Three-dimensional model construction method, device and electronic equipment

Abstract

The application provides a three-dimensional model construction method and device and electronic equipment, and belongs to the technical field of geological information. The method comprises the following steps: acquiring geological data corresponding to a target area; determining constraint conditions corresponding to the target area; and constructing a three-dimensional model based on the constraint conditions and the geological data. In this way, the three-dimensional model is constructed based on the constraint conditions and the geological data, and a three-dimensional model with consistent geological logic can be obtained, thereby solving the technical problem that, due to insufficient integration of geological knowledge, a three-dimensional model is prone to geological logic contradictions such as inverted strata and incorrect fault cutting relationships in the prior art.

Description

Technical Field

[0001] This application relates to the field of geological information technology, and in particular to a three-dimensional model construction method, apparatus and electronic equipment. Background Technology

[0002] In fields such as geological exploration, mineral resource development, geological disaster early warning, and underground engineering construction, three-dimensional models are the core foundation supporting scientific decision-making and intelligent engineering implementation.

[0003] In related technologies, existing 3D model construction methods are mainly divided into two categories: explicit modeling and implicit modeling. Explicit modeling (such as profile-based modeling and boundary representation) relies on manual intervention to construct the boundaries of geological bodies. Although it is suitable for simple geological structures, it has significant drawbacks such as low modeling efficiency, strong subjectivity, and difficulty in quantifying uncertainties when facing complex folds, faults, and multi-lithological interaction areas. Implicit modeling fits discrete geological data through mathematical functions (such as radial basis functions and interpolation algorithms), which can automatically generate continuous geological interfaces. It has a natural advantage in complex geological scenarios, but due to insufficient integration of geological knowledge, the 3D model is prone to geological logical contradictions such as inverted strata and incorrect fault cutting relationships. Summary of the Invention

[0004] The purpose of this application is to provide a method, apparatus, and electronic device for constructing three-dimensional models, in order to solve the technical problem in the prior art where insufficient integration of geological knowledge leads to geological logical contradictions in three-dimensional models, such as inverted strata and incorrect fault crossing relationships. The specific technical solution is as follows: In a first aspect of this application, a method for constructing a three-dimensional model is provided, the method comprising: Obtain geological data corresponding to the target area; Determine the constraints corresponding to the target region; Based on the constraints and the geological data, a three-dimensional model is constructed.

[0005] In an optional implementation, after acquiring the geological data corresponding to the target area, the following steps are included: Obtain the geological logic verification rules; Based on the geological logic verification rules, abnormal data points in the geological data corresponding to the target area are determined; Remove abnormal data points from the geological data corresponding to the target area.

[0006] In an optional implementation, after acquiring the geological data corresponding to the target area, the method further includes: Obtain the stratigraphic sequence relationship corresponding to the target area; Obtain the missing points corresponding to the target region; Based on the stratigraphic sequence relationship corresponding to the target area, the missing points corresponding to the target area are filled in.

[0007] In an optional implementation, determining the constraints corresponding to the target region includes: Obtain the sequence information corresponding to the target region; A sequence model is established based on the sequence information corresponding to the target region; The sequence model is transformed into constraints corresponding to the target region.

[0008] In an optional implementation, constructing a three-dimensional model based on the constraints and the geological data includes: Based on the spatial coordinates and attribute information in the geological data, an initial three-dimensional model is constructed. The initial 3D model is modified based on the constraints to obtain the 3D model.

[0009] In an optional implementation, constructing an initial three-dimensional model based on the spatial coordinates and attribute information in the geological data includes: Based on the spatial coordinates in the geological data, a three-dimensional structural model is constructed; Based on the attribute information in the geological data, a three-dimensional attribute model is constructed; The three-dimensional structural model and the three-dimensional attribute model are fused to obtain the initial three-dimensional model.

[0010] In an optional implementation, the step of modifying the initial 3D model based on the constraints to obtain the 3D model includes: The weighting coefficients are determined based on the aforementioned constraints. The initial 3D model is corrected based on the weighting coefficients to obtain the 3D model.

[0011] In an optional implementation, after constructing the 3D model, the following is also included: The geological data is resampled multiple times to generate at least one data perturbation set; For any of the data perturbation sets, a modified three-dimensional model is constructed based on the data perturbation set and the constraints. Based on the corrected three-dimensional model corresponding to each of the at least one data perturbation set, determine the predicted value corresponding to each spatial location in the three-dimensional model; The three-dimensional model is corrected based on the predicted values ​​corresponding to each spatial location in the model.

[0012] In a second aspect of this application, a three-dimensional model building apparatus is also provided, the apparatus comprising: The data acquisition module is used to acquire geological data corresponding to the target area. A constraint determination module is used to determine the constraint conditions corresponding to the target region; The model building module is used to build a three-dimensional model based on the constraints and the geological data.

[0013] In an optional implementation, after acquiring the geological data corresponding to the target area, the following steps are included: Obtain the geological logic verification rules; Based on the geological logic verification rules, abnormal data points in the geological data corresponding to the target area are determined; Remove abnormal data points from the geological data corresponding to the target area.

