Intelligent evaluation method and system for mineral resource exploration and storage medium

Abstract

The invention relates to the technical field of mineral exploration, and discloses an intelligent evaluation method and system for mineral resource exploration and a storage medium. The method comprises the steps of obtaining multi-source geological data of a to-be-evaluated area, dividing remote sensing physical data into first remote sensing physical data corresponding to a sampling point and second remote sensing physical data not corresponding to the sampling point, and constructing a preset model based on geological exploration data and the first remote sensing physical data, the model is used for estimating geological exploration data of a virtual sampling point, the estimated data and original data are combined to generate new multi-source geological data, a first geological space structure and a plurality of second geological space structures are respectively generated through two preset geological modeling methods, and the space structure closest to the first geological space structure is selected as a reference; according to the method, the reference geological space structure is analyzed, the mineral average abundance and the ore volume are calculated, then the mineral resource reserves are predicted and evaluated, the mineral resource evaluation accuracy and efficiency are improved, and the exploration cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mineral exploration, and in particular to an intelligent evaluation method and system for mineral resource exploration and a storage medium. BACKGROUND

[0002] With the rapid development of the global economy, the demand for mineral resources continues to grow. Traditional methods of mineral resource exploration mainly rely on the experience of geologists and field exploration, which not only consumes time and effort, but also limits the accuracy and efficiency of exploration under complex geological conditions. In recent years, with the rapid development of emerging technologies such as artificial intelligence, big data, and the Internet of Things, new opportunities have been brought to the field of mineral resource exploration. Using intelligent technology to evaluate mineral resources can more efficiently integrate multi-source data, improve the accuracy of exploration, reduce the cost of exploration, shorten the exploration cycle, and better meet the demand for efficient development and utilization of mineral resources in modern society.

[0003] Similar prior art includes Chinese patent application CN117392337A, which discloses a digitalized mineral exploration method based on AI. According to the element detection data in the area to be predicted, the mineral to be predicted is determined. According to the distribution of the mineral to be predicted in the area to be predicted, the size of each grid corresponding to the mineral to be predicted is determined, and the area to be predicted is converted into a gridded image according to the determined grid size. According to the actual situation of the geological map, the description vector corresponding to each grid is determined. According to the coupling relationship between the grids, the description vector corresponding to each grid is expanded. The description vector of each grid is brought into the corresponding grid to form a gridded geological map. The gridded geological map is input into a mineral identification model to obtain a mineral prediction result. A mineral distribution map is generated through the mineral prediction result. This method predicts the probability of each grid containing the mineral to be predicted through the gridded geological map and the multi-branch convolutional neural network model, but does not evaluate the mineral content in the area to be predicted. Chinese patent application CN119204462A discloses an intelligent mineral resource exploration evaluation system. Geological mineral exploration related data is collected from multiple data sources. The data is preprocessed to obtain preprocessed data. According to the preprocessed data, the rock physical properties and the stress state of the geological structure of the exploration area are analyzed to obtain the correlation between the rock physical properties and the stress state of the geological structure. According to the correlation between the rock physical properties and the stress state of the geological structure, a dynamic adjustment coefficient is calculated. The dynamic adjustment coefficient is used to estimate the mineral resource reserves. The mineral resource reserves are evaluated to obtain the final evaluation result. This method estimates and evaluates the mineral resource reserves by analyzing the rock physical properties and the stress state of the geological structure, but the precision and accuracy are not enough when facing complex geological conditions.

[0004] Therefore, it is an urgent problem to provide an intelligent evaluation method and system for mineral resource exploration and a storage medium to improve the accuracy and reliability of mineral resource exploration evaluation. SUMMARY

[0005] The present application provides an intelligent evaluation method and system for mineral resource exploration and a storage medium for improving the efficiency and accuracy of mineral resource evaluation.

[0006] In a first aspect, the present application provides an intelligent evaluation method for mineral resource exploration, which comprises: Step 1, obtaining multi-source geological data of the area to be evaluated, the multi-source geological data comprising remote sensing physical data, remote sensing image data, drilling data, geological structure data and geological exploration data; Step 2, defining the data corresponding to the sampling points of the geological exploration data in the remote sensing physical data as first remote sensing physical data, and the data not corresponding to the sampling points as second remote sensing physical data, constructing a preset model based on the geological exploration data and the first remote sensing physical data, inputting the second remote sensing physical data into the preset model, and obtaining estimated geological exploration data at the virtual sampling points in the area to be evaluated; Step 3, adding the estimated geological exploration data to the multi-source geological data to generate first multi-source geological data, and deleting the second remote sensing physical data from the multi-source geological data to generate second multi-source geological data; Step 4, generating a first geological spatial structure of the area to be evaluated based on the first multi-source geological data by a first preset geological modeling method, generating N1 second geological spatial structures based on the second multi-source geological data by a second preset geological modeling method, and selecting a spatial structure closest to the first geological spatial structure from all the second geological spatial structures as a reference geological spatial structure; Step 5, analyzing the reference geological spatial structure to obtain the average abundance of minerals and the volume of ores, and calculating the predicted reserves of mineral resources in the area to be evaluated based on the average abundance of minerals and the volume of ores; Step 6, evaluating the predicted reserves of mineral resources to obtain the final evaluation result.

