Complex Geological Structures Research Articles

Prospects for the gas and condensate production from the South Hrabyne zone of the Precarpathian foredeep

The main problems of prospecting and exploration of gas and gas condensate fields in the lithological and stratigraphic strata of the southwestern and central parts of the Bilche-Volytsia zone are due to the complex tectonic and lithological and stratigraphic conditions for the hydrocarbon deposits formation. The objective factors include the complex geological structure of reservoir rocks due to tectonic disturbances in the process of trap formation, the presence of various types of voids and clay material, as well as flooding of productive formations at the final stage of development. In addition, it is necessary to note the decrease in the information content and efficiency of both ground and borehole electrical exploration. At the same time, lithotypes with a complex petrographic and petrophysical thin layer structure of the rock matrix are observed in the Neogene deposits. Thus, in order to increase the information content of the results of geophysical well surveys (GWS) and the efficiency of hydrocarbon prospecting, it is necessary to form an optimal set of the latest geophysical methods, in particular: high-frequency induction logging with isoparametric sounding (HFILIS), nuclear magnetic logging (NML), as well as acoustic and radioactive studies. The introduction of this type of innovation will increase the information content of geological and geophysical studies. The main basis of this approach is the petrographic and petrophysical base for specific territories and prospecting areas. In view of the foregoing, we identified gas-saturated reservoir rocks, established the structure of their seal rocks, as well as determined the effective thicknesses of rocks and developed correlation schemes for their distribution within the Sarmatian, Badenian, and Helvetian deposits.

Facies conditional simulation based on VAE-GAN model and image quilting algorithm

Characterization of complex reservoir structures by using limited observations is challenging in geosciences because it requires to reproduce geological realism. We propose a novel method to reconstruct complex structures by combining variational autoencoder and generative adversarial networks (VAE-GAN) with conditional image quilting algorithm. It improves the stability of traditional GAN-based simulation method without decreasing the quality of patterns. Firstly, we construct a VAE-GAN model to extract the high-dimensional features of facies patterns and to create abundant new patterns. The VAE-GAN-based learning method has a good ability in feature learning from training patches and accurately reproduce new facies patterns. Finally, these new patterns are spliced together to reconstruct a complex geological structure by employing the conditional image quilting algorithm, in which patterns are pasted to the simulated areas based on the calculated minimum cost path. During this process, conditioning is also considered. Since the pattern is generated by using the deep learning method rather than directly extracted from the training image, the diversity of realizations is enhanced without losing reproducibility. Based on synthetic training image, several examples are described and analyzed in detail, demonstrating the effectiveness and reliability of the present method. In addition, the new method is applied to a real training image. The complex heterogeneous structures are well reproduced by our method, indicating its practicability.

First-order CO2 trapping characteristics of fold-and-thrust belts: Assessing carbon storage potential in the Appalachian Basin and beyond

Carbon capture and storage (CCS) is a strategy that is used to reduce global greenhouse gas emissions. As a result of increased government incentives and maturing carbon markets, CCS is currently experiencing an unprecedented level of public and commercial interest. In the United States, the Appalachian Basin contains abundant hydrocarbon resources and is the location of numerous industrial facilities, making the region a promising target for CCS development. However, the lack of seismic reflection surveys and well data, along with complex geologic structure throughout much of the basin, has limited the commercial interest in CCS development. This study proposes that the thin-skinned fold-and-thrust belt of the Appalachian Basin may contain geology suitable for secure long-term CO2 storage. This region, known as the Valley and Ridge physiographic province, holds complex fold-and-thrust structures that may effectively trap commercial volumes of CO2. We test this idea by developing a suite of kinematically feasible geologic interpretations for the Catawba syncline Pulaski thrust system in southwest Virginia. We then use these geologic models to conduct numerical simulations for CO2 storage within the fold-and-thrust belt structures of the Catawba syncline. Our simulation results indicate that the geometric configuration of fold-and-thrust belt structures may offer commercially viable CO2 traps for CCS projects within the Appalachian Basin and similar geologic settings worldwide.

