Mineral resource analysis system and method for potential mining area

Abstract

The invention discloses a mineral resource analysis system and method for a potential mining area, and belongs to the technical field of mineral resource analysis. Comprising a potential mining area identification unit which is used for determining, researching and predicting mineral types according to local related geological information, collecting corresponding analysis data and delimiting a to-be-identified area based on a processing analysis result of the analysis data; the geological data acquisition unit is used for determining sampling points according to the to-be-identified area and acquiring geological sample data and geological information; generating a geological unit data set; the graph structure unit is used for obtaining an embedded vector of each geological unit according to the geological unit data set; and the mineralization probability evaluation unit is used for obtaining the mineralization probability of each specific geological unit according to the analysis result of the graph structure.

Description

Technical Field

[0001] The present application relates to the field of mineral resource analysis technology, and more specifically, to a system and method for analyzing mineral resources in a potential mining area; Background Art

[0002] The prior art discloses a mineral resource analysis system for a potential mining area (publication number: CN113323662A), which uses a potential mining area identification unit to delineate an area to be identified based on the processing and analysis results of analysis data, and a geological data acquisition unit can determine a prediction area based on the area to be identified, thereby achieving accurate judgment of the location of the potential mining area; a reserve analysis and prediction module performs mineral reserve prediction and analysis on the prediction area according to a regional model and a spatial model, thereby accurately predicting the potential mineral resource volume; a prediction model optimization module optimizes a regional model and a spatial model constructed by a prediction model construction unit according to the difference between the mineral reserves predicted and analyzed by the reserve analysis and prediction module and the field exploration results, thereby continuously improving the prediction accuracy of the potential mineral resource volume.

[0003] The above-mentioned system has deficiencies in dealing with the spatial relationship between geological units, feature aggregation effect and prediction accuracy, which affects the overall mineralization prediction and evaluation effect.

[0004] Therefore, inventing a system and method for analyzing mineral resources in potential mining areas has become a technical problem that needs to be solved urgently in this field; Summary of the invention

[0005] In order to overcome a series of defects in the prior art, the purpose of this application is to provide a mineral resource analysis system for a potential mining area, including:

[0006] Potential mining area identification unit, used to determine the type of minerals to be studied and predicted based on relevant local geological information, collect relevant analytical data, and delineate the area to be identified based on the processing and analysis results of the analytical data;

[0007] The geological data collection unit is used to determine the sampling points according to the area to be identified, collect geological sample data and geological information, and generate a geological unit data set;

[0008] Graph structure unit: Based on the geological unit dataset, the embedding vector of each geological unit is obtained;

[0009] Mineralization probability assessment unit: Based on the analysis results of the graph structure, the mineralization probability of each specific geological unit is obtained.

[0010] Furthermore, the potential mining area identification unit includes: basic data collection module: using high-resolution satellite remote sensing technology to collect surface characteristics, geological structure and environmental information of the mining area;

[0011] The first data processing module: classify and organize the collected remote sensing data; normalize the data from different sources to ensure data consistency and comparability; remove outliers and noise in the data to improve data quality;

[0012] The first data analysis module is used to process and analyze the data processing results of the first data processing module and define the area to be identified.

[0013] Furthermore, the geological data acquisition unit includes: a geological data acquisition module: determining and setting up sampling points according to the area to be identified, collecting geological sample data at different depths; obtaining geological information of the mining area through gravity and magnetic measurements and electromagnetic measurements;

[0014] The second data processing module is used to classify the geological sample data and geological information collected by the geological data collection unit, and integrate the data information of adjacent areas in the same layer to generate a geological unit data set.

[0015] Furthermore, the graph structure unit:

[0016] Node and edge definition: The geological units in the geological unit dataset are defined as nodes in the graph structure, and the edges are defined according to the spatial relationship between the geological units and the corresponding weights are assigned;

[0017] Graph embedding: Graph embedding technology is used to convert high-dimensional geological data into low-dimensional vector representation, preserving the spatial relationship and mineralization characteristics between geological units;

[0018] Graph convolutional network analysis: Graph convolutional network is used to analyze the graph structure, extract the spatial characteristics and mineralization properties of geological units, and generate an embedding vector for each geological unit.

