Geochemical anomaly identification method and terminal device

Abstract

This application provides a method and terminal device for geochemical anomaly identification. The method includes: processing raw geochemical data to obtain data blocks; extracting elemental characteristics and spatial features corresponding to each element variable in the raw geochemical data based on the obtained data blocks; reconstructing geochemical data based on the elemental characteristics and spatial features corresponding to each element variable in the raw geochemical data; and identifying geochemical anomalies based on the reconstructed geochemical data and the raw geochemical data. This application can improve the accuracy and effectiveness of geochemical anomaly identification.

Description

Technical Field

[0001] This invention relates to the field of geochemical anomaly extraction technology, and in particular to a geochemical anomaly identification method and terminal equipment. Background Technology

[0002] Geochemical anomalies refer to mineral-induced anomalies. They play a crucial role in mineral exploration. Due to the complexity of mineralization processes, the distribution patterns of geochemical elements exhibit singularity, nonlinearity, and non-stationarity, and their spatial structure also displays complex characteristics. Currently, the main drawback of geochemical anomaly identification methods lies in their low accuracy and effectiveness. Summary of the Invention

[0003] This application provides a method and terminal device for identifying geochemical anomalies, which can solve the problem of low accuracy and effectiveness in identifying geochemical anomalies.

[0004] In a first aspect, embodiments of this application provide a method for identifying geochemical anomalies, including:

[0005] The raw geochemical data is processed to obtain data blocks;

[0006] Based on the obtained data blocks, the elemental characteristics of the original geochemical data and the spatial characteristics corresponding to each element variable in the original geochemical data are extracted.

[0007] Geochemical data reconstruction is performed based on elemental characteristics and the spatial characteristics corresponding to each elemental variable in the original geochemical data;

[0008] Geochemical anomalies are identified based on the reconstructed geochemical data and the original geochemical data obtained from the reconstruction.

[0009] Optionally, the raw geochemical data can be processed to obtain data blocks, including:

[0010] The original geochemical data were transformed using a central logarithmic ratio transformation.

[0011] The transformed raw geochemical data is then gridded; the gridded raw geochemical data is an M-row N-column matrix, and includes raw geochemical data corresponding to L element variables.

[0012] The original geochemical data after gridding is spatially segmented; the original geochemical data corresponding to each of the L element variables is segmented into I overlapping data blocks, each data block being an m-row n-column matrix.

[0013] Optionally, based on the obtained data blocks, the spatial features corresponding to each element variable in the original geochemical data can be extracted, including:

[0014] Divide the i-th data of each of the L element variables into blocks and arrange them row by row to obtain the row pattern matrix R. (i) ;in,

[0015] Through formula Row pattern matrix for the l-th element variable Perform sparse coding; where, Represents the row pattern matrix R (i) The submatrix corresponding to the l-th element variable, l = 1, ..., L, U l This represents the dictionary corresponding to the l-th element variable. U l It contains N1 columns. U l for sparse coefficient matrix;

[0016] Divide the i-th data of each of the L element variables into blocks and arrange them column-wise to obtain the column pattern matrix C. (i) ;in,

[0017] Through formula Column pattern matrix for the l-th element variable Perform sparse coding; where, Represents the column pattern matrix C (i) The submatrix corresponding to the l-th element variable, l = 1, ..., L, V l This represents the dictionary corresponding to the l-th element variable. V l It contains N2 columns. V represents l for sparse coefficient matrix;

[0018] Through formula Calculate the spatial features corresponding to the l-th element variable; where S l Let l represent the spatial characteristics corresponding to the l-th element variable, where l = 1, ..., L.

[0019] Optionally, based on the obtained data blocks, elemental characteristics of the original geochemical data can be extracted, including:

[0020] Vectorize the i-th data of each of the L element variables; where i = 1, 2, ..., I;

[0021] The vectorized data is divided into blocks according to the element variables, resulting in the element pattern matrix E. (i) ;in,

[0022] Through formula For the element pattern matrix E (i) Sparse coding is performed to obtain the elemental characteristics of the original geochemical data; where W represents the elemental characteristics of the original geochemical data. W contains N3 columns. Indicate W for E (i) The sparse coefficient matrix,

[0023] Optionally, geochemical data reconstruction can be performed based on elemental characteristics and the spatial characteristics corresponding to each elemental variable in the original geochemical data, including:

[0024] Based on the element features and the spatial features corresponding to each element variable, we obtain the spatial element features corresponding to each element variable;

[0025] Based on the spatial element characteristics corresponding to each element variable, calculate the sparsity coefficient of each data block obtained by segmentation;

[0026] Geochemical data is reconstructed based on the spatial element characteristics corresponding to each element variable and the sparsity coefficient of each data block obtained by segmentation.

