Mineral product multi-scale progressive prospecting prediction method based on big data
Through big data analysis and multi-scale progressive methods, combined with geological, geophysical and geochemical information, a three-dimensional model was constructed, which solved the systematic and accuracy problems of traditional mineral prospecting predictions and achieved accurate prediction and efficient management of mineral resource distribution characteristics.
Patent Information
- Application Number
- CN202510825442.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-19
- Publication Date
- 2025-09-12
AI Technical Summary
Traditional mineral exploration and prediction methods rely on the experience and intuition of geologists, lack systematicity and accuracy, and find it difficult to fully and deeply mine and utilize the information in geological data.
A multi-scale progressive mineral prospecting and prediction method based on big data is adopted, including data collection, preprocessing, cluster analysis, association rule mining and three-dimensional model construction. Combined with macro-, meso- and micro-scale analysis, an integrated three-dimensional model of stratum-structure-ore body is constructed to gradually narrow the prediction range and improve the prediction accuracy.
It has achieved a comprehensive disclosure of the distribution characteristics and enrichment patterns of mineral resources, improved the accuracy and efficiency of mineral prospecting, enhanced the availability and reliability of data, and provided a scientific basis for the development and utilization of mineral resources.
Smart Images
Figure CN120632508A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of progressive prospecting and prediction, and in particular to a multi-scale progressive prospecting and prediction method for mineral resources based on big data. Background Art
[0002] Mineral prospecting is the estimation or inference of unknown characteristics of past mineralization events. The prediction process is essentially a rigorous scientific and logical thinking process, including observation, analysis, induction, deduction, and reasoning. Mineralization prediction is based on geological spatiotemporal big data.
[0003] This involves a series of theories, methods, and key technologies related to the fourth paradigm of scientific research and geological data science. Establishing a workflow for the aggregation, integration, fusion, mining, and evaluation of geological big data that is suitable for prediction work will be of great help in conducting solid mineral prospecting and prediction work.
[0004] However, traditional prospecting and prediction methods often rely on the experience and intuition of geologists, lacking systematicity and accuracy. In addition, due to the complexity and diversity of geological data, traditional data processing methods find it difficult to comprehensively and deeply mine and utilize the information in these data.
[0005] Therefore, a more scientific, systematic and efficient prospecting prediction method is needed to solve these problems. Summary of the Invention
[0006] The purpose of the present invention is to provide a multi-scale progressive prospecting and prediction method for mineral resources based on big data to solve the problems raised in the above background technology.
[0007] To achieve the above objectives, the present invention provides the following technical solution: a multi-scale progressive prospecting prediction method for mineral resources based on big data, the method comprising the following steps: Step 1: Obtain geological survey data, geophysical data, geochemical data, remote sensing data, and known mineral point information data within the administrative area from various channels, and perform pre-processing steps, including data cleaning, format standardization, and data integration, to ensure data quality and consistency; Step 2: Based on data preprocessing, big data analysis techniques, including cluster analysis and association rule mining, are used to reveal the spatial distribution patterns of mineral resources and their correlation characteristics; Step 3: Based on the revealed spatial distribution patterns and correlation characteristics, an integrated three-dimensional model of "stratum-structure-ore body" is constructed to support the simulation of the spatial distribution of ore bodies. The model comprehensively considers geological, geophysical and geochemical information at different scales; Step 4: By constructing an integrated three-dimensional model of "stratum-structure-ore body", a progressive prediction of potential mineral resource areas is carried out. A preliminary prediction of the entire study area is made at the macro scale to screen out possible mineral resource-rich areas. The preliminary prediction results are further refined at the meso scale to determine the specific distribution range of mineral resources. Step 5: Make high-precision predictions on the distribution range of refined mineral resources at the micro scale, combine geological exploration data, and accurately define the location and shape of the ore body, thereby improving the accuracy and reliability of prospecting predictions.