[0019] Furthermore, the mineralization probability assessment unit includes:

[0020] Calculation of mineralization probability: Based on the analysis results of graph convolutional networks, the mineralization probability of each geological unit is calculated;

[0021] Prioritization: Rank the geological units according to their mineralization probability and identify areas with high mineralization potential;

[0022] Generation of mineralization potential assessment map: Generate a mineralization potential assessment map to intuitively display areas with high mineralization probability.

[0023] Furthermore, the mineralization probability assessment unit also includes:

[0024] Real-time data update: Combined with the regional geological information collected in real time, the geological unit data set and mineralization potential assessment map are continuously updated;

[0025] Mineral distribution analysis: Based on the updated mineralization potential assessment map, combined with historical data and field measurement data, analyze the mineral distribution and density;

[0026] Resource estimation: Accurately estimate the amount of mineral resources based on the geological characteristics and metallogenic characteristics of the mining area.

[0027] Furthermore,

[0028] Mineralization probability calculation: The embedding vector of each geological unit output by the graph convolutional network is input into the fully connected layer for further processing;

[0029] The fully connected layer maps the input embedding vector through linear transformation and nonlinear activation function to generate the output vector of each node; this process can be expressed as: zi = sigma (W hi + b) where zi is the output vector of node i, hi is the embedding vector of node i, W is the weight matrix, b is the bias vector, and sigma is the activation function;

[0030] Predicting the mineralization probability: The output vector is converted into a probability distribution through the softmax function, and the mineralization probability of each geological unit is calculated; this process can be expressed as: P(yi|zi)=text{softmax}(zi) where P(yi|zi) represents the mineralization probability of node i.

[0031] Furthermore, the evaluation map is generated using visualization tools to intuitively display the mineralization probability of the geological unit; different mineralization probability areas are color-coded to intuitively display areas with high mineralization probability; during the drawing process, different mineralization probability thresholds are set to highlight areas with high mineralization potential.

[0032] A protection method for a mineral resource analysis system in a potential mining area comprises the following steps:

[0033] S1 Data collection steps: Use high-resolution satellite remote sensing technology to collect surface features, geological structure and environmental information of the mining area; set up sampling points in the mining area to collect geological sample data at different depths; obtain geophysical information of the mining area through geophysical methods such as gravity and magnetic measurements and electromagnetic measurements;

[0034] S2 Data preprocessing steps: classify and organize the collected remote sensing data; normalize data from different sources to ensure data consistency and comparability; remove outliers and noise in the data to improve data quality;

[0035] S3 geological unit data set construction steps: integrate various pre-processed data to generate geological unit data sets; record the spatial coordinates and geological age information of geological units to form a multidimensional geological data set;

[0036] S4 Graph structure construction and analysis steps: define the geological unit area as the node in the graph structure, define the edge according to the spatial relationship between the geological units, and assign the corresponding weight; use graph embedding technology to convert high-dimensional geological data into low-dimensional vector representation, retain the spatial relationship and metallogenic characteristics between geological units; use graph convolutional network to analyze the graph structure and extract the spatial characteristics and metallogenic characteristics of geological units;

[0037] S5 Mineralization probability prediction and evaluation steps: Based on the analysis results of the graph convolutional network, the mineralization probability of each geological unit is calculated; the geological units are sorted by mineralization probability to identify areas with high mineralization potential; a mineralization potential assessment map is generated to intuitively display areas with high mineralization probability.

[0038] Compared with the prior art, the present application has the following beneficial effects: the system provides an efficient and accurate method for mineral resource analysis by combining high-resolution remote sensing technology, geological data acquisition and processing, graph structure analysis and mineralization probability prediction, thereby significantly improving the accuracy and reliability of mineralization prediction in potential mining areas.

[0039] This application fully captures the complex spatial relationships and mutual influences between geological units through graph structures, better represents and processes these spatial relationships, and improves the comprehensiveness and accuracy of the analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of the structure of a mineral resource analysis system for a potential mining area disclosed in an embodiment of the present application; DETAILED DESCRIPTION

[0041] In order to make the purpose, technical scheme and advantages of the implementation of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail below in conjunction with the drawings in the embodiment of the present invention. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of the embodiments.

