Alterated mineral extraction method and device, electronic equipment and storage medium

Abstract

The invention provides an altered mineral extraction method and device, electronic equipment and a storage medium, and belongs to the technical field of data processing. Fitting a fitting relationship between the contents of various altered minerals and the first magnetic susceptibility data on the basis of the characteristic data of the plurality of rock samples in the grid region, determining a regression coefficient corresponding to each altered mineral, and screening an altered mineral type combination corresponding to the grid region from the various altered minerals by utilizing the regression coefficient; combining the grid regions with the same altered mineral type combination to obtain a plurality of first distribution regions; obtaining a plurality of second distribution areas by using the hyperspectral data; and determining the intersection of the first distribution area and the second distribution area with the same altered mineral type combination as the area where the corresponding altered mineral is located. According to the altered mineral extraction method and device, the electronic equipment and the storage medium, the altered mineral extraction accuracy can be improved.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and more specifically, relates to a method and apparatus for extracting altered minerals, electronic equipment, and storage medium. Background Technology

[0002] In the field of mineral resource exploration, alteration minerals are the direct products of hydrothermal mineralization. Their types, combinations and spatial distribution are core geological indicators that indicate the location, mineralization type and scale of ore bodies. Accurate identification and extraction of alteration mineral information can significantly narrow down the prospecting target area and significantly reduce exploration costs and blind spots. In existing technologies, hyperspectral remote sensing equipment is typically used to acquire hyperspectral data of the area under study, and then the spatial distribution of alteration minerals is determined based on spectral characteristics. However, since hyperspectral data is easily affected by topographic shadows, atmospheric scattering, and mineral mixed spectra, it is difficult to accurately distinguish alteration minerals with similar spectral characteristics, resulting in large errors in the identification results and failing to meet the actual needs of high-precision mineral exploration. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, electronic device, and storage medium for extracting altered minerals, so as to improve the accuracy of altered mineral extraction.

[0004] A first aspect of this application provides a method for extracting altered minerals, comprising: The system acquires feature data corresponding to multiple rock samples within the target area, as well as hyperspectral data corresponding to the target area. The feature data includes first magnetic susceptibility data and the content of various alteration minerals contained in the rock samples. For each grid area within the target area, the content of each of the various alteration minerals and the first magnetic susceptibility data are fitted based on the characteristic data of multiple rock samples in the grid area. The regression coefficient corresponding to each alteration mineral is determined based on the fitting results. The regression coefficient is used to screen the combination of alteration mineral types corresponding to the grid area from the various alteration minerals in the grid area. By merging grid regions with the same combination of alteration mineral types, multiple primary distribution regions are obtained; The target region is divided according to the combination of alteration mineral types using the hyperspectral data, resulting in multiple secondary distribution regions; The intersection of the first distribution area and the second distribution area with the same combination of alteration minerals is determined as the area where the corresponding alteration mineral is located.

[0005] A second aspect of this application provides an alteration mineral extraction apparatus, comprising: The data acquisition module is used to acquire the characteristic data corresponding to multiple rock samples within the target area, as well as the hyperspectral data corresponding to the target area; the characteristic data includes first magnetic susceptibility data and the content of various alteration minerals contained in the rock samples; The data fitting module is used to fit the content of each of the multiple alteration minerals and the first magnetic susceptibility data for each grid area within the target area based on the characteristic data of multiple rock samples within the grid area. Based on the fitting results, the module determines the regression coefficient corresponding to each alteration mineral and uses the regression coefficient to screen the combination of alteration mineral types corresponding to the grid area from the multiple alteration minerals within the grid area. The first region determination module is used to merge grid regions with the same combination of alteration mineral types to obtain multiple first distribution regions; The second region determination module is used to divide the target region according to the combination of alteration mineral types using the hyperspectral data to obtain multiple second distribution regions; The region extraction module is used to determine the intersection of the first distribution area and the second distribution area with the same combination of alteration mineral types as the region where the corresponding alteration mineral is located.

[0006] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described alteration mineral extraction method.

[0007] In a fourth aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described alteration mineral extraction method.

[0008] The beneficial effects of the altered mineral extraction method and apparatus, electronic equipment, and storage medium provided in this application are as follows: This application embodiment, based on the geological genetic correlation between the magnetic susceptibility of rocks (first magnetic susceptibility data) and the content of alteration minerals, divides the target area into multiple grid regions. For each grid region, based on the characteristic data of all rock samples in that grid region, it fits the mapping relationship between the content of each alteration mineral and the first magnetic susceptibility data, and calculates and outputs the regression coefficient corresponding to each alteration mineral. The regression coefficient can quantitatively characterize the contribution of each alteration mineral content to the rock magnetic susceptibility. Based on the magnitude of the regression coefficient, alteration minerals with a strong correlation to the first magnetic susceptibility data are selected, and the combination of alteration mineral types corresponding to each grid region is determined.