[0014] In an optional implementation, after acquiring the geological data corresponding to the target area, the method further includes: Obtain the stratigraphic sequence relationship corresponding to the target area; Obtain the missing points corresponding to the target region; Based on the stratigraphic sequence relationship corresponding to the target area, the missing points corresponding to the target area are filled in.

[0015] In an optional implementation, the constraint condition determines the module, specifically for: Obtain the sequence information corresponding to the target region; A sequence model is established based on the sequence information corresponding to the target region; The sequence model is transformed into constraints corresponding to the target region.

[0016] In one optional implementation, the model building module includes: An initial model building unit is used to build an initial three-dimensional model based on the spatial coordinates and attribute information in the geological data; The model correction unit is used to correct the initial three-dimensional model based on the constraints to obtain the three-dimensional model.

[0017] In an optional implementation, the initial model building unit is specifically used for: Based on the spatial coordinates in the geological data, a three-dimensional structural model is constructed; Based on the attribute information in the geological data, a three-dimensional attribute model is constructed; The three-dimensional structural model and the three-dimensional attribute model are fused to obtain the initial three-dimensional model.

[0018] In an optional implementation, the model correction unit is specifically used for: The weighting coefficients are determined based on the aforementioned constraints. The initial 3D model is corrected based on the weighting coefficients to obtain the 3D model.

[0019] In an optional implementation, after constructing the 3D model, the following is also included: The geological data is resampled multiple times to generate at least one data perturbation set; For any of the data perturbation sets, a modified three-dimensional model is constructed based on the data perturbation set and the constraints. Based on the corrected three-dimensional model corresponding to each of the at least one data perturbation set, determine the predicted value corresponding to each spatial location in the three-dimensional model; The three-dimensional model is corrected based on the predicted values ​​corresponding to each spatial location in the model.

[0020] In a third aspect of the embodiments of this application, an electronic device is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor, when executing a program stored in memory, implements the three-dimensional model construction method described in any one of the first aspects above.

[0021] In a fourth aspect of the embodiments of this application, a storage medium is also provided, wherein the storage medium stores instructions that, when run on a computer, cause the computer to execute any of the three-dimensional model construction methods described in the first aspect above.

[0022] In a fifth aspect of the embodiments of this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the three-dimensional model construction methods described in the first aspect above.

[0023] The technical solution provided in this application involves acquiring geological data corresponding to a target area; determining the constraints corresponding to the target area; and constructing a three-dimensional model based on the constraints and geological data. This method of constructing a three-dimensional model based on constraints and geological data yields a geologically consistent three-dimensional model, solving the technical problem in existing technologies where insufficient integration of geological knowledge leads to geologically logical contradictions in the three-dimensional model, such as inverted strata and incorrect fault-cutting relationships. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0027] Figure 1 A schematic diagram illustrating the implementation process of a three-dimensional model construction method provided in this application embodiment; Figure 2 A schematic diagram illustrating the implementation process of another three-dimensional model construction method provided in this application embodiment; Figure 3 A schematic diagram illustrating the implementation process of another three-dimensional model construction method provided in this application embodiment; Figure 4 A schematic diagram illustrating the implementation process of an initial three-dimensional model construction method provided in this application embodiment; Figure 5 This is a schematic diagram of the structure of a three-dimensional model building device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0030] To address the technical problem in existing technologies where insufficient integration of geological knowledge leads to geologically logical contradictions in 3D models, such as inverted stratigraphy and incorrect fault crossing relationships, this application provides a method, apparatus, and electronic device for constructing a 3D model. This involves acquiring geological data corresponding to a target area; determining the constraints for that target area; and constructing a 3D model based on the constraints and geological data. This method of constructing a 3D model based on constraints and geological data results in a geologically logically consistent 3D model.

[0031] like Figure 1 The diagram shown illustrates the implementation flow of a three-dimensional model construction method provided in this application embodiment, which may specifically include the following steps: S101, Obtain the geological data corresponding to the target area.

[0032] In this embodiment, geological data corresponding to the target area is obtained. The target area refers to the geographical or geological region to be modeled, such as a mining area, an exploration area, or an engineering site. Geological data refers to the attribute data corresponding to the target area. Geological data may include spatial coordinate data (such as borehole locations, geophysical inversion anomaly coordinates, outcrop observation coordinates), attribute data (such as lithology, stratigraphic age, density, porosity, etc.), and auxiliary data (such as inclinometer data, geological profile data, etc.), which are not limited in this embodiment.

[0033] S102, Determine the constraints corresponding to the target region.

[0034] In this embodiment of the application, constraints corresponding to the target area are determined. These constraints refer to modeling limitations or rules set based on geological knowledge (such as stratigraphic sequence, lithological contact relationships, tectonic rules, etc.) to ensure the geological rationality of the subsequently constructed 3D model and prevent logical contradictions such as stratigraphic inversion or fault cutting errors in the 3D model.

[0035] Specifically, constraints can include stratigraphic sequence constraints, tectonic constraints, and lithological contact constraints. Stratigraphic sequence constraints define typical lithological assemblages and contact relationships (e.g., angular unconformity, conformable contact) for each stratum based on its age from youngest to oldest (e.g., Quaternary, Cretaceous, Jurassic, Permian). Tectonic constraints, for fault-developed regions, input parameters such as the fault's strike, dip, and dip angle to ensure that the displacement of strata on both sides of the fault conforms to the regional tectonic stress field characteristics. Lithological contact constraints define the contact type between different lithologies (e.g., gradual contact, abrupt contact) and set attribute gradient thresholds (e.g., density gradient ≥ 0.5 g / cm³) for abrupt contact interfaces. m).