[0008] Preferably, the data collection terminal includes a geological survey data module, a geophysical data module, a geochemical data module, a remote sensing data module and a mineral point information data module; The geological survey data module is used to collect basic information on geology, landforms, and rocks within the administrative area, as well as historical survey information and data; The geophysical data module is used to collect geophysical field data of the geomagnetic field, gravity field and electromagnetic field within the administrative area, as well as related geophysical exploration information and data; The geophysical data module collection formula is as follows: ; in, Represents the standardized value, that is, the original data Converted to a value under the standard normal distribution, is a specific observation in the original data set, Represents the mean of the original data set, which describes the center position of the data set. It is the standard deviation of the original data set, reflecting the degree of dispersion of the data relative to the mean.
[0009] Preferably, the geochemical data module is used to collect various element content data obtained from geochemical exploration within the administrative area; The remote sensing data module is used to collect mineral distribution image data taken by remote sensing satellites within the administrative area, and the data contains spectral information of different bands; The mineral point information numerical control module is used to integrate and analyze mineral point information data within the administrative area. The data covers the geographical location, mineral type, reserve estimation and historical exploration records of the mineral points.
[0010] Preferably, the data collection terminal includes a data preprocessing module; The data preprocessing module is used to perform preliminary cleaning and sorting of the collected geological exploration data, geophysical data, geochemical data, remote sensing data and mineral information data, remove outliers and duplicate data, and ensure the quality and accuracy of the data; The data preprocessing module performs format unification and standardization processing on the data The data preprocessing module uses the following formula: ; in, is the original data value, The minimum value in the original data is the maximum value in the original data, is the data value after normalization transformation.
[0011] Preferably, the data analysis terminal includes a cluster analysis module and an association rule mining module; The cluster analysis module is used to perform cluster analysis on the data values after normalization transformation, and by setting appropriate clustering parameters, group the data values with high similarity into one category, thereby discovering the potential laws and patterns in the data; The cluster analysis module includes K-means clustering and hierarchical clustering; The association rule mining module is used to mine the association relationship between data and find appropriate association rules from a large amount of data by setting appropriate support and confidence parameters; The association rule mining module uses the classic Apriori algorithm or FP-Growth algorithm to mine association rules.
[0012] Preferably, the model building end includes a model building module; The model building module is used to build an integrated three-dimensional model of the stratum-structure-ore body of mineral resources based on the results of the cluster analysis module and the association rule mining module; The model building module uses machine learning algorithms, including support vector machines, random forests, and neural networks, to perform deep learning and training on the data.
[0013] Preferably, the multi-scale prediction and analysis terminal includes a macro-scale module and a meso-scale module; The macro-scale module is used to perform macro-prediction and analysis on the overall distribution of mineral resources; The macro-scale module is used to conduct comprehensive analysis of geological, geophysical, and geochemical big data within the administrative area, combining geological historical evolution and plate tectonic theory geological knowledge to reveal the macro-distribution patterns and trends of mineral resources.
[0014] Preferably, the mesoscale module is used to perform more detailed mesoscale prediction and analysis of specific mineral resource-rich areas; The mesoscale module integrates high-resolution geological exploration data, remote sensing image data and microscopic characteristic information of mineral resources, and uses advanced geographic information system technology and spatial analysis methods to reveal the detailed distribution characteristics, enrichment patterns and ore-controlling factors of mineral resources in a specific area; The mesoscale module combines geological information on geological structure, magma activity and fluid migration to perform predictive analysis.
[0015] Preferably, the microscopic scale is used for refined microscopic prediction and analysis of mineral resource-rich areas; The microscopic scale uses high-precision instruments to conduct detailed tests on the chemical composition, physical properties and isotopic composition of rocks, minerals and fluid geological samples, combined with advanced micro-analysis techniques and data processing methods to reveal the microscopic genesis mechanism, occurrence state and distribution characteristics of mineral resources.
