Runoff from the high-cold mountains area (HCMA) is the most important water resource in the arid zone, and its accurate forecasting is key to the scientific management of water resources downstream of the basin. Constrained by the scarcity of meteorological and hydrological stations in the HCMA and the inconsistency of the observed time series, the simulation and reconstruction of mountain runoff have always been a focus of cold region hydrological research. Based on the runoff observations of the Yurungkash and Kalakash Rivers, the upstream tributaries of the Hotan River on the northern slope of the Kunlun Mountains at different time periods, and the meteorological and atmospheric circulation indices, we used feature analysis and machine learning methods to select the input elements, train, simulate, and select the preferences of the machine learning models of the runoffs of the two watersheds, and reconstruct the missing time series runoff of the Kalakash River. The results show the following. (1) Air temperature is the most important driver of runoff variability in mountainous areas upstream of the Hotan River, and had the strongest performance in terms of the Pearson correlation coefficient (ρ_XY) and random forest feature importance (FI) (ρ_XY = 0.63, FI = 0.723), followed by soil temperature (ρ_XY = 0.63, FI = 0.043), precipitation, hours of sunshine, wind speed, relative humidity, and atmospheric circulation were weakly correlated. A total of 12 elements were selected as the machine learning input data. (2) Comparing the results of the Yurungkash River runoff simulated by eight machine learning methods, we found that the gradient boosting and random forest methods performed best, followed by the AdaBoost and Bagging methods, with Nash–Sutcliffe efficiency coefficients (NSE) of 0.84, 0.82, 0.78, and 0.78, while the support vector regression (NSE = 0.68), ridge (NSE = 0.53), K-nearest neighbor (NSE = 0.56), and linear regression (NSE = 0.51) were simulated poorly. (3) The application of four machine learning methods, gradient boosting, random forest, AdaBoost, and bagging, to simulate the runoff of the Kalakash River for 1978–1998 was generally outstanding, with the NSE exceeding 0.75, and the results of reconstructing the runoff data for the missing period (1999–2019) could well reflect the characteristics of the intra-annual and inter-annual changes in runoff.

The Upper Permian marine shale of the inter-platform basin in the Nanpanjiang Basin are rich in organic matter, widely distributed, and relatively thick, indicating abundant resource potential for hydrocarbon exploration. To clarify the sedimentary condition and the variability of reservoir properties, the paleo-environment was reconstructed by using geochemical, mineralogical, rock-property, and pore-structure data. Building on a lithofacies classification, the development patterns of different shale lithofacies were revealed. Reservoir characteristics among lithofacies were compared using scanning electron microscopy (SEM), nuclear magnetic resonance (NMR), and low-temperature Nuclear Magnetic Resonance Cryoporometry (NMRC) experiments. A fractal analysis was performed based on NMR and NMRC data to quantify pore-scale heterogeneity, calculate fractal dimensions (D₁, D₂, and D_c), and evaluate the complexity of pore systems across lithofacies. Correlation analysis and redundancy analysis were applied to further explore the controlling factors of reservoir heterogeneity. The results showed that organic-rich shale in the Permian Linghao Formation occurred mainly in the 1st Member, with average total organic carbon (TOC) content of 2.57%, and the lower part of the 3rd Member (average TOC content 2.88%). In the 1st Member, high-carbon shale was deposited under humid conditions with intense weathering, abundant fine-grained clastic input from basin margins, strongly reducing (anoxic) bottom waters, vigorous phosphorus recycling, and moderate to low primary productivity. Using TOC and mineral composition, seven shale lithofacies were identified in the Linghao Formation, and their development patterns were established based on depositional paleo-environment characteristics and evolution. In the 1st Member, organic-rich shale was dominated by mixed lithofacies with moderate to high TOC. The paleo-environment exerted a primary control on reservoir properties, gas content, pore structure, and heterogeneity. The high-carbon lithofacies had the most favorable rock properties—higher porosity, greater pore volume, and higher gas content—and contained a larger proportion of well-developed organic pores. Fractal analysis revealed that seepage pores exhibited greater structural complexity than adsorption-related pores, with the high-carbon lithofacies showing the highest overall fractal dimensions and thus the strongest heterogeneity. Across the formation, higher clay content and TOC were the primary drivers of increased pore-scale heterogeneity, whereas greater feldspar and quartz contents tended to diminish it. Carbonates exerted a minor effect. Heterogeneity in adsorption pores exerted the strongest influence on differences among lithofacies. These results highlighted the utility of fractal analysis in quantitatively linking shale mineralogy and organic content to multiscale heterogeneity in inter-platform basin settings.

