Machine learning is the main technical means for lithofacies logging identification. As the main target of shale oil spatial distribution prediction, mud shale petrography is subjected to the constraints of stratigraphic inhomogeneity and logging information redundancy. Therefore, choosing the most applicable machine learning method for different geological characteristics and data situations is one of the key aspects of high-precision lithofacies identification. However, only a few studies have been conducted on the applicability of machine learning methods for mud shale petrography. This paper aims to identify lithofacies using commonly used machine learning methods. The study employs five supervised learning algorithms, namely Random Forest Algorithm (RF), BP Neural Network Algorithm (BPANN), Gradient Boosting Decision Tree Method (GBDT), Nearest Neighbor Method (KNN), and Vector Machine Method (SVM), as well as four unsupervised learning algorithms, namely K-means, DBSCAN, SOM, and MRGC. The results are evaluated using the confusion matrix, which provides the accuracy of each algorithm. The GBDT algorithm has better accuracy in supervised learning, while the K-means and DBSCAN algorithms have higher accuracy in unsupervised learning. Based on the comparison of different algorithms, it can be concluded that shale lithofacies identification poses challenges due to limited sample data and high overlapping degree of type distribution areas. Therefore, selecting the appropriate algorithm is crucial. Although supervised machine learning algorithms are generally accurate, they are limited by the data volume of lithofacies samples. Future research should focus on how to make the most of limited samples for supervised learning and combine unsupervised learning algorithms to explore lithofacies types of non-coring wells.

For the second member of the Permian Lucaogou Formation in Malang Sag, Santanghu Basin, we used field emission scanning electron microscopy (SEM), cryogenic nitrogen gas adsorption, and the micro/nano CT method, combined with the fractal theory, to depict the dense reservoir space types of the reservoir and the microcosmic pore structure characteristics, perform the quantitative evaluation of aperture size, pore shape, and connectivity, and to analyze the mineral composition of the micropore structure of the reservoir. The results show that the area is dominated by sandy/argillaceous dolomite, and the reservoir space types mainly develop dissolved intergranular pores and intergranular pores, a few microfractures, and parallel plate and slit nanoscale pores. There is a positive correlation between pore volume and specific surface area, with micropore volume accounting for 14.95%, mesopore volume at 82.47%, and macropore volume at 2.58%. The mesoporous volume provides the main pore storage space. The combined specific surface area of micropores and mesoporous pores accounts for more than 99% of the total specific surface area, providing almost all the pore surface area, which is the main site for shale oil and gas adsorption. The fractal dimension D value of the samples is between 2.39 and 2.49, and the pore distribution of shale is relatively uniform, mainly developing mesoporous pores. The specific surface area and average radius are positively correlated with the content of dolomite in mineral components. The results of the CT experiment also confirm that the pore throat of samples with high dolomite content is mostly a coarse tubular and banded distribution in three-dimensional space, with good connectivity.

Fractal dimension is an important parameter in the evaluation of tight reservoirs. For an outcrop section of the Nenjiang formation in the Songliao Basin, China, the pore structure and pore fractal characteristics of shale parasequences were investigated using fractal theory. In addition, factors causing pore structure changes were analyzed using the results of low-temperature nitrogen adsorption and scanning electron microscope (SEM) experiments. Conducive to gas migration and secondary pores development such as dissolution, results showed that nanoscale pores dominated by fracture-like morphology and consequent good internal connectivity were observed in each pore size section within the target layer. Each parasequence is characterized by a sequential upward decrease of average pore size and an upward increase of total pore volume, with an increasing number of pores from 2$$ nm to 50$$ nm. Pores are isolated from each other, with poor connectivity and relatively complex composition of brittle minerals and clay minerals. Main components of the brittle minerals, quartz and feldspar, occur in 20–50% and higher clay mineral content ranging from 50% to 70%. In the parasequence cycle, clay mineral gradually decreases while the brittle mineral content increases. Fractal dimension is negatively correlated with clay mineral content and positively correlated with brittle mineral (quartz and feldspar) content. The fractal dimension calculated by the imaging method and the FHH method shows an upward increasing tendency in each of the parasequence cycles. This is as a result of different phenomena, varied sediment hydrodynamic forces leading to particle size differences and increased brittle minerals resulting in microcracks, therefore, the fractal dimension of the large pores (imaging method) increases upward in the parasequence. Simultaneously, with increased content and accompanied dissolution of brittle minerals causing an increase of small pores from base to top of the parasequence, the fractal dimension of the small pores (FHH method) grows.