Unchartered fault through outcrop study by using simple structure from motion technique in seismicaly active area

Structure from motion (SfM) is a photogrammetric method used to reconstruct 3-Dimensional (3D) surfaces from the displacement of the camera in between several 2-dimensional photographs. This method can produce sparse and dense point clouds from which high-resolution surface models such as digital surface models and digital terrain models are obtained. SfM is not restricted to topographic surfaces, it also can be used to model various ground objects at different scales such as trees, buildings, outcrops and any other structure that can be photographed with an ordinary camera. Among this myriad of possibilities, the present contribution focuses on the reconstruction of 3D outcrop models, as they can become digital archives of geological and seismic activity, especially in countries where landscape remodeling activity and mining are important. Outcrop is a vertical exposure of particular rock formation. By knowing the characteristics of the outcrop, we can understand the reservoir characteristics and important stratigraphic information. Also, we can take more attention on microstructural information for both slope instability and seismic characteristics analysis. Thus, although SfM is relatively new in geoscience, this study will provide the usage of the SfM technique to support the outcrop analysis to obtain important micro-structure information of the outcrop. Further, this data was used to support the seismic susceptibility assessment in a very complex geological structure area.

Model-based assessment of interbasin groundwater flow in data scarce areas: the Gallocanta Lake endorheic watershed (Spain)

Aquifer systems, because of the presence of frequently complex geological structures, may extend beyond watersheds limits. Interbasin groundwater flow is often identified among watersheds. Because geological systems are complex ones, modelling tools are needed for its estimation. In this paper, we quantify the outflows from the endhoreic Gallocanta watershed (Spain) by means of a MODFLOW numerical model in order to assess the robustness of the boundaries of the Gallocanta Groundwater Body. Our results show the Gallocanta watershed is hydrogeologically connected with the adjoining Piedra-Ortiz and Jiloca watersheds (discharging annually in these basins about 4 and 1 Mm3 respectively). Furthermore, we hypothesized the presence of geological features altering the groundwater flow. Additional simulations were run to analyse the changes in the water budget in the cases of: i) groundwater pumping no longer allowed by the authorities, and ii) a potential drought scenario. In the first case, the results forecast an increase in discharge to the Piedra-Ortiz and Jiloca watersheds, while in the second case a diminution of the outflows to the two neighboring basins is foreseen.We then propose a larger and unique groundwater body, spanning from the Caminreal Springs on the east and the Piedra-Ortiz basin on the west, including a moving groundwater divide internal to the Gallocanta watershed. Monitoring the baseflow of the Piedra-Ortiz river and of the Caminreal Springs will allow to get information on the evolution of the groundwater resource availability in the Gallocanta watershed. Our results stress the importance of conjunctively using data and traditional geologic knowledge (i.e. surface geology maps) along with numerical modelling analyses. This holds especially true in areas, such those of hard-rock aquifers, where scarce hydrogeologic data are available, to test conceptual models, to derive and to infer information on water budgets and on the presence of relevant structural features driving the groundwater flow. This approach may lead to informed decision-making on groundwater body boundaries definition for the application of relevant groundwater management regulations.

Crustal structure across the Central part of Narmada-Son Lineament, India based on the interpretation of aeromagnetic and gravity data: Geological implications

Narmada-Son Lineament (NSL) is a prominent geo-tectonic feature located in central India, characterised by complex geological structures and evolution history. In this study, we present a detailed joint interpretation of the aeromagnetic and gravity anomaly maps to delineate the crustal structure in order to address the thermo-tectonic activity below the NSL region. The NW-SE linear trend observed in the aeromagnetic anomaly map correlates well with the major tectonic elements of the NSL and the Vindhyan basin. The low-pass filtered regional gravity anomaly map and corresponding residual anomaly map revealed several crustal-scale structural features in the study area. The Curie depth map of the region prepared from the magnetic anomaly map shows the variation between 24-48 km. The corresponding heat flow map correlates well with the trends in surface heat flow data. The gravity-derived Moho depth map reveals that the values vary between 30-40 km in the NSL region with deeper Moho below the Vindhyan basin. Further, the crustal models obtained from the constrained potential field modelling for two long transects across the NSL in the present study area revealed i) the absence of crustal underplating in the eastern part of NSL below Hirapur-Mandla region, ii) the presence of mid-crustal horst like structure below NSL in both the transects, iii) undulating Moho with higher density crustal rocks within the NSL compared to the surrounding areas. The modelled crustal structure and the analysis of Curie depth as well as heat flow maps of the study area, reveal that the NSL region was affected by repeated tectonic activities since the Proterozoic times, and the present-day tectonics of this belt is greatly influenced by the reactivation of pre-existing faults along the NSL.

