Lithium geochemical anomaly identification method and system for lithological complex area

Abstract

The invention is suitable for the field of mineral exploration, and provides a lithium geochemical anomaly identification method and system for a lithologic complex region, and the method comprises the following steps: obtaining the geochemical data of the region, and carrying out the preprocessing of the geochemical data of the region; according to the preprocessed geochemical data, determining a PLSR independent variable index; according to the PLSR independent variable indexes, constructing a PLSR regression model; according to the PLSR regression model, determining a lithium geochemical background value of each sample point in the region; and identifying lithium geochemical anomalies of the region according to the prediction upper limit of the lithium geochemical background value. According to the method, the regression model between the lithium and the lithology indication elements is constructed by utilizing the PLSR, so that the lithium geochemical background value of each sample point can be determined, the multi-collinearity problem in lithium multiple linear regression analysis is effectively solved, the calculation accuracy of the lithium geochemical background value of each sample point in a lithology complex region is improved, and the lithium geochemical background value of each sample point in the lithology complex region is calculated. And a solid foundation is laid for lithium geochemical anomaly identification.

Description

Technical Field

[0001] This invention belongs to the field of mineral exploration, and in particular relates to a method and system for identifying lithium geochemical anomalies in lithologically complex areas. Background Technology

[0002] Lithium (Li) is hailed as a "green energy metal" and "white oil," with wide applications in energy storage, metallurgy, and chemicals. In recent years, with the rapid development of the new energy vehicle industry, the demand for lithium resources both domestically and internationally has exploded, gradually increasing the need for lithium mineral resource exploration. In mineral resource exploration, geochemical anomalies are a crucial factor in determining whether further exploration can proceed, making accurate identification of geochemical anomalies of great significance. However, in the identification of lithium geochemical anomalies in lithologically complex areas, variations in elemental background are often a concern.

[0003] Scholars have proposed various solutions to the problem of varying element backgrounds, including the probabilistic lattice method, the fractal method, and unsupervised machine learning algorithms. k Algorithms such as -means clustering and EM clustering have played an important role in addressing elemental background variation, but they all share a common limitation: they cannot obtain the lithium geochemical background value for each sample point. These methods first classify regional geochemical data or samples, and then calculate the lithium background value for each class of samples separately, also known as the local background value. Although this type of method can reduce the influence of lithium background variation, the method of calculating local background values ​​by clustering samples is somewhat crude and insufficient to reflect the background variation of lithium across the entire region.

[0004] Multiple linear regression analysis is a highly effective method for addressing elemental background variation problems, allowing the determination of lithium geochemical background values ​​for each sample point. This method first explores the linear relationship between lithium and lithological indicator elements (such as Si and Al), then establishes a linear regression equation to estimate the lithium background value, effectively eliminating the influence of lithium background variation. However, because geochemical data are typically compositional data with a closure effect, significant correlations often exist between elements. These correlations can lead to multicollinearity in regression analysis, significantly affecting the accuracy of regression coefficients. Multicollinearity limits the application of this method in lithium anomaly identification.

[0005] In summary, determining the geochemical background of elements is a prerequisite for identifying geochemical anomalies. Existing technologies such as probabilistic lattice paper methods, fractal methods, and unsupervised machine learning algorithms can estimate the local background value of lithium, but cannot obtain the background value for each sample point. In addition, multiple linear regression analysis can obtain the lithium geochemical background value for each sample point, but it is significantly affected by multicollinearity, resulting in inaccurate estimation of lithium background values. Summary of the Invention

[0006] The purpose of this invention is to provide a method for identifying lithium geochemical anomalies in lithologically complex regions, thereby addressing the aforementioned technical problems.

[0007] This invention is implemented as follows: a method for identifying lithium geochemical anomalies in lithologically complex areas, comprising the following steps: Acquire regional geochemical data and preprocess the regional geochemical data; Based on the preprocessed geochemical data, the independent variable index of PLSR was determined; Based on the independent variable indicators of PLSR, a PLSR regression model is constructed; The lithium geochemical background value for each sample point in the region was determined based on the PLSR regression model. Based on the upper limit of the predicted lithium geochemical background value, lithium geochemical anomalies in the region are identified.