[0016] Preferably, the microscopic scale is also combined with microscopic information of geological microstructures, mineral assemblages and fluid inclusions to conduct in-depth research and predictive analysis.
[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention provides a more comprehensive and systematic method for mineral prospecting and prediction. By combining macro-scale, meso-scale and micro-scale analysis, it can more accurately reveal the distribution characteristics and enrichment patterns of mineral resources, thereby improving the accuracy and efficiency of prospecting. Moreover, under the action of the data collection end, the geological, physical and chemical multi-source heterogeneous data within the administrative area are efficiently integrated and managed, the standardization and normalization of data are realized, the availability and reliability of data are enhanced, and a solid foundation for mineral prediction is provided. Through intelligent data analysis and mining technology, the present invention automatically identifies key geological anomaly information and mineral resource characteristics, further improving the scientificity and accuracy of the prediction.
[0018] 2. This invention, by integrating a variety of geological information and data and utilizing advanced geographic information system technology and spatial analysis methods, achieves detailed prediction and analysis of mineral resources in a specific area, providing a scientific basis for the development and utilization of mineral resources. In addition, this method fully considers the complexity of the geological environment and the diversity of mineral resources, and through a multi-scale progressive analysis strategy, gradually narrows the prediction range, thereby improving the pertinence and practicality of the prediction results.
[0019] 3. This invention, through the use of high-precision instruments and micro-analysis technology, has conducted in-depth research on the microscopic genesis mechanism and occurrence state of mineral resources, providing technical support for the refined development and comprehensive utilization of mineral resources. At the same time, this method combines geostatistics and geological modeling technology to construct a three-dimensional geological model of mineral resources, which intuitively demonstrates the spatial distribution and enrichment characteristics of mineral resources, providing an intuitive and scientific basis for decision makers. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0021] Figure 1 This is a flow chart of a multi-scale progressive mineral prospecting prediction method based on big data of the present invention; Figure 2 This is a data collection terminal architecture diagram of a multi-scale progressive mineral prospecting prediction method based on big data of the present invention; Figure 3 This is a data analysis end architecture diagram of a multi-scale progressive mineral prospecting prediction method based on big data of the present invention; Figure 4 This is a model framework diagram of a multi-scale progressive mineral prospecting prediction method based on big data of the present invention; Figure 5 This is a multi-scale prediction and analysis terminal architecture diagram of a multi-scale progressive mineral prospecting prediction method based on big data of the present invention. DETAILED DESCRIPTION
[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0023] See also Figures 1 to 5 , the present invention provides a technical solution: A multi-scale progressive prospecting and prediction method for mineral resources based on big data. Example 1, please refer to Figure 1 As shown, the method includes the following steps: Step 1: Obtain geological survey data, geophysical data, geochemical data, remote sensing data, and known mineral point information data within the administrative area from various channels, and perform pre-processing steps, including data cleaning, format standardization, and data integration, to ensure data quality and consistency; Step 2: Based on data preprocessing, big data analysis techniques, including cluster analysis and association rule mining, are used to reveal the spatial distribution patterns of mineral resources and their correlation characteristics; Step 3: Based on the revealed spatial distribution patterns and correlation characteristics, an integrated three-dimensional model of "stratum-structure-ore body" is constructed to support the simulation of the spatial distribution of ore bodies. The model comprehensively considers geological, geophysical and geochemical information at different scales; Step 4: By constructing an integrated three-dimensional model of "stratum-structure-ore body", a progressive prediction of potential mineral resource areas is carried out. A preliminary prediction of the entire study area is made at the macro scale to screen out possible mineral resource-rich areas. The preliminary prediction results are further refined at the meso scale to determine the specific distribution range of mineral resources. Step 5: Make high-precision predictions on the distribution range of refined mineral resources at the micro scale, combine geological exploration data, and accurately define the location and shape of the ore body, thereby improving the accuracy and reliability of prospecting predictions.