Применение технологии объединения методов разведочных работ для достижения экологического эффекта на месторождениях Каспия

The method of performing exploration works allowing to obtain an environmental effect in the Caspian Sea fields is described in the article. The research area includes the Rakushechno-Latitudinal and Khvalynsko-Sarmatian zones. Deposits of these zones differ in a complex geological structure. When creating a model of deposits a set of data is used: high-precision 3D seismic surveys on the study area and the results of drilling wells. Such detail of seismic exploration works allows to obtain high-quality results that are due to the high density of reflection points over the area and to the maximum use of various dynamic parameters of reflected waves. The results of such surveys are used in the calculation of reserves, justification of work on additional exploration and subsequent operation. Based on the results of seismic surveys a quantitative forecast of reservoir properties was carried out due to the inversion. For implementation seismic data was processed while preserving the true amplitudes of the seismic signal. Drilling wells were also the main source of information when performing work on calculating reserves. The complex structure and heterogeneity conditions of reservoir properties in area and section, the presence of discontinuous violations led to the use of the described technology, which involves the assessment of reserves and their transfer to the industrial category without testing in the column and causing inflow to the surface. This is done by means of a comprehensive accelerated diagnostics of productive formations for the assessment of reserves of the industrial category. Such a diagnosis provides for the study of productive formations based on the analysis and generalization of accumulated material on core, GIS, GDIS, GDK-OPK and PVT studies, without conducting tests in wells. With the help of these studies the filtration-capacitance properties of rocks, the nature of fluid saturation, contact positions, static levels, reservoir and bottom-hole pressures and reservoir temperatures, as well as deep sampling are determined. The use of modern instruments such as MDT (reservoir Tester) makes it possible to obtain reliable deep samples of the reservoir fluid. The results of data interpretation are successfully approved when making reports on UVS reserves calculation.

Processing of electrical resistivity tomography data using convolutional neural network in ERT-NET architectures

Electrical resistivity tomography (ERT) inversion has emerged as an effective method for predicting resistivity in complex geological structures. In most cases, traditional ERT inversion problems are posed as nonlinear optimization problems. Solving distribution resistivity inversion can be computationally challenging for two reasons: one is the significant cost of software and the other is the issue of local minima. The ERT-NET architecture was developed in this study to learn the parameter regression relationship between geophysical ERT datasets and subsurface models. We developed a novel convolutional neural network (CNN) technique that comprised of a fully connected network (ERT-INET) and a fully convolutional network (ERT-UNET); both train ambiguity information of the inverted resistivity based on processing ERT datasets. We also output our network segmentation of pixel-wise prediction for ERT-INET and structured prediction segmentation. The noise assessments of our network inversion were managed by employing depth of investigation (DOI) and statistical analysis for evaluation performance. The DOI appeared to be effective in conveying the breadth of possibility within our networks. Moreover, the performances are either the synthetic resistivity model or the field resistivity data, both of which have an average of greater than 95%. The inversion results of both architectures are precisely and accurately expressed, containing approximately the ground truth models and thereby also the field observation models. We conclude that these ERT-NET architectures could be one approach to ERT interpretation handling, and we strongly suggest alternatives that promote the geoelectrical method of interpretation.

