Search Results (38)

Soft data, such as seismic imagery, plays a critical role in subsurface modeling by providing indirect constraints away from hard data locations. However, validating whether subsurface model realizations honor this type of data remains a challenge due to the lack of robust quantitative tools. This study introduces a machine learning-based workflow for soft data checking that uses an autoencoder (AE) to encode 2D seismic slices into a latent space. Subsurface model realizations are transformed into the same domain and projected into this latent space, enabling both visual and quantitative comparisons using principal component analysis and Euclidean distances. We demonstrate the workflow on rule-based models and their associated synthetic seismic data (soft data), showing that models with similar Markov chain parameters to the reference soft data score higher in proximity metrics. This approach provides a scalable, quantitative, and interpretable framework for evaluating the consistency between soft data and subsurface models, supporting better decision-making in reservoir characterization and other geoscience applications. Full article

In the context of the growing emphasis on sustainable development and building safety performance, wooden architecture will attract increasing attention due to its low-carbon characteristics and excellent seismic resistance. In this study, the bibliometric software Citespace is used for data visualization analysis based on the literature related to Chinese wooden architecture in the China National Knowledge Infrastructure (CNKI) and the Web of Science (WOS) databases, aiming to construct an analytical framework that integrates quantitative visualization and qualitative thematic interpretation which could reveal the current status, hotspots, and frontier trends of research in this field. The results show the following: Research on Chinese wooden architecture has shown a steady growth trend, indicating that it has received attention from an increasing number of scholars. Researchers and institutions are mainly concentrated in higher learning and research institutions in economically developed regions. Research hotspots cover subjects such as seismic performance, mortise–tenon structures, imitation wood structures, Dong architecture, Liang Sicheng, and the Society for the Study of Chinese Architecture. The research process of Chinese wooden architecture can be divided into three stages: the macro stage, the specific deepening stage, and the inheritance application and interdisciplinary integration stage. In the future, the focus will be on interdisciplinary research on wooden architecture from ethnic minority cultures and traditional dwellings. Full article

Accurate and rapid prediction of structural responses to seismic loading is critical for ensuring structural safety. Recently, there has been active research focusing on the application of deep learning techniques, including Physics-Informed Neural Networks (PINNs) and Long Short-Term Memory (LSTM) networks, to predict the dynamic behavior of structures. While these methods have shown promise, each comes with distinct limitations. PINNs offer physical consistency but struggle with capturing long-term temporal dependencies in nonlinear systems, while LSTMs excel in learning sequential data but lack physical interpretability. To address these complementary limitations, this study proposes a hybrid LSTM-PINN model, combining the temporal learning ability of LSTMs with the physics-based constraints of PINNs. This hybrid approach allows the model to capture both nonlinear, time-dependent behaviors and maintain physical consistency. The proposed model is evaluated on both single-degree-of-freedom (SDOF) and multi-degree-of-freedom (MDOF) structural systems subjected to the El-Centro ground motion. For validation, the 1940 El-Centro NS earthquake record was used, and the ground acceleration data were normalized and discretized for numerical simulation. The proposed LSTM-PINN is trained under the same conditions as the conventional PINN models (e.g., same optimizer, learning rate, and loss structure), but with fewer training epochs, to evaluate learning efficiency. Prediction accuracy is quantitatively assessed using mean error and mean squared error (MSE) for displacement, velocity, and acceleration, and results are compared with PINN-only models (PINN-1, PINN-2). The results show that LSTM-PINN consistently achieves the most stable and precise predictions across the entire time domain. Notably, it outperforms the baseline PINNs even with fewer training epochs. Specifically, it achieved up to 50% lower MSE with only 10,000 epochs, compared to the PINN’s 50,000 epochs, demonstrating improved generalization through temporal sequence learning. This study empirically validates the potential of physics-guided time-series AI models for dynamic structural response prediction. The proposed approach is expected to contribute to future applications such as real-time response estimation, structural health monitoring, and seismic performance evaluation. Full article