[0009] Furthermore, grid regions with the same alteration mineral species combinations are merged to obtain multiple first distribution regions, each corresponding to one type of alteration mineral species combination. Simultaneously, hyperspectral data is used to identify and spatially segment alteration mineral species combinations, resulting in multiple second distribution regions, each corresponding to one type of alteration mineral species combination. Spatial overlay analysis of the first and second distribution regions is performed, and the second distribution regions are validated based on the first distribution regions. This effectively eliminates false regions identified by hyperspectral analysis, achieving accurate extraction of alteration mineral regions. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A schematic flowchart of an alteration mineral extraction method provided in an embodiment of this application; Figure 2 This is a structural block diagram of an altered mineral extraction apparatus provided in one embodiment of this application; Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0014] Please refer to Figure 1 , Figure 1 This is a schematic flowchart of an alteration mineral extraction method provided in an embodiment of this application. The alteration mineral extraction method provided in this embodiment can be executed by an electronic device, and the method may include: S101: Obtain the characteristic data corresponding to each of the multiple rock samples in the target area, as well as the hyperspectral data corresponding to the target area; the characteristic data includes the first magnetic susceptibility data, and the content of each of the various alteration minerals contained in the rock samples.

[0015] In this embodiment, several rock samples can be collected from the mining area, and the magnetic susceptibility of each sample can be measured using a magnetic susceptibility meter to obtain the first magnetic susceptibility data of the rock samples. At the same time, the content of various alteration minerals contained in the rock samples can be determined by quantitative analysis of X-ray diffraction, electron probe microscopy, or statistical analysis under a polarizing microscope. In addition, hyperspectral remote sensing equipment can be used to acquire hyperspectral data of the target area, and the hyperspectral data can be preprocessed by atmospheric correction, geometric correction, and noise band removal to ensure the validity of the data.

[0016] S102: For each grid area within the target area, fit the relationship between the content of various alteration minerals and the first magnetic susceptibility data based on the characteristic data of multiple rock samples in the grid area. Determine the regression coefficient corresponding to each alteration mineral based on the fitting results. Use the regression coefficient to screen the combination of alteration mineral types corresponding to the grid area from the various alteration minerals in the grid area.

[0017] In this embodiment, considering that the magnetic susceptibility of a rock is determined by its internal mineral composition and content, and that the enrichment of specific alteration minerals directly leads to a regular change in the rock's magnetic susceptibility, the two are naturally related in terms of geological origin. Therefore, the target area can be divided into multiple grid regions. For each grid region, based on the characteristic data of all rock samples in that grid region, the mapping relationship between the content of each alteration mineral and the first magnetic susceptibility data is fitted to obtain the regression coefficient corresponding to each alteration mineral.

[0018] Specifically, the content of each of the various alteration minerals can be used as the independent variable, and the first magnetic susceptibility data as the dependent variable. A multiple linear regression equation can be fitted based on the characteristic data corresponding to each of the multiple rock samples to obtain the fitting relationship between the content of each alteration mineral and the first magnetic susceptibility data. For example, the fitting relationship can be expressed as the following equation: ; in, This represents the first magnetic susceptibility data. , ... This indicates the content of each alteration mineral. Represents the regression constant term. , ... This represents the regression coefficient corresponding to each altered mineral. This represents the fitting residual.

[0019] The regression coefficient can quantify the contribution of each alteration mineral content to the magnetic susceptibility of the rock. The larger the coefficient, the stronger the correlation between the alteration mineral and the magnetic susceptibility. Based on this, alteration minerals with a strong correlation to the first magnetic susceptibility data can be screened out, and the combination of alteration mineral types corresponding to each grid area can be determined.

[0020] S103: Merge grid regions with the same combination of alteration mineral types to obtain multiple first distribution regions.

[0021] In this embodiment, based on determining the alteration mineral type combination corresponding to each grid region, grid regions with the same alteration mineral type combination are merged to obtain multiple first distribution regions, and each first distribution region corresponds to a type of alteration mineral type combination.

[0022] S104: Using hyperspectral data, the target area is divided according to the combination of alteration mineral types to obtain multiple secondary distribution areas.

[0023] In this embodiment, hyperspectral data enables full-coverage spectral detection of the target area. Alteration minerals possess unique diagnostic spectral characteristics (such as characteristic absorption peaks and reflectance features). Through feature interpretation and spectral matching algorithms of hyperspectral full-band data, the spectral feature information of alteration minerals within the target area is extracted and accurately compared with a standard mineral spectral library. Based on this, qualitative analysis of alteration minerals is completed, enabling the identification and spatial division of alteration mineral species combinations, resulting in multiple secondary distribution regions. Similarly, each secondary distribution region corresponds to a type of alteration mineral species combination.

