A 3D attention U-Net network and its application in geological model parameterization

To solve the problems of convolutional neural network–principal component analysis(CNN-PCA)in fine description and generalization of complex reservoir geological features,a 3D attention U-Net network was proposed not using a trained C3D video motion analysis model to extract the style of a 3D model,and applied to complement the details of geologic model lost in the dimension reduction of PCA method in this study.The 3D attention U-Net network was applied to a complex river channel sandstone reservoir to test its effects.The results show that compared with CNN-PCA method,the 3D attention U-Net network could better complement the details of geological model lost in the PCA dimension reduction,better reflect the fluid flow features in the original geologic model,and improve history matching results.

The Method and Practice of Constructing 3D Geological Model from Coalfield Exploration 2D Maps

3D geological modeling is an inevitable choice for coal exploration to adapt to the transformation of coal mining for green, fine, transparent and Intelligent mining. In the traditional Coalfield exploration geological reports, the spatial expression form for the coal seams and their surrounding rocks are 2D maps. These 2D maps are excellent data sources for constructing 3D geological models of coal field exploration areas. How to construct 3D models from these 2D maps has been studying in coal exploration industry for a long time, and still no breakthrough has been achieved so far. This paper discusses the principle, method and software design idea of constructing 3D geological model of an exploration area with 2D maps made by AutoCAD/MapGIS. At first, the paper analyzes 3D geological surface expression mode in 3D geological modeling software. It is pointed out that although contour method has unique advantages in coal field exploration, TIN (Triangular Irregular Network) is still the standard configuration of 3D modeling software for coal field. Then, the paper discusses the method of 2D line features obtaining elevation and upgrading 2D curve to 3D curve. Next, the method of semi-automatic partition is introduced to build the boundary ring of the surface patch, that is, the user clicks and selects the line feature to build the outer boundary ring of the surface patch. Then, Auto-process method for fault line inside of the outer boundary ring is discussed, it including construction of fault ring, determining fault ring being normal fault ring or reverse fault ring and an algorithm of dealing with normal fault ring. An algorithm of dealing with reverse fault ring is discussed detailly, the method of expanding reverse fault ring and dividing the duplicate area in reverse fault into two portions is introduced. The paper also discusses the method of extraction ridge line/valley line, the construction of fault plane, the construction of stratum and coal body. The above ideas and methods have been initially implemented in the “3D modeling platform for coal field exploration” software, and applied to the 3D modeling practice of data from several coal field exploration areas in Ningxia, Shanxi, Qinghai, etc.

3D geological modeling for mineral resource assessment of the Tongshan Cu deposit,Heilongjiang Province,China

Three-dimensional geological modeling （3DGM） assists geologists to quantitatively study in three-dimensional （3D） space structures that define temporal and spatial relationships between geological objects. The 3D property model can also be used to infer or deduce causes of geological objects. 3DGM technology provides technical support for extraction of diverse geoscience information, 3D modeling, and quantitative calculation of mineral resources. Based on metallogenic concepts and an ore deposit model, 3DGM technology is applied to analyze geological characteristics of the Tongshan Cu deposit in order to define a metallogenic model and develop a virtual borehole technology; a BP neural network and a 3D interpolation technique were combined to integrate multiple geoscience information in a 3D environment. The results indicate： （1） on basis of the concept of magmatic-hydrothermal Cu polymetallic mineraliza- tion and a porphyry Cu deposit model, a spatial relational database of multiple geoscience information for mineralization in the study area （geology, geophysics, geochemistry, borehole, and cross-section data） was established, and 3D metallogenic geological objects including mineralization stratum, granodiorite, alteration rock, and magnetic anomaly were constructed; （2） on basis of the 3D ore deposit model, 23,800 effective surveys from 94 boreholes and 21 sections were applied to establish 3D orebody models with a kriging interpolation method; （3） combined 23,800 surveys involving 21 sections, using VC＋＋ and OpenGL platform, virtual borehole and virtual section with BP network, and an improved inverse distance interpolation （IDW） method were used to predict and delineate mineralization potential targets （Cu-grade of cell not less than 0.1%）; （4） comparison of 3D ore bodies, metallogenic geological objects of mineralization, and potential targets of mineralization models in the study area, delineated the 3D spatial and temporal relationship and causal processes among the ore bodies, alteration rock, metallo- genic stratum, intrusive rock, and the Tongshan Fault. This study provides important technical support and a scientific basis for assessment of the Tongshan Cu deposit and surrounding exploration and mineral resources.