[0042] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0043] The embodiments and directional terms described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0044] Example 1

[0045] like Figure 1 As shown, the present application discloses a mineral resource analysis system for a potential mining area, comprising:

[0046] Potential mining area identification unit, used to determine the type of minerals to be studied and predicted based on relevant local geological information, collect relevant analytical data, and delineate the area to be identified based on the processing and analysis results of the analytical data;

[0047] The geological data collection unit is used to determine the sampling points according to the area to be identified, collect geological sample data and geological information, and generate a geological unit data set;

[0048] Graph structure unit: Based on the geological unit dataset, the embedding vector of each geological unit is obtained;

[0049] Mineralization probability assessment unit: Based on the analysis results of the graph structure, the mineralization probability of each specific geological unit is obtained.

[0050] As an optional solution of this application document, the potential mining area identification unit includes: basic data acquisition module: using high-resolution satellite remote sensing technology to collect surface characteristics, geological structure and environmental information of the mining area; through high-resolution remote sensing images, accurately capture the surface morphology and changes of the mining area, combine multi-spectral and hyperspectral data to identify different geological units and vegetation coverage, and provide detailed geological background information.

[0051] The first data processing module: classify and organize the collected remote sensing data; normalize the data from different sources to ensure data consistency and comparability; remove outliers and noise in the data to improve data quality;

[0052] The specific preprocessing steps are:

[0053] Classify and organize the collected remote sensing data. Classify data from different sources according to their characteristics, including dividing remote sensing data into surface feature images and multispectral data. Through classification and organization, ensure that all types of data are clear and orderly, laying the foundation for subsequent processing and analysis.

[0054] Normalize data from different sources to ensure data consistency and comparability. Since different data sources have different measurement units and ranges, it is necessary to normalize the data. Through normalization, all data are converted to a unified scale to eliminate dimensional differences and ensure comparability between different data. This step is crucial to improving the accuracy and reliability of data analysis.

[0055] Remove outliers and noise from the data to improve data quality. Clean the collected raw data to detect and remove outliers and noise data to improve the overall quality of the data. Statistical analysis and machine learning algorithms can be used to identify and remove these data points that do not conform to normal patterns. The purpose of data cleaning is to ensure the authenticity and accuracy of the data, thereby improving the reliability of subsequent analysis results.

[0056] The first data analysis module is used to process and analyze the data processing results of the first data processing module and define the area to be identified.

[0057] As an optional solution of this application document, the geological data acquisition unit includes: geological data acquisition module: determining and setting up sampling points according to the area to be identified, collecting geological sample data at different depths; obtaining geological information of the mining area through gravity and magnetic measurements and electromagnetic measurements;

[0058] The second data processing module is used to classify the geological sample data and geological information collected by the geological data collection unit, and integrate the data information of adjacent areas in the same layer to generate a geological unit data set.

[0059] As an optional solution of this application document, the figure structure unit:

[0060] Node and edge definition: The geological units in the geological unit dataset are defined as nodes in the graph structure, and the edges are defined according to the spatial relationship between the geological units and the corresponding weights are assigned;

[0061] Graph embedding: Graph embedding technology is used to convert high-dimensional geological data into low-dimensional vector representation, preserving the spatial relationship and mineralization characteristics between geological units;

[0062] Graph convolutional network analysis: Graph convolutional network is used to analyze the graph structure, extract the spatial characteristics and mineralization properties of geological units, and generate an embedding vector for each geological unit.

[0063] As an optional solution of this application document, the mineralization probability assessment unit includes:

[0064] Calculation of mineralization probability: Based on the analysis results of graph convolutional networks, the mineralization probability of each geological unit is calculated;

[0065] Prioritization: Rank the geological units according to their mineralization probability and identify areas with high mineralization potential;

[0066] Generation of mineralization potential assessment map: Generate a mineralization potential assessment map to intuitively display areas with high mineralization probability.

[0067] As an optional solution of this application document, the mineralization probability assessment unit also includes:

[0068] Real-time data update: Combined with the regional geological information collected in real time, the geological unit data set and mineralization potential assessment map are continuously updated;

[0069] Mineral distribution analysis: Based on the updated mineralization potential assessment map, combined with historical data and field measurement data, analyze the mineral distribution and density;

[0070] Resource estimation: Accurately estimate the amount of mineral resources based on the geological characteristics and metallogenic characteristics of the mining area.