[0027] Optionally, based on the element features and the spatial features corresponding to each element variable, the spatial element features corresponding to each element variable are obtained, including:

[0028] Through formula Calculate the spatial element characteristics corresponding to each element variable;

[0029] Among them, D l w represents the spatial element characteristic corresponding to the l-th element variable. l It is the vector of the l-th row of the element feature W, where l = 1, ..., L.

[0030] Optionally, based on the spatial element characteristics corresponding to each element variable, the sparsity coefficient of each data block obtained from the segmentation is calculated, including:

[0031] Using the alternating direction multiplier method for the formula Solve the problem to obtain the sparsity coefficients of the i-th data block for the l-th element variable;

[0032] Where, vector This represents the vectorized form of the i-th data block with the l-th element variable. vector Let represent the sparsity coefficient of the i-th data block for the l-th element variable. λ a This represents the sparse regularization coefficient.

[0033] Optionally, geochemical data can be reconstructed based on the spatial element characteristics corresponding to each element variable and the sparsity coefficient of each data block obtained from the segmentation, resulting in reconstructed geochemical data, including:

[0034] Through formula Geochemical data reconstruction was performed to obtain reconstructed geochemical data;

[0035] The reconstructed geochemical data includes reconstructed geochemical data corresponding to L elemental variables, a vector. This represents the reconstructed geochemical data corresponding to the l-th element variable, where l = 1, ..., L, and is a vector. This represents the reconstructed geochemical data corresponding to the predefined l-th element variable, x. l This represents the original geochemical data corresponding to the l-th element variable in the original geochemical data. Represents a matrix consisting of 0s and 1s. λ0 and μ are both weighting coefficients used to balance the terms, with symbols... This represents the gradient operator.

[0036] Optionally, based on the reconstructed geochemical data and the original geochemical data, geochemical anomaly identification is performed, including:

[0037] Calculate the reconstruction error of the geochemical data based on the reconstructed geochemical data and the original geochemical data;

[0038] Geochemical anomalies are identified based on reconstruction errors.

[0039] Secondly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described geochemical anomaly identification method.

[0040] The beneficial effects of the embodiments in this application compared with the prior art are:

[0041] In the embodiments of this application, raw geochemical data is processed to obtain data blocks, and elemental characteristics and spatial features corresponding to each element variable in the raw geochemical data are extracted based on the obtained data blocks. Then, geochemical data is reconstructed based on the extracted elemental and spatial characteristics. Finally, geochemical anomaly identification is performed using the reconstructed geochemical data and the raw geochemical data. Because elemental and spatial characteristics are considered in conjunction with geochemical data reconstruction, the reconstructed geochemical data takes into account both spatial nonlocal structures and complex inter-element relationships. Therefore, the geochemical anomaly identification method based on this reconstructed geochemical data can effectively identify multivariate geochemical anomalies, improving the accuracy and effectiveness of geochemical anomaly identification.

[0042] Other beneficial effects of this application will be described in detail in the following detailed description section. Attached Figure Description

[0043] 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.

[0044] Figure 1 This is a flowchart of a geochemical anomaly identification method provided in an embodiment of this application;

[0045] Figure 2 This is a flowchart illustrating a specific implementation of step 13 provided in an embodiment of this application;

[0046] Figure 3 This is a schematic diagram of the ROC curve in an example of this application;

[0047] Figure 4 This is a schematic diagram of the prediction curve in an example of this application;

[0048] Figure 5 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0049] 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.

[0050] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0051] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0052] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [the described condition or event] is detected," or "in response to detection of [the described condition or event]."

[0053] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0054] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0055] To address the issue of low accuracy and effectiveness in geochemical anomaly identification, this application's embodiments combine the elemental characteristics and spatial features of each element variable in the geochemical data during reconstruction. This allows the reconstructed geochemical data to consider both the non-local spatial structure and the complex relationships between elements, thereby enabling the geochemical anomaly identification method based on this reconstructed geochemical data to effectively identify multivariate geochemical anomalies and improve the accuracy and effectiveness of geochemical anomaly identification.