3-D Geological Modeling-Concept,Methods and Key Techniques

3-D geological modeling plays an increasingly important role in Petroleum Geology, Mining Geology and Engineering Geology. The complexity of geological conditions requires different modeling methods in different situations. This paper summarizes the general concept of geological modeling; compares the characteristics of borehole-based modeling, cross-section based modeling and multi- source interactive modeling; analyses key techniques in 3-D geological modeling; and highlights the main difficulties and directions of future studies.

A 3D Geological Model Constrained by Gravity and Magnetic Inversion and its Exploration Implications for the World-class Zhuxi Tungsten Deposit, South China

The Zhuxi tungsten deposit in Jiangxi Province,South China,contains a total W reserve of about 2.86 Mt at an average grade of 0.54 wt%WO3,representing the largest W deposit in the world.Numerous studies on the metallogeny of the deposit have included its timing,the ore-controlling structures and sedimentary host rocks and their implications for mineral exploration.However,the deep nappe structural style of Taqian-Fuchun metallogenic belt that hosts the W deposit,and the spatial shape and scale of deeply concealed intrusions and their sedimentary host rocks are still poorly defined,which seriously restricts the discovery of new deposits at depth and in surrounding areas of the W deposit.Modern 3 D geological modeling is an important tool for the exploration of concealed orebodies,especially in brownfield environments.There are obvious density contrast and weak magnetic contrast in the ore-controlling strata and granite at the periphery of the deposit,which lays a physical foundation for solving the 3 D spatial problems of the ore-controlling geological body in the deep part of the study area through gravity and magnetic modeling.Gravity data(1:50000)and aeromagnetic data(1:50000)from the latest geophysical surveys of 2016-2018 have been used,firstly,to carry out a potential field separation to obtain residual anomalies for gravity and magnetic interactive inversion.Then,on the basis of the analysis of the relationship between physical properties and lithology,under the constraints of surface geology and borehole data,human-computer interactive gravity and magnetic inversion for 18 cross-sections were completed.Finally,the 3 D geological model of the Zhuxi tungsten deposit and its periphery have been established through these 18 sections,and the spatial shape of the intrusions and strata with a depth of 5 km underground were obtained,initially realizing―transparency‖for ore-controlling bodies.According the analysis of the geophysical,geochemical,and geological characteristics of the Zhuxi tungsten deposit,we discern three principles for prospecting and prediction in the research area,and propose five new exploration targets in its periphery.

Construction of carbonate reservoir knowledge base and its application in fracture-cavity reservoir geological modeling

To improve the efficiency and accuracy of carbonate reservoir research,a unified reservoir knowledge base linking geological knowledge management with reservoir research is proposed.The reservoir knowledge base serves high-quality analysis,evaluation,description and geological modeling of reservoirs.The knowledge framework is divided into three categories:technical service standard,technical research method and professional knowledge and cases related to geological objects.In order to build a knowledge base,first of all,it is necessary to form a knowledge classification system and knowledge description standards;secondly,to sort out theoretical understandings and various technical methods for different geologic objects and work out a technical service standard package according to the technical standard;thirdly,to collect typical outcrop and reservoir cases,constantly expand the content of the knowledge base through systematic extraction,sorting and saving,and construct professional knowledge about geological objects.Through the use of encyclopedia based collaborative editing architecture,knowledge construction and sharing can be realized.Geological objects and related attribute parameters can be automatically extracted by using natural language processing(NLP)technology,and outcrop data can be collected by using modern fine measurement technology,to enhance the efficiency of knowledge acquisition,extraction and sorting.In this paper,the geological modeling of fracture-cavity reservoir in the Tarim Basin is taken as an example to illustrate the construction of knowledge base of carbonate reservoir and its application in geological modeling of fracture-cavity carbonate reservoir.

