In order to reveal the driving mechanism of sea level changes in the North China Basin in the low latitudes of the Late Carboniferous. Taking Benxi-Taiyuan Formations in Liujiang Coalfield of North China Basin as an example,the restoration of sea level change in low latitude area and its relationship with glacier cycle in high latitude area are studied. The results show that: (1)Three sedimentary systems of coastal plain river-lake,littoral zone and shallow sea are identified in the target strata of the study area. The changes of sedimentary environment record two secondorder transgression-regression cycles(Bashkir-Middle Moscow period and Late Moscow-Early Assel period)and four third-order transgression-regression cycles(Early Bashkir period,Middle Bashkir-Early Moscow period,Late Moscow period and Late Moscow-Assel period). (2)The highlatitude glacial and interglacial periods correspond to the second-order relative high sea level and low sea level periods in the study area,respectively,indicating that the high-latitude glacial cycle is the main controlling factor of the second-order sea level change in the late Carboniferous low-latitude North China Basin. (3)The coal-organic-rich mudstone and bauxite developed during the glacial period,indicating the falling sea level and temperature during the glacial period,which is conducive to the exposure of sedimentary interfaces,swamping,and the generation and preservation of organicmatter in the epicontinental sea basin. At the same time,the decline of sea level during the glacial period also caused the prevalence of dry-wet alternate flood plain environment. In this environment,terrigenous clastic sediments are reweathered and leached,which promotes the formation of bauxite mudstone or bauxite. This study deepens our understanding of the driving mechanism of sea level change and the accumulation of sedimentary minerals such as coal and bauxite in the late Carboniferous North China Basin.

To investigate the feasibility of compressed carbon dioxide(CO₂)energy storage in deep aquifers of the Hengyang Basin,this study focuses on the Honghuatao Formation sandstone reservoir within the Cretaceous paleo-desert aeolian sedimentary strata. By integrating petrological characterization experiments with site-scale numerical simulations,the carbon sequestration and energy storage potential of the reservoir were systematically evaluated. Petrographic thin-section analysis,scanning electron microscopy(SEM),and porosity-permeability tests reveal that the Honghuatao Formation sandstone is predominantly composed of medium-to fine-grained feldspathic quartz sandstone with pervasive calcareous cementation. The reservoir exhibits low porosity and permeability,characteristic of tight sandstone. The overlying mudstone caprock,with negligible porosity and stable regional distribution,forms an effective reservoir-seal combination.A three-dimensional numerical model of the compressed CO₂ energy storage system was established based on experimental data. Simulation results indicate that under a reservoir permeability of 15×10^-3 μm^-2,60-day cyclic injection-withdrawal operations induce pressure fluctuations≤0.5 MPa,with energy round-trip efficiency exceeding 99.98%. Additionally,low-temperature CO₂ injection triggers localized temperature reduction(up to 5 ℃),pore pressure accumulation(maximum 1.27 MPa),partial effective stress reduction,and significant vertical displacement in the reservoir. The study demonstrates that the Honghuatao Formation sandstone holds potential for CO₂ storage and energy storage. However,its low permeability limits injection-withdrawal capacity,necessitating acidification or hydraulic fracturing modifications to enhance pore-permeability properties for scalable applications. This research provides theoretical insights into the utilization of paleo-desert aeolian sandstone for subsurface energy storage and the advancement of low-carbon energy technologies.

The Permian Shanxi Formation in the Yan’an Gas Field of the Ordos Basin contains tight sandstone gas reservoirs within a shallow delta front. However,predicting sandbody distribution is challenging due to strong reservoir heterogeneity,large well spacing,and the signal-attenuating effects of the Quaternary loess plateau. As a result,the distribution patterns of effective gas-bearing reservoirs remain poorly understood. Using the S2³ submember of the Shanxi Formation in the Gaojiahe area of the central Yan’an Gas Field as a case study,this research proposes an intelligent sandbody prediction method based on an adaptive weighting strategy. This approach integrates the relationship between amplitude-frequency characteristics and tuned thickness into an attention mechanism,establishing an adaptive weighting framework for multi-band seismic attributes. The weighting strategy prioritizes high-frequency attributes for identifying thin layers and low-frequency attributes for thick layers,effectively addressing sandbody prediction challenges in the presence of low-quality seismic data. Compared with existing methods,the proposed approach yields the most accurate sandbody thickness predictions across various ratios of learning wells to blind wells. For example,in a test involving 45 learning wells and 63 blind wells,the correlation coefficient(R) between predicted and actual sandbody thickness reached 0.85. Prediction results indicate that the S2³ submember in the Gaojiahe area develops wide,banded sand bodies deposited in a shallow-water delta-front environment. Thick,coarse-grained sediments in the main distributary channels,along with the main body and inner edge of the mouth bar,are confined within the palaeo-geomorphological low of the main valley. Due to wave scouring,these intervals exhibit high quartz content and represent the principal effective gas reservoirs.