[0024] S105: The intersection of the first and second distribution areas with the same combination of alteration mineral types is determined as the area where the corresponding alteration mineral is located.

[0025] In this embodiment, the first distribution area is obtained based on on-site geological statistics of the target area, and the second distribution area is obtained based on remote sensing spectral feature analysis of the target area. Spatial overlay analysis is performed on the first and second distribution areas, and the intersection area of ​​the first and second distribution areas is taken as the actual location of the corresponding alteration mineral combination, thereby completing the accurate extraction of the alteration mineral area.

[0026] As can be seen from the above, this embodiment, based on the geological genetic correlation between the magnetic susceptibility of rocks (first magnetic susceptibility data) and the content of alteration minerals, divides the target area into multiple grid regions. For each grid region, based on the characteristic data of all rock samples in that grid region, the mapping relationship between the content of each alteration mineral and the first magnetic susceptibility data is fitted, and the regression coefficient corresponding to each alteration mineral is calculated and output. The regression coefficient can quantitatively characterize the contribution of each alteration mineral content to the rock magnetic susceptibility. Therefore, based on the magnitude of the regression coefficient, alteration minerals that contribute significantly to the first magnetic susceptibility data can be screened, and the combination of alteration mineral types corresponding to each grid region can be determined.

[0027] Furthermore, grid regions with the same alteration mineral species combinations are merged to obtain multiple first distribution regions, each corresponding to one type of alteration mineral species combination. Simultaneously, hyperspectral data is used to identify and spatially segment alteration mineral species combinations, resulting in multiple second distribution regions, each corresponding to one type of alteration mineral species combination. Spatial overlay analysis of the first and second distribution regions is performed, and the second distribution regions are validated based on the first distribution regions. This effectively eliminates false regions identified by hyperspectral analysis, achieving accurate extraction of alteration mineral regions.

[0028] In one embodiment of this application, a combination of alteration mineral types corresponding to a grid region is obtained by screening from multiple alteration minerals within the grid region using regression coefficients, including: The regression coefficients corresponding to each alteration mineral are converted into standardized coefficients, and alteration minerals with standardized coefficients greater than a preset first threshold are selected to obtain the first set of alteration minerals. The combination of alteration mineral types in the grid area is determined based on the first set of alteration minerals.

[0029] In this embodiment, the original regression coefficients obtained by multiple linear regression are affected by the differences in the dimensions and numerical scales of the alteration mineral content. Therefore, it is not possible to directly compare the contribution intensity of different alteration minerals to the first magnetic susceptibility of the rock.

[0030] To address the aforementioned issues, this embodiment standardizes the original regression coefficients, converting the regression coefficients corresponding to all altered minerals into dimensionless, same-scale, and directly comparable standardized coefficients, thereby eliminating the dimensional and numerical scale differences in the content of different altered minerals.

[0031] For example, the coefficients corresponding to this type of altered mineral can be converted into standardized coefficients using the following formula: ; in, Represents the standardized coefficient. This represents the coefficient corresponding to this type of altered mineral. This represents the standard deviation of the content of various alteration minerals in the mapping model. This represents the first magnetic susceptibility data.

[0032] After converting the regression coefficients corresponding to each alteration mineral into standardized coefficients, for each grid region, alteration minerals with standardized coefficients greater than a first threshold can be selected to form a first alteration mineral set. This first alteration mineral set is then used as the combination of alteration mineral types for that grid region. Alternatively, the first alteration mineral set can be further screened to determine the combination of alteration mineral types for that grid region, as detailed in the following embodiments. The first threshold is a preset constant, and those skilled in the art can determine its specific value based on the geological background of the target region, such as 0.2, 0.3, etc.

[0033] In one embodiment of this application, for each grid region, the combination of alteration mineral types for that grid region is determined based on a first set of alteration minerals, including: For each alteration mineral in the first alteration mineral set, calculate the first correlation coefficient between the content of the alteration mineral and the first magnetic susceptibility data; if the first correlation coefficient corresponding to the alteration mineral is greater than a preset second threshold, then classify the alteration mineral into the second alteration mineral set. The combination of alteration mineral types in this grid area is determined based on the second alteration mineral set.

[0034] In this embodiment, the core assumption of the multiple linear regression model is that there is a linear relationship between the independent and dependent variables. However, during the model fitting process, due to problems such as multicollinearity and sample bias, false positive results may occur with significant regression coefficients but weak actual correlations.

[0035] To avoid the aforementioned problems, for each alteration mineral in the first alteration mineral set, a first correlation coefficient can be calculated between the content of the alteration mineral and the first magnetic susceptibility data. This first correlation coefficient directly reflects the strength of the correlation between the content of the alteration mineral and the first magnetic susceptibility data. Therefore, if the first correlation coefficient corresponding to the alteration mineral is greater than a preset second threshold, the alteration mineral is classified into the second alteration mineral set. The first correlation coefficient can be the existing Pearson correlation coefficient, and the second threshold is a preset constant. Those skilled in the art can set the specific value of the second threshold according to actual needs, such as 0.6, 0.7, etc.