[0071] As an optional solution of this application document, mineralization probability calculation: the embedding vector of each geological unit output by the graph convolutional network is input into the fully connected layer for further processing;

[0072] The fully connected layer maps the input embedding vector through linear transformation and nonlinear activation function to generate the output vector of each node; this process can be expressed as: zi = sigma (W hi + b) where zi is the output vector of node i, hi is the embedding vector of node i, W is the weight matrix, b is the bias vector, and sigma is the activation function;

[0073] Predicting the mineralization probability: The output vector is converted into a probability distribution through the softmax function, and the mineralization probability of each geological unit is calculated; this process can be expressed as: P(yi|zi)=text{softmax}(zi) where P(yi|zi) represents the mineralization probability of node i.

[0074] As an optional solution for this application document, a visualization tool is used to generate an assessment map to intuitively display the mineralization probability of the geological unit; different mineralization probability areas are color-coded to intuitively display areas with high mineralization probability; during the drawing process, different mineralization probability thresholds are set to highlight areas with high mineralization potential.

[0075] Example 2

[0076] The present application discloses a protection method for a mineral resource analysis system in a potential mining area, comprising the following steps:

[0077] S1 Data collection steps: Use high-resolution satellite remote sensing technology to collect surface features, geological structure and environmental information of the mining area; set up sampling points in the mining area to collect geological sample data at different depths; obtain geophysical information of the mining area through geophysical methods such as gravity and magnetic measurements and electromagnetic measurements; this step ensures the acquisition of comprehensive and accurate geological and geophysical information, providing high-quality data support for subsequent analysis.

[0078] S2 data preprocessing steps: classify and organize the collected remote sensing data; normalize data from different sources to ensure data consistency and comparability; remove outliers and noise in the data to improve data quality; ensure data consistency and reliability, thereby improving the accuracy of analysis results.

[0079] The steps of constructing the S3 geological unit data set are as follows: integrating various preprocessed data to generate a geological unit data set; recording the spatial coordinates and geological age information of the geological unit to form a multidimensional geological data set; this step integrates various data into a unified platform to facilitate comprehensive analysis and processing, and improve data utilization efficiency.

[0080] S4 graph structure construction and analysis steps: define the geological unit area as the node in the graph structure, define the edge according to the spatial relationship between the geological units, and assign corresponding weights; use graph embedding technology to convert high-dimensional geological data into low-dimensional vector representation, retain the spatial relationship and metallogenic characteristics between geological units; use graph convolutional network to analyze the graph structure and extract the spatial characteristics and metallogenic characteristics of the geological unit; this step improves the accuracy of geological unit analysis and metallogenic prediction through the application of graph structure and graph convolutional network.

[0081] S5 metallogenic probability prediction and evaluation step: Based on the analysis results of the graph convolutional network, calculate the metallogenic probability of each geological unit; sort the geological units by metallogenic probability and identify areas with high metallogenic potential; generate a metallogenic potential evaluation map to intuitively display areas with high metallogenic probability. This step provides a quantitative metallogenic probability prediction method to help identify and evaluate areas with high metallogenic potential and provide guidance for the exploration and development of mineral resources.

[0082] Finally, it should be pointed out that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A mineral resource analysis system for a potential mining area, characterized by: include: Potential mining area identification unit, used to determine the type of minerals to be studied and predicted based on relevant local geological information, collect relevant analytical data, and delineate the area to be identified based on the processing and analysis results of the analytical data; A geological data collection unit is used to determine sampling points according to the area to be identified and collect geological sample data and geological information; Generate geological unit datasets; Graph structure unit: Based on the geological unit dataset, the embedding vector of each geological unit is obtained; Mineralization probability assessment unit: Based on the analysis results of the graph structure, the mineralization probability of each specific geological unit is obtained.

2. A mineral resource analysis system for a potential mining area according to claim 1, characterized in that: The potential mining area identification unit includes: basic data collection module: using high-resolution satellite remote sensing technology to collect surface characteristics, geological structure and environmental information of the mining area; The first data processing module: classify and organize the collected remote sensing data; normalize the data from different sources to ensure data consistency and comparability; remove outliers and noise in the data to improve data quality; The first data analysis module is used to process and analyze the data processing results of the first data processing module and define the area to be identified.

