The total organic carbon (TOC) content of organic-rich shale is a key parameter in screening for potential source rocks and sweet spots of shale oil/gas. Traditional methods of determining the TOC content, such as the geochemical experiments and the empirical mathematical regression method, are either high cost and low-efficiency, or universally non-applicable and low-accuracy. In this study, we propose three machine learning models of random forest (RF), support vector regression (SVR), and XGBoost to predict the TOC content using well logs, and the performance of each model are compared with the traditional empirical methods. First, the decision tree algorithm is used to identify the optimal set of well logs from a total of 15. Then, 816 data points of well logs and the TOC content data collected from five different shale formations are used to train and test these three models. Finally, the accuracy of three models is validated by predicting the unknown TOC content data from a shale oil well. The results show that the RF model provides the best prediction for the TOC content, with R² = 0.915, MSE = 0.108, and MAE = 0.252, followed by the XGBoost, while the SVR gives the lowest predictive accuracy. Nevertheless, all three machine learning models outperform the traditional empirical methods such as Schmoker gamma-ray log method, multiple linear regression method and ΔlgR method. Overall, the proposed machine learning models are powerful tools for predicting the TOC content of shale and improving the oil/gas exploration efficiency in a different formation or a different basin.

The dolomitization of carbonate rocks has always been a hot topic in the study of the dolomite reservoir. In this study, the genesis of Cambrian dolomite in the Bachu area, Tarim Basin, was assessed through petrographic examinations, isotope compositions (C, O, and Sr), trace and rare earth elements, and fluid inclusion microthermometry. Microscopic analysis revealed three types of dolomites: very fine-crystalline, nonplanar dolomite (D1); fine-crystalline, nonplanar to planar-s dolomite (D2); and medium- to coarse-crystalline, planar-e to planar-s dolomite (D3). D1 dolomite exhibits well-preserved original sedimentary features, such as algal laminae, stromatolite, and evaporite streak, and is characterized by the ⁸⁷Sr/⁸⁶Sr value and δ¹⁸O value in equilibrium with the coeval seawater, its high Sr and Na content, and its low Mn content. This indicates that D1 dolomite is primarily a penecontemporaneous dolomite in tidal flat or lagoon environments, and its dolomitizing fluid is mainly evaporated mesosaline to penesaline seawater. D2 dolomite shows ghosts of precursor particles; features δ¹³C values in equilibrium with the coeval seawater, high ⁸⁷Sr/⁸⁶Sr values, low Sr content, and positive Eu anomaly; and is widely distributed close to stylolite. This illustrates that D2 dolomite was principally formed by seepage–reflux dolomitization, and is closely related to hydrothermal activity and pressure dissolution. D3 dolomite displays a crystal texture with a cloudy core and compositional zoning, and the original sedimentary fabrics cannot be identified. It has similar δ¹³C values and REE patterns to the calcite precipitated from coeval seawater, high ⁸⁷Sr/⁸⁶Sr values, low Sr contents and high Mn/Sr ratios, which suggests that D3 dolomite is chiefly related to the recrystallization of the precursor dolomite during the deep burial stage, and the deep circular brine provides Mg ions through the fluid–rock reaction. This study shows that the Cambrian dolomite in the Bachu area is mainly formed in the coeval seawater environment during the penecontemporaneous and shallow burial stages, and has extensively suffered from recrystallization and burial diagenesis due to long-term deep burial, which was further strengthened in the fracture-enriched area.