As the exploration and development of shale gas continue to deepen,the accurate and efficient division and prediction of lithofacies have become key factors in evaluating the quality of shale gas reservoirs. Traditional lithofacies logging identification methods are limited by their strong subjectivity,inability to handle large-scale datasets,and difficulty in effectively capturing the complex nonlinear relationships in the data. This study takes the Lower Cambrian Qiongzhusi Formation shale gas reservoir in the Sichuan Basin as an example. It utilizes precise data from rock core testing and logging curves to establish a lithofacies-labeled dataset. A novel ensemble learning(Voting)model is proposed,integrating traditional machine learning models(Decision Tree,Support Vector Machine(SVM),and K-Nearest Neighbors(KNN))and a deep learning model(1D Convolutional Neural Network,1D-CNN)for lithofacies classification and prediction. The study also compares the predictive performance of traditional machine learning and deep learning models with that of the ensemble learning model,assessing its application potential in complex shale lithofacies prediction. The results indicate that the ensemble learning(Voting)model achieves the highest lithofacies prediction accuracy of 94.0%,significantly outperforming individual base learners(Decision Tree,KNN,SVM,and 1D-CNN). The proposed ensemble learning method effectively overcomes the recognition bias caused by sample imbalance in traditional classification algorithms by leveraging the strengths of the four base learner models. This improvement enhances the ability to identify lithofacies with limited samples,providing technical support for the high-precision reconstruction of logging-based lithofacies profiles and sweet spot prediction in the deeply buried,over-mature Qiongzhusi Formation shale gas reservoirs in the Sichuan Basin.

In recent years,machine learning has shown significant advantages in reservoir parameter evaluation based on well logs. However,due to the limited size of core samples,the generalization ability of these models is often not guaranteed. In this study,more than 100 sets of high-pressure mercury injection data and seven types of well logs were collected from the Triassic Yanchang Formation in the Jiyuan area of the Ordos Basin. The study systematically compares the performance of TabPFN and seven other common machine learning methods under small data conditions. The SHAP interpretability analysis is also used to understand the model’s decision-making mechanisms. The results show: (1)The average permeability of the Yanchang Formation sandstone reservoir in the study area is 0.39×10^-3 μm²,which is typical of low- to ultra-low permeability reservoirs. These reservoirs have small pore throat radii and complex pore structures. The first principal component explains 65.00% of the total variance of the pore structure parameters. Combined with production data and mechanism analysis,it is considered an appropriate target variable for characterizing pore structure. (2)The TabPFN model performs excellently in small-data environments,achieving R² values of 0.81 and 0.87 in the validation and blind well test sets,respectively. Its high performance without parameter tuning demonstrates its outstanding applicability. (3)According to feature importance ranking,density log,sedimentary facies,acoustic log,geological layering,and deep resistivity are the top five features. Sedimentary facies and geological layering make greater contributions in extreme pore structure intervals,highlighting the critical role of discrete geological variables in improving model performance. This study provides an effective data-driven case for characterizing the pore structure of low-permeability sandstone reservoirs under small data conditions.

