Geological resource assessment method and system based on big data fusion

Abstract

The invention discloses a geological resource assessment method and system based on big data fusion, and relates to the technical field of geological data processing, and the method comprises the steps: defining a common point in a to-be-analyzed region, constructing a common region through the common point, constructing a common point region on the basis of the common point, and improving the sample number and quality condition of the common point. And configuring coordinate conversion parameters according to the public area, performing coordinate conversion and calibration on the geological multi-source position information of the area to be analyzed by virtue of the coordinate conversion parameters, and generating a three-dimensional geological model of the area to be analyzed. Therefore, the precision and reliability of multi-source position information fusion are improved. According to the method, the direct adjacent area and the interval adjacent area of each resource distribution area are defined and are combined to evaluate the geological resource reserves of the resource distribution areas, so that the geological resource evaluation accuracy and reliability are improved, and effective utilization and sustainable development protection of geological resources are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of geological data processing, and in particular to a geological resource assessment method and system based on big data fusion. Background Art

[0002] With the continuous development of geological exploration technology, the amount of geological data collected has increased dramatically. These data not only come from traditional geological exploration, geophysics, geochemistry and other methods, but also cover high-tech means such as remote sensing, drones, satellites, etc. The convergence of these multi-source data provides unprecedented rich information for geological resource assessment. However, how to effectively integrate, process and analyze these data to accurately assess the reserves of geological resources has become an urgent problem to be solved. Big data fusion technology came into being. It can integrate geological data from different channels, different formats and different precisions, and extract valuable information through algorithms such as data mining and machine learning, providing scientific, accurate and efficient support for geological resource assessment. The application of this technology not only improves the accuracy and efficiency of geological resource assessment, but also brings new development opportunities to the fields of geological exploration, resource development and environmental protection.

[0003] In the prior art, the coordinate systems of multi-source geological location information are not unified, resulting in poor accuracy and low reliability in geological resource assessment, and failing to effectively ensure full utilization and sustainable protection of geological resources.

[0004] Therefore, how to improve the accuracy and reliability of geological resource assessment is a technical problem that needs to be solved. Summary of the invention

[0005] The purpose of the present invention is to solve the problems of poor accuracy and low reliability of geological resource assessment in the prior art, and to propose a geological resource assessment method based on big data fusion, which includes: Obtain geological multi-source location information and geological resource information of the area to be analyzed, define common points in the area to be analyzed, and construct common areas through common points; Coordinate transformation parameters are configured according to the common area, and the coordinate transformation and calibration of the geological multi-source position information of the area to be analyzed are performed by means of the coordinate transformation parameters, so as to complete the fusion of the geological multi-source position information of the area to be analyzed and generate a three-dimensional geological model of the area to be analyzed; The internal boundary of the three-dimensional geological model of the area to be analyzed is divided to obtain multiple resource distribution areas, and the direct adjacent areas and the interval adjacent areas of each resource distribution area are defined; The geological resource content of the resource distribution area is evaluated in combination with the directly adjacent areas and the distance adjacent areas.

[0006] In some embodiments of the present application, common points within the area to be analyzed are defined, including: Analyze the geological multi-source location information and geological resource information of the area to be analyzed to confirm the area with obvious geological characteristics in the area to be analyzed, select geological characteristic points in the area with obvious geological characteristics, and retain the geological characteristic points that exist in each source location information in the geological multi-source location information; The change rate of each type of geological feature around the retained geological feature points is calculated, and the change rate of each type of geological feature is integrated to generate a geological change rate index. The geological feature points are screened out as common points in the area to be analyzed through the geological change rate index.

[0007] In some embodiments of the present application, a public area is constructed by using a public point, including: The area to be analyzed is divided into multiple sub-areas according to the location of the common points, and the density of common points in each sub-area is calculated. The sub-area density types are divided according to the density of common points, and the kernel function under each sub-area is selected. The bandwidth of the kernel function is determined by the geological change rate index of the common points, so as to evaluate the kernel density and generate the common point density distribution map of the area to be analyzed; Filter out high-density areas on the common point density distribution map, and calculate the relative distance between common points in the high-density area to filter out a high-density common point set; Identify the area boundaries of high-density common point sets and construct common areas.