[0008] Furthermore, the preprocessing steps for geochemical data specifically include: The regional geochemical data were processed using the central logarithmic ratio transformation method, and then outliers were removed iteratively using the 3σ method.

[0009] Furthermore, the steps for determining the independent variable indices of PLSR based on the preprocessed geochemical data specifically include: From the preprocessed geochemical data, lithological indicator elements that can reflect lithology and are not affected by mineralization, such as SiO2, Al2O3, Fe2O3, MgO, CaO, Na2O, K2O, Cr, Zr, Sr, etc., are screened out to form the initial set of independent variables; Calculate the regression coefficient of each independent variable in the initial set of independent variables, iteratively remove lithological indicator elements whose regression coefficients are less than a preset threshold, and determine the PLSR independent variable index.

[0010] Furthermore, the steps for constructing a PLSR regression model based on the PLSR independent variable indicators specifically include: Extracting component variables: Based on the PLSR independent variable index, let X be an n×p independent variable matrix and Y be an n×1 dependent variable vector, where Y is specifically a lithium content data matrix; find the weight vector w1 of the independent variable X in the high-dimensional space, construct the first component variable t1=Xw1, and solve for the weight vector w1 by maximizing the covariance max cov(t1,Y); Establish a regression model: Where c1 is the regression coefficient vector of Y, and E1 is the residual matrix of Y; regression is performed on the independent variable X: X = t 1 q 1T + F 1, where q1 is the regression coefficient vector of X, and F1 is the residual matrix of X; Iterative extraction of multiple component variables: Repeat the above steps for residual matrices E1 and F1 to extract the next pair of component variables t2 and w2, and so on, until a sufficient number of component variables are extracted; the PLSR regression model for lithium is expressed as: L i =XWC T +E; where L i It is the lithium geochemical background value, W is the weight vector. The matrix C is composed of the regression coefficient vector. The resulting matrix, E, is the final residual matrix; Determining the optimal number of component variables: Constructing the coefficient of determination R 2 With the predictive coefficient of determination R p 2 Two evaluation metrics, when R 2 and / or R p 2 Reaching the maximum, and R 2 and R p 2 When the value is closest, the optimal number of component variables can be obtained; where R is the closest. p 2 It can be determined by leave-one-out cross-validation; ; ; The PLSR regression model determines the final lithium geochemical background value based on the optimal number of component variables.

[0011] Furthermore, the steps for identifying regional lithium geochemical anomalies based on the predicted upper limit of lithium geochemical background values ​​specifically include: Based on the PLSR regression model for lithium, the upper limit of the predicted lithium geochemical background value for each sample point is calculated. The upper limit of the predicted lithium geochemical background value for each sample point is used as the background upper limit for the corresponding sample point. Calculate the difference between the actual observed value and the background upper limit to obtain the predicted residual value; Based on the predicted residual values, lithium geochemical anomalies in the region were identified.

[0012] Another object of the present invention is to provide a lithium geochemical anomaly identification system for lithologically complex areas, for implementing the above-mentioned lithium geochemical anomaly identification method, comprising: The data preprocessing module is used to acquire regional geochemical data and preprocess the regional geochemical data. The independent variable determination module is used to determine the PLSR independent variable indicators based on the preprocessed geochemical data. The regression model building module is used to build a PLSR regression model based on the PLSR independent variable indicators. The background value determination module is used to determine the lithium geochemical background value of each sample point in the region based on the PLSR regression model. Anomaly identification module is used to identify lithium geochemical anomalies in a region based on the predicted upper limit of the lithium geochemical background value.

