Inversion method and system for abundance of copper element in rock and related equipment

Abstract

The invention relates to the technical field of geological element determination, and discloses a method and a system for inversion of abundance of a copper element in rock and related equipment. The method comprises the following steps: acquiring spectral reflectivity data of a sample in a research area and actually measured content data of a target metal element; carrying out band optimization on the spectral reflectivity data to obtain an optimized characteristic band; based on the optimized characteristic wave band and the actually measured content data of the target metal element, obtaining predicted content data of the target metal element through a remote sensing inversion model; and on the basis of the predicted content data, copper element inversion is carried out by taking copper element related metal elements in the target metal elements as explanatory variables of the indirect inversion model, and copper element abundance is obtained. According to the method, the abundance of the copper element in the rock is indirectly inverted based on hyperspectral remote sensing, and the problem of low prediction precision of the copper element caused by no characteristic wave band in a traditional inversion model is solved; the precision of predicting the content of the copper element is improved; and a basis is provided for large-area application of remote sensing inversion element mapping.

Description

Technical Field

[0001] The present invention relates to the technical field of geological element determination, and in particular to a method, system and related equipment for inversion of copper abundance in rocks. Background Art

[0002] Copper is an important element in geosciences and can be transferred into different systems. The detection of copper content plays a key role in geochemical exploration and the search for mineral deposits. Hyperspectral remote sensing technology can quickly provide efficient technical assistance for estimating the copper content in rocks in (large-scale) uninhabited areas and making rapid indicative judgments on element anomaly areas.

[0003] At present, there are many models for inverting copper content from hyperspectral remote sensing data. The inversion is performed for the copper content in rocks, but the model accuracy is low. Since the characteristic band of copper in the spectral curve is not obvious, and the copper content values ​​in some samples in the mining area are abnormally high, the accuracy of copper inversion directly using reflectance spectrum is low. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method, system and related equipment for inversion of copper abundance in rocks in view of the problems existing in the prior art.

[0005] In a first aspect, the present application provides a method for inverting the abundance of copper in rocks, comprising:

[0006] Obtain spectral reflectance data of samples in the study area and measured content data of target metal elements;

[0007] The target metal elements include copper and at least two copper-related metal elements; the copper-related metal elements refer to metal elements whose correlation coefficient with copper is greater than a preset threshold;

[0008] The characteristic band optimization algorithm is used to optimize the band of spectral reflectance data to obtain the optimized characteristic band;

[0009] Based on the optimized characteristic bands and the measured content data of the target metal elements, the predicted content data of the target metal elements are obtained through the remote sensing inversion model;

[0010] Based on the predicted content data, the copper-related metal elements in the target metal elements are used as explanatory variables of the indirect inversion model to perform copper element inversion and obtain the copper element abundance.

[0011] In a second aspect, the present application provides a system for inverting the abundance of copper in rocks, comprising:

[0012] The measured data acquisition module is used to obtain the spectral reflectance data of the samples in the study area and the measured content data of the target metal elements;

[0013] The target metal elements include copper and at least two copper-related metal elements; the copper-related metal elements refer to metal elements whose correlation coefficient with copper is greater than a preset threshold;

[0014] The characteristic band optimization module is used to optimize the bands of the spectral reflectance data using the characteristic band optimization algorithm to obtain the optimized characteristic bands;

[0015] The remote sensing inversion module is used to obtain the predicted content data of the target metal element through the remote sensing inversion model based on the optimized characteristic bands and the measured content data of the target metal element;

[0016] The indirect inversion module is used to perform copper element inversion based on the predicted content data, taking the copper-related metal elements in the target metal elements as the explanatory variables of the indirect inversion model to obtain the copper element abundance.

[0017] In a third aspect, the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enable the computer to execute the method for inverting the abundance of copper in rocks as provided in the above technical solution.

[0018] In a fourth aspect, the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for inverting the abundance of copper in rocks provided by the above technical solution is implemented.

[0019] In a fifth aspect, the present application also provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the copper abundance inversion method in the rock provided by the above scheme.