[0008] In some embodiments of the present application, confirming the region boundary of a high-density common point set and constructing a common region includes: Analyze the characteristics of each high-density common point set to set the Alpha value threshold; Perform Delaunay triangulation on the high-density common point set, calculate the Alpha value of each edge in the Delaunay triangulation, and compare the relationship between the Alpha value and the Alpha value threshold to determine the edge belonging to the Alpha shape; Alpha shape edges are connected based on the edges belonging to the Alpha shape to form a region boundary of a high-density common point set, thereby constructing a common region.

[0009] In some embodiments of the present application, the characteristics of each high-density common point set are analyzed to set the Alpha value threshold, including: The characteristics of high-density common point sets include common point set density, noise conditions, and outlier conditions; Analyze the noise and outlier conditions to assess the noise and anomaly levels, and set the Alpha value threshold based on the density of common point sets, noise levels, and anomaly levels; ; in, For the The alpha value threshold of a high-density common point set, , are the combined weights of the noise level and the abnormality level, , Respectively The noise and abnormality of a high-density common point set, For the The initial threshold of the alpha value of a high-density common point set, It represents the initial threshold of the Alpha value obtained by mapping the comprehensive noise level and abnormality level. For the The common point density of a high-density common point set, is a preset constant.

[0010] In some embodiments of the present application, the coordinate conversion parameters are configured according to the common area, including: Based on the location information of the common area and the location information of the common points outside the common area, an optimization algorithm is used to solve the coordinate transformation parameters, which include translation parameters, rotation parameters and scale factors.

[0011] In some embodiments of the present application, the direct adjacent area and the spacing adjacent area of ​​each resource distribution area are defined, including: The other resource distribution areas adjacent to the resource distribution area are regarded as directly adjacent areas, the geological activity process is simulated on the three-dimensional geological model of the area to be analyzed, and other resource distribution areas that affect the resource distribution area are identified and recorded as the interval adjacent areas; The variograms of directly adjacent areas and spaced adjacent areas are constructed based on geological multi-source location information and geological resource information, and the influence weights of directly adjacent areas and spaced adjacent areas are calculated through the variograms.

[0012] In some embodiments of the present application, the geological resource content of the resource distribution area is evaluated by combining the directly adjacent area and the distance adjacent area, including: The assessment of geological resource content in the resource distribution area is the assessment of geological resource reserves; ; in, For the The estimated value of geological resource reserves in each resource distribution area, For the The observed value of geological resource reserves in each resource distribution area, For the The sum of the number of directly adjacent areas and distance adjacent areas of a resource distribution area, For the The resource distribution area The influence weight of the directly adjacent area or the distance adjacent area, Indicates The resource distribution area observations of directly adjacent regions or inter-neighboring regions, For directly adjacent areas and distance adjacent areas The maximum value in is a preset constant.

[0013] Correspondingly, the present application also provides a geological resource assessment system based on big data fusion, including: The first module is used to obtain geological multi-source location information and geological resource information of the area to be analyzed, define common points in the area to be analyzed, and construct common areas through common points; The second module is used to configure the coordinate transformation parameters according to the common area, and to perform coordinate transformation and calibration on the geological multi-source position information of the area to be analyzed by means of the coordinate transformation parameters, so as to complete the fusion of the geological multi-source position information of the area to be analyzed and generate a three-dimensional geological model of the area to be analyzed; The third module is used to divide the internal boundaries of the three-dimensional geological model of the area to be analyzed, obtain multiple resource distribution areas, and define the direct adjacent areas and the interval adjacent areas of each resource distribution area; The fourth module is used to evaluate the geological resource content of the resource distribution area by combining the directly adjacent areas and the distance adjacent areas.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. Construct a common area through common points, and build a common point area based on common points to improve the number and quality of common point samples. Configure coordinate transformation parameters according to the common area to improve the accuracy and reliability of multi-source location information fusion.

[0015] 2. Define the directly adjacent areas and the spaced adjacent areas of each resource distribution area, and combine them to evaluate the geological resource reserves of the resource distribution area, which improves the accuracy and reliability of geological resource evaluation and ensures that geological resources can be effectively utilized and sustainably protected. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a process of a geological resource assessment method based on big data fusion proposed by the present invention; Figure 2 This is a structural schematic diagram of a geological resource assessment system based on big data fusion proposed by the present invention. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0018] Reference Figure 1 , a geological resource assessment method based on big data fusion, including the following steps, Step S101, obtaining geological multi-source position information and geological resource information of the area to be analyzed, defining common points in the area to be analyzed, and constructing a common area through the common points.