[0036] S103, a three-dimensional model is constructed based on constraints and geological data.

[0037] In this embodiment, a three-dimensional model is constructed based on constraints and geological data. The three-dimensional model is a visual representation of the geographical or geological area to be modeled, used to intuitively display its spatial morphology and attribute distribution.

[0038] Based on the above description of the technical solution provided in the embodiments of this application, geological data corresponding to the target area is obtained; constraints corresponding to the target area are determined; and a three-dimensional model is constructed based on the constraints and geological data. Constructing a three-dimensional model based on constraints and geological data in this way yields a geologically consistent three-dimensional model, solving the technical problem in existing technologies where insufficient integration of geological knowledge leads to geological logical contradictions in the three-dimensional model, such as inverted strata and incorrect fault crossing relationships.

[0039] like Figure 2 The diagram shown illustrates the implementation flow of another three-dimensional model construction method provided in this application embodiment, which may specifically include the following: S201, Obtain the geological data corresponding to the target area.

[0040] In this embodiment of the application, this step is similar to step S101 above, and will not be described in detail here.

[0041] S202, Obtain geological logic verification rules.

[0042] In this embodiment, geological logic verification rules are obtained. These rules refer to a set of logical conditions established based on geological principles and regional geological understanding to determine the rationality of data, including but not limited to lithological attribute rules (such as coal seam density should be less than 2.0 g / cm³). 3 The sandstone porosity is between 10% and 20%, the stratigraphic sequence is regular (e.g., Jurassic strata should be above Permian strata), and the structural rationality is regular (e.g., there should be an interpretable displacement relationship between the strata on both sides of a fault). This application does not limit these aspects in the embodiments.

[0043] S203, based on geological logic verification rules, identifies abnormal data points in the geological data corresponding to the target area.

[0044] In this embodiment, abnormal data points in the geological data corresponding to the target area are identified based on geological logic verification rules. That is, logical consistency checks are performed on each point of the geological data in the target area based on these rules.

[0045] For example, for numerical attributes (such as density and porosity), we can first calculate their Z-score values, mark points with a value greater than 3 as candidate anomalies, and then make a second judgment based on geological logic verification rules to confirm whether they are real anomalies.

[0046] S204, remove abnormal data points from the geological data corresponding to the target area.

[0047] In this embodiment, abnormal data points in the geological data corresponding to the target area are removed. Furthermore, the sparse data areas formed after removal can be supplemented using neighboring borehole data interpolation to maintain the continuity of the data in spatial distribution; however, this embodiment does not limit this approach.

[0048] S205, Obtain the stratigraphic sequence relationship corresponding to the target area.

[0049] In this embodiment, the stratigraphic sequence relationship corresponding to the target area is obtained. The stratigraphic sequence relationship refers to the chronological order of strata and their corresponding lithological combinations established based on regional geological survey reports and stratigraphic principles. For example, the chronological order (from newest to oldest) is Quaternary, Cretaceous, Jurassic, and Permian; the corresponding lithological combinations are loose sediments, siltstone, sandstone + shale, and coal seam + mudstone; the contact relationship types are angular unconformity, conformable contact, and parallel unconformity, which are not limited in this embodiment.

[0050] S206, Obtain the missing points corresponding to the target region.

[0051] In this embodiment, missing points corresponding to the target area are obtained. Missing points refer to data points in geological data where attribute information is incomplete or completely missing, such as missing lithology categories or blank laboratory parameters in borehole records, or the complete absence of a stratum in some boreholes due to localized erosion. This embodiment does not limit this to specific cases.

[0052] S207, based on the stratigraphic sequence relationship corresponding to the target area, completes the missing points corresponding to the target area.

[0053] In this embodiment of the application, missing points in the target area are filled in based on the stratigraphic sequence relationship corresponding to the target area.

[0054] Specifically, the missing points can be filled in according to their type. If the missing point is an attribute missing point, it can be filled in according to the lithology or attribute mean of the stratum to which the point belongs; if the missing point is a complete stratum missing point, the stratum thickness at that point can be marked and the reason for the missing point (such as tectonic erosion, sedimentary discontinuity) can be recorded. This application does not limit this.

[0055] S208, Determine the constraints corresponding to the target region.

[0056] In this embodiment of the application, this step is similar to step S102 above, and will not be described in detail here.

[0057] S209, a three-dimensional model is constructed based on constraints and geological data.

[0058] In this embodiment of the application, this step is similar to step S103 above, and will not be described in detail here.

[0059] like Figure 3 The diagram shown illustrates the implementation flow of another three-dimensional model construction method provided in this application embodiment, which may specifically include the following: S301, Obtain geological data corresponding to the target area.

[0060] In this embodiment of the application, this step is similar to step S101 above, and will not be described in detail here.

[0061] S302, Obtain the sequence information corresponding to the target region.