[0020] The beneficial effects of the present invention are as follows: first, the predicted content data of the target metal element is obtained through the remote sensing inversion model, wherein the target metal element includes not only the copper element but also the copper-related metal elements; then the copper-related metal elements can be used as the explanatory variables of the indirect inversion model to perform copper element inversion, thereby realizing the indirect inversion of the copper abundance in the rock based on hyperspectral remote sensing, solving the problem of low copper element prediction accuracy due to the lack of characteristic bands in the traditional inversion model; improving the accuracy of predicting the copper content; and providing a basis for large-scale application of remote sensing inversion element mapping.

[0021] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flow chart of a method for inverting copper abundance in rocks, shown as an exemplary embodiment of the present application;

[0023] Figure 2 A flow chart of a method for inverting copper abundance in rocks shown as another exemplary embodiment of the present application;

[0024] Figure 3 is the element inversion accuracy map obtained by direct prediction method;

[0025] Figure 4 It is a schematic diagram of the correlation between copper element and copper-related metal elements;

[0026] Figure 5 The spatial distribution diagrams of copper elements obtained by direct prediction, indirect prediction and actual measurement respectively;

[0027] Figure 6 A block diagram of a copper abundance in rock inversion system shown as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0028] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0029] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0030] The solution provided in the embodiment of the present invention can be executed by any electronic device, for example, a terminal device, or jointly executed by a terminal device and a server. The server can be an independent server, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, etc., and is not limited here.

[0031] Figure 1 The following is a flow chart of a method for inverting the abundance of copper in rocks, as shown in an exemplary embodiment of the present application. Figure 1 As shown, in an exemplary embodiment, the inversion method for copper abundance in rock may include steps S101 to S104, which are described in detail as follows:

[0032] S101, obtaining the spectral reflectance data of the samples in the study area and the measured content data of the target metal elements.

[0033] It should be noted that the samples in the study area are: the samples obtained are distributed in the drilled holes where the ore is found and the areas around the ore body where no ore is found, as well as surface samples, which basically control the entire plane and vertical rock mass. The embodiment of the present invention uniformly samples the ore-bearing area and the non-ore-bearing area, thereby improving the robustness of the established model.

[0034] To ensure the accuracy of the experiment, the sample was cut into a suitable size when the probe distance was 5 cm. Therefore, the sample was cut into a square with a side length of 2.2 cm, which was exactly the surface of the cut slice to maintain the uniformity of the sample surface corresponding to the mineral composition identification, element content and spectrum measurement. The sample was first used for the measurement of reflectance spectrum and then for the measurement of element content.

[0035] The spectral reflectance can be measured by a portable field spectrometer (ASD: Fieldspec4), and the element content can be measured by an X-ray fluorescence spectrometer to analyze the element content of the sample. The spectrum is tested indoors, using a halogen lamp as the light source, and a white board is used for radiation calibration before measurement. ASD is used, the spectral resolution is 3nm / 10nm, the spectral sampling interval is 1nm, the wavelength range is 350-2500nm, and there are 2151 bands in total. It is collected under the standard observation geometry with an incident angle of 30° and an exit angle of 0° (measured from the vertical direction).

[0036] The target metal elements include copper and at least two copper-related metal elements; the copper-related metal elements refer to metal elements whose correlation coefficients with copper are greater than a preset threshold.

[0037] S102, using a characteristic band optimization algorithm to perform band optimization on the spectral reflectance data to obtain an optimized characteristic band;

[0038] S103, based on the optimized characteristic band and the measured content data of the target metal element, obtaining the predicted content data of the target metal element through the remote sensing inversion model;

[0039] S104, based on the predicted content data, copper-related metal elements in the target metal elements are used as explanatory variables of the indirect inversion model to perform copper element inversion to obtain copper element abundance.

[0040] In an embodiment of the present invention, firstly, predicted content data of a target metal element is obtained through a remote sensing inversion model, wherein the target metal element includes not only copper but also copper-related metal elements; then, the copper-related metal elements can be used as explanatory variables of an indirect inversion model to perform copper inversion, thereby realizing indirect inversion of copper abundance in rocks based on hyperspectral remote sensing, solving the problem of low copper prediction accuracy due to the lack of characteristic bands in traditional inversion models; improving the accuracy of predicting copper content; and providing a basis for large-scale application of remote sensing inversion element mapping.