[0019] In this embodiment, geological multi-source location information: collect geological location information of the area to be analyzed through geological surveys, remote sensing image interpretation, GPS field measurements, seismic exploration and other means. This information includes but is not limited to stratum distribution, geological structural lines, rock mass boundaries, etc. Resource information: collect relevant data on mineral resources, energy resources (such as oil and gas reservoirs), groundwater resources, etc. in the area to be analyzed. These data may come from geological exploration reports, mineral resource survey reports, hydrogeological survey reports, etc. Common points are location points that have obvious characteristics and are geologically representative in the geological multi-source location information.

[0020] It is understandable that in previous coordinate conversions or unifications, there were fewer high-quality common points, which resulted in errors in the converted coordinates. The purpose of constructing the public area here is to expand the high-quality common points to obtain more accurate coordinate conversion parameters, providing a basis for subsequent three-dimensional geological models and resource reserve assessments.

[0021] In some embodiments of the present application, common points within the area to be analyzed are defined, including: Analyze the geological multi-source location information and geological resource information of the area to be analyzed to confirm the area with obvious geological characteristics in the area to be analyzed, select geological characteristic points in the area with obvious geological characteristics, and retain the geological characteristic points that exist in each source location information in the geological multi-source location information; The change rate of each type of geological feature around the retained geological feature points is calculated, and the change rate of each type of geological feature is integrated to generate a geological change rate index. The geological feature points are screened out as common points in the area to be analyzed through the geological change rate index.

[0022] In this embodiment, areas with obvious geological features are identified, such as fault zones, fold axes, rock mass boundaries, etc. Geological feature points include fault intersections, fold axis points, rock mass boundary points, and other location points with obvious geological features. The change rate of geological features around the candidate points, such as fault displacement rate, fold deformation rate, etc., is calculated, and these transformation rates are integrated into a geological change rate indicator (weighted sum or weighted average). Points with higher change rates are selected as representative points because these points can more sensitively reflect the transformation of geological features.

[0023] In some embodiments of the present application, a public area is constructed by using a public point, including: The area to be analyzed is divided into multiple sub-areas according to the location of the common points, and the density of common points in each sub-area is calculated. The sub-area density types are divided according to the density of common points, and the kernel function under each sub-area is selected. The bandwidth of the kernel function is determined by the geological change rate index of the common points, so as to evaluate the kernel density and generate the common point density distribution map of the area to be analyzed; Filter out high-density areas on the common point density distribution map, and calculate the relative distance between common points in the high-density area to filter out a high-density common point set; Identify the area boundaries of high-density common point sets and construct common areas.

[0024] In this embodiment, the density of common points is the ratio of the number of common points to the area in the sub-region. The sub-region density type is divided according to the density of common points. The sub-region density type has two types: uniform distribution type and sparse distribution type. For the first type, a kernel function with a longer tail, such as a Gaussian kernel, is selected to better capture the details of the data. For the second type, if the data points are very concentrated in certain specific locations (such as geological faults, mineral deposits, etc.), a kernel function with a limited support range such as a uniform kernel or an Epanechnikov kernel can be considered. The geological change rate of common points can help determine the bandwidth size in the kernel function. For example, in areas with a high geological change rate, it means that the geological features have changed significantly in a short time (or short distance). In order to accurately capture these rapidly changing geological features, a smaller bandwidth should be selected. A smaller bandwidth can more closely follow the changes in data points, thereby providing higher resolution and more detailed geological information.

[0025] In this embodiment, Kernel Density Estimation (KDE) is a non-parametric method for estimating the density distribution of a data point set. Bandwidth is an important parameter in kernel density estimation, which determines the influence range of each point. If the bandwidth is too large, the density estimate may be too smooth, covering up the details of the data; if the bandwidth is too small, the density estimate may be too volatile and unable to reflect the overall trend of the data. For each location (usually a grid point or pixel) in the study area, its density value is calculated. The calculated density value is mapped to the grid or pixel of the study area to generate a density distribution map. The density distribution map usually indicates the density value in color or grayscale, and the darker the color or the larger the grayscale value, the higher the density. To filter multiple common points with relatively close distance and density, the distance measurement method (such as Euclidean distance, Manhattan distance, etc.) and density information can be combined. The density value of each point can be obtained by kernel density estimation, and then the distance between each point and its surrounding points is calculated, and the point set can be filtered according to the comprehensive index of density and distance (such as weighted sum, product, etc.).

