The activity of synsedimentary faults plays an important role in controlling the distribution of sand bodies in basins and furthermore the porosity and permeability of reservoirs. We have used fault interpretation, the method of image and granularity size analysis, and the seismic pumping effect to investigate the control of the activity of the Kongdong fault on the development degree of the dissolution pores and grain size, further studying the controlling mechanism of the activity of synsedimentary faults on reservoir quality (porosity and permeability). The results showed that the slip rate of synsedimentary faults is one of the main factors in controlling reservoir quality. The slip rate controls the accommodation space and hydrodynamic conditions and it furthermore controls the grain size. The higher the slip rate, the bigger the grain size in the downthrow wall of synsedimentary faults; the seismic pump produced by synsedimentary faults activity also controls the development degree of dissolution pores. The development degree of dissolution pores in the downthrown wall of synsedimentary faults is greater than that in the upthrown wall. Dissolution pores are more developed in areas with a large slip rate of synsedimentary faults. Porosity increases gradually with the increase of plane porosity of dissolution pores, whereas the changes of permeability are not obvious.

Lithofacies identification and classification are critical for characterizing the hydrocarbon potential of unconventional resources. Although extensive applications of machine learning models in predicting lithofacies have been applied to conventional reservoir systems, the effectiveness of machine learning models in predicting clay-rich, lacustrine shale lithofacies has yet to be tackled. Here, we apply machine learning models to conventional well log data to automatically identify the shale lithofacies of Gulong Shale in the Songliao Basin. The shale lithofacies were classified into six types based on total organic carbon and mineral composition data from core analysis and geochemical logs. We compared the accuracy of Multilayer Perceptron (MLP), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Random Forest models. We mitigated the bias of imbalanced data by applying oversampling algorithms. Our results show that ensemble methods (XGBoost and Random Forest) have a better performance in shale lithofacies identification than the other models do, with accuracies of 0.868 and 0.884, respectively. The organic siliceous shale proposed to have the best hydrocarbon potential in Gulong Shale can be identified with F1 scores of 0.853 by XGBoost and 0.877 by Random Forest. Our study suggests that ensemble machine learning models can effectively identify the lithofacies of clay-rich shale from conventional well logs, providing insight into the sweet spot prediction of unconventional reservoirs. Further improvements in model performances can be achieved by adding domain knowledge and employing advanced well log data.

The architecture analysis of the different orders sedimentary bodies is of great significance to the efficient development of oil and gas fields. In order to investigate the effects of the architectural interfaces on reservoir quality and heterogeneity, this study takes the Gudong oil field as a case to investigate the architectural characteristics of hierarchical bounding surfaces using detailed descriptions of core and wireline logs. Architectural models from the 7th-order to the 3rd-order are analyzed, and the developmental characteristics of the 5th-order braided river, 4th-order single sandstone, and 3rd-order accretion are summarized. The interlayer between two braided rivers is floodplain mud deposition, with poor physical properties, stable thickness, and strong blocking capacity. Two models of interlayers are found in the 4th-order deposition. The first interlayer is between the braided filling channel and midchannel bar, which is composed of generally fine-grained sediments with calcium cementation and poor physical properties. The second interlayer is a transformation belt between two midchannel bars and is generally composed of gravel-scoured deposition with penetration capability. The 3rd-order surfaces are defined as the surfaces of accretions within midchannel bars. Two models of interlayers are also found in the 3rd-order surfaces of accretions. The paleocurrent of the sandy braided river is reconstructed by synthesizing the core data, well logging data, and production performance data. A total of 1 fluvial system (7th-order), 2 compound braided rivers (6th-order), 11 braided rivers (5th-order), 41 midchannel bars (4th-order), and 96 accretions (3rd-order) are developed in the study area.

The Bakken Formation is a typical tight oil reservoir and oil production formation in the world. Pore structure is one of the key factors that determine the accumulation and production of the hydrocarbon. In order to study the pore structures and main controlling factors of the Bakken Formation, 12 samples were selected from the Bakken Formation and conducted on a set of experiments including X-ray diffraction mineral analysis (XRD), total organic carbon (TOC), vitrinite reflectance (R_o), and low-temperature nitrogen adsorption experiments. Results showed that the average TOC and R_o of Upper and Lower Bakken shale is 10.72 wt% and 0.86%, respectively. The Bakken Formation develops micropores, mesopores, and macropores. However, the Upper and Lower Bakken shale are dominated by micropores, while the Middle Bakken tight reservoir is dominated by mesopores. The total pore volume and specific surface area of the Middle Bakken are significantly higher than those of the Upper and Lower Bakken, indicating that Middle Bakken is more conducive to the storage of oil and gas. Through analysis, the main controlling factors for the pore structure of the Upper and Lower Bakken shale are TOC and maturity, while those for Middle Bakken are clay and quartz contents.