[0036] As can be seen from the above, this embodiment calculates the first correlation coefficient between the content of each alteration mineral and the first magnetic susceptibility data, and filters the first alteration mineral set based on the first correlation coefficient. This can further eliminate alteration minerals that "show false comprehensive contribution due to the interaction of other coexisting minerals" in the multiple regression fitting, thereby improving the accuracy of alteration mineral extraction.

[0037] In one embodiment of this application, for each grid region, the combination of alteration mineral types for that grid region is determined based on a second alteration mineral set, including: The normalized weights for each alteration mineral in the second alteration mineral set are determined based on the standardized coefficients corresponding to each alteration mineral in the second alteration mineral set. For each rock sample within the grid area, the content of each target alteration mineral in the rock sample is weighted and summed based on the corresponding normalization weight to obtain the second magnetic susceptibility data corresponding to the rock sample; the target alteration mineral is the alteration mineral included in the second alteration mineral set; Calculate the second correlation coefficient between the first and second magnetic susceptibility data corresponding to multiple rock samples; If the second correlation coefficient is greater than or equal to the preset third threshold, then the second set of alteration minerals is taken as the combination of alteration mineral types for the grid region.

[0038] In this embodiment, considering that there may be highly correlated alteration minerals among various alteration minerals, for example, chlorite and epidote have similar genesis, similar iron content, and completely consistent content change trends, when analyzing the first correlation coefficient corresponding to a single alteration mineral, it is actually epidote that drives the change in the first magnetic susceptibility data. However, because chlorite and epidote are highly correlated, the calculation result of the first correlation coefficient shows that chlorite and the first magnetic susceptibility data are also strongly correlated, thus leading to a false association between chlorite and the first magnetic susceptibility data.

[0039] To avoid the above problems, this embodiment obtains the second magnetic susceptibility data based on the normalization coefficient and content of each alteration mineral in the second alteration mineral set. The second magnetic susceptibility data can characterize the synergistic effect of each alteration mineral in the second alteration mineral set.

[0040] Specifically, the normalized weight of each alteration mineral in the second alteration mineral set can be determined first based on the standardized coefficients corresponding to each alteration mineral in the second alteration mineral set. For example, the normalized weight of each alteration mineral can be calculated using the following formula: ; in, This represents the normalized weight corresponding to the i-th alteration mineral. This represents the normalization factor of the i-th altered mineral. This indicates the number of different types of alteration minerals in the second alteration mineral set. This represents the sum of the normalized coefficients of all alteration minerals in the second alteration mineral set.

[0041] Based on the normalized weights corresponding to each alteration mineral, for each rock sample within the grid region, the content of each alteration mineral in the second alteration mineral set can be weighted and summed according to the corresponding normalized weights to obtain the second magnetic susceptibility data corresponding to the rock sample. The specific calculation formula is as follows: ; in, This indicates the second magnetic susceptibility data. This represents the normalized weight corresponding to the i-th alteration mineral. This indicates the content of the i-th alteration mineral.

[0042] Based on the second magnetic susceptibility data corresponding to each rock sample, the second correlation coefficient between the first and second magnetic susceptibility data corresponding to multiple rock samples is calculated. If the second correlation coefficient is greater than or equal to the preset third threshold, it indicates that the synergistic effect of each alteration mineral in the second alteration mineral set can accurately explain the numerical distribution characteristics of rock magnetic susceptibility. There is no false association caused by highly correlated minerals, and the second alteration mineral set can be regarded as the combination of alteration mineral types in the grid area.

[0043] As can be seen from the above, this embodiment calculates the second magnetic susceptibility data to characterize the synergistic effect of each alteration mineral in the second alteration mineral set. Then, by calculating the second correlation coefficient between the first and second magnetic susceptibility data, it can identify and eliminate false association combinations caused by highly correlated minerals, ensuring that the final alteration mineral combination is the core combination that truly dominates the magnetic susceptibility change and has geological genetic significance within the grid area, thereby obtaining an accurate combination of alteration mineral types.

[0044] In one embodiment of this application, for each grid region, if the second correlation coefficient is less than a preset third threshold, the alteration mineral extraction method further includes: Identify all subsets of the second altered mineral set; Each subset is selected as the target subset in descending order of the number of alteration mineral types contained in each subset; The process iteratively executes the following steps: treating each target subset as a second alteration mineral set; determining the normalized weight of each alteration mineral in the second alteration mineral set based on its normalized coefficient; for each rock sample within the grid region, weighting and summing the contents of each target alteration mineral in the rock sample based on its corresponding normalized weight to obtain the second magnetic susceptibility data for that rock sample; calculating the second correlation coefficient between the first and second magnetic susceptibility data for multiple rock samples; until a target subset exists whose second correlation coefficient is greater than or equal to a preset third threshold. The target subset is used as the combination of alteration mineral species for the grid region.