The research on pore structure and heterogeneity of shale reservoirs has always been a hotspot in the study of unconventional reservoir characteristics. China is a country dominated by continental shale. Compared with marine shale, continental shale has lower maturity and stronger reservoir heterogeneity. In this study, Sha-4 shale in the Liaohe Western Depression was selected for low-temperature nitrogen adsorption, scanning electron microscopy and other experiments revealing the pore structure and fractal characteristics of continental low mature organic-rich shale. The fractal dimension was calculated by the FHH model and the effects of TOC and mineral composition on pore structure and fractal characteristics were discussed. The results show that the Sha-4 shale in the study area is mainly mesoporous and the main pore types are inorganic pores with relatively large pore diameters, such as intergranular pores and inter-crystalline pores. The pore morphology is very complex, mainly narrow slit and flat pore, and the pore is often filled with organic matter. The fractal dimensions D₁ range from 2.58 to 2.87 and D₂ range from 2.18 to 2.55, and the pore structure shows obvious dual fractal characteristics. The pore structure and fractal characteristics of shale are mainly affected by TOC and quartz due to the low degree of the thermal evolution of shale and their effects are different from those of marine shale reservoirs. The increase in TOC reduces the heterogeneity of the shale reservoir. In addition, mineral particles with strong weathering resistance and stability such as quartz can protect the pore structure of shale, improve the pore structure and reduce the reservoir heterogeneity. This study can provide support for the study of low maturity continental shale reservoir heterogeneity in the Sha-4 member of the Liaohe Western Depression.

The 8# coal seam in the Benxi Formation of the southeastern margin of the Ordos Basin is a deep coal seam with abundant coalbed methane resources. Calcite veins are commonly developed within the 8# coal seam, and their formation processes and mechanisms have significant implications for the enrichment of deep coalbed methane. Genesis of the calcite veins was analyzed to reveal the impact of the calcite veins formation on coalbed methane accumulation, with an integrated application of petrographic study by thin section, cathodoluminescence analysis, carbon-oxygen isotope analysis, and homogeneous temperature measurements of fluid inclusions. The research findings indicate that the calcite veins in the 8# coal seam can be classified into three stages: C1, C2, and C3. The diagenetic fluids of C1 primarily originated from contemporaneous seawater. The fluids responsible for the formation of C2 primarily consist of organic fluids enriched in biogenic gas, whereas the fluids contributing to the formation of C3 are primarily associated with liquid hydrocarbons originated form decarboxylation of organic matter. Furthermore, the development of both C2 and C3 is influenced by deep hydrothermal fluids resulting from tectonic heating events during the Early Cretaceous. By combining analysis of the hydrocarbon accumulation history and burial history in the study area, it has been established that C2 formation occurred during the Late Triassic to Early Jurassic, while C3 formation took place during the Late Jurassic to Early Cretaceous. The exploration and production practices in the study area have firmly established the crucial significance of the formation and evolution of calcite veins within the 8# coal seam for the migration and accumulation of coalbed methane. The research outcomes provide valuable insights for the exploration of deep coalbed methane enrichment areas.

Oil content and the movability of shale oil are important indicators for the evaluation of continental shale oil. In recent years, the sandwiched shale oil in the fourth member of the Shahejie Formation in the Liaohe Western Depression area of the Bohai Bay Basin has shown great exploration potential, while the understanding of shale oil content and the movability of shale oil is weak. In this study, through a combination of core observations and experiments, we clarified the shale lithofacies types in the fourth member of the Shahejie Formation in the Liaohe Western Depression and explored the influencing factors of the characteristics in the oil-bearing and movability of shales in different lithofacies. The results of the study show that the organic matter content of the shale is high (TOC = 2.2–4.3%), but the maturity of thermal evolution is low (R_o = 0.38–0.55%), and the mineral component is dominated by clay minerals (30.3–72.7%), with quartz, feldspar, and other feldspar minerals developing secondarily. According to the content of organic matter, the mineral component, and the sedimentary structure, five types of lithofacies can be classified: organic-rich laminated clay-bearing felsic shale lithofacies (LS1), organic-rich laminated clay felsic mixed shale lithofacies (LS2), organic-rich layered clay felsic mixed shale lithofacies (LS3), organic-containing massive felsic-bearing clay shale lithofacies (LS4), and organic-containing massive clay felsic mixed shale lithofacies (LS5). The oil content of shale is mainly affected by the organic matter. The rate of increase in oil content of shale is fastest when the organic matter content is between 2 and 4%. The movability of shale oil is mainly controlled by the sedimentary structure, mineral component, and microscopic pore structure; the more the shale laminae is developed, the lower the clay content is, and the more the pore space is developed, the better the movability of shale oil is. Combined with the results of the shale oil content and mobility analysis in the study area, LS2 and LS3 are the dominant lithofacies in the fourth member of the Shahejie Formation in the study area, followed by LS1 >LS5 >LS4, so shale oil exploration should focus on the development of LS2 and LS3.