[0026] It can be understood that screening out a high-density common point set is to traverse all common points and search for multiple common points that are relatively close and have a high density, so as to facilitate the next step of determining the area boundary.

[0027] In some embodiments of the present application, confirming the region boundary of a high-density common point set and constructing a common region includes: Analyze the characteristics of each high-density common point set to set the Alpha value threshold; Perform Delaunay triangulation on the high-density common point set, calculate the Alpha value of each edge in the Delaunay triangulation, and compare the relationship between the Alpha value and the Alpha value threshold to determine the edge belonging to the Alpha shape; Alpha shape edges are connected based on the edges belonging to the Alpha shape to form a region boundary of a high-density common point set, thereby constructing a common region.

[0028] In this embodiment, the Alpha shape is a more flexible way to control the boundary shape of the region (determine the boundary of the region with high-density common points). It controls the tightness and smoothness of the boundary by adjusting a parameter (called the Alpha value).

[0029] General steps: 1. Determine the common points selected with high density.

[0030] 2. Choose a suitable Alpha value.

[0031] 3. Use the Alpha shape algorithm to generate the boundary shape based on the selected points and Alpha values.

[0032] 4. Generate and output the boundary shape as the boundary of the common area.

[0033] Construct a Delaunay triangulation: Before generating the Alpha shape, the point set needs to be Delaunay triangulated first.

[0034] Delaunay triangulation is an algorithm that partitions a point set into a series of disjoint triangles that satisfy the Delaunay conditions.

[0035] Calculate the alpha edge: For each edge in the Delaunay triangulation, calculate the corresponding Alpha value.

[0036] The alpha value is usually related to factors such as the length of the edge and the radius of the circumscribed circle of adjacent triangles.

[0037] Determines which edges are part of the Alpha shape based on the selected Alpha value (threshold).

[0038] Generate Alpha Shape: Connect the edges belonging to the Alpha shape to form a polygon or complex shape.

[0039] This polygon or shape is the desired common area boundary.

[0040] Post-processing: Perform post-processing on the generated Alpha shape, such as simplifying the border, removing redundant vertices, etc.

[0041] Make sure the generated shapes meet actual needs and have good visualization effects.

[0042] In some embodiments of the present application, the characteristics of each high-density common point set are analyzed to set the Alpha value threshold, including: The characteristics of high-density common point sets include common point set density, noise conditions, and outlier conditions; Analyze the noise and outlier conditions to assess the noise and anomaly levels, and set the Alpha value threshold based on the density of common point sets, noise levels, and anomaly levels; ; in, For the The alpha value threshold of a high-density common point set, , are the combined weights of the noise level and the abnormality level, , Respectively The noise and abnormality of a high-density common point set, For the The initial threshold of the alpha value of a high-density common point set, It represents the initial threshold of the Alpha value obtained by mapping the comprehensive noise level and abnormality level. For the The common point density of a high-density common point set, is a preset constant.

[0043] In this embodiment, the selection of the Alpha value threshold is affected by multiple characteristics of the point set (density, noise, and anomalies, etc.), for example, the amount and impact of noise in the evaluation point cloud. In the case of more noise, selecting a larger Alpha value can help reduce the impact of noise on the Alpha shape. The density of the common point set is the density of the point set combined with the kernel density of each common point in the previous step. The higher the density of the point set, the smaller the Alpha value is usually required to ensure that the boundary is tightly around the point set. For point sets with lower density, larger Alpha values ​​can be selected to generate smoother boundaries.

[0044] It should be noted that the noise and outlier conditions in the high-density common point set are specifically the noise and anomaly conditions of the data of the locations and resources inside the point set and around the points.

[0045] In this embodiment, It represents the correction of the initial threshold of the Alpha value obtained by comprehensively mapping the density of the point set to the degree of noise and the degree of abnormality. This is to balance the size of the control correction function.

[0046] Step S102, configuring coordinate transformation parameters according to the common area, using the coordinate transformation parameters to transform and calibrate the geological multi-source position information of the area to be analyzed, completing the fusion of the geological multi-source position information of the area to be analyzed, and generating a three-dimensional geological model of the area to be analyzed.