Seismic Elastic Parameter Inversion via a FCRN and GRU Hybrid Network with Multi-Task Learning

Seismic elastic parameter inversion translates seismic data into subsurface structures and physical properties of formations. Traditional model-based inversion methods have limitations in retrieving complex geological structures. In recent years, deep learning methods have emerged as preferable alternatives. Nevertheless, inverting multiple elastic parameters using neural networks individually is computationally intensive and can lead to overfitting due to a shortage of labeled data in field applications. Multi-task learning can be employed to invert elastic parameters simultaneously. In this work, a hybrid network that leverages the fully convolutional residual network (FCRN) and the gated recurrent unit network (GRU) is designed for the simultaneous inversion of P-wave velocity and density from post-stack seismic data. The FCRN efficiently extracts local information from seismic data, while the GRU captures global dependency over time. To further improve the horizontal continuity and inversion stability, we use a multi-trace to single-trace (M2S) inversion strategy. Consequently, we name our proposed method the M2S multi-task FCRN and GRU hybrid network (M2S-MFCRGRU). Through anti-noise experiments and blind well tests, M2S-MFCRGRU exhibits superior anti-noise performance and generalization ability. Comprehensive experimental inversion results also showcase the excellent lateral continuity, vertical resolution, and stability of the M2S-MFCRGRU inversion results.

Discontinuous Galerkin method for solving viscoacoustic wave equations with amplitude dissipation and phase dispersion separation in isotropic and anisotropic media

SUMMARY The standard-linear-solid (SLS) theory works well for viscoelasticity. However, the coupling of amplitude dissipation and phase dispersion makes it impossible to investigate their effects separately by the discontinuous Galerkin method (DGM). In this paper, we have derived newly viscoacoustic wave equations with amplitude dissipation and phase dispersion separation in isotropic and anisotropic media, based on a Fourier method, which is suitable for using a time–space-domain DGM on unstructured meshes. The basic framework of DGM is constructed and the amplitude-dissipation effect and the phase-dispersion effect in viscoacoustic wave equations are investigated. The original equation is first transformed into the frequency–wavenumber domain, where the amplitude dissipation and phase dispersion are separated effectively, and then the decoupled formulation is converted back to the time–space domain. The new equivalent and approximate equations can be obtained. Compared with the original equation, the newly approximated equation enables us to separate the amplitude-loss and phase-delay terms, respectively, and experiences four kinds of effects, namely acoustic effect, only amplitude-dissipation effect, only phase-dispersion effect and both amplitude-dissipation and phase-dispersion effect. Moreover, the stability condition and numerical dispersion for using DGM to solve the new and old equations are presented. Several numerical examples are used to verify the correctness and effectiveness of the modified approximate equations in viscoacoustic isotropic and anisotropic media. The numerical results in a cave and SEG/EAGE salt models demonstrate that the new equations combined with DGM have performances on viscoacoustic media with complex geological structures.

Microtremor analysis around Jari mud volcano, Bojonegoro

The earthquake that occurred in the Mount Pandan area in 2016 is thought to have triggered the emergence of a mudflow mixed with water and gas. The research area is in the Kendeng Zone with a complex geological structure. In this zone, there is a very fast sedimentation process so the buried material is not fully compacted. In this study, measurements were made of 6 microtremor data points around Jari Mud Volcano, Bojonegoro, East Java, Indonesia. Furthermore, the data obtained were processed using the HVSR analysis method. HVSR analysis is a method of processing microtremor signals to determine soil characteristics based on information on natural frequency values and its amplification. The result shows the natural frequency parameter and its amplification is slightly variated around Jari Mud Volcano, caused by sedimentary depth variation and/or the presence of existing rock. Based on 6 processed data, the natural frequency values range from 1.9 to 9.1 Hz. Meanwhile, the amplification value ranges from 2.6 to 4.4. Based on the amplification value, the research area is classified as low and medium amplification zones (low value dominance). This is because the amplification value is related to geomorphological conditions, in which the research area is located in the mountains and is composed of volcanic sediments.