[0062] In this embodiment of the application, sequence information corresponding to the target area is obtained. The sequence information refers to the stratigraphic chronology sequence and its corresponding lithological assemblage and contact relationships established based on regional geological survey reports and stratigraphic principles, and may include stratigraphic chronology sequences, lithological assemblage sequences, and contact relationship sequences.

[0063] The stratigraphic chronology (from newest to oldest) is: Quaternary, Cretaceous, Jurassic, and Permian; the lithological assemblage is: loose sediments, siltstone, sandstone + shale, and coal seam + mudstone; and the contact relationship is: angular unconformity, conformable contact, and parallel unconformity.

[0064] S303, Establish a sequence model based on the sequence information corresponding to the target region.

[0065] In this embodiment, a sequence model is established based on the sequence information corresponding to the target region. The initial sequence model is used to clarify the vertical and horizontal stacking relationships of each stratum, lithological evolution patterns, and key interface types.

[0066] S304 transforms the sequence model into constraints corresponding to the target region.

[0067] In this embodiment of the application, the sequence model is transformed into constraints corresponding to the target region. Specifically, constraints can include stratigraphic sequence constraints, tectonic constraints, and lithological contact constraints. Stratigraphic sequence constraints define typical lithological combinations and contact relationships (e.g., angular unconformity, conformable contact) for each stratum based on its age from youngest to oldest (e.g., Quaternary, Cretaceous, Jurassic, Permian), ensuring spatial continuity at the interfaces of the same strata and that the elevation difference between adjacent control points does not exceed the theoretical difference corresponding to the dip angle of the strata in the region. Tectonic constraints, for fault-developed areas, input parameters such as the strike, dip, and dip angle of the fault, constraining the displacement of strata on both sides of the fault to conform to the characteristics of the regional tectonic stress field. Lithological contact constraints define contact types between different lithologies (e.g., gradual contact, abrupt contact) and set attribute gradient thresholds (e.g., density gradient ≥ 0.5 g / cm³) for abrupt contact interfaces. m).

[0068] S305. Construct an initial three-dimensional model based on the spatial coordinates and attribute information in the geological data.

[0069] In this embodiment, an initial three-dimensional model is constructed based on the spatial coordinates and attribute information in the geological data. Spatial coordinates refer to the location information of control points extracted from the geological data in three-dimensional space, such as the eastward (X), northward (Y), and vertical (Z) coordinates of borehole control points, the coordinates of geophysical inversion anomaly points, and the coordinates of outcrop observation points. Attribute information refers to geological characteristic data associated with the spatial location, including but not limited to lithology (such as sandstone, shale, and coal seam), stratigraphic age, and core analysis parameters (such as density, porosity, and ore grade). This embodiment does not limit these parameters.

[0070] For details on how to construct an initial 3D model based on the spatial coordinates and attribute information in geological data, please refer to [reference needed]. Figure 4 The method shown. (As illustrated) Figure 4 The diagram shown illustrates the implementation flow of an initial 3D model construction method provided in this application embodiment, which may specifically include the following steps: S401, construct a three-dimensional structural model based on the spatial coordinates in the geological data.

[0071] In this embodiment of the application, a three-dimensional structural model is constructed based on the spatial coordinates in the geological data.

[0072] Specifically, a three-dimensional structural model can be constructed using a geological knowledge-guided weighted kriging interpolation algorithm. The specific steps include: setting up a three-dimensional interpolation grid (e.g., a planar resolution of 10m × 10m and a vertical resolution of 2m); constructing an improved variogram function, introducing a geological weight coefficient W (0.1 ≤ W ≤ 1.5), assigning higher weights to adjacent points that conform to the stratigraphic sequence, and assigning lower weights to points that cross faults or unconformities; calculating the vertical elevation of each stratigraphic interface through weighted kriging interpolation, and generating a continuous stratigraphic interface grid model, i.e., a three-dimensional structural model.

[0073] S402, Construct a three-dimensional attribute model based on the attribute information in the geological data.

[0074] In this embodiment of the application, a three-dimensional attribute model is constructed based on the attribute information in the geological data.

[0075] Specifically, a three-dimensional attribute model can be constructed using a multi-scale radial basis function interpolation algorithm. The specific steps include: converting lithology categories into numerical labels (e.g., sandstone=1, shale=2, coal seam=3); selecting a multi-scale Gaussian radial basis function and optimizing the scale parameters through cross-validation; calculating the probability distribution of lithology labels for each grid node; taking the label with the highest probability as the lithology category of that node to generate a three-dimensional lithology distribution model; and generating a three-dimensional attribute model for attributes such as density, porosity, and ore grade based on a lithology-attribute collaborative interpolation algorithm.

[0076] S403 merges the three-dimensional structural model and the three-dimensional attribute model to obtain the initial three-dimensional model.

[0077] In this embodiment, the three-dimensional structural model and the three-dimensional attribute model are fused to obtain an initial three-dimensional model. During the fusion process, the three-dimensional structural model is used as a framework to associate the mesh nodes of the three-dimensional attribute model with the corresponding geological bodies (such as coal seams and sandstone), and geological logic verification is performed to ensure that the attribute values ​​are within a reasonable range (such as retaining only the effective value of 1.2~1.5 g / cm³ for coal seam density).

