables show complex nonlinear relationships, while fracture-related anomalies tend to vary continuously within local depth intervals. Motivated by these characteristics, an intelligent fracture prediction method based on a hybrid iTransformer-LSTM network combined with Gaussian Mixture Model (GMM)-based sample augmentation is proposed. The iTransformer module is used to capture inter-feature dependencies among different logging variables, while the LSTM module further models sequential variations along the depth direction. In addition, GMM-based sample augmentation is applied to the training fracture samples to learn their multivariate distribution and generate statistically consistent synthetic samples, thereby alleviating the influence of limited fracture samples. The proposed method was evaluated on two wells from the C7 target interval. On the WELL1 test set, it achieved an accuracy of $0.714\pm 0.038$, a Macro-F1 score of $0.708\pm 0.093$, and an AUC of $0.816\pm 0.042$. On the independent WELL2 blind well, it achieved an accuracy of $0.816\pm 0.093$, a Macro-F1 score of $0.502\pm 0.034$, an AUC of $0.734\pm 0.016$, and a fracture recall of $0.813\pm 0.163$. These results suggest potential for fracture identification under highly imbalanced conditions.