Geological Model of Member 3 of Shahejie Formation Reservoir in Liuzan Oilfield, Eastern Hebei Province

A new geological model of Member 3 of Shahejie Formation reservoir in the Liuzan Oilfield, eastern Hebei Province was constructed by using modem reservoir modeling technology as sequence stratigraphy and conditional simulation combined with traditional geological analysis. The model consists of a stratigraphic framework model, a structural model, a sedimentary model and a reservoir model. The study shows that the reservoir is a relatively integrated nose structure, whose strata can be divided into 4 sets of parasequence, 12 parasequences. The submerged branched channel of fan delta front is the favorable microfacies, which controls the geometric shape and physical properties of reservoir sandstone. Oil is distributed in premium reservoir sandstones at structural high positions. According to the new geological model, not only the geological contradictions appearing during oil field development are resolved, but also the oil-bearing area is enlarged by 2.7km^2 and geological reserves increased by 156.9 million tons. The production capacity of the Liuzan Oilfield is increased by 0.27 million tons per year.

Research on dynamic updating of three dimensional geological modeling based on the OO-Solid model

The dynamic updating of the model included: the change of space border,addi- tion and reduction of spatial component (disappearing,dividing and merging),the change of the topological relationship and synchronous dynamic updating of database.Firstly, arming at the deficiency of OO-Solid model in the aspect of dynamic updating,modeling primitives of OO-Solid model were modified.And then the algorithms of dynamic updating of 3D geological model with the node data,line data or surface data change were dis- cussed.The core algorithms was done by establishing space index,following the way of facing the object from bottom to top,namely the dynamic updating from the node to arc, and then to polygon,then to the face of the component and finally to the geological object. The research has important theoretical and practical values in the field of three dimen- sional geological modeling and is significant in the field of mineral resources.

Reservoir geological modeling and significance of Cambrian Xiaoerblak Formation in Keping outcrop area, Tarim Basin, NW China

Take the Cambrian Xiaoerblak Formation in the Keping(Kalpin) outcrop area as an example, a 28 km reservoir scale geological model was built based on description of 7 profiles, observation of more than 1000 thin sections, petrophysical analysis of 556 samples and many geochemical tests. The Xiaoerblak Formation, 158–178 m thick, is divided into three members and 5 submembers, and is composed of laminated microbialite dolomite(LMD), thrombolite dolomite(TD), foamy-stromatolite dolomite(FSD), oncolite dolomite(OD), grain dolomite(GD)/crystalline dolomite with grain ghost and micritic dolomite(MD)/argillaceous dolomite. The petrology features show that its sediment sequence is micro-organism layer – microbial mound/shoal – tidal flat in carbonate ramp background from bottom up. The reservoir has 5 types of pores, namely, framework pore, dissolved vug, intergranular and intragranular dissolved pore and intercrystalline dissolved pore, as main reservoir space. It is found that the development of pore has high lithofacies selectivity, FSD has the highest average porosity, TD, OD and GD come second. The reservoir is pore-vug reservoir with medium-high porosity and medium-low permeability. The dolomite of Xiaoerblak Formation was formed in para-syngenetic to early diagenetic stage through dolomitization caused by seawater. The reservoir development is jointly controlled by sedimentary facies, micro-organism type, high frequency sequence interface and early dolomitization. The classⅠand Ⅱ reservoirs, with an average thickness of 41.2 m and average reservoir-stratum ratio of about 25.6%, have significant potential. It is predicted that the microbial mounds and shoals in the middle ramp around the ancient uplift are the favorable zones for reservoir development.

Quantitative evaluation of lateral sealing of extensional fault by an integral mathematical-geological model

To evaluate the lateral sealing mechanism of extensional fault based on the pressure difference between fault and reservoir, an integral mathematical-geological model of diagenetic time on diagenetic pressure considering the influence of diagenetic time on the diagenetic pressure and diagenetic degree of fault rock has been established to quantitatively calculate the lateral sealing ability of extensional fault. By calculating the time integral of the vertical stress and horizontal in-situ stress on the fault rock and surrounding rock, the burial depth of the surrounding rock with the same clay content and diagenesis degree as the target fault rock was worked out. In combination with the statistical correlation of clay content, burial depth and displacement pressure of rock in the study area, the displacement pressure of target fault rock was calculated quantitatively. The calculated displacement pressure was compared with that of the target reservoir to quantitatively evaluate lateral sealing state and ability of the extensional fault. The method presented in this work was used to evaluate the sealing of F_(1), F_(2) and F_(3) faults in No.1 structure of Nanpu Sag, and the results were compared with those from fault-reservoir displacement pressure differential methods without considering the diagenetic time and simple considering the diagenetic time. It is found that the results calculated by the integral mathematical-geological model are the closest to the actual underground situation, the errors between the hydrocarbon column height predicted by this method and the actual column height were 0–8 m only, proving that this model is more feasible and credible.