[0078] S306, Based on the constraints, the initial three-dimensional model is corrected to obtain the three-dimensional model.

[0079] In this embodiment, the initial 3D model is modified based on constraints to obtain the 3D model. This embodiment does not limit the scope of the invention.

[0080] Specifically, the process of modifying an initial 3D model based on constraints to obtain a 3D model may include the following steps: Step 61: Determine the weighting coefficients based on the constraints.

[0081] In this embodiment, weighting coefficients are determined based on constraints. Specifically, weighting coefficients can be assigned to different regions and geological interfaces according to the importance and geological rationality of each element in the constraints. For example, in a stratigraphically continuous region, the weighting coefficient is 1.2; in a fault-affected region, the weighting coefficient is 0.3; and at a lithological abrupt change interface, the weighting coefficient can be dynamically adjusted according to the attribute gradient threshold.

[0082] Step 62: Correct the initial 3D model based on the weighting coefficients to obtain the 3D model.

[0083] In this embodiment, the initial three-dimensional model is modified based on weighting coefficients to obtain a new three-dimensional model. Specifically, the interpolation results in the initial three-dimensional model are weighted and adjusted to ensure that the model meets constraints such as stratigraphic continuity, structural rationality, and lithological contact relationships, thereby obtaining a geologically consistent final three-dimensional model.

[0084] In addition, after constructing the 3D model, the following steps may also be included: Step 1: Resample the geological data multiple times to generate at least one data perturbation set.

[0085] In this embodiment, geological data is resampled multiple times to generate at least one data perturbation set. Specifically, the Bootstrap resampling method can be used to sample the original geological data multiple times (e.g., 100 times) to generate multiple data perturbation sets, in order to simulate the impact of data noise and sampling uncertainty on the modeling results. This embodiment does not limit this approach.

[0086] Step 2: For any set of data perturbations, construct a modified 3D model based on the set of data perturbations and constraints.

[0087] In this embodiment of the application, for any set of data perturbations, a modified three-dimensional model is constructed based on the set of data perturbations and constraints. That is, for each set of data perturbations, the above steps S301 to S306 are performed to construct the modified three-dimensional model.

[0088] Step 3: Determine the predicted value corresponding to each spatial location in the three-dimensional model based on the corrected three-dimensional model corresponding to at least one data perturbation set.

[0089] In this embodiment, the predicted value corresponding to each spatial location in the 3D model is determined based on the corrected 3D model corresponding to at least one data perturbation set. Specifically, the output results of all corrected 3D models at the same spatial location (such as lithological category labels, stratigraphic interface elevation values, and values ​​of various physical properties) are summarized, and their statistical characteristics are calculated. For example, the total number of lithological categories is counted, and the lithological category with the highest frequency is determined as the predicted value corresponding to that point. The mean of the stratigraphic elevation and the confidence interval of the attribute values ​​are calculated, thereby determining the predicted value corresponding to each spatial location in the 3D model.

[0090] Step 4: Correct the 3D model based on the predicted values ​​corresponding to each spatial location in the 3D model.

[0091] In this embodiment of the application, the three-dimensional model is corrected based on the predicted values ​​corresponding to each spatial location in the three-dimensional model.

[0092] Furthermore, the three-dimensional model construction method provided in this application embodiment is illustrated with specific examples: Step 1: Geological data preprocessing and standardization.

[0093] Data Acquisition and Integration: Collect discrete geological data for the target area, including but not limited to: Spatial coordinate data: three-dimensional coordinates of borehole control points (eastward X, northward Y, vertical Z), coordinates of geophysical inversion anomaly points, and coordinates of outcrop observation points; Geological attribute data: lithology (e.g., sandstone, shale, coal seam), stratigraphic age, and core analysis parameters (e.g., density, porosity, and ore grade); Auxiliary data: inclinometer data (used to correct borehole trajectory deviations), geological profile maps, and regional geological survey reports (including stratigraphic contact relationships and structural development characteristics). Integrate the above data into a standardized dataset, unify the coordinate system (e.g., using a Gaussian projection coordinate system, with the vertical axis based on sea level), and store it in a structured format (e.g., CSV, GeoJSON). Example data is shown in Table 1 below. Table 1

[0094] Missing data completion and outlier removal: To address issues such as "missing lithology categories" and "blank laboratory parameters" in borehole data, a similarity-based completion algorithm based on geological age is adopted: According to the regional stratigraphic column (such as the sequence relationship of Jurassic-sandstone → Permian-coal seam → Carboniferous-shale), the control points of missing attributes are completed according to the "typical lithology / attribute mean" of their respective stratigraphic ages; if a stratum is completely missing in some boreholes (such as stratum missing due to local erosion), the thickness of the stratum is marked as 0, and the reason for the missing data (such as tectonic erosion, sedimentary discontinuity) is recorded. Outlier Removal: An improved Z-score algorithm combined with geological logic verification is used to remove outlier data. For numerical attributes (such as density and porosity), the Z-score value is calculated (Z=(x-μ) / σ, where μ is the mean and σ is the standard deviation), and points with |Z|>3 are marked as candidate outliers. Combined with geological logic verification (such as "coal seam density should be less than 2.0 g / cm³" and "sandstone porosity is usually 10%~20%), outliers are confirmed and removed. For sparse areas after outlier removal, "interpolation of adjacent borehole data" is used to ensure the continuity of data spatial distribution.

