A deep-learning approach for reservoir evaluation for shale gas wells with complex fracture networks

Abstract

The complex fracture networks in shale gas reservoirs bring greater challenges and uncertainties to the modeling in reservoir evaluation. As the emerging potential technology, deep learning can be usefully applied to many aspects of reservoir evaluation. To further conduct the reservoir evaluation in rate transient analysis, this work proposes a data-driven proxy model for accurately evaluating the horizontal wells with complex fracture networks in shales. The production time, variable bottom hole pressure, and the fracture networks properties are used as input variables, while the output variable refers to the production for the forecast time period. The data from boundary element method is used to generate the proxy model for the learning process. The method of shuffled cross-validation is used to increase the model's accuracy and generalizability. The proxy model is coupled with recently developed deep learning methods such as attention mechanism, skip connection, and cross-validation to address the time series analysis problem for multivariate operating and physical parameters. Results demonstrate that the attention mechanism is robust. The operating parameters analysis shows that the attention mechanism has the ability to analyze variable pressure drop/flowrate data. Sensitivity analysis also indicates that the model takes into account the geometric characteristics of fracture network. The model reliability is proved by a case study from Marcellus shale. The computation time of the trained attention mechanism model is approximately 0.3 s, which equates to 3.8% of the physical model's running time.

Numerical Simulation of Fracture Flow Interaction Based on Discrete Fracture Model

“…From Figure 12, it can be observed that the impact of different oil-water viscosity ratios on f min and D is minimal, as the four curves are almost identical, and the influence of viscosity can only be reflected if the fracture permeability difference is small. The fracture flow rate formula derived from cubic law based on a single phase is applied to estimate the flow difference of fractures by previous researchers [51]. The equation indicates that permeability has a much greater impact on fracture flow than viscosity does.…”

Pore-Scale Transport Dynamic Behavior of Microspheres and Their Mechanisms for Enhanced Oil Recovery

“…Channeling of the injected fluid due to reservoir heterogeneity will reduce the swept fluid volume and reduce oil recovery. , No matter whether conventional or unconventional reservoirs − or gas − or water injection, plugging the dominant channels and expanding the swept volume of the injected fluid are the developmental ideas throughout the whole process of oil and gas field development . Additionally, due to the influence of reservoir wettability, the injected fluid tends to invade the pore throats with the least flow resistance under the action of a capillary force, which will also lead to the formation of dominant channels. , Therefore, the optimal selection of profile control agents and the revelation of their transport and plugging mechanisms in porous media are the focus of research. − …”

Microstructures and Pore Structures of Naturally Deformed Shales: Significance for Shale Gas Exploration in the Complex Tectonic Areas of the Margin of the Sichuan Basin, South China

“…Scholars have already conducted studies on the shale microstructures and pore structures in different strata and regions by various techniques, suggesting that their formation and evolution are affected by various geological conditions including the geochemistry, thermal maturity, lithology, and diagenesis. ,,, In addition, typical deformation microstructures of naturally deformed shales have been observed and investigated in the literature. ,− Nevertheless, few authors specifically address such geoscientific issues in deformed gas shale systems because they think complex deformation is an unfavorable condition for gas enrichment, and the relationship among the deformation property, gas storage, and migration have not been thoroughly explored. , …”

“…Unlike the gas shale in North America, which was found in relatively stable tectonic settings, Chinese organic-rich marine shale experienced several episodes of intensive tectonic activity after the end of hydrocarbon generation, which has given rise to complex tectonic settings. ,− Shale is deformed in situ and generally occurs at depths in the subsurface where pores and textures are formed under tectonic stress with new structures and tectonic characteristics . Obviously, the deformation properties in these naturally deformed shales are critical for enhanced (or further reduced) porosity and permeability, thus influencing the storage and migration of gas.…”

“…Obviously, the deformation properties in these naturally deformed shales are critical for enhanced (or further reduced) porosity and permeability, thus influencing the storage and migration of gas. Moreover, they can greatly affect the structural integrity, orientation, pore or fracture structure, connectivity, and continuity of shale. − Significant differences do exist in the reservoir property in undeformed shale versus deformed shale, which is the key and a challenge for understanding the gas storage and migration pathway and needs to be understood deeply. Powerful proof is that a number of shale gas fields, such as Fuling, Pengshui, Wulong, Wuxi, Chengkou, etc., and many wells have been discovered and drilled in such a strongly tectonic deformation areas, with high gas content, which would provide a great chance to understand how shale microstructure and pore structure develop during tectonic deformation. − …”