[0007] In combination with the first aspect, in a first implementation manner of the first aspect of the present application, step 2 comprises: Step 21, performing serialization processing on the geological exploration data based on the measured values of specific elements, setting a demarcation point, and dividing the serialized geological exploration data into N2 first data sets based on the demarcation point; Step 22, dividing the first remote sensing physical data into N2 first data sets based on the sampling points corresponding to the geological exploration data in each first data set to generate second data sets, and obtaining N2 second data sets after traversing all the first data sets; Step 23, training the N2 second data sets to generate a first model for identifying the data set to which the first remote sensing physical data belongs, and meanwhile, training each second data set respectively to construct a preset model corresponding to each second data set for predicting the geological exploration data based on the first remote sensing physical data; Step 24, dividing the second remote sensing physical data into different data sets using the first model, defining as attribution data sets, extracting any attribution data set, inputting the data in any attribution data set into the corresponding preset model, and obtaining the estimated geological exploration data corresponding to each data in any attribution data set.

[0008] With reference to the first aspect, in a second implementation manner of the first aspect of the present application, in step 21, the setting method of the demarcation point is as follows: Step 211, performing a predetermined algorithm on the measurement values corresponding to the specific element to generate transformed values, identifying the second quantile of all the transformed values, extracting the transformed values within a first preset range before and after the second quantile to generate a reference data set; Step 212, performing fitting processing on the data in the reference data set based on a preset mathematical method to generate a fitting line, and defining the value corresponding to each sampling point on the fitting line as a fitting value; Step 213, calculating the difference between the transformed value and the fitting value of each sampling point in the reference data set, and calculating the average value of the squares of all the differences, and defining the square root of the average value as a dispersion degree value; Step 214, setting a fluctuation range based on the second quantile and the dispersion degree value, setting the measurement value corresponding to the maximum transformed value within the fluctuation range as the first demarcation point, and setting the measurement value corresponding to the minimum transformed value within the fluctuation range as the second demarcation point.

[0009] With reference to the first aspect, in a third implementation manner of the first aspect of the present application, after step 2, the following steps are included: Step 11, extracting all the measurement values corresponding to the specific element from the geological exploration data, and deleting the values less than a first preset value from all the measurement values to generate a first to-be-analyzed value set; Step 12, obtaining the content range and the average content value of the specific element in the earth crust in the background area, and setting a reference value based on the content range, wherein the to-be-evaluated area is contained in the background area; Step 13, deleting the values greater than the reference value from the first to-be-analyzed value set to generate a second to-be-analyzed value set, taking the average content value as the average value of the second to-be-analyzed value set, and judging whether the second to-be-analyzed value set satisfies a preset distribution rule, if not, entering step 14, and if yes, entering step 15; Step 14, reducing the reference value by a second preset value to generate a new reference value, and defining the second set of to-be-analyzed values as the first set of to-be-analyzed values, and then returning to step 13; Step 15, defining the maximum value of the second set of to-be-analyzed values as the critical value of the specific element.

[0010] With reference to the first aspect, in a fourth implementation manner of the first aspect of the present application, step 3 comprises: traversing the first remote sensing physical data, and defining, as first redundant data, the geological exploration data corresponding to any sampling point and the first remote sensing physical data corresponding to the sampling point, when the measured value of the specific element corresponding to the sampling point is less than the critical value, and deleting the first redundant data from the second multi-source geological data to generate new second multi-source geological data; traversing the estimated geological exploration data, and defining, as second redundant data, the estimated geological exploration data corresponding to any virtual sampling point and the second remote sensing physical data corresponding to the virtual sampling point, when the measured value of the specific element corresponding to the virtual sampling point is less than the critical value, and deleting the first redundant data and the second redundant data from the first multi-source geological data to generate new first multi-source geological data.

[0011] With reference to the first aspect, in a fifth implementation manner of the first aspect of the present application, step 4 comprises: Step 41, performing feature extraction on the first feature parameter of each second geological space structure respectively, reducing the total number of first feature parameters to a preset number, and obtaining a low-dimensional space structure corresponding to each second geological space structure; Step 42, performing value assignment processing on the non-numerical parameter in each low-dimensional space structure based on a preset rule, then performing standardization processing on the second feature parameter of all low-dimensional space structures, calculating the Euclidean distance between any two low-dimensional space structures based on the standardization processing result, grouping all second geological space structures based on the Euclidean distance, and obtaining N3 space structure sets; Step 43, performing deposit geological feature extraction on all geological space structures, and respectively obtaining first ore body attribute parameters and second ore body attribute parameters corresponding to the first geological space structure and each second geological space structure; Step 44, extracting any space structure set, and performing statistical analysis on the second ore body attribute parameters of all second geological space structures in the space structure set to obtain third ore body attribute parameters of the space structure set; Step 45: After traversing all spatial structure sets, define the spatial structure set corresponding to the third ore body attribute parameter having the greatest similarity to the first ore body attribute data as a specific structure set, perform mineral resource assessment on the first geological spatial structure and each third geological spatial structure, and obtain the first mineral resource statistical parameter and the second mineral resource statistical parameter, wherein the third geological spatial structure is the second geological spatial structure included in the specific structure set; Step 46: Define the third geological spatial structure corresponding to the second mineral resource statistical parameter having the greatest similarity to the first mineral resource statistical parameter as a reference geological spatial structure.

[0012] In combination with the first aspect, in a sixth implementation of the first aspect of the present application, step 42 further includes: Calculating the ratio of the total number to N3; when the ratio is greater than a second preset range, dividing the area to be evaluated into N3 sub-evaluation areas, dividing the first multi-source geological data and the second multi-source geological data into different sub-evaluation areas, and then returning to step 4 to perform mineral reserve prediction for each sub-evaluation area; When the ratio is less than the second preset range, a new sampling point is generated based on the coordinates of the existing sampling point, and geological data is collected for the new sampling point. After the collection is completed, the process returns to step 1.