[0095] Lithological Imbalance Handling: To address the modeling bias caused by an excessive number of dominant lithological samples and an insufficient number of niche lithological samples in borehole data, a SMOTE-ENN hybrid sampling algorithm is used to balance lithological samples: Oversampling (SMOTE): For niche lithological samples (such as coal seams and ore bodies), new samples are synthesized (virtual control points are generated by interpolation in the feature space of adjacent samples) to increase their sample ratio; Undersampling (ENN): For dominant lithological samples (such as sandstone), the nearest neighbor algorithm (ENN) is used to remove redundant samples (such as points with dense spatial clusters and repeated attributes) and retain representative samples; ultimately, the ratio of the number of samples of each lithology is controlled within 1:5 to ensure the accuracy of subsequent lithological classification and interpolation.

[0096] Step 2, geological knowledge modeling and constraint construction.

[0097] Stratigraphic Chronology and Lithological Sequence Definition: Based on regional geological survey reports and stratigraphic principles, a stratigraphic chronology-lithological sequence model of the target area is established to clarify the spatial superposition relationship of strata and the lithological evolution law: Stratigraphic chronology is arranged from newest to oldest (e.g., "Quaternary-Tertiary-Cretaceous-Jurassic-Triassic-Permian"), and typical lithological assemblages corresponding to each chronology are defined; key stratigraphic interfaces (e.g., unconformities, parallel unconformities) are marked, and the contact relationship between strata above and below the interfaces (e.g., angular unconformities, conformable contacts) is clarified. An example sequence is shown below. Stratigraphic age (from newest to oldest): Quaternary-Cretaceous-Jurassic-Permian; Corresponding lithological assemblage: loose sediments - siltstone - sandstone + shale - coal seam + mudstone; Contact relationships: angular non-conformity - conformity contact - parallel non-conformity; Construction constraints and geological rule embedding: Transform prior geological knowledge into mathematical constraints and embed them into the subsequent implicit interpolation process to avoid geological logical contradictions in the model.

[0098] 1) Stratigraphic continuity constraint: The interfaces of the same strata should be spatially continuous, without any geologically unrelated interruptions (except for faults). Mathematically, this is expressed as "the elevation difference between the stratigraphic interfaces of adjacent control points ≤ the theoretical difference corresponding to the dip angle of the regional strata"; 2) Tectonic constraint: For regions with developed faults, input parameters such as the strike, dip, and dip angle of the fault to define the spatial extent of the fault (hanging wall, footwall), and constrain "the displacement of the strata on both sides of the fault conforms to the characteristics of the regional tectonic stress field"; 3) Lithological contact constraint: Define the contact types of different lithologies (e.g., gradual contact, abrupt contact). For abrupt contact (e.g., the interface between coal seam and shale), constrain the interpolation algorithm to ensure that the rate of change of the attribute gradient at the interface is ≥ a threshold (e.g., density gradient ≥ 0.5 g / cm³). m).

[0099] Step 3: Implicit interpolation calculation and geological body structure modeling.

[0100] Stratigraphic Interface Interpolation Based on Improved Kriging Algorithm: Determining the Interpolation Grid. Based on the target area and modeling accuracy requirements, a three-dimensional interpolation grid is set (e.g., planar resolution 10m×10m, vertical resolution 2m), with grid nodes representing the geological interface elevation points to be calculated. Constructing the Variance Function: Combining stratigraphic continuity constraints, the traditional spherical Variance Function is improved by introducing a "geological weight coefficient." For adjacent points conforming to the stratigraphic sequence, the weight is increased (e.g., weight coefficient 1.2); for points crossing faults or unconformities, the weight is decreased (e.g., weight coefficient 0.3). The Variance Function expression is: γ(h)=C0+C·[1.5(h / a)-0.5(h / a)³]·W; Where h is the distance between two points, C0 is the nugget value, C is the sill value, a is the range, and W is the geological weight coefficient (0.1≤W≤1.5).

[0101] Calculate the elevation of the stratigraphic interface: For each grid node, calculate the vertical elevation Z of its corresponding stratigraphic interface using the improved Kriging algorithm to obtain the three-dimensional grid surface of the stratigraphic interface (such as the Permian coal seam floor interface and the Jurassic sandstone roof interface).

[0102] 3D Lithology Modeling Based on Radial Basis Functions: Multi-scale radial basis functions (RBF) are used to construct implicit lithology functions, enabling continuous lithological distribution characterization in 3D space: 1) Lithology Encoding: Discrete lithology categories (e.g., sandstone=1, shale=2, coal seam=3) are converted into numerical labels; 2) Basis Function Selection and Parameter Optimization: A multi-scale Gaussian radial basis function (φ(r)=exp(-(εr)²), where ε is the scale parameter) is selected, and the ε value is optimized through K-fold cross-validation (e.g., ε=0.05 for coal seams and ε=0.02 for widely distributed sandstone); 3) Construction of Implicit Lithology Functions: For each grid node, the probability distribution of its lithology label is calculated using RBF interpolation (e.g., probability of belonging to coal seam=0.92, probability of belonging to shale=0.08). The label with the highest probability is taken as the lithology category of that node, generating a 3D lithology model.