[0056] The geochemical anomaly identification method provided in this application will be described below with reference to specific embodiments.

[0057] This application provides a method for identifying geochemical anomalies. This method can be executed by a terminal device or by a device (such as a chip) applied within the terminal device. The following embodiments use the execution of this method by a terminal device as an example. As an example, the terminal device can be a tablet, server, or laptop computer, etc., and this application does not limit this to any particular type.

[0058] like Figure 1 As shown, the geochemical anomaly identification method provided in this application includes the following steps:

[0059] Step 11: Process the raw geochemical data to obtain data blocks.

[0060] The aforementioned raw geochemical data can be the actual geochemical data of a target region, which can be a geographical area requiring geochemical anomaly identification. Specifically, this raw geochemical data can be obtained by collecting data from the target region using commonly used geochemical data acquisition methods.

[0061] As an optional example, the specific implementation process of step 11 above is as follows:

[0062] The first step is to transform the raw geochemical data using a centered-logratio transformation (clr).

[0063] For example, suppose the original geochemical data is a composition data set X consisting of D row vectors. D ={x1,x2,…,x r ,…,x D}, x r Let clr represent the original geochemical data (i.e., composition data) corresponding to the r-th element variable, where r = 1, 2, ..., D, and D is the total number of element variables in the original geochemical data. Then, the formula for transforming the original geochemical data using clr is: Where g(x) = [x1·x2…·x D ] 1 / D It represents the geometric mean.

[0064] It should be noted that using CLR to transform data is a common transformation method, so the process of this transformation will not be described in detail here.

[0065] The second step is to grid the transformed raw geochemical data; the gridded raw geochemical data is an M-row N-column matrix, and the gridded raw geochemical data includes the raw geochemical data corresponding to L element variables.

[0066] In some embodiments of this application, in order to improve the accuracy and effectiveness of geochemical anomaly identification, the original geochemical data after transformation can be normalized before gridding.

[0067] In some embodiments of this application, to ensure the accuracy of gridding, the original geochemical data can be gridded using an inverse distance weighted interpolation method.

[0068] The third step is to spatially segment the gridded raw geochemical data; whereby the raw geochemical data corresponding to each of the L element variables is segmented into I overlapping data blocks, each data block being an m-row n-column matrix.

[0069] Step 12: Based on the obtained data blocks, extract the elemental characteristics of the original geochemical data and the spatial characteristics corresponding to each element variable in the original geochemical data.

[0070] In some embodiments of this application, sparse coding can be used to extract the aforementioned elemental and spatial features for subsequent geochemical data reconstruction.

[0071] Step 13: Reconstruct geochemical data based on elemental characteristics and the spatial characteristics corresponding to each elemental variable in the original geochemical data.

[0072] Step 14: Based on the reconstructed geochemical data and the original geochemical data obtained from the reconstruction, geochemical anomalies are identified.

[0073] In some embodiments of this application, the reconstruction error of the geochemical data can be calculated first based on the reconstructed geochemical data and the original geochemical data, and then geochemical anomaly identification can be performed based on the reconstruction error.

[0074] In some embodiments of this application, the aforementioned reconstruction error is used to represent the geochemical anomaly score for subsequent geochemical anomaly identification.

[0075] Specifically, it can be done through formulas Calculate the reconstruction error. Where AnomalyScore(e,f) represents the reconstruction error, x efl This represents the elemental abundance value of the l-th element variable at position (e, f) in the original geochemical data, where l = 1, ..., L. This represents the elemental content value of the l-th element variable at position (e,f) in the reconstructed geochemical data.

[0076] In some embodiments of this application, the maximum Youden index can be used to obtain the optimal threshold for distinguishing between anomalies and background. Then, geochemical anomaly scores greater than or equal to the optimal threshold in the reconstruction error are classified as geochemical anomalies, and geochemical anomaly scores less than the optimal threshold are classified as geochemical background, thus achieving geochemical anomaly identification. The calculation process of the Youden index is as follows: Take a point on the Receiver Operating Characteristic Curve (ROC), and the difference between its ordinate (true positive rate) and abscissa (false positive rate) is the Youden index. It should be noted that using the Youden index and reconstruction error for geochemical anomaly identification is a commonly used anomaly identification method; therefore, the Youden index will not be discussed in detail here.