Seismic waveform feature extraction is a critical task in seismic exploration, as it directly impacts reservoir prediction and geological interpretation. However, large-scale seismic data and nonlinear relationships between seismic signals and reservoir properties are challenging for traditional machine learning methods. To address these limitations, this paper proposes a novel framework combining Convolutional Neural Network (CNN) and Uniform Manifold Approximation and Projection (UMAP) for seismic waveform feature extraction and analysis. The UMAP-CNN framework leverages the strengths of manifold learning and deep learning, enabling multi-scale feature extraction and dimensionality reduction while preserving both local and global data structures. The evaluation experiments, which considered runtime, receiver operating characteristic (ROC) curves, embedding distribution maps, and other quantitative assessments, illustrated that the UMAP-CNN outperformed t-distributed stochastic neighbor embedding (t-SNE), locally linear embedding (LLE) and isometric feature mapping (Isomap). A case study in the Ordos Basin further demonstrated that UMAP-CNN offers a high degree of accuracy in predicting coal seam thickness. Furthermore, our framework exhibited superior computational efficiency and robustness in handling large-scale datasets. Full article

This study aims to mitigate slope-collapse hazards that threaten life and property at the Lujiawan resettlement site in Wanbi Town, Dayao County, Yunnan Province, within the Guanyinyan hydropower reservoir. It integrates centimeter-level point-cloud data collected by a DJI Matrice 350 RTK equipped with a Zenmuse L2 airborne LiDAR (Light Detection And Ranging) sensor with detailed structural-joint survey data. First, qualitative structural interpretation is conducted with stereographic projection. Next, safety factors are quantified using the limit-equilibrium method, establishing a dual qualitative–quantitative diagnostic framework. This framework delineates six hazardous rock zones (WY1–WY6), dominated by toppling and free-fall failure modes, and evaluates their stability under combined rainfall infiltration, seismic loading, and ambient conditions. Subsequently, six-degree-of-freedom Monte Carlo simulations incorporating realistic three-dimensional terrain and block geometry are performed in RAMMS::ROCKFALL (Rapid Mass Movements Simulation—Rockfall). The resulting spatial patterns of rockfall velocity, kinetic energy, and rebound height elucidate their evolution coupled with slope height, surface morphology, and block shape. Results show peak velocities ranging from 20 to 42 m s⁻¹ and maximum kinetic energies between 0.16 and 1.4 MJ. Most rockfall trajectories terminate within 0–80 m of the cliff base. All six identified hazardous rock masses pose varying levels of threat to residential structures at the slope foot, highlighting substantial spatial variability in hazard distribution. Drawing on the preceding diagnostic results and dynamic simulations, we recommend a three-tier “zonal defense with in situ energy dissipation” scheme: (i) install 500–2000 kJ flexible barriers along the crest and upper slope to rapidly attenuate rockfall energy; (ii) place guiding or deflection structures at mid-slope to steer blocks and dissipate momentum; and (iii) deploy high-capacity flexible nets combined with a catchment basin at the slope foot to intercept residual blocks. This staged arrangement maximizes energy attenuation and overall risk reduction. This study shows that integrating high-resolution 3D point clouds with rigid-body contact dynamics overcomes the spatial discontinuities of conventional surveys. The approach substantially improves the accuracy and efficiency of hazardous rock stability assessments and rockfall trajectory predictions, offering a quantifiable, reproducible mitigation framework for long slopes, large rock volumes, and densely fractured cliff faces. Full article

The bottom-simulating reflector (BSR) serves as an important seismic indicator for identifying gas hydrate-bearing sediments. This review synthesizes global BSR observations and demonstrates that spatial relationships among BSRs, free gas, and gas hydrates frequently deviate from one-to-one correspondence. Moreover, our analysis reveals that more than 35% of global BSRs occur shallower than the bases of gas hydrate stability zones, especially in deepwater regions, suggesting that the BSRs more accurately represent the interface between the gas hydrate occurrence zone and the underlying free gas zone. BSR morphology is influenced by geological settings, sediment properties, and seismic acquisition parameters. We find that ~70–80% of BSRs occur in fine-grained, grain-displacive sediments with hydrate lenses/nodules, while coarse-grained pore-filling sediments host <20%. BSR interpretation remains challenging due to limitations in traditional P-wave seismic profiles and conventional amplitude versus offset (AVO) analysis, which hinder accurate fluid identification. To address these gaps, future research should focus on frequency-dependent AVO inversion based on viscoelastic theory, multicomponent full-waveform inversion, improved anisotropy assessment, and quantitative links between rock microstructure and elastic properties. These innovations will shift BSR research from static feature mapping to dynamic process analysis, enhancing hydrate detection and our understanding of hydrate–environment interactions. Full article