[0041] Optionally, in some exemplary embodiments, the spectral reflectance data is optimized by using a characteristic band optimization algorithm to obtain an optimized characteristic band, including: using a principal component analysis method to convert the n-dimensional original features of the spectral reflectance data into a set of new k orthogonal features; wherein n is the dimension of the original feature, which is determined according to the original data and is the same as the number of known sampling points, and k is the number of orthogonal features, which is also determined according to the data characteristics, with the maximum value being the dimension of the original data feature and the minimum value being 1; reconstructing k orthogonal features according to the n-dimensional original features to obtain an optimized characteristic band. Specifically, the m*n data set is multiplied by the characteristic vector (n*k) of k n-dimensional characteristic vectors to obtain the final reduced-dimensional data.

[0042] In an embodiment of the present invention, the feature band optimization algorithm adopts the principal component analysis method PCA. In the principal component analysis method PCA, a set of mutually orthogonal axes are searched out from the original space in sequence, and the selection of new axes is closely related to the data; principal component analysis can map high-dimensional data to a low-dimensional space while retaining the most important features in the data set.

[0043] Optionally, in some exemplary embodiments, obtaining predicted content data of the target metal element through a remote sensing inversion model includes: performing remote sensing inversion through a random forest method to obtain predicted content data of the target metal element.

[0044] In the embodiment of the present invention, the remote sensing inversion model adopts the random forest method. The random forest is an integrated algorithm composed of decision trees. It is a binary data partitioning algorithm designed to solve data classification and regression problems. It can train decision trees without deleting variables and determine the final result by voting. Random forest can effectively handle problems with a large amount of input data and can still maintain considerable accuracy when the input data contains missing data. As a supervised learning strategy, the random forest method can handle data sets that are mixed with categorical and numerical variables, and can also realize multi-category analysis, and it is not affected by the order of magnitude of different features.

[0045] Optionally, in some exemplary embodiments, copper-related metal elements in the target metal elements are used as explanatory variables of a remote sensing inversion model to perform indirect inversion of copper elements to obtain copper element abundance, including: using copper-related metal elements in the target metal elements as part of an optimized characteristic band to participate in copper element inversion to obtain copper element abundance.

[0046] A simplest model is like y=ax+b. Among them, y represents the content of target metal elements, such as Fe, Ni and Cu, and x represents the hyperspectral characteristic band (usually there are multiple, only one is given here). a and b are the parameters obtained in the model training stage. Direct inversion is to take the copper content as y, and then predict the copper content based on the characteristic band. For example, the direct inversion model of the Cu element is Cu=a(characteristic band)+b. The indirect inversion model is to take the content of Fe and Ni as part of the characteristic band to participate in the prediction of Cu content. The indirect inversion model of Cu is Cu=a(characteristic band, Fe and Ni)+b.

[0047] Optionally, in some exemplary embodiments, the inversion of copper abundance in rocks further includes: interpolating the copper content spatial distribution map using the inverse distance weighted method. Specifically, interpolating the copper content spatial distribution map using the inverse distance weighted method includes:

[0048] Determine the interpolation point (x, y) to the known sampling point Z (x i ,y i ) i :

[0049]

[0050] According to the distance d i , the weight value w of the interpolation point is determined by the following formula i :

[0051]

[0052] In the formula, n is the number of known sampling points, and the known sampling points are obtained by sampling the measured content data of the target metal element. For each position to be interpolated, it is necessary to calculate the distance between the position to be interpolated and all known sampling points, and convert the distance into a weight. Generally speaking, the smaller the distance between the sampling point and the position to be interpolated, the greater the influence of the sampling point on the difference result, so the weight is inversely proportional to the distance.

[0053] According to the weight value w i and all known sampling points Z(x i ,y i ) Calculate the value of the point to be interpolated:

[0054]

[0055] In the formula, z 0 is the value of the point to be interpolated, w i is the weight value, n is the number of known sampling points, Z(x i ,y i are known sampling points.

[0056] In an embodiment of the present invention, a spatial distribution map of copper content is obtained by interpolation using an inverse distance weighted algorithm based on sampling data, which can be used as a labeling map and compared with a subsequent spatial distribution map generated based on model prediction to verify the accuracy of the result.