[0024] Example 2, please refer to Figure 2-3 As shown, the data collection end includes a geological survey data module, a geophysical data module, a geochemical data module, a remote sensing data module, and a mineral point information data module; The geological survey data module is used to collect basic information on geology, landforms, and rocks within the administrative area, as well as historical survey information and data; The geophysical data module is used to collect geophysical field data of the geomagnetic field, gravity field and electromagnetic field within the administrative area, as well as related geophysical exploration information and data; The geophysical data module collection formula is as follows: ; in, Represents the standardized value, that is, the original data Converted to a value under the standard normal distribution, is a specific observation in the original data set, Represents the mean of the original data set, which describes the center position of the data set. It is the standard deviation of the original data set, reflecting the degree of dispersion of the data relative to the mean.
[0025] The geochemical data module is used to collect various element content data obtained from geochemical exploration within the administrative area; The remote sensing data module is used to collect mineral distribution image data taken by remote sensing satellites within the administrative area. The data contains spectral information of different bands; The mineral point information CNC module is used to integrate and analyze mineral point information data within the administrative area. The data covers the geographical location of the mineral point, mineral type, reserve estimation and historical exploration records.
[0026] The data collection end includes a data preprocessing module; The data preprocessing module is used to perform preliminary cleaning and sorting of the collected geological exploration data, geophysical data, geochemical data, remote sensing data and mineral information data, remove outliers and duplicate data, and ensure the quality and accuracy of the data; The data preprocessing module unifies and standardizes the data format The data preprocessing module uses the following formula: ; in, is the original data value, The minimum value in the original data is the maximum value in the original data, is the data value after normalization transformation.
[0027] The data analysis end includes a cluster analysis module and an association rule mining module; The cluster analysis module is used to perform cluster analysis on the data values after normalization transformation. By setting appropriate clustering parameters, data values with high similarity are grouped into one category, thereby discovering the potential laws and patterns in the data; The cluster analysis module includes K-means clustering and hierarchical clustering; The association rule mining module is used to mine the association relationship between data and find appropriate association rules from a large amount of data by setting appropriate support and confidence parameters; The association rule mining module uses the classic Apriori algorithm or FP-Growth algorithm to mine association rules.
[0028] Example 3, please refer to Figure 4-5 As shown, the model building end includes a model building module; The model building module is used to construct an integrated three-dimensional model of mineral resources (stratum-structure-ore body) based on the results of the cluster analysis module and the association rule mining module; The model building module uses machine learning algorithms, including support vector machines, random forests, and neural networks, to perform deep learning and training on data.
[0029] The multi-scale prediction and analysis end includes a macro-scale module and a meso-scale module; The macro-scale module is used to conduct macro-prediction and analysis of the overall distribution of mineral resources; The macro-scale module is used to conduct comprehensive analysis of geological, geophysical, and geochemical big data within the administrative area, combining geological historical evolution and plate tectonic theory geological knowledge to reveal the macro-distribution patterns and trends of mineral resources.
[0030] The mesoscale module is used to conduct more detailed mesoscale prediction and analysis of specific mineral resource-rich areas; The mesoscale module integrates high-resolution geological exploration data, remote sensing image data, and microscopic characteristic information of mineral resources, and uses advanced geographic information system technology and spatial analysis methods to reveal the detailed distribution characteristics, enrichment patterns, and ore-controlling factors of mineral resources in a specific area. The mesoscale module combines geological information on geological structure, magma activity and fluid migration for predictive analysis.
[0031] The micro-scale is used for detailed micro-prediction and analysis of mineral resource-rich areas; At the micro scale, high-precision instruments are used to conduct detailed tests on the chemical composition, physical properties and isotopic composition of rock, mineral and fluid geological samples, combined with advanced micro-analysis techniques and data processing methods to reveal the microscopic genesis mechanism, occurrence state and distribution characteristics of mineral resources.
