The total organic carbon content (TOC) is a core indicator for shale gas reservoir evaluations. Machine learning-based models can quickly and accurately predict TOC, which is of great significance for the production of shale gas. Based on conventional logs, the measured TOC values, and other data of 9 typical wells in the Jiaoshiba area of the Sichuan Basin, this paper performed a Bayesian linear regression and applied a random forest machine learning model to predict TOC values of the shale from the Wufeng Formation and the lower part of the Longmaxi Formation. The results showed that the TOC value prediction accuracy was improved by more than 50% by using the well-trained machine learning models compared with the traditional method in an overmature and tight shale. Using the halving random search cross-validation method to optimize hyperparameters can greatly improve the speed of building the model. Furthermore, excluding the factors that affect the log value other than the TOC and taking the corrected data as input data for training could improve the prediction accuracy of the random forest model by approximately 5%. Data can be easily updated with machine learning models, which is of primary importance for improving the efficiency of shale gas exploration and development.

The Linnan Sag is one of the main oil-producing units in the Huimin Depression, Eastern China, and the pore pressure gradients obtained from drill stem tests (DSTs) range from 9.0 to 16.0 MPa/km. Uncertainty about the origin and distribution of abnormally high pressures in the Linnan Sag has led to different interpretations of hydrocarbon accumulation and resource assessments, and it interferes with safe drilling. In the Linnan Sag, mudstone compaction curves are substantially affected by several non-compaction factors, and the normal trend of the compaction curve is difficult to determine. The determination of the origin and distribution of overpressure in the Linnan Sag is a challenge. In this study, the factors that may affect mudstone compaction—such as the shale volume, higher calcareous, and organic matter content—were carefully examined and processed. The pressures in the mudstones were estimated by the corrected mudstone compaction curves, which were compiled from acoustic, density, and neutron logs, and calibrated using DST and mud weight data. The log response–vertical effective stress and acoustic velocity-density crossplots were used to identify the mechanisms that generate overpressure. The comprehensive compaction curve shows that the mudstones in the overpressured layer exhibit clear disequilibrium compaction characteristics. The logging response crossplots demonstrate that those overpressured points were consistent with the loading curve. The findings suggest that, the fundamental mechanism resulting in overpressures is the disequilibrium compaction of thick Paleocene mudstones. Hydrocarbon generation and vertical transfer of overpressure may be the main unloading mechanisms, which corresponds to the overpressure points that deviate from the loading curves. Since organic matter cracking may occur in formations at depths greater than 4000 m (Ro > 1.0%), the contribution of hydrocarbon generation to overpressuring is expected to be limited. The transfer of overpressure through opening faults is therefore considered to be the main cause of higher overpressure in local sandstones. The overpressures in the mudstones are characterized by a gradual decrease from the center to the margin in the Linnan Sag. The pressure in the isolated sand bodies are generally similar to that in the surrounding mudstones, whereas it can be lower or higher when the overpressure in the sand bodies are vertically transferred by faults to other pressure systems. The results of this analysis provide an indication of the magnitude, mechanism, and distribution of overpressure in the Linnan Sag. This insight can be used to guide further exploration of the Linnan Sag and similar geological basins.

Subsurface pore pressure affects the direction of hydrocarbon migration, determines the distribution of the hydrocarbon reservoir, and provides scientific reference for drilling planning. Overpressures are widespread in the Paleogene Shahejie Formation in the Linnan Sag, which is closely related to the distribution of oil reservoir. However, the overpressure generation mechanisms are undefined, let alone the relationship between the evolution of paleo-overpressure and hydrocarbon migration in the Linnan Sag, which brings great challenges for the understanding of oil accumulation and future oil exploration. Basin modeling was carried out to solve the issue of quantitative evaluation of overpressure mechanisms and to restore the overpressure evolution of the Paleogene source rocks. The implications for the pore pressure prediction and oil migration in the Linnan Sag were further discussed. The modeling results show that the disequilibrium compaction of mudstones is a dominated overpressure mechanism of source rocks in the Linnan Sag, which accounts for approximately 90% of the measured overpressure in the region. The remainder part of overpressure was generated by hydrocarbon generation; however, the effects of hydrocarbon generation on overpressure evolution were limited in the intervals deeper than 4000 m. The significance of the overpressure mechanism is that the porosity-dependent method will give a satisfactory pressure prediction result in the current exploration depth range (3800–4300 m). The overpressure evolution of the source rock has undergone a cycle of “accumulation-dissipation-reaccumulation,” which corresponds to the age of 45.5–24.0 Ma (Es3-Ed period), 24.6–14.0 Ma (Ed period), and 14.0–0 Ma (Ng-Qp period). The oil potential of the Es3l shows good inheritance with the overpressure in the source rock, indicating overpressure increased the driving force for oil migration. The oil released from the source rock has a trend to migration from the center of the sag to the uplift belt, which is also indicated by the physical properties of crude oil. The knowledge of the generation and evolution of overpressure has great significance for further exploration in the Linnan Sag and other extensional basins.