[0013] In a second aspect, the present application provides an intelligent assessment system for mineral resource exploration, the system comprising: A data acquisition module is used to acquire multi-source geological data of the area to be assessed, wherein the multi-source geological data includes remote sensing physical data, remote sensing image data, drilling data, geological structure data and geological exploration data; a data filling module, configured to define data in the remote sensing physical data corresponding to sampling points of the geological exploration data as first remote sensing physical data, and data not corresponding to the sampling points as second remote sensing physical data, construct a preset model based on the geological exploration data and the first remote sensing physical data, input the second remote sensing physical data into the preset model, and obtain estimated geological exploration data at virtual sampling points in the area to be evaluated; a data grouping module, configured to add the estimated geological exploration data to the multi-source geological data to generate first multi-source geological data, and delete the second remote sensing physical data from the multi-source geological data to generate second multi-source geological data; a spatial structure generation module, configured to generate a first geological spatial structure of the area to be evaluated based on the first multi-source geological data using a first preset geological modeling method, generate N1 second geological spatial structures based on the second multi-source geological data using a second preset geological modeling method, and select, from all the second geological spatial structures, a spatial structure that is closest to the first geological spatial structure as a reference geological spatial structure; The reserve prediction module is configured to analyze the reference geological space structure, obtain the average abundance of minerals and the volume of ores, and calculate the predicted reserve of mineral resources in the to-be-evaluated area based on the average abundance of minerals and the volume of ores. The intelligent evaluation module is configured to evaluate the predicted reserve of mineral resources and obtain a final evaluation result.

[0014] The third aspect of the present application provides a computer-readable storage medium, which stores instructions, when the instructions are executed on a computer, the computer executes the above-mentioned intelligent evaluation method for mineral resource exploration.

[0015] Compared with the prior art, the technical scheme of the present application has at least the following advantages: 1. By integrating various data sources such as remote sensing physical data, remote sensing image data, drilling data, geological structure data and geological exploration data, the geological characteristics of the to-be-evaluated area can be more comprehensively reflected, which helps to build a comprehensive and detailed geological space structure model.

[0016] 2. Based on the existing data, a preset model is constructed based on the geological exploration data and the first remote sensing physical data, and the geological exploration data at the virtual sampling points is predicted based on the preset model, which improves the completeness and accuracy of the data, and can improve the data coverage range and accuracy while reducing the sampling cost.

[0017] 3. The first geological space structure and a plurality of second geological space structures are generated based on different first multi-source geological data and second multi-source geological data, and the second geological space structure closest to the first geological space structure is selected as the reference geological space structure closest to the actual situation based on similarity analysis, which reduces the deviation of a single model and improves the accuracy and reliability of the reserve prediction of mineral resources. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 An embodiment schematic diagram of the intelligent evaluation method for mineral resource exploration in the embodiment of the present application; Figure 2 An embodiment schematic diagram of the generation method of the estimated geological exploration data in the embodiment of the present application; Figure 3 An embodiment schematic diagram of the new sampling point setting in the embodiment of the present application; Figure 4 An embodiment of the intelligent evaluation system for mineral resource exploration in the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0020] The embodiments of the present application provide an intelligent evaluation method, system and storage medium for mineral resource exploration. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variation thereof is intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0021] For ease of understanding, the specific process of the embodiments of the present application is described below. Please refer to Figure 1 An embodiment of the intelligent evaluation method for mineral resource exploration in the embodiments of the present application includes: Step 1, obtaining multi-source geological data of the area to be evaluated, the multi-source geological data including remote sensing physical data, remote sensing image data, drilling data, geological structure data and geological exploration data.

[0022] Specifically, the multi-source geological data of the area to be detected is obtained by using geological survey, drilling, remote sensing and geophysical prospecting technology. The remote sensing physical data refers to the data related to the geological physical characteristics obtained from the upper space of the earth by remote sensing technology, such as the vertical height relative to the sea level, the terrain inclination, and the ratio of the intensity of the reflected light to the intensity of the incident light at a certain wavelength, etc.; the remote sensing image data refers to the image of the area to be evaluated obtained by satellite or aerial remote sensing equipment; the drilling data refers to the sample data of underground rock and ore obtained by drilling engineering, including rock composition, ore grade, rock thickness, etc.; the geological structure data refers to the data describing the internal structure of the geological area, such as the dip angle, strike, thickness, distribution characteristics of the stratum, etc.; the geological exploration data refers to the geological information obtained by geological exploration means (such as geological mapping, geochemical exploration, etc.), including rock type, ore composition ratio, content, ground stability, stratum age, etc.

[0023] Step 2, define the data corresponding to the sampling points of the geological exploration data in the remote sensing physical data as first remote sensing physical data, and the data not corresponding to the sampling points as second remote sensing physical data, construct a preset model based on the geological exploration data and the first remote sensing physical data, input the second remote sensing physical data into the preset model, and obtain the estimated geological exploration data at the virtual sampling points in the to-be-evaluated region.

[0024] Specifically, remote sensing physical data provides rich information of the earth's surface and atmosphere, and there is a certain correlation between these information and geological exploration data. By establishing a mathematical model and using a machine learning algorithm, these correlations can be analyzed to predict the geological exploration data of unknown regions.

[0025] Actual exploration is time-consuming and laborious, and the number of sampling points for collecting geological exploration data is limited. Remote sensing physical data is relatively easy to obtain, usually has high spatial resolution and coverage, and does not completely correspond to the sampling points of geological exploration data. The remote sensing physical data is divided into first remote sensing physical data corresponding to the sampling points of the geological exploration data and second remote sensing physical data not corresponding to the sampling points. The relationship between remote sensing physical data and geological exploration data is learned using the first remote sensing physical data and geological exploration data, a model for predicting geological exploration data is constructed, and then the actual geological exploration data at the virtual sampling points corresponding to the second remote sensing physical data is estimated using the model. This can supplement the geological exploration data and improve the data integrity of the entire to-be-evaluated region, providing more comprehensive data support for subsequent geological spatial structure generation and reserve estimation.