[0013] This invention provides a method for identifying lithium geochemical anomalies in lithologically complex areas. It utilizes PLSR (Lithium Phosphate Regression Synthesis) to construct a regression model between lithium and lithological indicator elements, thereby determining the lithium geochemical background value for each sample point. This effectively solves the multicollinearity problem in lithium multiple linear regression analysis, improving the accuracy of lithium geochemical background value calculation for each sample point in lithologically complex areas and laying a solid foundation for lithium geochemical anomaly identification. Furthermore, this invention can eliminate meaningless or false lithium geochemical anomalies in high-background areas, reducing unnecessary subsequent anomaly verification efforts and lowering exploration risks; and it can identify weak lithium geochemical anomalies in low-background areas, improving exploration success rates. Given the current situation where surface and shallow mineral deposits are increasingly scarce, and the focus of mineral resource exploration is shifting towards finding deep and concealed deposits, weak geochemical anomalies are often more significant. Attached Figure Description

[0014] Figure 1 A flowchart illustrating the lithium geochemical anomaly identification method for lithologically complex regions provided in this embodiment of the invention.

[0015] Figure 2 This is a graph showing the relationship between the number of component variables and the coefficient of determination and the predictive coefficient of determination.

[0016] Figure 3 This is a spatial variation diagram of lithium geochemical background values.

[0017] Figure 4 This is a lithium geochemical anomaly map; in the figure, a represents the lithium geochemical anomaly identification results based on PLSR. b represents the lithium geochemical anomaly identification results based on the [mean + 2 standard deviation] method.

[0018] Figure 5 A schematic diagram of the structure of a lithium geochemical anomaly identification system for lithologically complex regions provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0020] like Figure 1 As shown, in one embodiment of the present invention, a method for identifying lithium geochemical anomalies in lithologically complex regions based on partial least squares regression (PLSR) is provided, specifically including the following steps: S100. Acquire regional geochemical data and preprocess the regional geochemical data; S200. Based on the preprocessed geochemical data, determine the independent variable index of PLSR; S300. Construct a PLSR regression model based on the PLSR independent variable indicators; S400. Based on the PLSR regression model, determine the lithium geochemical background value for each sample point in the region; S500: Identify lithium geochemical anomalies in the region based on the upper limit of the predicted lithium geochemical background value.

[0021] In this embodiment of the invention, a regression model between lithium and lithological indicator elements is established using PLSR to calculate the lithium geochemical background value of each sample point, thereby delineating lithium geochemical anomalies. This effectively solves the multicollinearity problem in lithium multiple linear regression analysis, improves the accuracy of lithium geochemical background value calculation for each sample point in lithologically complex areas, and lays a solid foundation for the identification of lithium geochemical anomalies.

[0022] In a preferred embodiment of the present invention, the step of preprocessing geochemical data specifically includes: The regional geochemical data were processed using the central logarithmic ratio transformation method, and then outliers were removed iteratively using the 3σ method.

[0023] In practical applications, to eliminate the influence of the "closure effect," this embodiment of the invention employs the central logarithmic ratio transformation method to process regional geochemical data. This method not only preserves all elemental information but also exhibits robustness against outliers. The specific calculation formula for a single sample is as follows: ; Where clr(x) represents the data after central logarithmic ratio transformation; x represents the element content; x1, x2...x p These represent the element content of the 1st, 2nd...pth variables, respectively; This is the geometric mean of the sample; subsequently, the 3σ (standard deviation) technique is used to eliminate outliers. The calculation process includes the following two steps: first, calculate the mean and standard deviation of the original data; then, remove values ​​outside the range of [mean ± 3 standard deviations]; repeat the above operation until all data are within the above range.

[0024] In a preferred embodiment of the present invention, the step of determining the PLSR independent variable index based on the preprocessed geochemical data specifically includes: S210. Select lithological indicator elements that reflect lithology and are not affected by mineralization from the preprocessed geochemical data to form the initial set of independent variables; S220. Calculate the regression coefficient of each independent variable in the initial set of independent variables, iteratively remove lithological indicator elements whose regression coefficients are less than a preset threshold, and determine the PLSR independent variable index.