[0032] The microscopic scale also combines the microscopic information of geological microstructure, mineral combination and fluid inclusions for in-depth research and predictive analysis.
[0033] The present invention provides a more comprehensive and systematic mineral prospecting and prediction method. By combining macro-scale, meso-scale and micro-scale analysis, it more accurately reveals the distribution characteristics and enrichment laws of mineral resources, improves the accuracy and efficiency of prospecting, and, under the action of the data collection end, efficiently integrates and manages geological, physical and chemical multi-source heterogeneous data within the administrative area, realizes data standardization and normalized processing, enhances data availability and reliability, and provides a solid foundation for mineral prediction. Through intelligent data analysis and mining technology, the present invention automatically identifies key geological anomaly information and mineral resource characteristics, further improving the scientificity and accuracy of the prediction; by integrating a variety of geological information and data, and utilizing advanced geographic information system technology and spatial analysis methods, it realizes detailed prediction and analysis of mineral resources in a specific area, providing a scientific basis for the development and utilization of mineral resources; in addition, the method also fully considers the complexity of the geological environment and the diversity of mineral resources, and through a multi-scale progressive analysis strategy, gradually narrows the prediction range, and improves the pertinence and practicality of the prediction results.
[0034] By using high-precision instruments and micro-analysis technology, we have conducted in-depth research on the microscopic genesis mechanism and occurrence state of mineral resources, providing technical support for the refined development and comprehensive utilization of mineral resources. At the same time, this method combines geostatistics and geological modeling technology to construct a three-dimensional geological model of mineral resources, which intuitively shows the spatial distribution and enrichment characteristics of mineral resources, providing an intuitive and scientific basis for decision makers. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A multi-scale progressive mineral prospecting prediction method based on big data, characterized by: The method comprises the following steps: Step 1: Obtain geological survey data, geophysical data, geochemical data, remote sensing data, and known mineral point information data within the administrative area from various channels, and perform pre-processing steps, including data cleaning, format standardization, and data integration, to ensure data quality and consistency; Step 2: Based on data preprocessing, big data analysis techniques, including cluster analysis and association rule mining, are used to reveal the spatial distribution patterns of mineral resources and their correlation characteristics; Step 3: Based on the revealed spatial distribution patterns and correlation characteristics, an integrated three-dimensional model of "stratum-structure-ore body" is constructed to support the simulation of the spatial distribution of the ore body. The model comprehensively considers geological, geophysical, and geochemical information at different scales; Step 4: By constructing an integrated three-dimensional model of "stratum-structure-ore body", a progressive prediction of potential mineral resource areas is carried out. At the macroscale, a preliminary prediction is made for the entire study area to screen out possible mineral resource-rich areas. At the mesoscale, the preliminary prediction results are further refined to determine the specific distribution range of mineral resources. Step 5: Make high-precision predictions on the distribution range of refined mineral resources at the micro scale, combine geological exploration data, and accurately define the location and shape of the ore body, thereby improving the accuracy and reliability of prospecting predictions.
2. The method for multi-scale progressive prospecting and prediction of mineral resources based on big data according to claim 1, characterized in that: The data collection terminal includes a geological survey data module, a geophysical data module, a geochemical data module, a remote sensing data module and a mineral point information data module; The geological survey data module is used to collect basic information on geology, landforms, and rocks within the administrative area, as well as historical survey information and data; The geophysical data module is used to collect geophysical field data of the geomagnetic field, gravity field and electromagnetic field within the administrative area, as well as related geophysical exploration information and data; The geophysical data module collection formula is as follows: ； in, Represents the standardized value, that is, the original data Converted to a value under the standard normal distribution, is a specific observation in the original data set, Represents the mean of the original data set, which describes the center position of the data set. It is the standard deviation of the original data set, reflecting the degree of dispersion of the data relative to the mean.