Combined back-analysis method of ground stress based on refined geological modeling

A new back-analysis method of ground stress is proposed with comprehensive consideration of influence of topography, geology and nonlinear physical mechanical properties of rock on ground stress. This method based on non-uniform rational B-spline (NURBS) technology provides the means to build a refined three-dimensional finite element model with more accurate meshing under complex terrain and geological conditions. Meanwhile, this method is a back-analysis of ground stress with combination of multivariable linear regression model and neural network (ANN) model. Firstly, the regression model is used to fit approximately boundary loads. Regarding the regressed loads as mean value, some sets of boundary loads with the same interval are constructed according to the principle of orthogonal design, to calculate the corresponding ground stress at the observation positions using finite element method. The results (boundary loads and the corresponding ground stress) are added to the samples for ANN training. And on this basis, an ANN model is established to implement higher precise back-analysis of initial ground stress. A practical application case shows that the relative error between the inversed ground stress and observed value is mostly less than 10 %, which can meet the need of engineering design and construction requirements.

Three-dimensional geological modelling and direction of hydrothermal alteration of Horne deposit, Blake River Group, Quebec, Canada

The Horne deposit with rich Cu and Au in Noranda region of Black River Group in Quebec has high economic significance.Current researches on Horne deposit are mostly based on two-dimensional maps and statistical data.It is hard to reflect the spatial structure and characteristics of Horne orebody directly.In this paper,GIS was used to digitize the mining plan-view maps at different depths,stope maps,the boundary of the massive sulfide in drilling trajectories as well as the grade data of Au and Cu of Horne deposit.Meanwhile,the authors established the grade attribute database.Subsequently the three-dimensional(3D)geological model and grade attribute model of Horne orebody were established by Geological Object Computer Aided Design(GOCAD).Positions of two vents and directions of hydrothermal alteration in Horne deposit were inferred based on the property of the major fault,characteristics of hydrothermal alteration,the enrichment morphology and spatial distribution of high-grade Cu in the Cu attribute model.

Application of 3D Reservoir Geological Model on Es1 Formation, Block Nv32, Shenvsi Oilfield, China

Three-dimensional geological modeling of reservoirs is an essential tool to predict reservoir performance and improve the understanding of reservoir uniqueness in Es1 formation. The paper focuses on the use of petrel software to build three-dimensional reservoir geological model which characterizes and assesses block Nv32 that located in the west of the Shenvsi oilfield in the south of Cangzhou city, Hebei province of China, and has an oil-bearing area of 1.4 km2. This study is depending on integration data from well logs of 22 wells which provided from geology, geophysics, and petrophysics to identify and provide precise depict of the subsurface internal structure and the reservoir heterogeneity. Input data was used to build the structural model, sedimentary facies model, petrophysical properties (porosity, permeability, saturation, and N/G model, and finally to determine the reservoir volume. The lithological facies were simulated using the assigned value method. Moreover, Petrophysical properties (Porosity, permeability, oil saturation and net to gross) were constructed for each zone using the Sequential Gaussian Simulation method to guide the distribution of petrophysical properties of Es1 formation, block Nv32. Statistical analysis of the porosity, permeability, oil saturation and N/G model present that the porosity occurrence distribution is mainly concern between 0.2% - 36.39% of block Nv32 with an average porosity value of 17.5%, permeability between 0.017 mD to 974.8 mD, having an average permeability of 59.44 mD, oil saturation between 0.00 to 0.95 having an average value of 0.22, and N/G is mainly concentrated between 0.01 to 1.00 within an average value of 0.61. This research has indicated the reliability of the three-dimensional model technique as a suitable tool to provide a sufficient understanding of petrophysical distribution. The south-western and north-western indicate that oilfield is very promising an exploratory well should be drilled to find out the thickness and size of the reservoir.