3. The mineral resource analysis system for a potential mining area according to claim 1, characterized in that: The geological data acquisition unit includes: Geological data acquisition module: determine the establishment of sampling points according to the area to be identified, collect geological sample data at different depths; obtain geological information of the mining area through gravity and magnetic measurements and electromagnetic measurements; The second data processing module is used to classify the geological sample data and geological information collected by the geological data collection unit, and integrate the data information of adjacent areas in the same layer to generate a geological unit data set.

4. A mineral resource analysis system for a potential mining area according to claim 1, characterized in that: The second data analysis module: graph structure unit: Node and edge definition: The geological units in the geological unit dataset are defined as nodes in the graph structure, and the edges are defined according to the spatial relationship between the geological units and the corresponding weights are assigned; Graph embedding: Graph embedding technology is used to convert high-dimensional geological data into low-dimensional vector representation, preserving the spatial relationship and mineralization characteristics between geological units; Graph convolutional network analysis: Graph convolutional network is used to analyze the graph structure, extract the spatial characteristics and mineralization properties of geological units, and generate an embedding vector for each geological unit.

5. A mineral resource analysis system for a potential mining area according to claim 4, characterized in that: The mineralization probability assessment unit includes: Calculation of mineralization probability: Based on the analysis results of graph convolutional networks, the mineralization probability of each geological unit is calculated; Prioritization: Rank the geological units according to their mineralization probability and identify areas with high mineralization potential; Generation of mineralization potential assessment map: Generate a mineralization potential assessment map to intuitively display areas with high mineralization probability.

6. The mineral resource analysis system for a potential mining area according to claim 1, characterized in that: The mineralization probability assessment unit also includes: Real-time data update: Combined with the regional geological information collected in real time, the geological unit data set and mineralization potential assessment map are continuously updated; Mineral distribution analysis: Based on the updated mineralization potential assessment map, combined with historical data and field measurement data, analyze the mineral distribution and density; Resource estimation: Accurately estimate the amount of mineral resources based on the geological characteristics and metallogenic characteristics of the mining area.

7. A mineral resource analysis system for a potential mining area according to claim 5, characterized in that: Mineralization probability calculation: The embedding vector of each geological unit output by the graph convolutional network is input into the fully connected layer for further processing; The fully connected layer maps the input embedding vector through linear transformation and nonlinear activation function to generate the output vector of each node; this process can be expressed as: i =sigma, where z i is the output vector of node i, h i is the embedding vector of node i, W is the weight matrix, b is the bias vector, and sigma is the activation function; Predicting the mineralization probability: The output vector is converted into a probability distribution through the softmax function, and the mineralization probability of each geological unit is calculated; this process can be expressed as: P = text{softmax}, where P represents the mineralization probability of node i.

8. The mineral resource analysis system for a potential mining area according to claim 1, characterized in that: Use visualization tools to generate assessment maps to intuitively display the mineralization probability of geological units; color-code different mineralization probability areas to intuitively display areas with high mineralization probability; During the mapping process, different mineralization probability thresholds are set to highlight areas with high mineralization potential.

9. The protection method of a mineral resource analysis system of a potential mining area according to claim 1, characterized in that: The following steps are involved: S1 Data collection steps: Use high-resolution satellite remote sensing technology to collect surface features, geological structure and environmental information of the mining area; set up sampling points in the mining area to collect geological sample data at different depths; obtain geophysical information of the mining area through geophysical methods such as gravity and magnetic measurements and electromagnetic measurements; S2 Data preprocessing steps: classify and organize the collected remote sensing data; normalize data from different sources to ensure data consistency and comparability; remove outliers and noise in the data to improve data quality; S3 geological unit data set construction steps: integrate various pre-processed data to generate geological unit data sets; record the spatial coordinates and geological age information of geological units to form a multidimensional geological data set; S4 Graph structure construction and analysis steps: define the geological unit area as the node in the graph structure, define the edge according to the spatial relationship between the geological units, and assign the corresponding weight; use graph embedding technology to convert high-dimensional geological data into low-dimensional vector representation, retain the spatial relationship and metallogenic characteristics between geological units; use graph convolutional network to analyze the graph structure and extract the spatial characteristics and metallogenic characteristics of geological units; S5 metallogenic probability prediction and evaluation step: Based on the analysis results of the graph convolutional network, the metallogenic probability of each geological unit is calculated; Sort geological units by mineralization probability to identify areas with high mineralization potential; generate mineralization potential assessment maps to visually display areas with high mineralization probability.

Images