[0047] In this embodiment, a small number of high-quality common points are expanded into a smaller common area to expand the number of common point samples and improve the accuracy of coordinate conversion. Commonly used coordinate conversion algorithms include seven-parameter conversion and four-parameter conversion, etc. The calculated coordinate conversion parameters are applied to the multi-source geological position information to perform coordinate conversion. Ensure that the converted coordinate system is consistent with the target coordinate system. Calibrate the converted geological position information to check its degree of conformity with the actual situation. If calibration problems are found, adjust the coordinate conversion parameters or algorithms in time until the conversion results meet the requirements.

[0048] In some embodiments of the present application, the coordinate conversion parameters are configured according to the common area, including: Based on the location information of the common area and the location information of the common points outside the common area, an optimization algorithm is used to solve the coordinate transformation parameters, which include translation parameters, rotation parameters and scale factors.

[0049] In this embodiment, the seven parameters include three translation parameters (dx, dy, dz), three rotation parameters (rx, ry, rz) and a scale factor (s). These parameters are calculated by the least square method or other optimization algorithms to minimize the difference between the transformed coordinates and the actual coordinates. The four parameters include two translation parameters (dx, dy), one rotation parameter (usually around the Z axis, i.e., θ) and a scale factor (s).

[0050] Step S103, dividing the internal boundaries of the three-dimensional geological model of the area to be analyzed to obtain multiple resource distribution areas, and defining the direct adjacent areas and the interval adjacent areas of each resource distribution area.

[0051] In this embodiment, the calibrated geological position information is used to construct a three-dimensional model framework of the area to be analyzed, which includes a three-dimensional representation of the stratum surface, geological structure lines, rock mass boundaries, etc.

[0052] Use 3D modeling software or programming libraries (such as OpenGL, VTK, etc.) to visualize the 3D model. Add geological features such as stratigraphic lithology, fossil distribution, geological age, etc. on the basis of the 3D model framework, and enhance the geological expression ability of the 3D model through texture mapping, color coding, etc. Optimize and improve the 3D model to ensure that it accurately reflects the geological characteristics and transformation of the study area. Consider the dynamic nature of geological processes and add a time dimension to the 3D model to simulate and predict geological evolution. Determine the specific location and distribution range of resources based on the results of geological exploration and resource surveys. Accurately mark the location of resources in the 3D model, such as the 3D boundaries of ore bodies, oil reservoirs, gas reservoirs, etc. Divide the 3D model into regions based on geological characteristics (such as stratigraphic lithology, structural type), resource distribution, topography, and other factors. Ensure that each region has relatively independent geological characteristics and resource attributes for subsequent management and evaluation. Clarify the boundaries and scope of each region, and use 3D surfaces or polygons to represent the boundaries of the region. Assign a unique identifier to each region for subsequent processing and analysis.

[0053] In some embodiments of the present application, the direct adjacent area and the spacing adjacent area of ​​each resource distribution area are defined, including: The other resource distribution areas adjacent to the resource distribution area are regarded as directly adjacent areas, the geological activity process is simulated on the three-dimensional geological model of the area to be analyzed, and other resource distribution areas that affect the resource distribution area are identified and recorded as the interval adjacent areas; The variograms of directly adjacent areas and spaced adjacent areas are constructed based on geological multi-source location information and geological resource information, and the influence weights of directly adjacent areas and spaced adjacent areas are calculated through the variograms.

[0054] In this embodiment, the directly adjacent areas of each area are determined based on the geographic spatial relationship. These areas may have direct contact and influence on the target area in terms of geological characteristics and resource distribution. Considering the scope of influence of geological processes or resource migration, the affected adjacent areas of each area are determined. Although these areas may not be directly adjacent to the target area, their geological characteristics or resource changes may have an impact on the target area. The variogram is a mathematical function that describes the difference in resource reserves between two points in space, also known as the semi-variance function. It reflects the variability and correlation of resource reserves in space. Using the collected data, the differences in resource reserves at different distances are calculated to obtain the experimental variogram. Select a suitable theoretical variogram model (such as a spherical model, an exponential model, etc.) for fitting, and adjust the model parameters to make the theoretical variogram and the experimental variogram as consistent as possible.