[0077] It is worth mentioning that, in some embodiments of this application, since elemental characteristics and spatial characteristics are considered in combination when reconstructing geochemical data, the reconstructed geochemical data takes into account both the non-local structure in space and the complex correlation between elements. As a result, the geochemical anomaly identification method based on the reconstructed geochemical data can effectively identify multivariate geochemical anomalies and improve the accuracy and effectiveness of geochemical anomaly identification.

[0078] The specific implementation process of step 12 above will be illustrated below.

[0079] In some embodiments of this application, the specific implementation of extracting the spatial features corresponding to each element variable in the raw geochemical data includes the following steps:

[0080] Step 12.1: Divide the i-th data of each of the L element variables into blocks and arrange them by row to obtain the row pattern matrix R. (i) ;in,

[0081] Step 12.2, using the formula Row pattern matrix for the l-th element variable Perform sparse coding; where, Represents the row pattern matrix R (i) The submatrix corresponding to the l-th element variable, l = 1, ..., L, U l This represents the dictionary (i.e., feature set) corresponding to the l-th element variable. U l It contains N1 columns (that is, N1 atoms, which are basis vectors representing elemental characteristics). Ul for The sparse coefficient matrix.

[0082] In some embodiments of this application, U l and This can be obtained by solving the following sparse constraint matrix decomposition problem:

[0083]

[0084] Where, λ R This is the sparsity regularization parameter, which controls the strength of the sparsity regularization. Symbol ||·|| F And ||·||1 represent the Frobenius norm and respectively. norm ( The norm (the commonly used norm) is used. Norm approximation norm ( The norm (a commonly used norm) constrains sparsity, and thus sparsity constraints are used to obtain input data. A simple representation of U l Able to capture the main signal in the input data, when U l When fixed, for The optimization problem can be viewed as Lasso regression; therefore, the above formula can be solved using a non-negative dictionary learning algorithm to obtain U. l and

[0085] Step 12.3: Divide the i-th data of each of the L element variables into blocks and arrange them column-wise to obtain the column pattern matrix C. (i) ;in,

[0086] Step 12.4, using the formula Column pattern matrix for the l-th element variable Perform sparse coding; where, Represents the column pattern matrix C (i) The submatrix corresponding to the l-th element variable, l = 1, ..., L, V l This represents the dictionary (i.e., feature set) corresponding to the l-th element variable. V l It contains N² columns (meaning it has N² atoms, which are basis vectors representing elemental characteristics). V represents l for The sparse coefficient matrix.

[0087] In some embodiments of this application, V l and This can be obtained by solving the following sparse constraint matrix decomposition problem:

[0088]

[0089] Where, λ c This is the sparsity regularization parameter, which controls the strength of the sparsity regularization. (Similar to the above U...) l and The solution process is similar, V l and It can be obtained through a non-negative dictionary learning algorithm.

[0090] Step 12.5, using the formula Calculate the spatial features corresponding to the l-th element variable; where S l This represents the spatial characteristics corresponding to the l-th element variable. symbol This represents the Kronecker product.

[0091] In some embodiments of this application, the specific implementation of extracting elemental features from raw geochemical data includes the following steps:

[0092] Step 12.6: Divide the i-th data of each of the L element variables into blocks and vectorize them; where i = 1, 2, ..., I.

[0093] Step 12.7: Arrange the vectorized data blocks according to the element variables to obtain the element pattern matrix E. (i) ;in,

[0094] Step 12.8, using the formula For the element pattern matrix E (i) Sparse coding is performed to obtain the elemental characteristics of the original geochemical data; where W represents the elemental characteristics (and dictionary) of the original geochemical data. W contains N3 columns (that is, N3 atoms, which are basis vectors representing elemental characteristics). Indicate W for E (i) The sparse coefficient matrix, This can minimize matrix decomposition errors.

[0095] W and This can be obtained by solving the following sparse constraint matrix decomposition problem:

[0096]

[0097] Where, λ EThis is the sparsity regularization parameter, which controls the strength of the sparsity regularization. (Similar to the above U...) l and The solution process is similar, W and It can be obtained through a non-negative dictionary learning algorithm.

[0098] The specific implementation process of step 13 above will be illustrated below.

[0099] In some embodiments of this application, such as Figure 2 As shown, the specific implementation of step 13 above includes the following steps:

[0100] Step 131: Based on the element features and the spatial features corresponding to each element variable, obtain the spatial element features corresponding to each element variable.