An improved reverse time migration for subsurface imaging over complex geological structures: A numerical study

In seismic exploration, it is a critical task to image and interpret different seismic signatures over complex geology due to strong lateral velocity contrast, steep reflectors, overburden strata and dipping flanks. To understand the behavior of these seismic signatures, nowadays Reverse Time Migration (RTM) technique is used extensively by the oil & gas industries. During the extrapolation phase of RTM, the source wavefield needs to be saved, which needs high storage memory and large computing time. These two are the main obstacles of RTM for production use. In order to overcome these disadvantages, in this study, a second-generation improved RTM technique is proposed. In this improved form, a shift operator is introduced at the time of imaging condition of RTM algorithm which is performed automatically both in space and time domain. This effort is made to produce a better-quality image by minimizing the computational time as well as numerical artefacts. The proposed method is applied over various benchmark models and validated by implementing over one field data set from the Jaisalmer Basin, India. From the analysis, it is observed that the method consumes a minimum of 45% less storage space and reduce the execution time by 20%, as compared to conventional RTM. The proposed RTM is found to work efficiently in comparison to the conventional RTM both in terms of imaging quality and minimization of numerical artefacts for all the benchmark models as well as field data.

Impact of Soil Properties’ Spatial Correlation Lengths and Inclination on Permanent Slope Displacements Due to Earthquake Excitation

Natural disasters, when and where they occur, often cause serious social and economic consequences, which require an urgent solution to the problem. In particular, Greece, which is characterized by a complex geological structure and intense tectonic stress, has suffered and continues to suffer the consequences of such catastrophic phenomena. Among the various destructive phenomena recorded on the Earth’s surface, two of the most important problems are landslides and land subsidence. The above phenomena may cause, in addition to the serious case of loss of human life, a threat to the social and economic fabric affecting sustainability in general, i.e., the quality of life of an area (destruction of property, filling of reservoirs, blockage of streams and rivers, etc.). In fact, landslides are a phenomenon with enormous social and economic consequences, since apart from the financial burden due to the collapse of a technical project or the interruption of transportation, they are accompanied by the loss of human life. This research examines the stochastic characteristics of a slopes’ stability to investigate the variation range of permanent earthquake movements. More specifically, the influence of inclination as well as the lengths of the spatial correlation of ground are investigated. The method in the present study follows the development of arbitrary fields of soil properties, which follow the Gaussian distribution characterized by autocorrelation lengths lx and ly in the horizontal and vertical directions, respectively, mean value μ, standard deviation σ, and cross-correlation coefficients ρij. The estimation of permanent displacements is performed by the combination of the Local Average Subdivision algorithm and the FLAC software (Fast Lagrangian Analysis of Continua) used in the parametric investigation of this work. The results of this research showed that the spatial correlation of the properties has an important impact on the permanent displacements of slopes caused by strong earthquake excitations.

The Deformation Law of a Soft-Rock Cavern by Step Excavation in a Pumped Storage Power Station

The surrounding rock stability of large underground caverns in a pumped storage power station is one of the most crucial problems in hydropower project design and construction. In the construction of hydropower projects in Southwest China, many underground soft-rock caverns in are excavated. Influenced by the high sidewall, high ground stress, large burial depth, and hydrodynamic pressure action, the deformation of the cavern is special, especially in terms of its soft-rock distribution. At present, most research of underground engineering on soft-rock stability focuses on small-scale tunnel excavations in homogeneous geological conditions, with limited studies on the large-scale excavation of deeply buried underground powerhouses in complex geological structures, featuring extensive soft-rock-layer exposure on the cavern wall. Therefore, it is particularly important to investigate the excavation method of and support measures for soft-rock caverns under complex geological conditions. Based on laboratory rock mechanics testing (petrographic analysis, uniaxial compressive strength tests, shear tests, and triaxial compression creep tests) and the distribution characteristics of the surrounding soft-rock layer of the proposed underground powerhouse, obtained from the survey, we discuss the excavation and support measurements. These include the influence of support measures on the deformation of the underground excavated cavern considering the inclination of rock layers, the impact of the excavation under supported conditions on the deformation of the underground cavern, and the correlation between the lining thickness and stress variation within the lining.