[0026] Step 3, add the estimated geological exploration data to the multi-source geological data to generate first multi-source geological data, and delete the second remote sensing physical data from the multi-source geological data to generate second multi-source geological data.

[0027] Specifically, by adding the estimated geological exploration data to the multi-source geological data, the data gaps between actual sampling points can be filled, making the first multi-source geological data more complete, and the first geological spatial structure generated based on the first multi-source geological data can more accurately reflect the actual geological conditions. By deleting the second remote sensing physical data from the original multi-source geological data, the redundancy information in the data can be reduced, improving the quality and usability of the data, and the multiple second geological spatial structures generated based on the second multi-source geological data can reduce the impact of redundant data on the geological spatial structure.

[0028] Step 4, generate a first geological spatial structure of the to-be-evaluated region based on the first multi-source geological data by a first preset geological modeling method, generate N1 second geological spatial structures based on the second multi-source geological data by a second preset geological modeling method, and select a spatial structure closest to the first geological spatial structure from all second geological spatial structures as a reference geological spatial structure.

[0029] Specifically, the geological space structure is a three-dimensional space model of the area to be evaluated, the first preset geological modeling method is to generate the geological space structure by geological modeling software (such as GOCAD, Surpac, Leapfrog, etc.), and the second preset geological modeling method is to construct the geological space structure by using the multiple-point geostatistics method. The multiple-point geostatistics method is a statistical-based geological modeling method for generating a three-dimensional geological model. It captures complex geological patterns and structures by using training images and generates multiple possible geological models by calculating conditional probabilities. By constructing the geological space structure reflecting the spatial distribution of geological bodies through the multiple-point geostatistics method, more complex geological structures such as faults, folds, veins, etc. can be captured, and multiple geological space structures can be generated, each of which is generated based on the conditions of known data points, providing different possible implementations of ore body characteristics, so as to evaluate the uncertainty of ore body characteristics.

[0030] The first geological space structure is a three-dimensional space model generated based on more complete data, which can more comprehensively reflect the geological characteristics of the area to be evaluated, and the second geological space structure is a three-dimensional space model considering the uncertainty of ore body characteristics. By comparing the similarity of multiple second geological space structures and the first geological space structure, the closest structure is selected as the reference geological space structure, which can reduce the error that may be caused by a single modeling method, select the geological space structure most similar to the actual geological data, and perform mineral resource reserve prediction based on the reference geological space structure closest to the actual geological conditions, thereby improving the accuracy of resource estimation.

[0031] Step 5, analyzing the reference geological space structure to obtain the average mineral abundance and ore volume, and calculating the predicted mineral resource reserves of the area to be evaluated based on the average mineral abundance and ore volume.

[0032] Specifically, the average mineral abundance refers to the average content of the target mineral in the reference geological space structure, and the ore volume refers to the total volume of the ore in the reference geological space structure. The product of the average mineral abundance and the ore volume is taken as the predicted mineral resource reserves.

[0033] Step 6, evaluating the predicted mineral resource reserves to obtain the final evaluation result.

[0034] Specifically, the evaluation result includes mineral resource reserve evaluation result (estimating the total amount of all mineral resources in the area, including different types of mineral resources (such as metal mineral resources, non-metal mineral resources, energy mineral resources, etc.)), mineral resource economic value evaluation result (estimating the economic value of mineral resources according to ore grade, market price, etc.), mineral resource development feasibility evaluation (evaluating the mining technical conditions of the ore deposit, including ore body occurrence conditions, rock stability, groundwater conditions, etc.), etc.

[0035] In a specific embodiment, the process of performing step 2 can specifically include the following steps: Step 21, based on the measured value of the specific element, the geological exploration data is serialized, the demarcation point is set, and the serialized geological exploration data is divided into N2 first data sets based on the demarcation point.

[0036] Step 22, based on the sampling point corresponding to the geological exploration data in each first data set, the first remote sensing physical data is divided into N2 first data sets to generate second data sets. After traversing all first data sets, N2 second data sets are obtained.

[0037] Step 23, training N2 second data sets to generate a first model for identifying the data set to which the first remote sensing physical data belongs, and training each second data set respectively to build a preset model corresponding to each second data set for predicting geological exploration data based on the first remote sensing physical data.

[0038] Step 24, using the first model to divide the second remote sensing physical data into different data sets, defined as the attribution data set, extracting any attribution data set, inputting the data in any attribution data set into the corresponding preset model, and obtaining the estimated geological exploration data corresponding to each data in any attribution data set.

[0039] The generation method flow chart of the estimated geological exploration data is shown in Figure 2 Specifically, the specific element is a key element related to mineral resources, such as gold, copper, iron, etc., and the measured value refers to the existence degree or content of a certain element or compound in the earth's crust, usually expressed in mass percentage or ppm (parts per million). Based on the demarcation point, the serialized geological exploration data is divided into different sets, which can make the data with the same or similar specific element content into a set, and the data in each set has similar characteristics (low specific element content, general specific element content, high specific element content). Based on the spatial correspondence between the sampling point and the remote sensing physical data, the remote sensing physical data is correspondingly divided into different data sets and stored correspondingly with its corresponding remote sensing physical data to generate a data pair set (i.e. second data set).