[0101] In some embodiments of this application, it can be achieved through formulas Calculate the spatial element features corresponding to each element variable. Where D l w represents the spatial element characteristic corresponding to the l-th element variable. l It is the vector of the l-th row of the element feature W, where l = 1, ..., L, and the symbol is... This represents the Kronecker product.

[0102] Step 132: Calculate the sparsity coefficient of each data block obtained by segmentation based on the spatial element characteristics corresponding to each element variable.

[0103] In some embodiments of this application, the alternating direction multiplier method (ADMM) can be used to solve the following formula to obtain the sparsity coefficients of the i-th data block of the l-th element variable:

[0104]

[0105] Where, vector This represents the vectorized form of the i-th data block with the l-th element variable. vector Let represent the sparsity coefficient of the i-th data block for the l-th element variable. λ a This represents the sparsity regularization coefficient, which controls the sparsity of the sparse coding.

[0106] Specifically, the convex problem in the above formula can be transformed into an ADMM form using ADMM, effectively solving the optimization problem of the above formula and obtaining...

[0107] Step 133: Geochemical data is reconstructed based on the spatial element characteristics corresponding to each element variable and the sparsity coefficient of each data block obtained by segmentation, resulting in reconstructed geochemical data.

[0108] In some embodiments of this application, geochemical data can be reconstructed using the following formula to obtain reconstructed geochemical data:

[0109]

[0110] The final reconstructed geochemical data includes reconstructed geochemical data corresponding to L elemental variables, a vector. This represents the reconstructed geochemical data corresponding to the l-th element variable, where l = 1, ..., L, and is a vector. This represents the reconstructed geochemical data corresponding to the predefined l-th element variable, x. l This represents the original geochemical data corresponding to the l-th element variable in the original geochemical data. Represents a matrix consisting of 0s and 1s. λ0 and μ are both used to balance the terms (i.e., the three terms in the above formula): and The weighting coefficients, with symbols This represents the gradient operator.

[0111] The optimization of the above formula is a simple linear least squares problem, which can be solved directly in a linear fashion:

[0112]

[0113] in, It is the Laplacian matrix generated by gradient operations; It is an identity matrix. Therefore, the reconstructed geochemical data can be directly solved using the above formula.

[0114] It should be noted that the first term in the above formula (i.e. This is to ensure that the information for reconstruction comes from D. l and The second item (i.e.) )express With x l The distance between them can constrain the reconstructed data to approximate the original data x during the reconstruction process. l The third item (i.e.) ) indicates in the gradient domain With x l The distance between the two is obtained by minimizing x. l and The gradient difference between them is used to eliminate the problem of gaps after reconstructing data from overlapping data blocks, ensuring that the reconstructed data can be seamlessly reconstructed from the overlapping data blocks during the reconstruction process.

[0115] In some embodiments of this application, the results of geochemical anomaly identification can be evaluated based on ROC curves and AUC values ​​(AUC value refers to the area under the ROC curve). The spatial correlation between anomaly scores and the distribution of known gold deposits can be used to represent the performance of geochemical anomaly identification. The AUC value is used to quantify the spatial correlation between anomaly scores and known gold deposits. Known gold deposits within the study area (i.e., the target area mentioned above) are used as positive sample data, and some points with very low mineralization probabilities are selected as negative sample data. The AUC value is then calculated using the following formula:

[0116]

[0117]

[0118] Where n is the number of positive samples and p is the number of negative samples. g (g = 1, 2, 3…n) represents the anomaly score of the g-th positive sample, y h (h = 1, 2, 3…p) represents the anomaly score of the h-th positive sample. In practical use, the AUC ranges from 0.5 to 1. The higher the AUC value and the closer it is to 1, the better the performance of the identification method in this application embodiment in identifying geochemical anomalies. An AUC value of 0.5 indicates that the identification result of the identification method in this application embodiment is a random pattern.

[0119] As can be seen, in some embodiments of this application, the identification method of this application can utilize sparse coding to obtain a joint sparse representation of the spatial-elemental structure of geochemical data, comprehensively considering the spatial dimension and elemental dimension of geochemical data, taking into account the spatial structure and elemental correlation of geochemical data, and effectively identifying geochemical anomalies.

[0120] To facilitate understanding of the identification effect of the above geochemical anomaly identification method, a specific example is provided here to illustrate the method.