[0025] In practical applications, establishing a PLSR regression model for lithium first requires determining the independent variables. Specifically, lithological indicator elements that reflect lithology, have high stability, and are unaffected by mineralization are selected, such as Cr, La, Ni, Sr, Th, Ti, U, V, Y, Zr, Al2O3, CaO, Fe2O3, K2O, MgO, Na2O, and SiO2. Subsequently, elements with small contributions to modeling are eliminated through iterative analysis of the regression coefficients of each independent variable. A larger regression coefficient indicates a greater contribution to modeling, and vice versa.

[0026] In a preferred embodiment of the present invention, the step of constructing a PLSR regression model based on the PLSR independent variable index specifically includes: S310. Extracting component variables: Based on the PLSR independent variable index, let X be an n×p independent variable matrix and Y be an n×1 dependent variable vector, where Y is specifically a lithium content data matrix; find the weight vector w1 of the independent variable X in the high-dimensional space, construct the first component variable t1=Xw1, and solve for the weight vector w1 by maximizing the covariance max cov(t1,Y). S320. Establish a regression model: Where c1 is the regression coefficient vector of Y, and E1 is the residual matrix of Y; regression is performed on the independent variable X: X = t 1 q 1 T + F 1, where q1 is the regression coefficient vector of X, and F1 is the residual matrix of X; S330. Iterative extraction of multiple component variables: Repeat the above steps for the residual matrices E1 and F1 to extract the next pair of component variables t2 and w2, and so on, until a sufficient number of component variables are extracted; the PLSR regression model of lithium is expressed as: L i =XWC T +E; where L i It is the lithium geochemical background value, W is the weight vector. The matrix C is composed of the regression coefficient vector. The resulting matrix, E, is the final residual matrix; S340. Determine the optimal number of component variables: Construct the coefficient of determination R. 2 With the predictive coefficient of determination R p 2 Two evaluation metrics, when R 2 and / or R p 2 Reaching the maximum, and R 2 and R p 2 When the value is closest, the optimal number of component variables can be obtained; where R is the closest. p 2 It can be determined by leave-one-out cross-validation; ; ; Among them, the sum of squared predicted residuals equals The sum of squared residuals equals The sum of the squares of the actual observations equals , It is the first The actual observed values ​​of each sample Is the first When one sample is removed as a test sample, the model is trained based on the remaining samples and... The first component regression Predicted values ​​for each sample It is the first Predicted values ​​for each sample It is the average of all actual observations. It represents the total number of samples.

[0027] It should be noted that the predictive determination coefficient R0 p 2 The closer the value is to 1, the stronger the predictive power of the PLSR regression model; the coefficient of determination R... 2 The closer the value is to 1, the stronger the explanatory power of the PLSR regression model for the dependent variable.

[0028] S350. Based on the optimal number of component variables, determine the PLSR regression model for the final lithium geochemical background value.

[0029] In a preferred embodiment of the present invention, the step of identifying lithium geochemical anomalies in a region based on the predicted upper limit of lithium geochemical background values ​​specifically includes: S510. Based on the PLSR regression model for lithium, calculate the upper limit of the predicted lithium geochemical background value for each sample point. This represents the reasonable maximum value that the predicted target can reach at a specified confidence level (usually 95%). Upper limit of prediction = predicted value + (t × standard error of prediction), where t is the critical value of a t-distribution with (np-1) degrees of freedom, and the standard error of prediction includes the overall error of the model and the uncertainty of the new observation.

[0030] S520. The predicted upper limit of the lithium geochemical background value of each sample point is used as the background upper limit of the corresponding sample point. S530. Calculate the difference between the actual observed value and the background upper limit to obtain the predicted residual value; S540. Based on the predicted residual values, determine the lithium geochemical anomalies in the region.