[0057] The copper abundance in rock inversion method provided by the embodiment of the present invention can realize the indirect inversion of Cu abundance in rock based on hyperspectral remote sensing, which can solve the problem that the characteristic band of Cu element is not obvious or the accuracy of direct prediction of Cu element is not high, and improve the accuracy of predicting Cu element content, providing a basis for the future large-scale application of remote sensing inversion element mapping.

[0058] Figure 2 This is a flow chart of a method for inverting the abundance of copper in rocks, shown in another exemplary embodiment of the present application. Figure 2 As shown, in an exemplary embodiment, the inversion method of copper abundance in rock may include the following steps, which are described in detail as follows:

[0059] (1) Obtain spectral reflectance data of samples in the study area and measured content data of target metal elements;

[0060] To ensure the accuracy of the experiment, the sample was cut into a size suitable for the probe distance of 5 cm. Therefore, the sample was cut into a square with a side length of 2.2 cm, which was exactly the surface of the cut slice to maintain the uniformity of the sample surface corresponding to the mineral composition identification and element content and spectral measurement. The spectral test was carried out indoors using a portable field spectrometer (ASD: Fieldspec4), using a halogen lamp as the light source, and a white board was used for radiation calibration before measurement. The spectral resolution was 3nm / 10nm, the spectral sampling interval was 1nm, and the wavelength range was 350-2500nm, with a total of 2151 bands. These spectra were collected in a dark room under the standard observation geometry of 30° incident angle and 0° exit angle (measured from the vertical direction). All spectral data were smoothed by Savitzky-Gol ay to reduce the influence of laboratory light environment differences and sample pretreatment.

[0061] The samples (rocks) were analyzed in the laboratory using a Niton XL3t950 portable X-ray fluorescence analyzer produced by the American Thermo Scientific (Niton) Company. The instrument working mode was set to copper / zinc mode. The measurement time was set to 120 seconds, and three points were calculated on the same surface of each rock sample to improve the representativeness and stability of the element content results. The element content of the samples was analyzed using an X-ray fluorescence spectrometer. The chemical analysis results are the analysis results of the whole rock samples, so the attached samples of the chemical analysis were directly used for the spectral test. The sample state was consistent, which was conducive to the comparative analysis.

[0062] In this embodiment, the target metal element includes copper and at least two copper-related metal elements, and the copper-related metal elements are selected from iron and nickel.

[0063] (2) Optimization of characteristic bands of spectral reflectance data;

[0064] While providing rich information, hyperspectral remote sensing data also reduces the accuracy and efficiency of modeling to a certain extent. The correlation between bands also increases the complexity of problem analysis. The characteristic band optimization method is principal component analysis. Principal component analysis (PCA) is the most widely used algorithm for dimensionality reduction and band extraction. As the most classic unsupervised dimensionality reduction algorithm, PCA is widely used in the analysis tasks of hyperspectral images (HSIs). The core principle of PCA is to convert n-dimensional features into a new set of k orthogonal features, usually called principal components (PCs), and reconstruct these features based on the original n-dimensional data. In PCA, a set of mutually orthogonal axes are searched out from the original space in sequence. The selection of new axes is closely related to the data.

[0065] After PCA optimization, the contribution rate gradually increases with the increase in the number of principal components, and reaches the maximum contribution rate when the number of principal components is 4.

[0066] (3) Obtain the predicted data of target element content in the study area through remote sensing inversion model;

[0067] The inversion method is the random forest method, which is an integrated algorithm composed of decision trees. It is a binary data partitioning algorithm designed to implement data classification and regression problems. It can train decision trees without removing variables and determine the final result by voting. Random forests can effectively handle problems with a large amount of input data and can still maintain considerable accuracy when the input data contains missing data. As a supervised learning strategy, the random forest method can handle data sets that are mixed with categorical and numerical variables, and can also implement multi-category analysis, and it is not affected by the order of magnitude of different features.