[0121] In this example, the target area is the Jiaoxi North Gold Mining Cluster in Shandong Province. Geochemical anomaly extraction was performed using geochemical measurements of 39 elements from stream sediments in the case study area as raw data, employing the identification method described in this application. The geochemical data, after CLR transformation, was spatially segmented. The data for each element (i.e., the element variables mentioned earlier) was divided into 16×16 data blocks. After segmentation, each element's data yielded 97 data blocks within the study area.

[0122] Based on the data blocks arranged in three modes, elemental features and spatial features of each element are extracted. The elemental features have 2 atoms (2 columns in the elemental feature matrix), while the spatial features have 10 atoms (10 columns in the spatial feature matrix). Then, a joint spatial elemental feature is obtained from the calculated elemental features and spatial features of each element, containing 10 * 10 * 2 = 200 atoms. The sparsity coefficient for each data block is calculated based on the joint spatial elemental feature. Finally, the complete geochemical data is reconstructed based on the calculated spatial elemental feature and sparsity coefficient.

[0123] Based on the reconstructed geochemical data and the original geochemical data, the reconstruction error is calculated as the geochemical anomaly score.

[0124] The results of geochemical anomaly extraction were evaluated based on ROC curves and AUC values. The ROC curves are shown below. Figure 3 As shown, the predictivity curve is as follows: Figure 4 As shown, AUC = 0.908, indicating that the geochemical anomaly extraction results of the identification method in this application embodiment are closely related to the distribution of known gold deposits, verifying the effectiveness of the identification method in this application embodiment.

[0125] Finally, the optimal threshold for distinguishing anomalies from background is obtained based on the Youden index. In mineral potential prediction, the Youden index has been used to determine the optimal threshold for geochemical anomalies. The Youden index of the identification method in this embodiment is 0.699, corresponding to an anomaly score of 8.454. The value of the Youden index is much greater than 0, indicating that the anomaly score calculated by the identification method in this embodiment is closely related to the distribution of known mineral deposits. Based on the calculation results of the Youden index, we classify the originally continuous geochemical anomaly scores, retaining anomaly scores greater than or equal to the threshold (8.454), removing anomaly scores less than the threshold, and delineating geochemical anomaly regions based on the classification results.

[0126] The terminal device provided in this application will be described exemplarily below with reference to specific embodiments.

[0127] like Figure 5 As shown, embodiments of this application provide a terminal device, such as... Figure 5 As shown, the terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 5 The diagram shows only one processor, a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, wherein the processor D100 executes the computer program D102 to implement the steps in any of the above method embodiments.

[0128] Specifically, when the processor D100 executes the computer program D102, it processes the raw geochemical data to obtain data blocks, extracts elemental characteristics of the raw geochemical data and spatial characteristics corresponding to each element variable in the raw geochemical data based on the obtained data blocks, and then reconstructs the geochemical data based on the extracted elemental and spatial characteristics. Finally, it uses the reconstructed geochemical data and the raw geochemical data to identify geochemical anomalies. Because elemental and spatial characteristics are considered in conjunction with geochemical data reconstruction, the reconstructed geochemical data takes into account both the non-local spatial structure and the complex relationships between elements. Therefore, the geochemical anomaly identification method based on this reconstructed geochemical data can effectively identify multivariate geochemical anomalies, improving the accuracy and effectiveness of geochemical anomaly identification.

[0129] The processor D100 can be a central processing unit (CPU), or it can 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. A general-purpose processor can be a microprocessor or any conventional processor.

[0130] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may be an external storage device of the terminal device D10, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal device D10. Furthermore, the memory D101 may include both internal and external storage units of the terminal device D10. The memory D101 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory D101 can also be used to temporarily store data that has been output or will be output.

[0131] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0132] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0133] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0134] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0135] If the integrated unit is implemented as 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, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. 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 at least: any entity or device capable of carrying computer program code to a terminal device, a recording medium, 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. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0136] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0137] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. 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 implementation should not be considered beyond the scope of this application.