Regional 3D geological modeling along metro lines based on stacking ensemble model

This paper presents a regional 3D geological modeling method based on the stacking ensemble technique to overcome the challenges of sparse borehole data in large-scale linear underground projects.The proposed method transforms the 3D geological modeling problem into a stratigraphic property classification problem within a subsurface space grid cell framework.Borehole data is pre-processed and trained using stacking method with five different machine learning algorithms.The resulting modelled regional cells are then classified,forming a regional 3D grid geological model.A case study for an area of 324 km2 along Xuzhou metro lines is presented to demonstrate the effectiveness of the proposed model.The study shows an overall prediction accuracy of 85.4%.However,the accuracy for key stratigraphy layers influencing the construction risk,such as karst carve strata,is only 4.3%due to the limited borehole data.To address this issue,an oversampling technique based on the synthetic minority oversampling technique(SMOTE)algorithm is proposed.This technique effectively increases the number of sparse stratigraphic samples and significantly improves the prediction accuracy for karst caves to 65.4%.Additionally,this study analyzes the impact of sampling distance on model accuracy.It is found that a lower sampling interval results in higher prediction accuracy,but also increases computational resources and time costs.Therefore,in this study,an optimal sampling distance of 1 m is chosen to balance prediction accuracy and computation cost.Furthermore,the number of geological strata is found to have a negative effect on prediction accuracy.To mitigate this,it is recommended to merge less significant stratigraphy layers,reducing computation time.For key strata layers,such as karst caves,which have a significant impact on construction risk,further onsite sampling or oversampling using the SMOTE technique is recommended.

Geological modeling of coalbed methane reservoirs in the tectonically deformed coal seam group in the Dahebian block,western Guizhou,China

The widely spread Carboniferous-Permian coal seam group in southern China has great potential for coalbed methane resources,but the extensively developed tectonically deformed coal seriously restricts its development.Taking the Dahebian block in western Guizhou as the study area,the geological model of coalbed methane reservoirs in the tectonically deformed coal seam group was established,and the spatial distribution pattern of model parameters was clarified by clustering algorithms and factor analysis.The facies model suggests that the main coal body structures in Nos.1,4,and 7 coal seams are cataclastic coal and granulated coal,whereas the No.11 coal seam is dominated by granulated coal,which has larger thicknesses and spreads more continuously.The in situ permeability of primary undeformed coal,cataclastic coal,granulated coal,and mylonitized coal reservoirs are 0.333 mD,0.931 mD,0.146 mD,and 0.099 mD,respectively,according to the production performance analysis method.The property model constructed by facies-controlled modeling reveals that Nos.1,4,and 7 coal seams have a wider high-permeability area,but the gas content is lower;the high-permeability area in the No.11 coal seam is more limited,but the gas content is higher.The results of the self-organizing map neural network and K-means clustering indicate that the geological model can be divided into 6 clusters,the model parameter characteristics of the 6 clusters are summarized by data analysis in combination with 6 factors extracted by factor analysis,and the application of data analysis results in multi-layer coalbed methane co-development is presented.This study provides ideas for the geological modeling in the tectonically deformed coal seam group and its data analysis.

Geological characteristics and models of fault-foldfracture body in deep tight sandstone of the second member of Upper Triassic Xujiahe Formation in Xinchang structural belt of Sichuan Basin,SW China

In the second member of the Upper Triassic Xujiahe Formation(T_(3)x_(2))in the Xinchang area,western Sichuan Basin,only a low percent of reserves has been recovered,and the geological model of gas reservoir sweet spot remains unclear.Based on a large number of core,field outcrop,test and logging-seismic data,the T_(3)x_(2) gas reservoir in the Xinchang area is examined.The concept of fault-fold-fracture body(FFFB)is proposed,and its types are recognized.The main factors controlling fracture development are identified,and the geological models of FFFB are established.FFFB refers to faults,folds and associated fractures reservoirs.According to the characteristics and genesis,FFFBs can be divided into three types:fault-fracture body,fold-fracture body,and fault-fold body.In the hanging wall of the fault,the closer to the fault,the more developed the effective fractures;the greater the fold amplitude and the closer to the fold hinge plane,the more developed the effective fractures.Two types of geological models of FFFB are established:fault-fold fracture,and matrix storage and permeability.The former can be divided into two subtypes:network fracture,and single structural fracture,and the later can be divided into three subtypes:bedding fracture,low permeability pore,and extremely low permeability pore.The process for evaluating favorable FFFB zones was formed to define favorable development targets and support the well deployment for purpose of high production.The study results provide a reference for the exploration and development of deep tight sandstone oil and gas reservoirs in China.