[0045] In this embodiment, for each grid region, if the second correlation coefficient is less than the preset third threshold, it indicates that there are highly correlated alteration minerals in the second alteration mineral set. The redundant correlation formed by these minerals will interfere with the accuracy of magnetic susceptibility fitting, causing the fitted second magnetic susceptibility to deviate from the measured first magnetic susceptibility data. It is necessary to remove these redundant highly correlated minerals to remove false correlation interference and determine the final combination of alteration mineral types.

[0046] Specifically, all possible subsets of the second alteration mineral set can be enumerated. The subset with the most alteration mineral types is selected as the target subset to be verified, ordered from largest to smallest number. Each target subset replaces the original second alteration mineral set, and the calculation steps for the second correlation coefficient are iteratively executed. Specifically: the normalized weight of each alteration mineral in the second alteration mineral set is determined based on its standardized coefficient; for each rock sample within the grid region, the content of each target alteration mineral in the rock sample is weighted and summed based on its corresponding normalized weight to obtain the second magnetic susceptibility data for that rock sample; the second correlation coefficient between the first and second magnetic susceptibility data for multiple rock samples is calculated. If a target subset exists whose second correlation coefficient is greater than or equal to a preset third threshold, it indicates that the synergistic effect of the alteration minerals within the target subset can accurately explain the numerical distribution characteristics of the rock's magnetic susceptibility, and there is no spurious association caused by highly correlated minerals. This target subset can then be considered as the combination of alteration mineral types for the grid region.

[0047] As can be seen from the above, this embodiment, targeting alteration minerals with highly correlated content, accurately eliminates redundant minerals that cause interference and removes spurious correlations between minerals by enumerating all subsets of the second alteration mineral set and substituting them one by one for verification and iterative optimization. This ensures that the final determined combination of alteration mineral types is truly effective in interpreting magnetic susceptibility. Furthermore, determining the order of iterative calculations based on the number of mineral types maximizes the retention of core alteration minerals related to magnetic susceptibility and avoids the omission of alteration minerals.

[0048] In one embodiment of this application, each subset is selected as a target subset in descending order of the number of alteration mineral types contained in each subset, including: All subsets are sorted in the first level according to the number of alteration mineral types contained in each subset from largest to smallest; If there are multiple subsets with the same first-level sort, the subset is taken as the undetermined subset. The sum of the normalization coefficients corresponding to each alteration mineral in each undetermined subset is calculated. The multiple undetermined subsets are sorted in the second level according to the order of the sum of the normalization coefficients from largest to smallest. Based on the order determined by the first-level sort and the second-level sort, each subset is taken as the target subset in turn.

[0049] In this embodiment, when sorting all subsets of the second alteration mineral set, the first-level sorting can be performed by ranking the number of alteration mineral types in each subset from largest to smallest, thus initially determining the priority of each subset to be verified. If multiple subsets have the same number of alteration mineral types, these subsets are designated as undetermined subsets. For each undetermined subset, the standardized coefficients corresponding to all alteration minerals within that subset are accumulated to obtain the sum of the standardized coefficients for each undetermined subset. Then, the second-level sorting of the undetermined subsets is performed according to the descending order of the sum of the standardized coefficients. The results of the first-level and second-level sortings are integrated to achieve the sorting of all subsets.

[0050] As can be seen from the above, this embodiment performs a first-level sorting based on the number of alteration mineral types, which can prioritize the verification of subsets with more complete mineral types and retain the core alteration minerals related to magnetic susceptibility within the grid area to the greatest extent. For undetermined subsets with the same number of alteration mineral types, the standardized coefficients corresponding to all alteration minerals in the subset are accumulated. The higher the sum of the coefficients, the stronger the comprehensive contribution of the minerals in the subset to the magnetic susceptibility of the rock. Using the sum of the standardized coefficients as the sorting basis, subsets with a higher probability of fitting the target and stronger geological rationality can be prioritized to enter the verification stage, greatly reducing the number of invalid iterations and quickly locking in the optimal target subset.

[0051] In one embodiment of this application, the hyperspectral data includes the spectral features of multiple pixels; the target area is divided according to the combination of alteration mineral types using the hyperspectral data to obtain multiple second distribution areas, including: Spectral features of pure mineral pixels in hyperspectral data are extracted to obtain multiple first-endmember spectral features; Each first endmember spectral feature is matched with a preset spectral library, and multiple second endmember spectral features are selected from the multiple first endmember spectral features based on the matching results; each second endmember spectral feature corresponds to an alteration mineral. The spectral features of each pixel are decomposed into a linear combination of the spectral features of each second endmember, and the combination coefficient of each second endmember spectral feature in the linear combination is used as the abundance value of the corresponding alteration mineral. For each pixel, alteration minerals with abundance values ​​greater than a preset abundance threshold are selected to obtain the combination of alteration mineral types for that pixel. Pixels with the same alteration mineral type combination are merged to obtain the second distribution area of ​​the corresponding alteration mineral type combination.