[0103] Step 4, Modeling Uncertainty Quantification: To address the "model uncertainty caused by data noise and interpolation algorithm bias" in implicit modeling, the Stochastic Gradient Langevin Boosting (SGLB) algorithm is used to improve traditional machine learning models (such as XGBoost) to achieve uncertainty quantification: 1) Sample Perturbation: Bootstrap resampling is performed on the original geological data (e.g., generating 100 perturbation sample sets) to simulate the impact of data noise on modeling; 2) Model Training and Prediction: Based on each perturbation sample set, the improved XGBoost model is trained (introducing random noise during gradient descent using the SGLB algorithm to simulate algorithm uncertainty), outputting the "lithology category prediction value + confidence interval" and "stratum interface elevation prediction value + standard deviation" for each grid node; 3) Uncertainty Visualization: The uncertainty results are transformed into visual indicators, such as: for lithology models, "color depth" is used to represent confidence level (dark color = high confidence, light color = low confidence); for stratum interfaces, "error bars" are used to represent elevation standard deviation (the longer the error bar, the higher the uncertainty).

[0104] Step 5: Multi-attribute collaborative modeling and model fusion.

[0105] Implicit interpolation of geological attributes: Based on standardized core analysis parameters (such as density, porosity, and ore grade), an attribute-lithology co-interpolation algorithm is used to generate a three-dimensional distribution model of geological attributes: 1) Attribute correlation analysis: The correlation between attributes and lithology is analyzed through Pearson correlation coefficient (e.g., "coal seam density and porosity are negatively correlated, correlation coefficient = -0.85"); 2) Weighted interpolation calculation: For each grid node, combined with its lithology category, "lithology-weighted IDW interpolation" is used. The weight coefficient of adjacent points of the same lithology is increased (e.g., 1.5), and the weight coefficient of points of different lithologies is decreased (e.g., 0.5), ensuring that the attribute distribution conforms to the inherent laws of lithology; 3) Attribute model output. Generate 3D mesh models of various attributes (such as density model and ore grade model), as shown in the following examples: Density model: reflects the density differences of different lithologies (coal seam 1.2~1.5g / cm³, sandstone 2.5~2.8g / cm³); Ore grade model: depicts the spatial variation of grade in the ore body distribution area (such as high grade in the center of the ore body and low grade at the edge).

[0106] Structure-attribute model fusion: The "structural model" (stratigraphic interface, lithological distribution) and "attribute model" (density, grade) of a geological body are fused to establish an "integrated structure-attribute model": 1) Using the structural model as a framework, the grid nodes of the attribute model are associated with the corresponding geological bodies (such as coal seams and sandstone); 2) Model fusion rules are defined, such as "only valid values ​​of 1.2~1.5 g / cm³ are retained for the density attribute within the coal seam range, and values ​​outside the range are marked as invalid", to ensure the geological rationality of the model.

[0107] Step 6: Model visualization and output.

[0108] 3D Model Visualization: Employing multi-dimensional visualization technology, the implicit modeling results are displayed intuitively: 1) Structural Visualization: Using isosurface algorithms (such as the moving cube algorithm), 3D isosurfaces of stratigraphic interfaces and lithological boundaries are extracted, and different colors are used to distinguish lithology (e.g., brown for coal seams and gray for sandstone); 2) Attribute Visualization: Using volume rendering technology, attribute models are color-mapped (e.g., "red = high grade, blue = low grade" for ore grade), and transparent display is supported (e.g., transparent display of sandstone to highlight coal seam distribution); 3) Slice Analysis: Model slices in any direction (e.g., horizontal slices, vertical slices) are generated to display the lithology and attribute distribution at the slice location.

[0109] Model Output and Format Conversion: Outputs modeling results in commonly used engineering formats to support subsequent applications. 1) Structural Model: Outputs in STL (for 3D printing) and VTK (for ParaView visualization) formats; 2) Attribute Model: Outputs in NetCDF (for numerical simulation) and CSV (for data analysis) formats; 3) Report Generation: Automatically generates modeling reports, including data sources, algorithm parameters, model accuracy evaluation (such as cross-validation error), geological conclusions, etc.

[0110] Corresponding to the above method embodiments, this application also provides a three-dimensional model construction apparatus, such as... Figure 5 As shown, the device may include a data acquisition module 501, a constraint determination module 502, and a model building module 503.

[0111] Data acquisition module 501 is used to acquire geological data corresponding to the target area; The constraint determination module 502 is used to determine the constraint conditions corresponding to the target region. Model building module 503 is used to build three-dimensional models based on constraints and geological data.

[0112] In an optional implementation, after acquiring the geological data corresponding to the target area, the process includes: Obtain the geological logic verification rules; Based on geological logic verification rules, abnormal data points in the geological data corresponding to the target area are identified. Remove outlier data points from the geological data corresponding to the target area.

[0113] In an optional implementation, after acquiring the geological data corresponding to the target area, the method further includes: Obtain the stratigraphic sequence relationship corresponding to the target area; Obtain the missing points corresponding to the target region; Based on the stratigraphic sequence relationship corresponding to the target area, the missing points in the target area are filled in.