3. The multi-scale progressive prospecting prediction method for mineral resources based on big data according to claim 2, characterized in that: The geochemical data module is used to collect various element content data obtained from geochemical exploration within the administrative area; The remote sensing data module is used to collect mineral distribution image data taken by remote sensing satellites within the administrative area, and the data contains spectral information of different bands; The mineral point information numerical control module is used to integrate and analyze mineral point information data within the administrative area. The data covers the geographical location, mineral type, reserve estimation and historical exploration records of the mineral points.
4. The method for multi-scale progressive prospecting and prediction of mineral resources based on big data according to claim 2, characterized in that: The data collection terminal includes a data preprocessing module; The data preprocessing module is used to perform preliminary cleaning and sorting of the collected geological exploration data, geophysical data, geochemical data, remote sensing data and mineral information data, remove outliers and duplicate data, and ensure the quality and accuracy of the data; The data preprocessing module performs format unification and standardization processing on the data; The data preprocessing module uses the following formula: ； in, is the original data value, The minimum value in the original data is the maximum value in the original data, is the data value after normalization transformation.
5. The multi-scale progressive prospecting prediction method for mineral resources based on big data according to claim 1, characterized in that: The data analysis end includes a cluster analysis module and an association rule mining module; The cluster analysis module is used to perform cluster analysis on the data values after normalization transformation, and by setting appropriate clustering parameters, group the data values with high similarity into one category, thereby discovering the potential laws and patterns in the data; The cluster analysis module includes K-means clustering and hierarchical clustering; The association rule mining module is used to mine the association relationship between data and find appropriate association rules from a large amount of data by setting appropriate support and confidence parameters; The association rule mining module uses the classic Apriori algorithm or FP-Growth algorithm to mine association rules.
6. The multi-scale progressive prospecting prediction method for mineral resources based on big data according to claim 1, characterized in that: The model building end includes a model building module; The model building module is used to build an integrated three-dimensional model of the stratum-structure-ore body of mineral resources based on the results of the cluster analysis module and the association rule mining module; The model building module uses machine learning algorithms, including support vector machines, random forests, and neural networks, to perform deep learning and training on the data.
7. The multi-scale progressive prospecting prediction method for mineral resources based on big data according to claim 1, characterized in that: The multi-scale prediction and analysis terminal includes a macro-scale module and a meso-scale module; The macro-scale module is used to perform macro-prediction and analysis on the overall distribution of mineral resources; The macro-scale module is used to conduct comprehensive analysis of geological, geophysical, and geochemical big data within the administrative area, combining geological historical evolution and plate tectonic theoretical geological knowledge to reveal the macro-distribution patterns and trends of mineral resources.
8. The multi-scale progressive prospecting prediction method for mineral resources based on big data according to claim 7, characterized in that: The mesoscale module is used to conduct more detailed mesoscale prediction and analysis of specific mineral resource-rich areas; The mesoscale module integrates high-resolution geological exploration data, remote sensing image data and microscopic characteristic information of mineral resources, and uses advanced geographic information system technology and spatial analysis methods to reveal the detailed distribution characteristics, enrichment patterns and ore-controlling factors of mineral resources in a specific area; The mesoscale module combines geological information on geological structure, magma activity and fluid movement to perform predictive analysis.
9. The multi-scale progressive prospecting and prediction method for mineral resources based on big data according to claim 1, characterized in that: The microscopic scale is used for detailed microscopic prediction and analysis of mineral resource-rich areas; The microscopic scale uses high-precision instruments to conduct detailed tests on the chemical composition, physical properties and isotopic composition of rocks, minerals and fluid geological samples, combined with advanced micro-analysis techniques and data processing methods to reveal the microscopic genesis mechanism, occurrence state and distribution characteristics of mineral resources.
10. The multi-scale progressive prospecting and prediction method for mineral resources based on big data according to claim 9, characterized in that: The microscopic scale also combines the microscopic information of geological microstructure, mineral combination and fluid inclusion to conduct in-depth research and predictive analysis.