The sepiolite-containing succession in the Member 1 of the Middle Permian Maokou Formation in the Sichuan Basin exhibit self-generation and self-accumulation characteristics,positioning them as a promising new frontier for the exploration of unconventional gas reservoirs. However,the identification and predictive distribution of these strata are still underdeveloped. This study utilizes core samples,thin sections,X-ray diffraction(XRD)analysis,well logging,and mud logging data,performing sensitivity analysis to select six key well log curves: CNL,DEN,GR,RT,RXO,and AC. The SMOTE algorithm is employed to address feature imbalance. The workflow for predicting sepiolite-containing succession based on multi-gradient boosting algorithms is as follows: (1)The CatBoost algorithm is used for binary classification to determine the presence of sepiolite;(2)CatBoost performs multi-class classification to categorize the morphology of sepiolite-containing succession;(3)XGBoost is applied for regression analysis to predict the talc content in the sepiolite-containing succession;(4)The effective thickness of sepiolite-containing succession is identified based on talc content. The sepiolite-containing succession in the Member 1 of Maokou Formation primarily exhibit three morphologies: spotty,lenticular,and layered. Prediction results indicate that spotty talc is mainly developed in the northern and central southern regions of Sichuan Basin,with thickness increasing toward the northeast;lenticular talc is predominantly distributed in the western Sichuan region;and layered talc is mainly found in north western,central and southern Sichuan Basin. Overall,the sepiolite-containing succession in the Member 1 of Maokou Formation show a distribution pattern of‘thicker in the northeast,thinner in the southwest.’The Tongjiang-Changshou intracratonic sag area and the Hechuan-Weiyuan-Luzhou region serve as the sedimentary centers for the effective thickness of sepiolite-containing succession,providing a basis for future exploration and deployment in these areas.

This research uses the basic end-member modeling algorithm,non-parametric estimation decomposition algorithm,and grain size-standard deviation method to evaluate the grain-size data of the Holocene sediments from core SE3 in the Hangzhou Bay area,in order to investigate the vertical distribution pattern of different grain-size end-members and their coupling relationship with environmental evolution. Results show that the basic end-member modeling algorithm acts as the best method in decomposing grain-size end-member in comparison with the other two methods. Five grain-size end-members were identified in the study area by the basic end-member modeling algorithm: EM1(clay and silt),EM2(coarse silt and very coarse silt),EM3(very coarse silt,very fine sand and fine sand),EM4(fine sand and medium sand)and EM5(medium sand and coarse sand). Their vertical distribution patterns are controlled by the evolution of sea level,depositional environment,and dynamic process. The coarse-grained end-members EM5 and EM4,representing bed load,are primarily supplied by the Qiantang River and distributed in the amalgamated fluvial channel,floodplain,and paleo-estuarine deposits. As sea levels rising,the content of proximal EM5 decreases upwards,while the content of relatively distal EM4 increases. The fine-grained end-members EM2 and EM1,representing suspended load,are distributed in the offshore shallow marine and present-day estuary stratigraphic units;they are mainly derived from the Changjiang by a combination of alongshore and tidal currents in a high sea-level setting. EM3,representing bed load with a normal distribution of grain size,is primarily distributed in the present-day estuary deposits,and probably represents the sediment transported and sorted by tidal currents and storm surges. This study sheds a new light in reconstructing the evolution history of sea level,environment,and source-to-sink processes in estuarine areas by using sensitive grain-size end-member algorithm analysis.

The Taohe River Basin is a key origin of prehistoric cultures in western China,with a clearly defined cultural evolution trajectory,making it an ideal area for studying prehistoric human activities. Based on a comprehensive collection of archaeological site data,this study uses methods such as site analysis,tomb excavations,and grid reconstruction models to reconstruct the settlement patterns,populations,and cultivated lands during five cultural phases in the basin: Yangshao,Majiayao,Qijia,Xindian,and Siwa. The analysis indicates: (1)Prehistoric settlements in this region expanded from the source of the Wei River to the Taohe River Basin,reaching their peak during the Majiayao and Qijia cultures(5.4~3.6 ka BP),and then gradually contracted and diversified after 3.4 ka BP,with corresponding changes in population and cultivated land. (2)The changes in prehistoric cultivated land in this region were significantly influenced by climatic changes. During the Yangshao to Qijia cultural period,he climate was relatively warm and moist,fostering agricultural development,which led to an increase in settlements and population. After 3.6 ka BP,as the climate shifted to cooler and drier conditions,production modes diversified;the lower-altitude northern areas continued to focus on agriculture,while the higher-altitude southern areas developed a mixed farming-pastoral economy.