[0055] Step S104, evaluating the geological resource content of the resource distribution area by combining the directly adjacent areas and the distance adjacent areas.

[0056] In some embodiments of the present application, the geological resource content of the resource distribution area is evaluated by combining the directly adjacent area and the distance adjacent area, including: The assessment of geological resource content in the resource distribution area is the assessment of geological resource reserves; ; in, For the The estimated value of geological resource reserves in each resource distribution area, For the The observed value of geological resource reserves in each resource distribution area, For the The sum of the number of directly adjacent areas and distance adjacent areas of a resource distribution area, For the The resource distribution area The influence weight of the directly adjacent area or the distance adjacent area, Indicates The resource distribution area observations of directly adjacent regions or inter-neighboring regions, For directly adjacent areas and distance adjacent areas The maximum value in is a preset constant.

[0057] In this embodiment, the observed value is a sample value obtained through actual measurement or determination, which cannot accurately describe the resource reserves. The estimated value is an estimate of the overall parameter calculated based on sample data (including the observed value) and a certain estimation method (such as the Kriging method).

[0058] In this embodiment, express The maximum value in Correction of the average value of the region's own observations and the observations evaluated from other regions' observations, This is to balance the size in the correction function.

[0059] Correspondingly, this application also provides a geological resource assessment system based on big data fusion, such as Figure 2 As shown, including The first module is used to obtain geological multi-source location information and geological resource information of the area to be analyzed, define common points in the area to be analyzed, and construct common areas through common points; The second module is used to configure the coordinate transformation parameters according to the common area, and to perform coordinate transformation and calibration on the geological multi-source position information of the area to be analyzed by means of the coordinate transformation parameters, so as to complete the fusion of the geological multi-source position information of the area to be analyzed and generate a three-dimensional geological model of the area to be analyzed; The third module is used to divide the internal boundaries of the three-dimensional geological model of the area to be analyzed, obtain multiple resource distribution areas, and define the direct adjacent areas and the interval adjacent areas of each resource distribution area; The fourth module is used to evaluate the geological resource content of the resource distribution area by combining the directly adjacent areas and the distance adjacent areas.

[0060] Compared with the prior art, the present invention has the following beneficial effects: 1. Construct a common area through common points, and build a common point area based on common points to improve the number and quality of common point samples. Configure coordinate transformation parameters according to the common area to improve the accuracy and reliability of multi-source location information fusion.

[0061] 2. Define the directly adjacent areas and the spaced adjacent areas of each resource distribution area, and combine them to evaluate the geological resource reserves of the resource distribution area, which improves the accuracy and reliability of geological resource evaluation and ensures that geological resources can be effectively utilized and sustainably protected.

[0062] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0063] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present invention.

[0064] Those skilled in the art will appreciate that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more systems different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0065] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A geological resource assessment method based on big data fusion, characterized in that: include, Obtain geological multi-source location information and geological resource information of the area to be analyzed, define common points in the area to be analyzed, and construct common areas through common points; Coordinate transformation parameters are configured according to the common area, and the coordinate transformation and calibration of the geological multi-source position information of the area to be analyzed are performed by means of the coordinate transformation parameters, so as to complete the fusion of the geological multi-source position information of the area to be analyzed and generate a three-dimensional geological model of the area to be analyzed; The internal boundary of the three-dimensional geological model of the area to be analyzed is divided to obtain multiple resource distribution areas, and the direct adjacent areas and the interval adjacent areas of each resource distribution area are defined; The geological resource content of the resource distribution area is evaluated in combination with the directly adjacent areas and the distance adjacent areas.

2. The geological resource assessment method based on big data fusion according to claim 1, characterized in that: Define common points within the area to be analyzed, including, Analyze the geological multi-source location information and geological resource information of the area to be analyzed to confirm the area with obvious geological characteristics in the area to be analyzed, select geological characteristic points in the area with obvious geological characteristics, and retain the geological characteristic points that exist in each source location information in the geological multi-source location information; The change rate of each type of geological feature around the retained geological feature points is calculated, and the change rate of each type of geological feature is integrated to generate a geological change rate index. The geological feature points are screened out as common points in the area to be analyzed through the geological change rate index.