Three-dimensional geological modeling and its application in Digital Mine

The 3D geological modeling is the prerequisite and core foundation for Digital Mine.Although this new technology brings new opportunities and motivation for the mineral exploration industry,it still has many difficulties to be solved in this area.Based on the characteristics of mine data and the aim of Digital Mine construction,this paper introduces a theory including multi-source data coupling,multi-modeling methods integration,multi-resolution visualization and detection,and multidimensional data analysis and application.By analyzing problems such as the uncertainty in each step of the modeling process,we designed a novel modeling method that can be applied to the complex geological body modeling,mineral resource/reserve estimation,and the mining exploration engineering.Along with the process of mine exploration,development,and reclamation,3D modeling undergoes the process of"construction-simulation-revision"during which the 3D model is able to be dynamically updated and gradually improved.Based on the result of practical utilization,it is proven that the methodology introduced by this paper can be used to build an effective 3D model by fully using the mining data under the control of spatial information quality evaluation.Our experiments show that such a 3D model can be used to evaluate the mine resource and provide the scientific evidence to improve mining efficiency during the various stages of evolvement process in mine.

A Web-based system enabling the integration,analysis,and 3D sub-surface visualization of groundwater monitoring data and geological models

The 3D Water Chemistry Atlas is an intuitive,open source,Web-based system that enables the three-dimensional(3D)sub-surface visualization of ground water monitoring data,overlaid on the local geological model(formation and aquifer strata).This paper firstly describes the results of evaluating existing virtual globe technologies,which led to the decision to use the Cesium open source WebGL Virtual Globe and Map Engine as the underlying platform.Next it describes the backend database and search,filtering,browse and analysis tools that were developed to enable users to interactively explore the groundwater monitoring data and interpret it spatially and temporally relative to the local geological formations and aquifers via the Cesium interface.The result is an integrated 3D visualization system that enables environmental managers and regulators to assess groundwater conditions,identify inconsistencies in the data,manage impacts and risks and make more informed decisions about coal seam gas extraction,waste water extraction,and water reuse.

Framework system and research flow of uncertainty in 3D geological structure models

Uncertainty in 3D geological structure models has become a bottleneck that restricts the development and application of 3D geological modeling.In order to solve this problem during periods of accuracy assessment,error detection and dynamic correction in 3D geological structure models,we have reviewed the current situation and development trends in 3D geological modeling.The main context of uncertainty in 3D geological structure models is discussed.Major research issues and a general framework system of uncertainty in 3D geological structure models are proposed.We have described in detail the integration of development practices of 3D geological modeling systems,as well as the implementation process for uncertainty evaluation in 3D geological structure models.This study has laid the basis to build theoretical and methodological systems for accuracy assessment and error correction in 3D geological models and can assist in improving 3D modeling techniques under complex geological conditions.

An Approach to Computer Modeling of Geological Faults in 3D and an Application

3D geological modeling, one of the most important applications in geosciences of 3D GIS, forms the basis and is a prerequisite for visualized representation and analysis of 3D geological data. Computer modeling of geological faults in 3D is currently a topical research area. Structural modeling techniques of complex geological entities contain- ing reverse faults are discussed and a series of approaches are proposed. The geological concepts involved in computer modeling and visualization of geological fault in 3D are explained, the type of data of geological faults based on geo- logical exploration is analyzed, and a normative database format for geological faults is designed. Two kinds of model- ing approaches for faults are compared: a modeling technique of faults based on stratum recovery and a modeling tech- nique of faults based on interpolation in subareas. A novel approach, called the Unified Modeling Technique for stratum and fault, is presented to solve the puzzling problems of reverse faults, syn-sedimentary faults and faults terminated within geological models. A case study of a fault model of bed rock in the Beijing Olympic Green District is presented in order to show the practical result of this method. The principle and the process of computer modeling of geological faults in 3D are discussed and a series of applied technical proposals established. It strengthens our profound compre- hension of geological phenomena and the modeling approach, and establishes the basic techniques of 3D geological modeling for practical applications in the field of geosciences.