[0040] The first model and the preset model are neural network models. A corresponding preset model is constructed for each second data set to improve the prediction ability of the model. When data estimation is performed, the second remote sensing physical data is first classified based on the first model, and the second remote sensing physical data is divided into different data sets, realizing the classification prediction of the remote sensing data of the unsampled area, and associating them with similar geological conditions. Then, based on the data set, the preset model corresponding to the data set is extracted, and the estimated geological exploration data corresponding to each remote sensing physical data in the data set is obtained based on the preset model, which can more accurately predict the geological exploration data of the virtual sampling point and improve the accuracy of the geological exploration data estimation.

[0041] In a specific embodiment, in step 21, the setting method of the demarcation point is: Step 211, performing a predetermined algorithm on the measurement value corresponding to the specific element to generate a transformed value, identifying the second quantile of all transformed values, extracting the transformed values within the first preset range before and after the second quantile, and generating a reference data set.

[0042] Step 212, fitting processing the data in the reference data set based on a preset mathematical method to generate a fitting line, and defining the value corresponding to each sampling point on the fitting line as a fitting value.

[0043] Step 213, calculating the difference between the transformed value and the fitting value of each sampling point in the reference data set, and calculating the average value of the square of all differences, and defining the square root of the average value as a dispersion degree value.

[0044] Step 214, setting a fluctuation range based on the second quantile and the dispersion degree value, setting the measurement value corresponding to the maximum transformed value in the fluctuation range as the first demarcation point, and setting the measurement value corresponding to the minimum transformed value in the fluctuation range as the second demarcation point.

[0045] Specifically, the predetermined algorithm includes data standardization, data normalization, logarithm, logarithm-linear transformation, square root transformation, etc. The predetermined algorithm is executed to process the non-linear relationship and heteroscedasticity of the data, so as to eliminate the dimension effect, compress the dynamic range, effectively adjust the data distribution, and help improve the performance and effect of the model.

[0046] Extract the transformation values in the first preset range before and after the second quantile to generate a reference data set. For example, the first preset range is set to 10% of the transformation values before and after the second quantile to generate the reference data set (for example, the second quantile is 10, and the reference data set is generated based on the numbers between [9, 11]). The first preset range is set according to the experience of a person skilled in the art or according to the actual application scene, and the embodiments of the present application are not limited thereto. Then, the data in the reference data set is fitted based on a preset mathematical method (for example, linear regression, curve fitting, etc.) to generate a fitting line.

[0047] The fluctuation range is set based on the second quantile and the dispersion degree value, which can more reasonably divide the data interval. For example, the fluctuation range is [M-2×SD, M+2×SD], where M is the second quantile and SD is the dispersion degree value. The maximum value and the minimum value in the fluctuation range are used to determine the demarcation point, which can more accurately divide the data set and improve the accuracy of data classification.

[0048] In a specific embodiment, step 2 is followed by: Step 11, extracting all measurement values corresponding to the specific element from the geological exploration data, and deleting values less than a first preset value from all measurement values to generate a first set of analysis values.

[0049] Step 12, obtaining the content range and average content of the specific element in the crust in the background area, and setting a reference value based on the content range, wherein the evaluation area is contained in the background area.

[0050] Step 13, deleting values greater than the reference value from the first set of analysis values to generate a second set of analysis values, taking the average content as the average value of the second set of analysis values, and determining whether the second set of analysis values meets a preset distribution rule. If not, go to step 14, if yes, go to step 15.

[0051] Step 14, reducing the reference value by a second preset value to generate a new reference value, and defining the second set of analysis values as the first set of analysis values, and then returning to step 13.

[0052] Step 15, defining the maximum value of the second set of analysis values as the critical value of the specific element.

[0053] Specifically, the specific element is a key element related to mineral resources, such as gold, copper, iron, etc. The first preset value is a background value or a detection limit value. By deleting values less than the first preset value, data that may not have mineral value is removed, noise is reduced, and the efficiency of data processing is improved.

[0054] The background area is a larger area in which the to-be-evaluated area is located, and generally contains the to-be-evaluated area and the geological environment of the surrounding area. The content range of a specific element in the earth crust in the background area refers to the normal content range of the specific element in the earth crust in an area not affected by mineralization, which is generally obtained through geological investigation and statistical analysis.

[0055] First, the maximum value of the content range of the specific element in the background area or a certain percentage (for example, 90%) thereof is set as a reference value. For example, if the content range of copper (Cu) in the background area is 0.1% to 2.0%, 2.0% or 90% thereof (i.e., 1.8%) can be taken as the reference value. Next, the measured values of the specific element extracted from the geological exploration data are analyzed to form a second set of to-be-analyzed values. If the value set does not satisfy the preset distribution rule (such as symmetric unimodal asymptotic distribution, Gaussian distribution or bell-shaped distribution), it usually means that there are measured values corresponding to mineralization anomalies in the data. Mineralization can cause the content of some elements to be significantly higher than the background value, forming geochemical anomalies, and these anomaly values are usually high values at the tail of the data distribution. Therefore, the reference value needs to be reduced by a second preset value (for example, 0.1%) to generate a new reference value, and the judgment is made again. If the data in the second set of to-be-analyzed values obeys the preset distribution rule, it usually means that these data mainly reflect the distribution of the background value (i.e., the area without obvious mineralization). At this time, the maximum value of the data in the second set of to-be-analyzed values when the data obeys the preset distribution rule can be taken as the critical value for judging whether there is mineralization. This critical value is used to distinguish between background values and mineralization anomaly values, so as to more accurately identify the mineralization area.

[0056] Specifically, the background area is a more extensive area than the to-be-evaluated area, and the data thereof reflects the general range of the content of the specific element in the earth crust in the region. Taking the above-mentioned average value as the average value of the second set of to-be-analyzed values can reduce the possibility of misjudgment and improve the reliability of judging the preset distribution rule.