Addressing the critical challenges of sealing integrity and operational optimization in aquifer gas storage (AGS), this study focuses on a block within the Qianjiang Basin to systematically investigate geological modeling and injection–production strategies. Utilizing 3D seismic interpretation, drilling, and logging data, a stochastic geological modeling approach was employed to construct a high-resolution 3D reservoir model, elucidating the distribution of reservoir properties and trap configurations. Numerical simulations optimized the gas storage parameters, yielding an injection rate of 160 MMSCF/day (40 MMSCF/well/day) over 6-month-long hot seasons and a production rate of 175 MMSCF/day during 5-month-long cold seasons. Interval theory was innovatively applied to assess fault stability under parameter uncertainty, determining a maximum safe operating pressure of 23.5 MPa—12.3% lower than conventional deterministic results. The non-probabilistic reliability analysis of caprock integrity showed a maximum 11.1% deviation from Monte Carlo simulations, validating the method’s robustness. These findings establish a quantitative framework for site selection, sealing system evaluation, and operational parameter design in AGS projects, offering critical insights to ensure safe and efficient gas storage operations. This work bridges theoretical modeling with practical engineering applications, providing actionable guidelines for large-scale AGS deployment. Full article

Accurate characterization of subsurface geological structures, particularly those obscured by strong coal-seam reflections, is essential for hydrocarbon exploration in subtle reservoirs. Enhancing seismic resolution remains a pivotal technical challenge in addressing this demand. Here, we present a multitrace reflectivity inversion method guided by geological sparsity principles. This method establishes quantitative relationships between sparse inversion operators and the spatial positions of stratigraphic boundaries. Specifically, by integrating prior geological knowledge, such as stratigraphic boundaries and stable sedimentary structures, as constraint operators within the sparsity matrix, this method results in a geologically interpretable and robust inversion framework. Subsequently, we validated this method through synthetic data and field applications in a carbonate fracture–cavity reservoir in the Ordos Basin of western China. The enhanced seismic resolution demonstrates that our method effectively restores shielded reservoir reflections beneath coal seams. Clearer than conventional sparse inversion techniques, the coherence attribute of the enhanced seismic resolution reveals distinct fracture–cavity geometries. Moreover, integrated analyses of well logs, fracture–cavity characterization, and drilling production data further confirm the accuracy and reliability of the inversion results. In conclusion, this method effectively leverages accurate geological structural information to enhance localized seismic resolution, thereby providing robust support for the exploration of subtle hydrocarbon reservoirs. Full article

Seismic data are easily contaminated by random noise, impairing subsequent geological interpretation tasks. Existing denoising methods like low-rank approximation (LRA) and deep learning (DL) show promising denoising capabilities but still have limitations; for instance, LRA performance is parameter-sensitive, and DL networks lack interpretation. As an alternative, this paper introduces the low-rank tensor network (LRTNet), an innovative approach that integrates low-rank tensor approximation (LRTA) with DL. Our method involves constructing a noise attenuation model that leverages LRTA, total variation (TV) regularization, and weighted tensor nuclear norm minimization (WTNNM). By applying the alternating direction method of multipliers (ADMM), we solve the model and transform the iterative schemes into a DL framework, where each iteration corresponds to a network layer. The key learnable parameters, including weights and thresholds, are optimized using labeled data to enhance performance. Quantitative evaluations on synthetic data reveal that LRTNet achieves an average signal-to-noise ratio (SNR) of 9.37 dB on the validation set, outperforming Pyseistr (6.46 dB) and TNN-SSTV (6.10 dB) by 45.0% and 53.6%, respectively. Furthermore, tests on real field datasets demonstrate consistent enhancements in noise suppression while preserving critical stratigraphic structures and fault discontinuities. The embedded LRTA mechanism not only improves network interpretability, but also reduces parameter sensitivity compared to conventional LRA methods. These findings position LRTNet as a robust, physics-aware solution for seismic data restoration. Full article