[0052] In this embodiment, existing algorithms such as Pure Pixel Index and Endmember Extraction (N-FINDR) can be used to screen out pure mineral pixels with extremely low spectral mixing and material composition close to that of a single mineral from all pixels in the hyperspectral data. The spectral features of the pure mineral pixels are then extracted to obtain multiple first endmember spectral features. These multiple first endmember spectral features can characterize all dominant alteration minerals with high abundance, strong mineralization correlation, or wide spatial distribution in the target area.

[0053] Each altered mineral possesses unique diagnostic spectral characteristics (such as characteristic absorption peaks and reflectance curve morphology). By comparing the first end-member spectral characteristics with the pure spectra of various standard altered minerals stored in a preset spectral library (such as USGS), the second end-members that are confirmed as altered minerals are screened out, and background end-members such as vegetation, soil, and surrounding rocks are removed to obtain multiple second end-member spectral characteristics.

[0054] Based on this, a Linear Spectral Mixture Model (SMA) is used to decompose the mixed spectral features of each pixel into a linear combination of the spectral features of each second endmember, and the abundance value corresponding to each alteration mineral in each pixel is obtained. For each pixel, alteration minerals with abundance values ​​greater than a preset abundance threshold are selected to obtain the alteration mineral type combination of that pixel; pixels with the same alteration mineral type combination are merged to obtain the second distribution region of the corresponding alteration mineral type combination.

[0055] Based on the same inventive concept, this application also provides an alteration mineral extraction apparatus for implementing the alteration mineral extraction method described above. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the alteration mineral extraction apparatus provided below can be found in the limitations of the alteration mineral extraction method described above, and will not be repeated here.

[0056] This application provides an alteration mineral extraction device, such as... Figure 2 As shown, the altered mineral extraction device 20 includes: a data acquisition module 21, a data fitting module 22, a first region determination module 23, a second region determination module 24, and a region extraction module 25.

[0057] The data acquisition module 21 is used to acquire the characteristic data corresponding to each of multiple rock samples within the target area, as well as the hyperspectral data corresponding to the target area; the characteristic data includes the first magnetic susceptibility data and the content of each of the various alteration minerals contained in the rock samples; The data fitting module 22 is used to fit the fitting relationship between the content of various alteration minerals and the first magnetic susceptibility data based on the characteristic data of multiple rock samples in each grid area within the target area. Based on the fitting results, the regression coefficient corresponding to each alteration mineral is determined, and the combination of alteration mineral types corresponding to the grid area is obtained by screening from the various alteration minerals in the grid area using the regression coefficient. The first region determination module 23 is used to merge grid regions with the same combination of alteration mineral types to obtain multiple first distribution regions; The second region determination module 24 is used to divide the target region according to the combination of alteration mineral types using hyperspectral data to obtain multiple second distribution regions; The region extraction module 25 is used to determine the intersection of the first distribution area and the second distribution area with the same combination of alteration mineral types as the area where the corresponding alteration mineral is located.

[0058] In one embodiment of this application, the data fitting module 22 is specifically used for: The regression coefficients corresponding to each alteration mineral are converted into standardized coefficients, and alteration minerals with standardized coefficients greater than a preset first threshold are selected to obtain the first set of alteration minerals. The combination of alteration mineral types in the grid area is determined based on the first set of alteration minerals.

[0059] In one embodiment of this application, the data fitting module 22 is further configured to: For each alteration mineral in the first alteration mineral set, calculate the first correlation coefficient between the content of the alteration mineral and the first magnetic susceptibility data; if the first correlation coefficient corresponding to the alteration mineral is greater than a preset second threshold, then classify the alteration mineral into the second alteration mineral set. The combination of alteration mineral types in this grid area is determined based on the second alteration mineral set.

[0060] In one embodiment of this application, the data fitting module 22 is further configured to: The normalized weights for each alteration mineral in the second alteration mineral set are determined based on the standardized coefficients corresponding to each alteration mineral in the second alteration mineral set. For each rock sample within the grid area, the content of each target alteration mineral in the rock sample is weighted and summed based on the corresponding normalization weight to obtain the second magnetic susceptibility data corresponding to the rock sample; the target alteration mineral is the alteration mineral included in the second alteration mineral set; Calculate the second correlation coefficient between the first and second magnetic susceptibility data corresponding to multiple rock samples; If the second correlation coefficient is greater than or equal to the preset third threshold, then the second set of alteration minerals is taken as the combination of alteration mineral types for the grid region.