The Lower Jurassic Ahe Formation is an important exploration target for deep clastic reservoirs in the eastern Kuqa Depression. The Ahe Formation sandstones show heterogeneous porosity and permeability petrophysical properties. These properties have been poorly understood, limiting forecast of petroleum accumulations and making it difficult to develop the reservoirs. Based on cores, thin sections, SEM, and fluid inclusions, this study examined sandstone composition and texture and diagenetic heterogeneity at the core scale. The aim was to understand the influence of variations in detrital composition and texture on diagenetic and reservoir quality evolution. The Ahe Formation sandstones are dominantly fine- to coarse-grained litharenites, with minor feldspathic litharenites. In fining-up sand beds, detrital grain size determines the degree of mechanical compaction and, consequently, the abundance of porosity through ductile grains and muddy matrix. Local complete calcite cementation is a noticeable exception to this general trend. Three sandstone petrofacies have been defined based on texture and framework composition, detrital matrix, diagenesis, and pore types: (1) ductile-lean sandstone, (2) ductile-rich sandstone, and (3) tightly calcite-cemented sandstone. Different petrofacies experienced contrasting diagenetic and porosity evolution pathways. Ductile-lean sandstones underwent lower degree of compaction relative to ductile-rich sandstones during the eodiagenesis stage, and extensive grain dissolution occurred. The petrofacies remained relatively porous and permeable before early oil arrival. With continued burial, the porosity and permeability in the sandstones were further reduced by cementation. The petrofacies still had moderate porosity and permeability and were substantially charged when late petroleum migrated into the reservoirs. Thus, ductile-lean sandstones constitute effective reservoir rocks in deep reservoirs. By translating petrofacies to signatures of well logs, the effective properties of the reservoir rocks can be forecasted at the well scale.

The sandstone sections in the Upper Jurassic red beds of the Yongjin area in the central Junggar Basin are important oil and gas reservoirs. The debate over whether red beds are of primary depositional or secondary diagenetic origin persists, leading to uncertainties in the interpretation of reservoir sedimentary facies. This study uses core samples and employs thin section microscope observations, scanning electron microscopy, X-ray diffraction, and major and trace element analyses to investigate the formation period and paleoclimate conditions of red beds and explore the origin of red sandstone. The Upper Jurassic red beds are mainly deposited in arid delta plain environments. The framework grains of the red sandstone are composed of quartz (averaging 22.6%), feldspar (averaging 16.3%), and rock fragments (averaging 36.7%). The rock fragments in the sandstone are mainly composed of intermediate basic volcanic rocks and cryptocrystalline acid volcanic rocks, which are rich in mafic silicate minerals such as olivine, pyroxene, ilmenite, and magnetite. In situ hematitization of ilmenite is observed in the rock fragments, suggesting that the in situ alteration of mafic silicate minerals in the parent rock is the main source of iron ions for hematite. Tiny hematite crystals (2.1 μm) are observed in clay mineral micropores via SEM. Abundant mixed-layer illite/smectite clay indicates early smectite transformation, providing a minor source of iron ions for hematite. Hematite in the red sandstone occurs as a grain-coating type, predating quartz overgrowth, feldspar overgrowth, and (ferroan) calcite and (ferroan) dolomite precipitation. Residual hematite coatings between detrital grain point contacts indicate that hematite is a product of syn-sedimentary or very early diagenetic precipitation, ruling out the possibility that red sandstone formation was caused by later atmospheric water leaching during the fold and thrust belt stage. The average chemical index of alteration (CIA) for the red sandstone is 52.2, whereas the CIA for the red mudstone averages 59.5, and the chemical index of weathering (CIW) reached a maximum of 69. These values indicate that the rocks have undergone mild chemical weathering in arid climates. Additionally, the ratios of trace elements indicate that the water bodies were in an oxidizing state during the sedimentary period. The arid climate and oxidative water conditions were ideal for hematite preservation, thus facilitating red bed formation. The red bed sediments in the study area represent a direct response to the Late Jurassic aridification event and can be compared to global climate change. The results have important implications for stratigraphic correlation and interpretation of reservoir sedimentary facies in the study area while also providing a valuable case study for global research on red beds.