Reservoir geological modeling plays a crucial role in characterizing the spatial distribution and heterogeneity of subsurface reservoirs. The exploration of deep oil and gas resources is not only a global trend in the oil industry but also an inevitable choice for China to ensure energy security and achieve sustainable development in the oil and gas industry. Oil and gas exploration and development technologies have also made continuous breakthroughs, providing strong support for the sustained increase in China’s deep and ultra-deep oil and gas production. Deep and ultra-deep oil and gas reservoirs exhibit high levels of heterogeneity, which are governed by the original sedimentation processes and have a significant impact on oil and gas migration and accumulation. However, traditional pixel-based stochastic reservoir modeling encounters challenges when attempting to effectively simulate multiple facies simultaneously or objects with intricate internal hierarchical architectures. To address the characterization of highly heterogeneous deep and ultra-deep oil and gas reservoirs, this study defines unit architecture bodies, such as point bars, braided rivers, and mouth bars, incorporating internal nested hierarchies. Furthermore, a novel object-based stochastic modeling method is proposed, which leverages seismic and well logging interpretation data to construct and simulate reservoir bodies. The methodology is rooted in the unit element theory. In this approach, sedimentary facies models are stochastically constructed by selecting appropriate unit elements from a database of different sedimentary environments using Sequential Indicator Simulation. The modeling process is constrained by time sequence, event, and sedimentary microfacies distributions. Additionally, the porosity and permeability of each microfacies in the reservoir model are quantitatively characterized based on statistics derived from porosity and permeability data of different strata, sedimentary microfacies, and rock facies in the study area. To demonstrate the superiority and reliability of this novel modeling method, a modeling case is presented. The case utilizes braided river unit elements as objects for the stochastic simulation of the target reservoir. The results of the case study highlight the advantages and robustness of the proposed modeling approach. Full article

Cambrian subsalt dolomite is an important strategic area for natural gas exploration in the Tarim Basin. The gypsum-salt rocks, argillaceous mudstone and argillaceous dolomite strata developed in large areas of the Middle Cambrian can be used as good caprocks. The sealing ability and favorable area distribution of the Middle Cambrian caprock in the Tarim Basin are studied through the lithofacies paleogeography and microscopic evaluation of the Middle Cambrian strata in this paper. Based on the 2D seismic interpretation covering the entire basin, combined with data from drilling, outcrops, well logging, core samples and thin sections, the sedimentary characteristics and lithofacies paleogeography of the Middle Cambrian were studied and then the thickness of the Middle Cambrian gypsum-salt rocks, gypsiferous mudstone and gypsiferous dolomite was analyzed in the Tarim Basin. Studies suggest that the Middle Cambrian is primarily characterized by the development of restricted-platform facies. In the Awati Depression, the northern part of the Tazhong Uplift, the southern part of the Manxi Low Uplift, and the central and northern parts of the Bachu Uplift, the thickness of the gypsum-salt rock strata is relatively large. Moreover, centered on the northern part of the Bachu Uplift, the thickness of the gypsum-salt rocks decreases irregularly towards the periphery, forming a circumferential distribution. To investigate the sealing ability of caprocks, 64 core samples from four wells were examined under a microscope, and physical parameters as well as breakthrough-pressure tests were conducted. By establishing correlations between various parameters, the sealing ability of different rock types in the Cambrian formation within the study area was quantitatively assessed. The research suggests that gypsum-salt rocks exhibit superior sealing ability compared to gypsiferous mudstone and gypsiferous dolomite, but factors such as faults and geological conditions of gypsum can influence the sealing performance of caprocks. According to both micro- and macro-scale evaluations of the Cambrian strata in the study area, along with constraints imposed by actual drilling exploration results, a comprehensive evaluation method for assessing caprock sealing ability has been established. The results suggest that the Awat Depression, the western and southern parts of the Manxi Low Uplift, the northern and western parts of the Tazhong Uplift, and the central part of the Tabei Uplift are favorable areas for the development of caprocks. Full article

The Near-Surface-Mounted (NSM) technique for Fiber-Reinforced Polymer (FRP) strengthening is widely applied in the seismic retrofitting of concrete structures. The key aspect of the NSM technique lies in the adhesive performance between the FRP, adhesive layer, and concrete. In order to accurately predict the bond strength of embedded reinforced NSM FRP–concrete, this study constructs the relationship between the influencing factors of bonding performance and bond strength based on four machine learning (ML) algorithms: Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB). A unified and interpretable prediction method for FRP–concrete interface bond strength based on SHAP values and ML algorithms is proposed. The results indicate that the ML models exhibit good predictive performance, with the R² of the test set ranging from 0.8190 to 0.9621, showing higher accuracy than empirical calculation formulas. Among them, the RF algorithm demonstrates the highest overall accuracy and optimal performance. Additionally, the SHAP (Shapley additional explanations) method quantitatively confirms that the width of the FRP strip has the most significant impact on bond strength. The newly developed hybrid ML model has the potential to become a new choice for accurately assessing the bond strength of NSM FRP strengthening technology. Full article