[0057] In a specific embodiment, the process of performing step 3 can specifically include the following steps: (1) Traverse the first remote sensing physical data, and when the measured value of the specific element corresponding to any sampling point is less than the critical value, define the geological exploration data and the first remote sensing physical data corresponding to any sampling point as first redundant data, delete the first redundant data from the second multi-source geological data, and generate new second multi-source geological data.

[0058] (2) traversing the estimated geological exploration data, when the measured value corresponding to a specific element at any virtual sampling point is less than a critical value, defining the estimated geological exploration data and the second remote sensing physical data corresponding to any virtual sampling point as second redundant data, deleting the first redundant data and the second redundant data from the first multi-source geological data, and generating new first multi-source geological data.

[0059] Specifically, removing redundant data irrelevant to mineral resources or below a critical value can reduce noise in the data, improve the quality and availability of the data, and improve the efficiency and accuracy of subsequent geological modeling and resource assessment.

[0060] In a specific embodiment, the process of performing step 4 can specifically include the following steps: Step 41, respectively extracting features from the first characteristic parameters of each second geological spatial structure, reducing the total number of first characteristic parameters to a preset number, and obtaining a low-dimensional spatial structure corresponding to each second geological spatial structure.

[0061] Step 42, based on a preset rule, assigning values to non-numerical parameters in each low-dimensional spatial structure, then normalizing the second characteristic parameters of all low-dimensional spatial structures, calculating the Euclidean distance between any two low-dimensional spatial structures based on the normalization result, grouping all second geological spatial structures based on the Euclidean distance, and obtaining N3 spatial structure sets.

[0062] Step 43, extracting deposit geological features from all geological spatial structures, and respectively obtaining first ore body attribute parameters and second ore body attribute parameters corresponding to the first geological spatial structure and each second geological spatial structure.

[0063] Step 44, extracting any spatial structure set, statistically analyzing the second ore body attribute parameters of all second geological spatial structures in any spatial structure set, and obtaining third ore body attribute parameters of any spatial structure set.

[0064] Step 45, after traversing all spatial structure sets, defining the spatial structure set corresponding to the third ore body attribute parameter with the highest similarity to the first ore body attribute data as a specific structure set, and respectively performing mineral resource assessment on the first geological spatial structure and each third geological spatial structure, obtaining first mineral resource statistical parameters and second mineral resource statistical parameters, wherein the third geological spatial structure is a second geological spatial structure included in the specific structure set.

[0065] Step 46, defining the third geological spatial structure corresponding to the second mineral resource statistical parameter with the highest similarity to the first mineral resource statistical parameter as a reference geological spatial structure.

[0066] Specifically, the number of second geological space structures generated by the second preset geological modeling method can be very large and diverse, and directly selecting a reference geological space structure from all the second geological space structures can not only be computationally expensive, but also can ignore some important geological features. By grouping, a large number of geological space structures are divided into a plurality of smaller space structure sets, each set containing geological space structures with similar geological features, which can significantly reduce the number of geological space structures that need to be evaluated and improve computational efficiency.

[0067] The second geological space structure is a high-dimensional three-dimensional space model, which usually contains a large number of feature parameters. Before grouping, a multi-dimensional scaling method (MDS), principal component analysis (PCA), or other techniques are used for dimensionality reduction to reduce the number of feature parameters, thereby reducing computational complexity and improving computational efficiency.

[0068] In geological modeling, a geological space structure usually contains various geological features and parameters, which can be continuous numerical values (such as the size and grade of an ore body) or discrete categories (such as the type of an ore body or the type of a rock layer). In order to calculate the distance between these geological space structures, it is necessary to convert discrete categories into numerical values (i.e., non-numerical parameter assignment processing). For example, ore body type: category 1 represents ore body type A, and category 2 represents ore body type B. During assignment processing, ore body type A is assigned a value of 1, and ore body type B is assigned a value of 2. Rock layer type: category 1 represents sandstone, category 2 represents shale, and category 3 represents limestone, etc. During assignment processing, sandstone is assigned a value of 1, shale is assigned a value of 2, and limestone is assigned a value of 3.

[0069] Specifically, the ore body attribute parameters include the shape, distribution, location, volume, and extension range of the ore body. Statistical analysis is performed on the content of useful minerals in each third geological space structure to obtain the average value, standard deviation, coefficient of variation, and distribution as mineral resource statistical parameters.

[0070] In a specific embodiment, the process of performing step 42 further includes the following steps: (1) Calculate the ratio of the total number to N3. When the ratio is greater than a second preset range, divide the evaluation area into N3 sub-evaluation areas, divide the first and second multi-source geological data into different sub-evaluation areas, and then return to step 4 to perform mineral reserve prediction for each sub-evaluation area.

[0071] (2) When the ratio is less than the second preset range, generate new sampling points based on the existing sampling point coordinates, collect geological data for the new sampling points, and after the collection is complete, return to step 1.

[0072] Specifically, when the ratio of the total number to N3 is greater than the second preset range, it can be judged that the ore body structure (ore body number, distribution, horizon, etc.) of the to-be-evaluated region is relatively complex. In order to improve the accuracy of the ore body reserve prediction, the to-be-evaluated region is divided into multiple sub-evaluation regions, and each sub-evaluation region is evaluated respectively. When the ratio of the total number to N3 is greater than the second preset range, it means that the data is insufficient, and in order to improve the accuracy of the ore body reserve prediction, new sampling points need to be added to collect more geological data. Preferably, the new sampling points are set according to the distance between the existing sampling points, as shown in Figure 3 P1, P2, P3 and P4 are existing sampling points, and the distances between P1 and P4, P2 and P4, and P3 and P4 are large, so new sampling points P5, P6 and P7 are re-set.