3. The geological resource assessment method based on big data fusion according to claim 2 is characterized in that: And build public areas through public points, including, The area to be analyzed is divided into multiple sub-areas according to the location of the common points, and the density of common points in each sub-area is calculated. The sub-area density types are divided according to the density of common points, and the kernel function under each sub-area is selected. The bandwidth of the kernel function is determined by the geological change rate index of the common points, so as to evaluate the kernel density and generate the common point density distribution map of the area to be analyzed; Filter out high-density areas on the common point density distribution map, and calculate the relative distance between common points in the high-density area to filter out a high-density common point set; Identify the area boundaries of high-density common point sets and construct common areas.

4. The geological resource assessment method based on big data fusion according to claim 3 is characterized in that: Confirm the area boundaries of high-density common point sets and construct common areas, including, Analyze the characteristics of each high-density common point set to set the Alpha value threshold; Perform Delaunay triangulation on the high-density common point set, calculate the Alpha value of each edge in the Delaunay triangulation, and compare the relationship between the Alpha value and the Alpha value threshold to determine the edge belonging to the Alpha shape; Alpha shape edges are connected based on the edges belonging to the Alpha shape to form a region boundary of a high-density common point set, thereby constructing a common region.

5. The geological resource assessment method based on big data fusion according to claim 4 is characterized in that: Analyze the characteristics of each high-density common point set to set the alpha value threshold, including, The characteristics of high-density common point sets include common point set density, noise conditions, and outlier conditions; Analyze the noise and outlier conditions to assess the noise and anomaly levels, and set the Alpha value threshold based on the density of common point sets, noise levels, and anomaly levels; ； in, For the The alpha value threshold of a high-density common point set, , are the combined weights of the noise level and the abnormality level, , Respectively The noise and abnormality of a high-density common point set, For the The initial threshold of the alpha value of a high-density common point set, It represents the initial threshold of the Alpha value obtained by mapping the comprehensive noise level and abnormality level. For the The common point density of a high-density common point set, is a preset constant.

6. The geological resource assessment method based on big data fusion according to claim 1, characterized in that: Configure coordinate transformation parameters based on common areas, including, Based on the location information of the common area and the location information of the common points outside the common area, an optimization algorithm is used to solve the coordinate transformation parameters, which include translation parameters, rotation parameters and scale factors.

7. The geological resource assessment method based on big data fusion according to claim 1 is characterized in that: Define the direct and inter-neighboring areas for each resource distribution area, including, The other resource distribution areas adjacent to the resource distribution area are regarded as directly adjacent areas, the geological activity process is simulated on the three-dimensional geological model of the area to be analyzed, and other resource distribution areas that affect the resource distribution area are identified and recorded as the interval adjacent areas; The variograms of directly adjacent areas and spaced adjacent areas are constructed based on geological multi-source location information and geological resource information, and the influence weights of directly adjacent areas and spaced adjacent areas are calculated through the variograms.

8. The geological resource assessment method based on big data fusion according to claim 7 is characterized in that: An assessment of the geological resource content of the resource distribution area is conducted in combination with the directly adjacent areas and the intervening adjacent areas, including: The assessment of geological resource content in the resource distribution area is the assessment of geological resource reserves; ； in, For the The estimated value of geological resource reserves in each resource distribution area, For the The observed value of geological resource reserves in each resource distribution area, For the The sum of the number of directly adjacent areas and distance adjacent areas of a resource distribution area, For the The resource distribution area The influence weight of the directly adjacent area or the distance adjacent area, Indicates The resource distribution area observations of directly adjacent regions or inter-neighboring regions, For directly adjacent areas and distance adjacent areas The maximum value in is a preset constant.

9. A geological resource assessment system based on big data fusion, characterized in that: include, The first module is used to obtain geological multi-source location information and geological resource information of the area to be analyzed, define common points in the area to be analyzed, and construct common areas through common points; The second module is used to configure the coordinate transformation parameters according to the common area, and to perform coordinate transformation and calibration on the geological multi-source position information of the area to be analyzed by means of the coordinate transformation parameters, so as to complete the fusion of the geological multi-source position information of the area to be analyzed and generate a three-dimensional geological model of the area to be analyzed; The third module is used to divide the internal boundaries of the three-dimensional geological model of the area to be analyzed, obtain multiple resource distribution areas, and define the direct adjacent areas and the interval adjacent areas of each resource distribution area; The fourth module is used to evaluate the geological resource content of the resource distribution area by combining the directly adjacent areas and the distance adjacent areas.

Images