[0061] In one embodiment of this application, for each grid region, if the second correlation coefficient is less than a preset third threshold, the data fitting module 22 is further configured to: Identify all subsets of the second altered mineral set; Each subset is selected as the target subset in descending order of the number of alteration mineral types contained in each subset; The process iteratively executes the following steps: treating each target subset as a second alteration mineral set; determining the normalized weight of each alteration mineral in the second alteration mineral set based on its normalized coefficient; for each rock sample within the grid region, weighting and summing the contents of each target alteration mineral in the rock sample based on its corresponding normalized weight to obtain the second magnetic susceptibility data for that rock sample; calculating the second correlation coefficient between the first and second magnetic susceptibility data for multiple rock samples; until a target subset exists whose second correlation coefficient is greater than or equal to a preset third threshold. The target subset is used as the combination of alteration mineral species for the grid region.

[0062] In one embodiment of this application, the data fitting module 22 is further configured to: All subsets are sorted in the first level according to the number of alteration mineral types contained in each subset from largest to smallest; If there are multiple subsets with the same first-level sort, the subset is taken as the undetermined subset. The sum of the normalization coefficients corresponding to each alteration mineral in each undetermined subset is calculated. The multiple undetermined subsets are sorted in the second level according to the order of the sum of the normalization coefficients from largest to smallest. Based on the order determined by the first-level sort and the second-level sort, each subset is taken as the target subset in turn.

[0063] In one embodiment of this application, the hyperspectral data includes the spectral features of multiple pixels; the second region determination module 24 is specifically used for: Spectral features of pure mineral pixels in hyperspectral data are extracted to obtain multiple first-endmember spectral features; Each first endmember spectral feature is matched with a preset spectral library, and multiple second endmember spectral features are selected from the multiple first endmember spectral features based on the matching results; each second endmember spectral feature corresponds to an alteration mineral. The spectral features of each pixel are decomposed into a linear combination of the spectral features of each second endmember, and the combination coefficient of each second endmember spectral feature in the linear combination is used as the abundance value of the corresponding alteration mineral. For each pixel, alteration minerals with abundance values ​​greater than a preset abundance threshold are selected to obtain the combination of alteration mineral types for that pixel. Pixels with the same alteration mineral type combination are merged to obtain the second distribution area of ​​the corresponding alteration mineral type combination.

[0064] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The functions of the data acquisition module 21, data fitting module 22, first region determination module 23, second region determination module 24, and region extraction module 25 are shown.

[0065] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0066] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0067] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store preset constants such as a first threshold, a second threshold, and a third threshold.

[0068] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the altered mineral extraction method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0069] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0070] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., provided on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0071] Those skilled in the art will recognize that the modules / units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0072] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules, units, or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or modules / units, or it may be an electrical, mechanical, or other form of connection.

[0074] The modules / units described as separate components may or may not be physically separate. Similarly, the components shown as modules / units may or may not be physical modules / units; they may be located in one place or distributed across multiple network modules / units. Some or all of the modules / units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0075] Furthermore, the functional modules / units in the various embodiments of this application can be integrated into one processing module / unit, or each module / unit can exist physically separately, or two or more modules / units can be integrated into one module / unit. The integrated modules / units described above can be implemented in hardware or in the form of software functional modules / units.

[0076] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for extracting altered minerals, characterized in that, include: The system acquires feature data corresponding to multiple rock samples within the target area, as well as hyperspectral data corresponding to the target area. The feature data includes first magnetic susceptibility data and the content of various alteration minerals contained in the rock samples. For each grid area within the target area, the content of each of the various alteration minerals and the first magnetic susceptibility data are fitted based on the characteristic data of multiple rock samples in the grid area. The regression coefficient corresponding to each alteration mineral is determined based on the fitting results. The regression coefficient is used to screen the combination of alteration mineral types corresponding to the grid area from the various alteration minerals in the grid area. By merging grid regions with the same combination of alteration mineral types, multiple primary distribution regions are obtained; The target region is divided according to the combination of alteration mineral types using the hyperspectral data, resulting in multiple secondary distribution regions; The intersection of the first distribution area and the second distribution area with the same combination of alteration minerals is determined as the area where the corresponding alteration mineral is located.

2. The method for extracting altered minerals as described in claim 1, characterized in that, Using the regression coefficients, combinations of alteration mineral types corresponding to the grid region are obtained from various alteration minerals within that grid region, including: The regression coefficients corresponding to each alteration mineral are converted into standardized coefficients, and alteration minerals with standardized coefficients greater than a preset first threshold are selected to obtain the first set of alteration minerals. The combination of alteration mineral types in the grid region is determined based on the first set of alteration minerals.