[0073] The above describes the intelligent evaluation method for mineral resource exploration in the embodiments of the present application. The intelligent evaluation system for mineral resource exploration in the embodiments of the present application is described below. Please refer to Figure 4 An embodiment of the intelligent evaluation system for mineral resource exploration in the embodiments of the present application includes: The data acquisition module 10 is configured to acquire multi-source geological data of the to-be-evaluated region, and the multi-source geological data includes remote sensing physical data, remote sensing image data, drilling data, geological structure data and geological exploration data.

[0074] The data filling module 20 is configured to define the data corresponding to the sampling points of the geological exploration data in the remote sensing physical data as first remote sensing physical data, and define the data not corresponding to the sampling points as second remote sensing physical data, construct a preset model based on the geological exploration data and the first remote sensing physical data, input the second remote sensing physical data into the preset model, and acquire estimated geological exploration data at the virtual sampling points in the to-be-evaluated region.

[0075] The data grouping module 30 is configured to add the estimated geological exploration data to the multi-source geological data to generate first multi-source geological data, and delete the second remote sensing physical data from the multi-source geological data to generate second multi-source geological data.

[0076] The spatial structure generation module 40 is configured to generate a first geological spatial structure of the to-be-evaluated region by a first preset geological modeling method according to the first multi-source geological data, generate N1 second geological spatial structures by a second preset geological modeling method based on the second multi-source geological data, and select a spatial structure closest to the first geological spatial structure from all the second geological spatial structures as a reference geological spatial structure.

[0077] The reserve prediction module 50 is configured to analyze the reference geological spatial structure, acquire the average mineral abundance and the ore volume, and calculate the predicted reserves of the mineral resources in the to-be-evaluated region based on the average mineral abundance and the ore volume.

[0078] The intelligent evaluation module 60 is configured to evaluate the predicted reserves of the mineral resources and obtain a final evaluation result.

[0079] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium or a volatile computer readable storage medium. The computer readable storage medium stores instructions, and when the instructions are executed on a computer, the computer performs the steps of the intelligent evaluation method for mineral resource exploration.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0081] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or say the part that makes contributions to the prior art, or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0082] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features. Such 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 application.

Claims

1. An intelligent assessment method for mineral resource exploration, characterized in that: The method comprises: Step 1: Acquire multi-source geological data of the area to be assessed, wherein the multi-source geological data includes remote sensing physical data, remote sensing image data, drilling data, geological structure data, and geological exploration data; Step 2: defining data in the remotely sensed physical data corresponding to the sampling points of the geological exploration data as first remotely sensed physical data, and defining data not corresponding to the sampling points as second remotely sensed physical data; constructing a preset model based on the geological exploration data and the first remotely sensed physical data; inputting the second remotely sensed physical data into the preset model to obtain estimated geological exploration data at the virtual sampling points in the area to be evaluated; Step 3: adding the estimated geological exploration data to the multi-source geological data to generate first multi-source geological data, and deleting the second remote sensing physical data from the multi-source geological data to generate second multi-source geological data; Step 4: Generate a first geological spatial structure of the area to be assessed using a first preset geological modeling method based on the first multi-source geological data; generate N1 second geological spatial structures using a second preset geological modeling method based on the second multi-source geological data; and select, from all the second geological spatial structures, a spatial structure that is closest to the first geological spatial structure as a reference geological spatial structure; Step 5: Analyze the reference geological spatial structure to obtain average mineral abundance and ore volume, and calculate the predicted reserves of mineral resources in the area to be assessed based on the average mineral abundance and the ore volume; Step 6: Evaluate the predicted reserves of the mineral resources to obtain the final evaluation results.

2. The intelligent assessment method for mineral resource exploration according to claim 1, characterized in that: The step 2 includes: Step 21: Serialize the geological exploration data based on the measured values ​​of specific elements, set a demarcation point, and divide the serialized geological exploration data into N2 first data sets based on the demarcation point; Step 22: Based on the sampling points corresponding to the geological exploration data in each first data set, the first remote sensing physical data is divided into N2 first data sets to generate second data sets. After traversing all first data sets, N2 second data sets are obtained. Step 23: training the N2 second data sets to generate a first model for identifying the data set to which the first remotely sensed physical data belongs. Simultaneously, training each second data set separately to construct the preset model for predicting the geological exploration data based on the first remotely sensed physical data corresponding to each second data set. Step 24: Use the first model to divide the second remote sensing physical data into different data sets, defined as belonging data sets, extract any belonging data set, input the data in any of the belonging data sets into the corresponding preset model, and obtain the estimated geological exploration data corresponding to each data in any of the belonging data sets.

3. The intelligent assessment method for mineral resource exploration according to claim 2, characterized in that: In step 21, the method for setting the demarcation point is: Step 211: Execute a predetermined algorithm on the measured values ​​corresponding to the specific element to generate transformed values, identify the quantiles of all transformed values, extract the transformed values ​​within a first preset range before and after the quantiles, and generate a reference data set; Step 212: Fitting the data in the reference data set based on a preset mathematical method to generate a fitting line, and defining the value corresponding to each sampling point on the fitting line as a fitting value; Step 213: Calculate the difference between the transformed value and the fitted value of each sampling point in the reference data set, calculate the average of the squares of all the differences, and define the square root of the average as the dispersion value; Step 214: Set a fluctuation range based on the quantile and the dispersion value, set the measured value corresponding to the maximum transformed value within the fluctuation range as a first dividing point, and set the measured value corresponding to the minimum transformed value within the fluctuation range as a second dividing point.