Prediction of Marine Thin Shale Gas Reservoir with Seismic Phase-Controlled Nonlinear Stochastic Inversion

Due to the complicated interference sources and low signal-to-noise ratio of seismic records, conventional seismic inversion methods are difficult to accurately identify shale gas reservoirs with a thickness of less than 10 m. This presents great challenges to shale gas exploration and development in China. Seismic phase-controlled nonlinear stochastic inversion (SPCNSI) is related to the heterogeneity of underground media. With the constraints of the stratigraphic sequence or seismic facies models, the minimum value between the seismic model and seismic record can be solved through iterative processes. Based on the solved acoustic velocity in formation, the constraints for SPCNSI can be formed with the matching relationship between target layers and different sequences in three-dimensional space. The prediction resolution of an unconventional reservoir can be effectively improved by combining logging, geological and seismic information. The method is suitable for predicting thin shale gas reservoirs in complex geological structures. In this study, SPCNSI was developed to predict the thin-layer marine shale gas reservoir in the southeast of Chongqing; the horizontal and vertical distribution characteristics were proven in the Longmaxi Formation and the Wufeng Formation; thin layers with a thickness of less than 7 m were also discovered. According to the results, three sets of potential development areas were determined by the inversion method, and the accuracy and reliability of the method were verified by logging and productivity testing.

Experimental study on dynamic pore-fracture evolution and multiphase flow in oil-saturated coal considering the influence of in-situ stress

The methane drainage in liquid-saturated coal is directly related to the multiphase flow in complex geological structures. In this study, the pore-fracture dynamic evolution induced by in-situ stress and the corresponding gas-liquid migration and morphology characteristics were investigated by a self-developed online LF-NMR triaxial stress system. The dynamic variation, obvious change, and slight response were occurred at the migration pore (MP＞3ms), percolation pore (0.3ms < PP < 3ms), and adsorption pore (AP<0.3ms) with the increased stress, and development of gas channel was contributed by MP (15%–20%), AP (5%–10%), and PP(0–5%) responding to the gas flooding. The pore-fracture successively experienced compression, dilation, expansion, and coalescence, and PP and MP dominated the fracture initialization and connection. The permeability is negatively correlated with the fractal dimension of the pore-fracture structure and is exponentially related to the porosity and MP porosity. The longitudinal shear fracture is beneficial for the gas-liquid migration, and the horizontal tension crack connects the scattered pore and branch fracture. The gas channel was influenced by the liquid capillary pressure and gas jiamin effect in poor pore-fracture and mainly influenced by the gas slippage effect, immiscible behavior, and fracture surface tension force in mature pore-fracture. The optimal gas channel occurred at the crack-propagation period, which was located at around 70% peak strength with 1.5md permeability, high liquid relative permeability and lower gas relative permeability. The findings provide significant insight into methane extraction.

Prediction of Leakage Pressure in Fractured Carbonate Reservoirs Based on PSO-LSTM Neural Network

Shunbei Oilfield is a fractured carbonate reservoir with complex geological structures that are influenced by fault movements and prone to collapse and leak incidents. Precisely predicting leakage pressure is crucial for conducting fracturing operations in the later stages of production. However, current fracture-related leakage pressure prediction models mostly rely on statistical and mechanical methods, which require the consideration of factors such as fracture aperture and parameter selection, thereby leading to limitations in prediction efficiency and accuracy. To enhance the accuracy of reservoir leakage pressure prediction, this study leverages the advantages of artificial intelligence methods in dealing with complex nonlinear problems and proposes an optimized Long Short-Term Memory (LSTM) neural network prediction approach using the Particle Swarm Optimization (PSO) algorithm. Firstly, the Spearman correlation coefficient is used to evaluate the correlation between nine parameter features and leakage pressure. Subsequently, an LSTM network framework is constructed, and the PSO algorithm is applied to optimize its hyper-parameters, establishing an optimal model for leakage pressure prediction. Finally, the model’s performance is evaluated using the Coefficient of Determination (R2), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The evaluation results demonstrate that the PSO-optimized LSTM model achieved an R2 of 0.828, RMSE of 0.049, and MAPE of 3.2, all of which outperformed the original model. The optimized LSTM model showed an average accuracy approximately 12.8% higher than that of the single LSTM model, indicating its higher prediction accuracy. The verification results from multiple development wells in this block further confirmed that the deep learning model established in this study surpassed traditional methods in prediction accuracy. Consequently, this approach is beneficial for drilling engineers and decision-makers to plan drilling operations more effectively and achieve accurate risk avoidance during the drilling process.