[0114] In an optional implementation, the constraint determination module 502 is specifically used for: Obtain the sequence information corresponding to the target region; Establish a sequence model based on the sequence information corresponding to the target region; The sequence model is transformed into constraints corresponding to the target region.

[0115] In an optional implementation, the model building module 503 includes: The initial model building unit 5031 is used to build an initial three-dimensional model based on the spatial coordinates and attribute information in the geological data; The model correction unit 5032 is used to correct the initial three-dimensional model based on the constraints to obtain the three-dimensional model.

[0116] In an optional implementation, the initial model building unit 5031 is specifically used for: Construct a three-dimensional structural model based on the spatial coordinates in the geological data; Construct a three-dimensional attribute model based on the attribute information in the geological data; The three-dimensional structural model and the three-dimensional attribute model are fused to obtain the initial three-dimensional model.

[0117] In an optional implementation, the model correction unit 5032 is specifically used for: Weighting coefficients are determined based on constraints. The initial 3D model is corrected based on the weighting coefficients to obtain the 3D model.

[0118] In an alternative implementation, after constructing the 3D model, the following steps are also included: Geological data is resampled multiple times to generate at least one data perturbation set; For any set of data perturbations, construct a modified three-dimensional model based on the set of data perturbations and constraints; Based on the corrected 3D model corresponding to at least one data perturbation set, determine the predicted value corresponding to each spatial location in the 3D model; The 3D model is corrected based on the predicted values ​​corresponding to each spatial location in the 3D model.

[0119] This application also provides an electronic device, such as... Figure 6 As shown, it includes a processor 601, a communication interface 602, a memory 603, and a communication bus 604, wherein the processor 601, the communication interface 602, and the memory 603 communicate with each other through the communication bus 604. Memory 603 is used to store computer programs; In one embodiment of this application, when the processor 601 executes a program stored in the memory 603, it performs the following steps: Obtain geological data corresponding to the target area; determine the constraints corresponding to the target area; and construct a three-dimensional model based on the constraints and geological data.

[0120] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0121] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0122] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0123] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0124] In another embodiment provided in this application, a storage medium is also provided, which stores instructions that, when run on a computer, cause the computer to execute any of the three-dimensional model construction methods described in the above embodiments.

[0125] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the three-dimensional model construction methods described in the above embodiments.

[0126] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a storage medium or transmitted from one storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0127] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0128] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0129] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the protection scope of this application.

Claims

1. A method for constructing a three-dimensional model, characterized in that, The method includes: Obtain geological data corresponding to the target area; Determine the constraints corresponding to the target region; Based on the constraints and the geological data, a three-dimensional model is constructed.

2. The method according to claim 1, characterized in that, After obtaining the geological data corresponding to the target area, the following steps are included: Obtain the geological logic verification rules; Based on the geological logic verification rules, abnormal data points in the geological data corresponding to the target area are determined; Remove abnormal data points from the geological data corresponding to the target area.

3. The method according to claim 1, characterized in that, After obtaining the geological data corresponding to the target area, the process also includes: Obtain the stratigraphic sequence relationship corresponding to the target area; Obtain the missing points corresponding to the target region; Based on the stratigraphic sequence relationship corresponding to the target area, the missing points corresponding to the target area are filled in.

4. The method according to claim 1, characterized in that, The constraints for determining the target region include: Obtain the sequence information corresponding to the target region; A sequence model is established based on the sequence information corresponding to the target region; The sequence model is transformed into constraints corresponding to the target region.

5. The method according to claim 1, characterized in that, The construction of a three-dimensional model based on the constraints and the geological data includes: Based on the spatial coordinates and attribute information in the geological data, an initial three-dimensional model is constructed. The initial 3D model is modified based on the constraints to obtain the 3D model.

6. The method according to claim 5, characterized in that, The step of constructing an initial three-dimensional model based on the spatial coordinates and attribute information in the geological data includes: Based on the spatial coordinates in the geological data, a three-dimensional structural model is constructed; Based on the attribute information in the geological data, a three-dimensional attribute model is constructed; The three-dimensional structural model and the three-dimensional attribute model are fused to obtain the initial three-dimensional model.

7. The method according to claim 5, characterized in that, The step of correcting the initial 3D model based on the constraints to obtain the 3D model includes: The weighting coefficients are determined based on the aforementioned constraints. The initial 3D model is corrected based on the weighting coefficients to obtain the 3D model.

8. The method according to claim 1, characterized in that, Following the construction of the 3D model, the following is also included: The geological data is resampled multiple times to generate at least one data perturbation set; For any of the data perturbation sets, a modified three-dimensional model is constructed based on the data perturbation set and the constraints. Based on the corrected three-dimensional model corresponding to each of the at least one data perturbation set, determine the predicted value corresponding to each spatial location in the three-dimensional model; The three-dimensional model is corrected based on the predicted values ​​corresponding to each spatial location in the model.

9. A three-dimensional model construction device, characterized in that, The device includes: The data acquisition module is used to acquire geological data corresponding to the target area. A constraint determination module is used to determine the constraint conditions corresponding to the target region; The model building module is used to build a three-dimensional model based on the constraints and the geological data.

10. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method described in any one of claims 1-8.

Images