4. The intelligent assessment method for mineral resource exploration according to claim 1, characterized in that: The step 2 then includes: Step 11: extracting all measured values ​​corresponding to a specific element from the geological exploration data, and deleting values ​​less than a first preset value from all the measured values ​​to generate a first set of values ​​to be analyzed; Step 12: Obtain the content range and average content of the specific element in the earth's crust in the background area, and set a reference value based on the content range, wherein the area to be evaluated is included in the background area; Step 13: Delete values ​​greater than the reference value from the first set of values ​​to be analyzed to generate a second set of values ​​to be analyzed. Use the average content value as the average value of the second set of values ​​to be analyzed to determine whether the second set of values ​​to be analyzed satisfies a preset distribution rule. If not, proceed to step 14. If yes, proceed to step 15. Step 14: reduce the reference value by a second preset value to generate a new reference value, and define the second set of values ​​to be analyzed as the first set of values ​​to be analyzed, and then return to step 13; Step 15: Define the maximum value of the second set of values ​​to be analyzed as the critical value of the specific element.

5. The intelligent assessment method for mineral resource exploration according to claim 4, characterized in that: The step 3 includes: traversing the first remote sensing physical data, when a measured value corresponding to the specific element at any sampling point is less than the critical value, defining the geological exploration data corresponding to any of the sampling points and the first remote sensing physical data as first redundant data, deleting the first redundant data from the second multi-source geological data, and generating new second multi-source geological data; The estimated geological exploration data are traversed, and when a measured value corresponding to the specific element at any virtual sampling point is less than the critical value, the estimated geological exploration data and the second remote sensing physical data corresponding to any virtual sampling point are defined as second redundant data, and the first redundant data and the second redundant data are deleted from the first multi-source geological data to generate new first multi-source geological data.

6. The intelligent assessment method for mineral resource exploration according to claim 1, characterized in that: The step 4 comprises: Step 41: extracting features from the first characteristic parameters of each second geological spatial structure, reducing the total number of the first characteristic parameters to a preset number, and obtaining a low-dimensional spatial structure corresponding to each second geological spatial structure; Step 42: Based on a preset rule, assign a value to a non-numerical parameter in each low-dimensional spatial structure, then standardize the second characteristic parameters of all low-dimensional spatial structures, calculate the Euclidean distance between any two low-dimensional spatial structures based on the standardization result, group all second geological spatial structures based on the Euclidean distance, and obtain N3 spatial structure sets; Step 43: Extract ore deposit geological characteristics from all geological spatial structures, and obtain first ore body attribute parameters and second ore body attribute parameters corresponding to the first geological spatial structure and each of the second geological spatial structures; Step 44: extract any spatial structure set, perform statistical analysis on the second ore body attribute parameters of all second geological spatial structures in any of the spatial structure sets, and obtain third ore body attribute parameters of any of the spatial structure sets; Step 45: After traversing all spatial structure sets, define the spatial structure set corresponding to the third ore body attribute parameter having the greatest similarity to the first ore body attribute data as a specific structure set, perform mineral resource assessment on the first geological spatial structure and each third geological spatial structure, and obtain first mineral resource statistical parameters and second mineral resource statistical parameters, wherein the third geological spatial structure is the second geological spatial structure included in the specific structure set; Step 46: Define the third geological spatial structure corresponding to the second mineral resource statistical parameter having the greatest similarity to the first mineral resource statistical parameter as a reference geological spatial structure.

7. The intelligent assessment method for mineral resource exploration according to claim 6, characterized in that: The step 42 further includes: Calculating a ratio of the total number to N3; when the ratio is greater than a second preset range, dividing the area to be evaluated into N3 sub-evaluation areas, dividing the first multi-source geological data and the second multi-source geological data into different sub-evaluation areas, and then returning to step 4 to perform mineral reserve prediction for each sub-evaluation area; When the ratio is less than the second preset range, a new sampling point is generated based on the coordinates of the existing sampling point, and geological data is collected for the new sampling point. After the collection is completed, the process returns to step 1.

8. An intelligent assessment system for mineral resource exploration, characterized in that: The system comprises: A data acquisition module is used to acquire multi-source geological data of the area to be evaluated, wherein the multi-source geological data includes remote sensing physical data, remote sensing image data, drilling data, geological structure data and geological exploration data; a data filling module, configured to define data in the remotely sensed physical data corresponding to sampling points of the geological exploration data as first remotely sensed physical data, and define data not corresponding to the sampling points as second remotely sensed physical data, construct a preset model based on the geological exploration data and the first remotely sensed physical data, input the second remotely sensed physical data into the preset model, and obtain estimated geological exploration data at virtual sampling points in the area to be evaluated; a data grouping module, configured to add the estimated geological exploration data to the multi-source geological data to generate first multi-source geological data, and delete the second remote sensing physical data from the multi-source geological data to generate second multi-source geological data; a spatial structure generation module, configured to generate a first geological spatial structure of the area to be assessed using a first preset geological modeling method based on the first multi-source geological data, generate N1 second geological spatial structures using a second preset geological modeling method based on the second multi-source geological data, and select, from all the second geological spatial structures, a spatial structure that is closest to the first geological spatial structure as a reference geological spatial structure; A reserve prediction module is used to analyze the reference geological spatial structure, obtain average mineral abundance and ore volume, and calculate the predicted reserves of mineral resources in the area to be evaluated based on the average mineral abundance and the ore volume; The intelligent evaluation module is used to evaluate the predicted reserves of the mineral resources and obtain the final evaluation results.

9. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the intelligent assessment method for mineral resource exploration as described in any one of claims 1 to 7 is implemented.

Images