3. The method for extracting altered minerals as described in claim 2, characterized in that, For each grid region, the combination of alteration mineral types for that grid region is determined based on the first alteration mineral set, including: For each alteration mineral in the first alteration mineral set, a first correlation coefficient is calculated between the content of the alteration mineral and the first magnetic susceptibility data; if the first correlation coefficient corresponding to the alteration mineral is greater than a preset second threshold, then the alteration mineral is classified into the second alteration mineral set. The combination of alteration mineral types in the grid region is determined based on the second set of alteration minerals.

4. The method for extracting altered minerals as described in claim 3, characterized in that, For each grid region, the combination of alteration mineral types for that grid region is determined based on the second alteration mineral set, including: The normalized weight of each alteration mineral in the second alteration mineral set is determined based on the normalized coefficient corresponding to each alteration mineral in the second alteration mineral set; For each rock sample within the grid area, the content of each target alteration mineral in the rock sample is weighted and summed based on the corresponding normalization weight to obtain the second magnetic susceptibility data corresponding to the rock sample; the target alteration mineral is the alteration mineral contained in the second alteration mineral set; Calculate the second correlation coefficient between the first magnetic susceptibility data and the second magnetic susceptibility data corresponding to multiple rock samples; If the second correlation coefficient is greater than or equal to the preset third threshold, then the second set of altered minerals is taken as the combination of altered mineral types in the grid region.

5. The method for extracting altered minerals as described in claim 4, characterized in that, For each grid region, if the second correlation coefficient is less than a preset third threshold, the alteration mineral extraction method further includes: Determine all subsets of the second altered mineral set; Each subset is selected as the target subset in descending order of the number of alteration mineral types contained in each subset; The process involves iteratively executing the following steps: treating each target subset as the second alteration mineral set; determining the normalized weight of each alteration mineral in the second alteration mineral set based on its normalized coefficient; for each rock sample within the grid region, weighting and summing the contents of each target alteration mineral in the rock sample based on its corresponding normalized weight to obtain the second magnetic susceptibility data corresponding to the rock sample; calculating the second correlation coefficient between the first magnetic susceptibility data and the second magnetic susceptibility data corresponding to multiple rock samples, until a target subset exists whose second correlation coefficient is greater than or equal to a preset third threshold. The target subset is used as the combination of alteration mineral species for the grid region.

6. The method for extracting altered minerals as described in claim 5, characterized in that, The step of sequentially selecting each subset as the target subset according to the descending order of the number of alteration mineral types contained in each subset includes: All subsets are sorted in the first level according to the number of alteration mineral types contained in each subset in descending order; If there are multiple subsets with the same first-level sort, the subset is regarded as a pending subset. The sum of the normalization coefficients corresponding to each alteration mineral in each pending subset is calculated. The multiple pending subsets are sorted in the second level according to the order of the sum of the normalization coefficients from largest to smallest. Based on the order determined by the first-level sorting and the second-level sorting, each subset is sequentially taken as the target subset.

7. The method for extracting altered minerals as described in claim 1, characterized in that, The hyperspectral data includes the spectral features of multiple pixels; the target area is divided according to the combination of alteration mineral types using the hyperspectral data to obtain multiple second distribution areas, including: The spectral features of pure mineral pixels in the hyperspectral data are extracted to obtain multiple first endmember spectral features; Each first endmember spectral feature is matched with a preset spectral library, and multiple second endmember spectral features are selected from the multiple first endmember spectral features based on the matching results; each second endmember spectral feature corresponds to an alteration mineral. The spectral features of each pixel are decomposed into a linear combination of the spectral features of each second endmember, and the combination coefficient of each second endmember spectral feature in the linear combination is used as the abundance value of the corresponding alteration mineral. For each pixel, alteration minerals with abundance values ​​greater than a preset abundance threshold are selected to obtain the combination of alteration mineral types for that pixel. Pixels with the same alteration mineral type combination are merged to obtain the second distribution area of ​​the corresponding alteration mineral type combination.

8. An alteration mineral extraction device, characterized in that, include: The data acquisition module is used to acquire the characteristic data corresponding to multiple rock samples within the target area, as well as the hyperspectral data corresponding to the target area; the characteristic data includes first magnetic susceptibility data and the content of various alteration minerals contained in the rock samples; The data fitting module is used to fit the content of each of the multiple alteration minerals and the first magnetic susceptibility data for each grid area within the target area based on the characteristic data of multiple rock samples within the grid area. Based on the fitting results, the module determines the regression coefficient corresponding to each alteration mineral and uses the regression coefficient to screen the combination of alteration mineral types corresponding to the grid area from the multiple alteration minerals within the grid area. The first region determination module is used to merge grid regions with the same combination of alteration mineral types to obtain multiple first distribution regions; The second region determination module is used to divide the target region according to the combination of alteration mineral types using the hyperspectral data to obtain multiple second distribution regions; The region extraction module is used to determine the intersection of the first distribution area and the second distribution area with the same combination of alteration mineral types as the region where the corresponding alteration mineral is located.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images