[0031] In practical applications, the lithium geochemical background value of each sample point can be determined based on the PLSR regression model of the aforementioned lithium geochemical background value. Considering the uncertainty of the parameter estimation of the PLSR regression model and the random variability of the data itself, the upper limit of the predicted background value can be used to identify anomalies: the upper limit of the predicted background value of each sample point fitted by PLSR is taken as the upper limit of the background of the corresponding sample point, and the difference between the actual observed value and the upper limit of the background is calculated to obtain the predicted residual value. Samples with a predicted residual value greater than 0 can be regarded as anomalous samples, and thus the lithium geochemical anomaly in the region can be determined.

[0032] Taking the identification of lithium geochemical anomalies in river sediments in northeastern Hunan as an example, this paper details the application process and results of the present invention.

[0033] I. Data Preprocessing: Data preprocessing is crucial for PLSR modeling. Before modeling, central logarithmic ratio transformation was performed on 1:200,000 stream sediment geochemical data of northeastern Hunan. Then, the 3σ technique was used to iteratively remove outliers from the data to ensure data quality.

[0034] II. Construction of the PLSR regression model for lithium: 1. Determining Independent Variables: The study area contains granite, monzogranite, granodiorite, sandstone, siltstone, mudstone, slate, and other complex lithologies. Therefore, a sufficient number of elements need to be selected as independent variables to better reflect the lithological characteristics of the study area. Based on the above analysis and the correlation coefficient analysis results of lithium with other elements, lithological indicator elements such as Cr, La, Ni, Sr, Th, Ti, U, V, Y, Zr, Al2O3, CaO, Fe2O3, K2O, MgO, Na2O, and SiO2 were initially selected as independent variables. Then, through multiple iterations, the contribution (regression coefficient) of each independent variable to the model was calculated, and elements with small regression coefficients were eliminated, as they had little effect on the model performance but could lead to overfitting. After multiple iterations to screen the independent variables, the independent variable indicators for the lithium PLSR regression model were finally determined to be Sr, Ti, V, Y, Al2O3, CaO, Fe2O3, K2O, and MgO.

[0035] 2. Model Performance Evaluation: After determining the independent variable indicators, a PLSR regression model for lithium was established. The coefficient of determination R was constructed using the method described above. 2 With the predictive coefficient of determination R p 2 Two evaluation indicators, such as Figure 2 As shown, the R-squared values ​​of the model are displayed for different numbers of component variables. 2 (Fitting) and R p 2 The relationship of (cross-validation). As can be seen from the graph, as the number of component variables increases, R... 2 and R p 2 All values ​​initially rise and then fall; when the number of component variables reaches 6, R... p 2 It reaches its maximum value. Although R reaches its maximum value at this point. 2 The maximum value has not yet been reached, but the difference between the two indicators is minimal. Therefore, according to the optimal model selection criterion, the PLSR regression model is considered optimal at this stage.

[0036] 3. Determining the PLSR regression model for lithium: After determining the optimal number of component variables to be 6, the PLSR regression equation for the lithium geochemical background value was finally established: L i (Background value) = 3.83750 - 0.17707 × Sr - 0.35090 × Ti - 0.17547 × V - 0.32998 × Y + 0.49467 × Al2O3 - 0.08215 × CaO - 0.30069 × Fe2O3 + 0.10333 × K2O + 0.25553 × MgO.

[0037] III. Lithium Anomaly Identification Based on PLSR Regression Model: The lithium geochemical background value for each sample point was calculated based on the PLSR regression equation described above. Significant differences exist in the lithium geochemical background values ​​among different samples (e.g., ...). Figure 3 (As shown in the figure). These differences are closely related to the lithological background of the sample points. Specifically, samples from the northeast and southwest of the study area generally have high lithium geochemical background values. The lithology in these two regions is mainly granitic. During the multi-stage differentiation of magma, lithium gradually accumulates, thus forming areas with high background values. If a traditional uniform background value is used to delineate anomalies across the entire area, these high background areas may be misjudged as anomalous areas. However, their high background values ​​are not caused by mineralization, but are a natural result of the geochemical properties of lithium. Conversely, the metamorphic sandstone, slate, and sandstone areas in the central part of the study area exhibit low background values. If a uniform background value is used for anomaly delineation, it is very likely that weak anomalies in these areas that may reflect mineralization will be overlooked.