Due to the diversity of pore types, it is challenging to characterize the Middle East’s Cretaceous carbonate reservoir or accurately predict its petrophysical properties. In this paper, pore structure in the reservoir is first classified using a comprehensive method. Then, based on the identified pore structure types, a new permeability model with high prediction precision is established. The reservoir is dominated by 6 pore types, such as intergrain pores and moldic pores, and 6 rock types. Grainstone, algal packstone, algal wackestone, and foraminifera wackestone are porous rock types, and echinoderm wackestone and mudstone are nonporous rock types. The types of pore structure in the study area can be divided into four types. Type I has midhigh porosity and medium-high permeability due to its large throat, while type II has a fine throat type with midhigh porosity and midpermeability. Due to their isolated pores, the permeability is low in types III and IV, and out of these two, type III has better storage capacity. Movable fluid saturation calculated by the spectral coefficient method and can characterize the boundary between the connected pores and unconnected pores very well in the research area. It is not accurate enough to simply classify the pore structure by permeability and porosity. The combination of porosity, permeability, , flow zone indicator, and the reservoir quality index can effectively distinguish and classify pore structure types in noncoring wells. The characteristics of each pore structure type are consistent with those of the fractal dimension, which thereby proves the effectiveness of the pore structure classification. New permeability prediction models are proposed for different pore structure types, and good prediction results have been obtained. This study is of great significance for enhancing oil recovery.

The tight sandstone reservoirs of the Permian Shihezi and Shanxi Formation with strong heterogeneity constitute the main producing zone of the eastern Sulige gas field. The process of differential densification results in various reservoir qualities. Mineral composition, structural characteristic, pore system, and diagenesis were investigated with analyses of well logs, thin sections, porosity, and horizontal permeability of the core plugs; environmental scanning electron microscopy (ESEM); nuclear magnetic resonance (NMR); X-ray computed tomography (X-CT); and fluid inclusion homogenization temperature. The results show that lithic sandstone reservoirs experienced complex and various diagenetic evolutions. Eight types of densification modes can be divided according to the diagenesis paths; these modes represent lithofacies with different densification times and reservoir qualities. Intense mechanical compaction is the main reason for the formation of lithofacies 1, 2, and 5. Lithofacies 4, 6, and 7 formed due to intense cementation, increasing the impermeability of the diagenetic system. The primary pore space in lithofacies 3 is preserved due to the overpressure and chlorite coatings. The dissolution and weak cementation of lithofacies 8 contribute to reservoir development. The middle-lower part of braided channel lags and channel bars, the middle part of meandering riverbed lags, and the middle part of point bars are favourable for reservoir development.

Pyrite is a mineral that is commonly found in shale gas reservoirs. Its genetic mechanism and impact on pore and organic matter in shale gas reservoirs are critical for shale gas exploration. This study selects the Longmaxi shale (Lower Silurian) in the Changning area of the southern Sichuan Basin by comprehensively using a scanning electron microscope (SEM), X-ray diffraction (XRD), total organic carbon (TOC), and image processing technology. The type and characteristics of pyrite in shale reservoirs are studied, the sedimentary environment and genetic mechanism of pyrite are analyzed, and the influence of pyrite formation on organic matter enrichment and reservoir formation is evaluated. The results showed that pyrite in shale primarily forms framboidal pyrite, euhedral pyrite, and subhedral pyrite, with particle sizes ranging from 1 to 15 μm. The maximum framboid diameter (MFD) is less than 20 μm, with the average particle size distribution of 3–5 μm. These parameters indicate the vulcanization and blocking environment. The reducing environment promotes organic matter enrichment and preservation. Framboidal pyrite has two genetic sequences: rich organic matter and poor organic matter. The development of organic matter will limit the continuous radial growth of pyrite and is conducive to the protection of pores, and the formation of pyrite can reduce the activation energy of kerogen reaction and catalyze the hydrocarbon generation of organic matter, resulting in higher gas content. The framboidal pyrite content can be used to predict high-quality shale gas reservoirs.