Three-Dimensional Geological–Geophysical Modeling and Prospecting Indications of the Ashele Ore Concentration Area in Xinjiang Based on Irregular Sections

The Ashele ore concentration area is an important area for polymetallic ore concentration in Xinjiang, China. Scholars have made progress in understanding the ore-controlling structures, ore-bearing horizons, and metallogenic age of this area. However, there are still uncertainties about the 3D distributions of plutons, fault structures, and ore-bearing strata, which restrict the development of deep and peripheral ore prospecting and the discovery of new ore bodies in the area. This study proposes a geological–geophysical modeling method based on irregular sections and uses this method to establish a 3D geological–geophysical model based on physical property data, boreholes, surface geological maps, and geophysical data. The model shows that the study area has many hidden rock masses with various depths and shapes and fracture structures with complex shapes. The fault structure in the area is complex, and the ore bodies are controlled by the faults. The ore-bearing geological units (Ashele Formation) exhibit an obvious east–west-trending W-shaped fold structure. The deep part of the northern Ashele Formation extends northward slightly, and the southern Ashele Formation has thick strata, with depths generally greater than 2 km. Based on the information on deep structures provided by the model, three metallogenic prospective areas are predicted, which points out the direction for further prospecting work in the ore concentration area and shows that the adopted modeling method and process have good applicability for constructing 3D models of ore concentration areas with sparse data, large area, and complex geological structures. The proposed modeling method provides technical support for ore prospecting, particularly in the overburden area or ore concentration area with sparse data.

Addressing Geological Challenges in Mineral Resource Estimation: A Comparative Study of Deep Learning and Traditional Techniques

Spatial prediction of orebody characteristics can often be challenging given the commonly complex geological structure of mineral deposits. For example, a high nugget effect can strongly impact variogram modelling. Geological complexity can be caused by the presence of structural geological discontinuities combined with numerous lithotypes, which may lead to underperformance of grade estimation with traditional kriging. Deep learning algorithms can be a practical alternative in addressing these issues since, in the neural network, calculation of experimental variograms is not necessary and nonlinearity can be captured globally by learning the underlying interrelationships present in the dataset. Five different methods are used to estimate an unsampled 2D dataset. The methods include the machine learning techniques Support Vector Regression (SVR) and Multi-Layer Perceptron (MLP) neural network; the conventional geostatistical methods Simple Kriging (SK) and Nearest Neighbourhood (NN); and a deep learning technique, Convolutional Neural Network (CNN). A comparison of geologic features such as discontinuities, faults, and domain boundaries present in the results from the different methods shows that the CNN technique leads in terms of capturing the inherent geological characteristics of given data and possesses high potential to outperform other techniques for various datasets. The CNN model learns from training images and captures important features of each training image based on thousands of calculations and analyses and has good ability to define the borders of domains and to construct its discontinuities.

Цеолитовая минерализация пород-коллекторов севера Западной Сибири: литолого-геофизические аспекты и особенности разработки

As the hydrocarbon production tends to decline, formations with a complex geological structure and various secondary mineral formation types of reservoir rocks gain a considerable attention. The importance of secondary minerals for formation of pore and void space structure in hydrocarbon reservoirs is extremely high. The physical and chemical properties of these minerals should be considered during exploration works, calculation of reserves, reservoir engineering, wellwork planning. This article highlights the methodological study approach of mountain rocks with zeolitization based on the results of modern lithological, analytical, and laboratory research. The implementation of the approach allowed for recommendations for rapid quantitative assessment of zeolite content in the Lower Cretaceous sediments of the Bolshekhetskaya Depression.