[0038] The upper limit of the predicted lithium geochemical background value for each sample point fitted by PLSR was used as the upper limit of the background for the corresponding region. The difference between the actual observed value and the upper limit of the background was calculated, i.e., the prediction residual value. Samples with a prediction residual value greater than 0 were considered anomalous samples. 115 lithium anomalous samples were calculated. The prediction residual values ​​of these anomalous samples were sorted in ascending order, with 0 as the lower limit of anomalousness. The prediction residual values ​​corresponding to 50% and 75% of the cumulative number of anomalous samples were used as the criteria for classifying medium and high anomalies. A lithium geochemical anomaly map was then drawn, as shown below. Figure 4 As shown in a.

[0039] IV. Evaluation of Anomaly Identification Performance: To evaluate the lithium anomaly identification performance of the PLSR regression model, the traditional [mean + 2 standard deviations] method was also used to identify lithium anomalies in the study area, such as... Figure 4 As shown in b. The [mean + 2 standard deviation] method uses the 3σ technique to cyclically eliminate outliers, and then uses the formula: robust mean + 2 robust standard deviation to calculate the upper limit of the uniform background value for the entire area, which is used to identify lithium geochemical anomalies. Comparative analysis of the lithium geochemical anomalies identified by the PLSR regression model method and traditional methods shows that the PLSR regression model identification method provided in this embodiment of the invention significantly improves the identification accuracy of lithium anomalies in the study area, mainly in the following two aspects: (1) Enhanced correlation between anomalies and known lithium deposits (points): Compared with traditional methods, the anomalies identified by the PLSR regression model have a stronger spatial correlation with known lithium deposits (points). For example, the A1 and A3 anomalies delineated by PLSR correspond to two lithium deposits, while anomalies delineated using traditional methods cannot identify these deposits. The reason may be that both deposits are located in low background areas, and anomalies in these areas may be masked by stronger anomalies in other areas.

[0040] (2) Effective reduction of spurious anomalies: The PLSR regression model significantly reduced meaningless anomalies in areas B1 and B2, which are located within granite intrusions where lithium background values ​​are naturally elevated due to the unique geochemical properties of lithium. Traditional methods identified all granite intrusions in the southwestern part of the study area as lithium anomalies; however, no proven mineral deposits were found in these areas. The PLSR regression model successfully narrowed down the anomaly range, focusing on specific areas within the granite and areas in contact with the surrounding rocks. Minimizing such spurious anomalies in high background areas is crucial for the deployment of subsequent exploration work.

[0041] like Figure 5 As shown, in another embodiment of the present invention, a lithium geochemical anomaly identification system for lithologically complex areas is also provided to implement the above-mentioned lithium geochemical anomaly identification method, comprising: The data preprocessing module 10 is used to acquire regional geochemical data and preprocess the regional geochemical data. Independent variable determination module 20 is used to determine PLSR independent variable indicators based on preprocessed geochemical data; The regression model building module 30 is used to build a PLSR regression model based on the PLSR independent variable indicators. Background value determination module 40 is used to determine the lithium geochemical background value of each sample point in the region based on the PLSR regression model. Anomaly identification module 50 is used to identify lithium geochemical anomalies in a region based on the predicted upper limit of the lithium geochemical background value.

[0042] It should be noted that each of the above modules can be implemented as a computer program, which can run on a computer device. The computer device's memory can store the computer program that makes up each module, enabling the processor to execute each step of the above method.

[0043] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0044] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory.

[0045] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A method for identifying lithium geochemical anomalies in lithologically complex areas, characterized in that, Includes the following steps: Acquire regional geochemical data and preprocess the regional geochemical data; Based on the preprocessed geochemical data, the independent variable index of PLSR was determined; Based on the independent variable indicators of PLSR, a PLSR regression model is constructed; The lithium geochemical background value for each sample point in the region was determined based on the PLSR regression model. Based on the upper limit of the predicted lithium geochemical background value, lithium geochemical anomalies in the region are identified.