[0068] When the input data is original data, the data optimization method selects principal component analysis to reduce the dimension and inputs the random forest method. Figure 3 is the element inversion accuracy map obtained by direct prediction method, such as Figure 3 As shown, the determination coefficient R of Fe element 2 Reaching 0.69, the R 2 It reaches 0.74, but Cu is only 0.17. It is determined that the copper element has a lower inversion accuracy. The reasons for the low inversion accuracy of the Cu element may be the following two points. The characteristic band of the Cu element in the measured spectral curve of the rock sample is not obvious, and the correlation between the Cu element and the spectral curve is not obvious. Secondly, the Cu element content values ​​in some samples are abnormally high. Therefore, the embodiment of the present invention uses other metal elements with a high correlation with the Cu element to indirectly invert the Cu element in the rock.

[0069] (4) Fe and Ni elements are used as explanatory variables in the inversion of Cu elements;

[0070] Figure 4 This is a schematic diagram of the correlation between copper and copper-related metal elements. Figure 4 It can be seen that the metal elements with the highest correlation with Cu are Fe and Ni, with correlation coefficients r reaching 0.43 and 0.78 respectively. The predicted Fe and Ni elements are added to the characteristic bands as variables to invert the Cu element and obtain a new inversion model.

[0071] (5) Predict the Cu element content based on the new inversion model, and evaluate its spatial distribution and accuracy.

[0072] Fe and Ni were used as explanatory variables, and Cu was used as a predictor variable. 75% of the data set was used to train the model, and 25% was used to verify the model accuracy. Fe and Ni as explanatory variables can improve the inversion accuracy of Cu elements to a certain extent. Compared with the direct method (ORI-PCA-RF), R 2 Increased by 35%.

[0073] Figure 5 The spatial distribution diagrams of copper elements obtained by direct prediction, indirect prediction and actual measurement are shown in Figure 2. The direct prediction and indirect prediction methods are interpolated with the actual Cu element space. From the spatial distribution diagram, it can be seen that the indirect prediction of Cu elements is more intuitive and has higher accuracy than the direct prediction of Cu elements.

[0074] This shows that using other elements related to Cu as explanatory variables to establish an indirect inversion model for Cu is of great significance in improving the inversion of Cu metal elements in rocks. It is possible to consider incorporating more related elements and improving the preprocessing method to further improve the inversion accuracy of Cu elements.

[0075] The copper abundance in rock inversion method provided by the embodiment of the present invention realizes the indirect inversion of copper abundance in rock based on hyperspectral remote sensing, solves the problem of low copper element prediction accuracy due to the lack of characteristic bands in the traditional inversion model; improves the accuracy of predicting Cu element content; and provides a basis for large-scale application of remote sensing inversion element mapping.

[0076] Figure 6 The following is a block diagram of a copper abundance inversion system in a rock according to an exemplary embodiment of the present application. Figure 6 As shown, in an exemplary embodiment, the inversion system for copper abundance in rocks may include a measured data acquisition module, a characteristic band optimization module, a remote sensing inversion module and an indirect inversion module.

[0077] The measured data acquisition module is used to obtain the spectral reflectance data of the samples in the study area and the measured content data of the target metal elements; wherein the target metal elements include copper and at least two copper-related metal elements; the copper-related metal elements refer to metal elements whose correlation coefficient with the copper element is greater than a preset threshold;

[0078] The characteristic band optimization module is used to optimize the bands of the spectral reflectance data using the characteristic band optimization algorithm to obtain the optimized characteristic bands;

[0079] The remote sensing inversion module is used to obtain the predicted content data of the target metal element through the remote sensing inversion model based on the optimized characteristic bands and the measured content data of the target metal element;

[0080] The indirect inversion module is used to perform copper element inversion based on the predicted content data, taking the copper-related metal elements in the target metal elements as the explanatory variables of the indirect inversion model to obtain the copper element abundance.

[0081] In an embodiment of the present invention, firstly, predicted content data of a target metal element is obtained through a remote sensing inversion model, wherein the target metal element includes not only copper but also copper-related metal elements; then, the copper-related metal elements can be used as explanatory variables of an indirect inversion model to perform copper inversion, thereby realizing indirect inversion of copper abundance in rocks based on hyperspectral remote sensing, solving the problem of low copper prediction accuracy due to the lack of characteristic bands in traditional inversion models; improving the accuracy of predicting copper content; and providing a basis for large-scale application of remote sensing inversion element mapping.