Structural fracture distribution is essential in oil and gas transportation and development in passive continental margin basins. In this paper, taking as an example the clastic reservoirs in the A-Basin, a passive continental margin in northeastern South America, the paleotectonic stress field of the Late Cretaceous Maastrichtian formation in Basin A was numerically simulated by finite element technique through the integrated interpretation of seismic total data, logging data and core data, and the distribution of tectonic fractures was later predicted based on rock fracture criterion. The results of the study show that: (1) The distribution of tectonic stress and fractures during the Late Cretaceous Maastrichtian formation of Basin A is affected by the fracture zone, mechanical properties of rocks and tectonic stress, regions with extensive fracture development are susceptible to stress concentrations, resulting in significant stress gradients. (2) The development of structural fractures in the study area was predicted using the Griffiths criterion, and the tensile rupture coefficient T was introduced to quantitatively characterise the intensity of fracture development, with larger values reflecting a higher degree of fracture development. The well-developed and relatively well-developed fractures are mainly located in the fracture zones and the interior of submarine fans. (3) Fracture zones and sedimentary phases mainly control structural fractures in Basin A; within 5 km outside the fracture zones, the development of fractures is controlled by the fracture zones, beyond which the regional tectonic stress field controls them; inside the sedimentary fan, the development of fractures is controlled by the sedimentary subphase, which decreases in the order of the upper fan, the middle fan, and the lower fan; inside the subphase, they are controlled by the regional tectonic stress field, and the fractures show the increasing trend in the direction of NW-NE. Full article

The Qiulitage fold and thrust belt (QFTB) is situated in the Kuqa Depression, exhibiting spectacular salt structures with well-defined geometric and kinematic characteristics and thereby playing a significant role in advancing the study of salt structures worldwide. This research, based on regional geology, well logging, and newly acquired three-dimensional seismic data, applies principles of salt-related fault structures to interpret seismic data and restore structural equilibrium in the Qiulitage fold and thrust belt within the Kuqa Depression by conducting quantitative studies on structural geometry and kinematics. Results indicate clear differences in salt structures between the eastern and western segments of it, vertically divided into upper salt, salt layer, and lower salt and horizontally into four parts. The Dina segment features a single-row basement-involved thrust fault, the East QFTB segment displays detachment thrust faults involving cover layers, the Central QFTB segment exhibits detachment thrust faults involving multiple rows of cover layers, the leading edge forms structural wedges, and the West QFTB segment develops blind-thrust faults. During the deposition of the Kangcun formation, the eastern profile experiences an 18% shortening rate, 14% in the central part, and 9% in the western part. For the Kuqa formation, the eastern profile experiences a 10% shortening rate, 9% in the central part, and 3% in the western part, indicating more significant deformation in the east than in the west. Quantitative statistical analysis reveals that different types of detachments, paleogeomorphology, and northeast-directed compressive stress exert control over the Qiulitage fold-thrust belt. Full article

The eastern margin of the Tibetan Plateau is one of the regions with the most severe landslide disasters on a global scale. With the intensification of seismic activity around the Tibetan Plateau and the increase in extreme rainfall events, the prevention of landslide disasters in the region is facing serious challenges. This article selects the Bailong River Basin located in this region as the research area, and the historical landslide data obtained from high-precision remote sensing image interpretation combined with field validation are used as the sample library. Using machine learning algorithms and data-driven landslide susceptibility assessment as the methods, 17 commonly used models and 17 important factors affecting the development of landslides are selected to carry out the susceptibility assessment. The results show that the BaggingClassifier model shows advantageous applicability in the region, and the landslide susceptibility distribution map of the Bailong River Basin was generated using this model. The results show that the road and population density are both high in very high and high susceptible areas, indicating that there is still a significant potential landslide risk in the basin. The quantitative evaluation of the main influencing factors emphasizes that distance to a road is the most important factor. However, due to the widespread utilization of ancient landslides by local residents for settlement and agricultural cultivation over hundreds of years, the vast majority of landslides are likely to have occurred prior to human settlement. Therefore, the importance of this factor may be overestimated, and the evaluation of the factors still needs to be dynamically examined in conjunction with the development history of the region. The five factors of NDVI, altitude, faults, average annual rainfall, and rivers have a secondary impact on landslide susceptibility. The research results have important significance for the susceptibility assessment of landslides in the complex environment of human–land interaction and for the construction of landslide disaster monitoring and early warning systems in the Bailong River Basin. Full article