2. The method for identifying lithium geochemical anomalies in lithologically complex areas according to claim 1, characterized in that, The steps for preprocessing geochemical data specifically include: The regional geochemical data were processed using the central logarithmic ratio transformation method, and then outliers were removed iteratively using the 3σ method.

3. The method for identifying lithium geochemical anomalies in lithologically complex areas according to claim 1, characterized in that, The steps for determining the independent variable indices of PLSR based on preprocessed geochemical data include: From the preprocessed geochemical data, lithological indicator elements that can reflect lithology and are not affected by mineralization are selected to form the initial set of independent variables; Calculate the regression coefficient of each independent variable in the initial set of independent variables, iteratively remove lithological indicator elements whose regression coefficients are less than a preset threshold, and determine the PLSR independent variable index.

4. The method for identifying lithium geochemical anomalies in lithologically complex areas according to claim 1, characterized in that, The steps for constructing a PLSR regression model based on the PLSR independent variable indicators specifically include: Extracting component variables: Based on the PLSR independent variable index, let X be an n×p independent variable matrix and Y be an n×1 dependent variable vector, where Y is specifically a lithium content data matrix; find the weight vector w1 of the independent variable X in the high-dimensional space, construct the first component variable t1=Xw1, and solve for the weight vector w1 by maximizing the covariance max cov(t1,Y); Establish a regression model: Where c1 is the regression coefficient vector of Y, and E1 is the residual matrix of Y; regression is performed on the independent variable X: X = t 1 q 1 T + F 1, where q1 is the regression coefficient vector of X, and F1 is the residual matrix of X; Iterative extraction of multiple component variables: Repeat the above steps for residual matrices E1 and F1 to extract the next pair of component variables t2 and w2, and so on, until a sufficient number of component variables are extracted; the PLSR regression model for lithium is expressed as: L i =XWC T +E; where L i It is the lithium geochemical background value, W is the weight vector. The matrix C is composed of the regression coefficient vector. The resulting matrix, E, is the final residual matrix; Determining the optimal number of component variables: Constructing the coefficient of determination R 2 With the predictive coefficient of determination R p 2 Two evaluation metrics, when R 2 and / or R p 2 Reaching the maximum, and R 2 and R p 2 When the value is closest, the optimal number of component variables can be obtained; where R is the closest. p 2 It can be determined by leave-one-out cross-validation; ； ； The PLSR regression model determines the final lithium geochemical background value based on the optimal number of component variables.

5. The method for identifying lithium geochemical anomalies in lithologically complex areas according to claim 1, characterized in that, The steps for identifying regional lithium geochemical anomalies based on the predicted upper limit of lithium geochemical background values ​​specifically include: Based on the PLSR regression model for lithium, the upper limit of the predicted lithium geochemical background value for each sample point is calculated. The upper limit of the predicted lithium geochemical background value for each sample point is used as the background upper limit for the corresponding sample point. Calculate the difference between the actual observed value and the background upper limit to obtain the predicted residual value; Based on the predicted residual values, lithium geochemical anomalies in the region were identified.

6. A lithium geochemical anomaly identification system for lithologically complex areas, used to implement the lithium geochemical anomaly identification method according to any one of claims 1-5, characterized in that, include: The data preprocessing module is used to acquire regional geochemical data and preprocess the regional geochemical data. The independent variable determination module is used to determine the PLSR independent variable indicators based on the preprocessed geochemical data. The regression model building module is used to build a PLSR regression model based on the PLSR independent variable indicators. The background value determination module is used to determine the lithium geochemical background value of each sample point in the region based on the PLSR regression model. Anomaly identification module is used to identify lithium geochemical anomalies in a region based on the predicted upper limit of the lithium geochemical background value.

Images