[0082] An embodiment of the present invention also provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enable the computer to execute the method for inverting the abundance of copper in rocks provided in any of the above embodiments.

[0083] An embodiment of the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for inverting the abundance of copper in rocks as provided in any of the above embodiments is implemented.

[0084] The embodiment of the present invention also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the copper abundance inversion method in the rock provided in the above various optional embodiments.

[0085] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0088] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0090] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for inverting the abundance of copper in rocks, characterized in that: include: Obtain spectral reflectance data of samples in the study area and measured content data of target metal elements; Wherein, the target metal element includes copper and at least two copper-related metal elements; the copper-related metal element refers to a metal element whose correlation coefficient with copper is greater than a preset threshold; Using a characteristic band optimization algorithm to perform band optimization on the spectral reflectance data to obtain an optimized characteristic band; Based on the optimized characteristic band and the measured content data of the target metal element, the predicted content data of the target metal element is obtained through a remote sensing inversion model; Based on the predicted content data, the copper-related metal elements in the target metal elements are used as explanatory variables of the remote sensing inversion model to perform indirect inversion of the copper element to obtain the copper element abundance.

2. The method according to claim 1, characterized in that The at least two copper-related metal elements include iron and nickel.

3. The method according to claim 1, characterized in that The step of optimizing the spectral reflectance data using a characteristic band optimization algorithm to obtain an optimized characteristic band includes: The n-dimensional original features of the spectral reflectance data are converted into a set of new k orthogonal features using principal component analysis; wherein n is the dimension of the original features, which is the same as the number of known sampling points, and k is the number of orthogonal features; The k orthogonal features are reconstructed according to the n-dimensional original features to obtain the optimized feature bands.

4. The method according to claim 1, characterized in that: The method of obtaining the predicted content data of the target metal element by using the remote sensing inversion model includes: The remote sensing inversion is performed through the random forest method to obtain the predicted content data of the target metal element.

5. The method according to claim 1, characterized in that The method of using the copper-related metal elements in the target metal elements as explanatory variables of the remote sensing inversion model to perform indirect inversion of the copper element to obtain the abundance of the copper element includes: The copper-related metal elements in the target metal elements are used as a part of the optimized characteristic band to participate in the copper element inversion to obtain the copper element abundance.

6. The method according to any one of claims 1 to 5, characterized in that: Also includes: The spatial distribution map of copper content was obtained by interpolation using the inverse distance weighted method.

7. The method according to claim 6, characterized in that The spatial distribution map of copper content obtained by interpolation using the inverse distance weighted method includes: Determine the interpolation point (x, y) to the known sampling point Z (x i ,y i ) i : According to the distance d i , the weight value w of the interpolation point is determined by the following formula i : Wherein, n is the number of known sampling points; the known sampling points are obtained by sampling the measured content data of the target metal element; According to the weight value w i and all known sampling points Z(x i ,y i ) Calculate the value of the point to be interpolated: In the formula, z0 is the value of the point to be interpolated, w i is the weight value, n is the number of known sampling points, Z(x i ,y i are known sampling points.

8. A copper abundance inversion system in rocks, characterized in that: include: The measured data acquisition module is used to obtain the spectral reflectance data of the samples in the study area and the measured content data of the target metal elements; Wherein, the target metal element includes copper and at least two copper-related metal elements; the copper-related metal element refers to a metal element whose correlation coefficient with copper is greater than a preset threshold; A characteristic band optimization module, used to optimize the spectral reflectance data using a characteristic band optimization algorithm to obtain an optimized characteristic band; A remote sensing inversion module, used for obtaining predicted content data of the target metal element through a remote sensing inversion model based on the optimized characteristic band and the measured content data of the target metal element; The indirect inversion module is used to perform copper element inversion based on the predicted content data by taking the copper element-related metal elements in the target metal element as explanatory variables of the indirect inversion model to obtain the copper element abundance.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a computer, the computer is enabled to execute the copper abundance inversion method in rocks as described in any one of claims 1 to 7.

10. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the copper abundance inversion method in rocks as described in any one of claims 1 to 7 when executing the program.

Images