[0138] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0139] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0140] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for identifying geochemical anomalies, characterized by, include: The raw geochemical data is processed to obtain data blocks; Based on the obtained data blocks, the elemental characteristics of the original geochemical data and the spatial characteristics corresponding to each element variable in the original geochemical data are extracted. Geochemical data reconstruction is performed based on the elemental characteristics and the spatial characteristics corresponding to each elemental variable in the original geochemical data. Based on the reconstructed geochemical data and the original geochemical data obtained from the reconstruction, geochemical anomalies are identified. Based on the obtained data blocks, the spatial features corresponding to each element variable in the original geochemical data are extracted, including: The The first element variable in the nth element variable The data blocks are arranged row by row to obtain the row pattern matrix. ;in, , ; Through formula For the first Row pattern matrix of element variables Perform sparse coding; where, Represents the row pattern matrix The corresponding number in the middle A submatrix with element variables, Indicates the first A dictionary corresponding to each element variable , Include Each column express for sparse coefficient matrix; The first data block of each of the element variables is arranged by column to obtain a column mode matrix ; wherein, , , ; Through formula For the first Column pattern matrix of element variables Perform sparse coding; where, Represents column pattern matrix The corresponding number in the middle A submatrix with element variables, , Indicates the first A dictionary corresponding to each element variable , Include Each column express for sparse coefficient matrix; Through formula Calculate the first Spatial features corresponding to each element variable; among which... Indicates the first Spatial characteristics corresponding to each element variable ; The step of extracting elemental characteristics from the original geochemical data based on the obtained data blocks includes: vectorizing the first data block of each of the element variables; wherein ; The element mode matrix is obtained by arranging the data block after vectorization according to element variables ; wherein ; Through formula For element pattern matrix Sparse coding is performed to obtain the elemental characteristics of the original geochemical data; wherein... The elemental characteristics of the raw geochemical data are indicated. , Include Each column express for The sparse coefficient matrix, ; The process of reconstructing geochemical data based on the elemental characteristics and the spatial characteristics corresponding to each elemental variable in the original geochemical data includes: Based on the element features and the spatial features corresponding to each element variable, the spatial element features corresponding to each element variable are obtained; Based on the spatial element characteristics corresponding to each element variable, calculate the sparsity coefficient of each data block obtained by segmentation; Geochemical data is reconstructed based on the spatial element characteristics corresponding to each element variable and the sparsity coefficient of each data block obtained by segmentation.

2. The method of claim 1, wherein, The process of processing the raw geochemical data to obtain data blocks includes: The original geochemical data were transformed using a central logarithmic ratio transformation. The transformed raw geochemical data is then gridded; wherein, the gridded raw geochemical data is a... OK The original geochemical data, after being gridded, includes a matrix of columns. The original geochemical data corresponding to each element variable; The original geochemical data after gridding is spatially segmented; wherein, the... The raw geochemical data corresponding to each element variable in the 1 element variable is divided into 1 Each of the overlapping data blocks is a... OK A matrix of columns.

3. The method of claim 1, wherein, The step of obtaining the spatial element features corresponding to each element variable based on the element features and the spatial features corresponding to each element variable includes: The spatial element feature corresponding to each element variable is calculated by the formula ​ wherein, represents the spatial element feature corresponding to the element variable, is a vector of element features of the row, .

4. The method of claim 3, wherein, The step of calculating the sparsity coefficient of each data block obtained by segmentation based on the spatial element characteristics corresponding to each element variable includes: Using the alternating direction multiplier method for the formula Solving for the first... The first element variable The sparsity coefficient of each data block; Where, vector Indicates the first The first element variable Vectorized form of each data block ,vector Indicates the first The first element variable The sparsity coefficient of each data block. , , This represents the sparse regularization coefficient.

5. The method of claim 4, wherein, The process of reconstructing geochemical data based on the spatial element characteristics corresponding to each element variable and the sparsity coefficient of each data block obtained from the segmentation yields reconstructed geochemical data, including: The geochemical data reconstruction is performed by formula to obtain reconstructed geochemical data. The reconstructed geochemical data includes the aforementioned Reconstructed geochemical data corresponding to each element variable, vector Indicates the first Reconstructed geochemical data corresponding to each element variable ,vector Represents the predefined first Reconstructed geochemical data corresponding to each element variable Indicating the first in the original geochemical data The original geochemical data corresponding to each element variable Represents a matrix consisting of 0s and 1s. , and These are all weighting coefficients used to balance the terms, with symbols... This represents the gradient operator.

6. The method of claim 5, wherein, The process of identifying geochemical anomalies based on the reconstructed geochemical data and the original geochemical data includes: Based on the reconstructed geochemical data and the original geochemical data, calculate the reconstruction error of the geochemical data; Geochemical anomalies are identified based on the reconstruction errors.

7. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the geochemical anomaly identification method as described in any one of claims 1 to 6.

Images