At the Changning block and at the Luzhou block, the genetic mechanism of low-resistivity shale and its impact on reservoir quality are currently a hot topic on a world-wide scale. Shale with resistivity lower than 20 Ω·m is widely developed at the Wufeng-Longmaxi Formation in the Southern Sichuan Basin, bringing a considerable challenge for reservoir prediction using the electromagnetic method. This paper discusses the genetic mechanisms and reservoir qualities of three low-resistivity shale reservoir types in the Southern Sichuan Basin (the Changning block and Luzhou block). Three primary elements controlling low-resistivity shale distribution in the Southern Sichuan Basin have been deduced: widely distributed gravity flow deposits, poor structural preservation conditions and shale graphitization caused by Emeishan basalt. Specifically, (1) the shale reservoir with a resistivity <12 Ω·m was uniformly distributed with gravity flow deposits in the Southern Sichuan Basin. High clay mineral contents (especially illite) in gravity flow deposits increased cation exchange capacity and irreducible water saturation at shale reservoir, decreasing electrical resistivity. (2) The resistivity of the shale reservoir close to a complex fault-fracture zone was generally lower than 20 Ω·m, indicating that poor structural preservation conditions played an important role in the wide distribution of low-resistivity shale. The resistivity of the shale reservoir near NE-trending faults at the Changning block was significantly lower than that in other areas. (3) Emeishan basalt caused extensive shale graphitization at the west of the Changning block, which was limited at the Luzhou block. The shale resistivity at the Luzhou block was not affected by graphitization. Among three types of low-resistivity shale, type III was characterized by high quartz content, high TOC, high porosity, high gas content and low graphitization. Although the resistivity of type III is generally lower that 20 Ω·m, it is still a favorable exploration target in the Southern Sichuan Basin.

This paper documents depositional structures and their reservoir characteristics in the Wufeng–Longmaxi shale from outcrops and cores using thin sections, X-ray powder diffraction (XRD) analysis, carbon–sulfur analyzer, helium porosimeter, decay permeameter, and focused ion beam scanning electron microscope (FIB-SEM). In the study area, clayey and silty laminae abound in the shale. Clayey laminae are rich in bedding parallel fractures, microfractures, and organic pore networks. Silty laminae are rich in isolated inorganic pores and limited amounts of bedding non-parallel fractures. Various inter-lamination of clayey and silty laminae form five depositional structure types which are closely related to the ancient hydrodynamics, paleoredox condition, and sedimentation rate and have significant impacts on shale fractures, microfractures, pore types, pore-size distribution, and porosity. For the paper lamination (PL) and grading lamination composed of siltstone and claystone (GL-SC), organic pores account for 71.6% and 61.4% of the total, and dense bedding parallel and non-parallel fractures intersect to form connective networks. In the interlaminated lamination composed of siltstone and claystone (IL), grading lamination composed of claystone (GL-C) and structureless beds (SB), organic pores merely account for 20% to 51.8% of the total and minor isolated bedding parallel fractures occur. Among five depositional structure types, the PL and GL-SC have the highest porosity, permeability, TOC content, siliceous content, organic pore proportions, and ratios of horizontal to vertical permeability, which help them become shale gas exploration and development targets.

The sediment provenance influences the formation of the shale gas sweet-spot interval of the Upper Ordovician–Lower Silurian Wufeng–Longmaxi shale from the Yangtze Platform, South China. To identify the provenance, the mineralogy and geochemistry of the shale were investigated. The methods included optical microscopy analysis, X-ray diffraction testing, field-emission scanning electron imaging, and major and trace element analysis. The Wufeng–Longmaxi shale is mainly composed of quartz (avg. 39.94%), calcite (avg. 12.29%), dolomite (avg. 11.75%), and clay minerals (avg. 28.31%). The LM1 interval is the shale gas sweet-spot and has the highest contents of total quartz (avg. 62.1%, among which microcrystalline quartz accounts for 52.8% on average) and total organic carbon (avg. 4.6%). The relatively narrow range of TiO₂–Zr variation and the close correlation between Th/Sc and Zr/Sc signify no obvious sorting and recycling of the sediment source rocks. Sedimentary sorting has a limited impact on the geochemical features of the shale. The relatively high value of ICV (index of compositional variability) (1.03–3.86) and the low value of CIA (chemical index of alteration values) (50.62–74.48) indicate immature sediment source rocks, probably undergoing weak to moderate chemical weathering. All samples have patterns of moderately enriched light rare-earth elements and flat heavy rare-earth elements with negative Eu anomalies (Eu/Eu* = 0.35–0.92) in chondrite-normalized diagrams. According to Th/Sc, Zr/Sc, La/Th, Zr/Al₂O₃, TiO₂/Zr, Co/Th, SiO₂/Al₂O₃, K₂O/Na₂O, and La/Sc, it can be inferred that the major sediment source rocks were acidic igneous rocks derived from the active continental margin and continental island arc. A limited terrigenous supply caused by the inactive tectonic setting is an alternative interpretation of the formation of the sweet-spot interval.

Uncertain provenance and tectonic setting of shale has constrained the exploration and exploitation of natural gas in the Wufeng–Longmaxi Formation in the southern Sichuan Basin, China. Therefore, this study analyzed the mineral petrology and geochemistry to assess the effects of sorting, recycling, weathering, and paleoclimate on the deeply buried shale. The findings revealed that the mineral composition is dominated by biogenic quartz, terrigenous clay minerals, and carbonate minerals. Combinations of clay lamina and silty lamina occur in black shale. The geochemical characteristics of these sedimentary rocks remain unaffected by sedimentary sorting and recycling processes. The clastic sediments primarily originate from the felsic igneous rock source that underwent moderate weathering during its initial deposition in the collision environment. Based on the comprehensive analysis of the paleoclimate and paleoprovenance characteristics, Wufeng–Longmaxi Formation characteristics are considered to have undergone six stages, among which the stage of relative enrichment of organic matter corresponds to LM1, LM2–3, and LM4. Following the Hirnantian glacial period, the era has witnessed global warming, marked by glacier melting, a rise in global sea level, and a decrease in terrestrial debris supply, collectively facilitating organic matter enrichment. During the LM5 and LM6–8 periods, the increase in source supply caused by the Leshan–Longnvsi and Qianzhong–Xuefeng uplift inhibited organic matter enrichment.

Gas saturation prediction is a crucial area of research regarding shale gas reservoirs, as it plays a vital role in optimizing development strategies and improving the efficiency of exploration efforts. Despite the advancements in deep learning techniques, accurately modeling the complex nonlinear relationships involved in gas saturation prediction remains a challenge. To address this issue, we propose a novel cascaded model, CLAP, combining convolutional neural networks (CNNs) and Long Short-Term Memory (LSTM) with an attention mechanism. It effectively captures and visualizes the intricate nonlinear relationships, enabling accurate gas saturation prediction in shale gas reservoirs. In this study, nine logging curves from 27 shale gas wells in the Changning area of the Sichuan Basin were used to train the CLAP model for predicting the gas saturation of the Wufeng-Longmaxi Formation shale. Compared to the Archie and random forest models, the CLAP model exhibited enhanced accuracy in predicting shale gas saturation. Promisingly, the CLAP model demonstrates outstanding statistical performance in gas saturation prediction, achieving an impressive R² score of 0.762 and a mean square error (MSE) score of 0.934. These positive results highlight the effectiveness and potential utility of our proposed CLAP model in accurately predicting gas saturation in shale gas reservoirs. The application of deep learning techniques, such as CNNs, LSTM, and attention mechanisms, presents a promising avenue for further advancements in this field.

In recent years, big data and artificial intelligence technology have developed rapidly and are now widely used in fields of geophysics, well logging, and well test analysis in the exploration and development of oil and gas. The development of shale gas requires a large number of production wells, so big data and artificial intelligence technology have inherent advantages for evaluating the productivity of gas wells and analyzing the influencing factors for a whole development block. To this end, this paper combines the BP neural network algorithm with random probability analysis to establish a big data method for analyzing the influencing factors on the productivity of shale gas wells, using artificial intelligence and in-depth extraction of relevant information to reduce the unstable results from single-factor statistical analysis and the BP neural network. We have modeled and analyzed our model with a large amount of data. Under standard well conditions, the influences of geological and engineering factors on the productivity of a gas well can be converted to the same scale for comparison. This can more intuitively and quantitatively reflect the influences of different factors on gas well productivity. Taking 100 production wells in the Changning shale gas block as a case, random BP neural network analysis shows that maximum EUR can be obtained when a horizontal shale gas well has a fracture coefficient of 1.6, Type I reservoir of 18 m thick, optimal horizontal section of 1600 m long, and 20 fractured sections.