GF-5 remote sensing image and ground soil hyperspectrum combined heavy metal content quantitative inversion method and system

Abstract

The invention relates to a heavy metal content quantitative inversion method and system combining a GF-5 remote sensing image and a ground soil hyperspectrum, and the method comprises the steps: obtaining a bare soil image based on a normalized vegetation index value of the GF-5 remote sensing image, and carrying out the DS correction and first-order derivative spectrum transformation of the bare soil image; obtaining ground hyperspectral reflectivity data, soil heavy metal content and remote sensing image hyperspectral reflectivity data of the sampling points; dS correction and first-order derivative spectrum transformation are carried out on the hyperspectral reflectivity data of the remote sensing image; screening remote sensing image hyperspectral reflectivity data after first-order derivative spectral transformation through a Boruta algorithm, and constructing a heavy metal inversion model in combination with the soil heavy metal content; and predicting the bare soil image after the first-order derivative spectral transformation based on a heavy metal inversion model to obtain a heavy metal content pollution spatial distribution diagram. The soil heavy metal pollution condition in a large range can be rapidly and accurately monitored, and a basis is provided for ecological restoration.

Description

Technical Field

[0001] The invention belongs to the technical field of soil heavy metal content hyperspectral remote sensing quantitative inversion, and specifically relates to a heavy metal content quantitative inversion method and system combining GF-5 remote sensing images with ground soil hyperspectral. Background Art

[0002] Heavy metal pollution in soil has become an important research topic in the field of environmental science. The accumulation of heavy metal content will not only have a negative impact on the soil ecosystem, but also pose a serious threat to human health through the food chain. Therefore, how to quickly and accurately monitor the content of heavy metals in soil is of great significance to environmental remediation. Traditional soil heavy metal detection methods usually use field soil collection and laboratory chemical analysis. This method has high detection accuracy but is time-consuming, costly, and difficult to achieve large-scale monitoring.

[0003] At the same time, with the development of remote sensing technology, satellite remote sensing has gradually become the main means of environmental monitoring due to its advantages such as high efficiency and low cost. Among them, hyperspectral remote sensing has been widely used in soil heavy metal pollution monitoring research due to its advantages of strong multi-spectral continuity of bands, making quantitative inversion of soil heavy metal content possible. In particular, the domestically produced GF-5 hyperspectral remote sensing, with a spectral range of 400-2500nm, is consistent with the ground hyperspectral band range and is deeply favored by remote sensing personnel in the field of inverting soil heavy metal content.

[0004] Although the GF-5 image inversion of soil heavy metal content is effective, there are still many technical difficulties in the inversion process due to sensor limitations, natural and human factors. For example, due to the limitation of the spatial resolution of hyperspectral images, soil spectra will be mixed; when measuring the content and spectrum of soil samples, there will be human interference; while hyperspectral has the advantages of multiple bands and high spectral resolution, it also brings problems such as large data redundancy and strong collinearity between bands. In addition, capturing the spectral response of trace elements in soil, especially heavy metals, is still a major challenge. There is still uncertainty in estimating the content of heavy metals in soil using hyperspectral image data. Therefore, there is an urgent need to develop feasible and reliable methods and systems for estimating heavy metal concentrations using GF-5AHSI images. Summary of the invention

[0005] In order to effectively combine the ground indoor spectrum and the GF-5 spectrum to achieve the purpose of large-scale rapid monitoring of soil heavy metal content, the present invention provides a method and system for quantitative inversion of heavy metal content by combining GF-5 remote sensing images with ground soil hyperspectral.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A quantitative inversion method for heavy metal content combining GF-5 remote sensing images and ground soil hyperspectral includes the following steps:

[0008] Collect soil samples at preset sampling points and download GF-5 remote sensing images of the sampling points

[0009] Based on the normalized vegetation index value of the GF-5 remote sensing image, a bare soil image is obtained, and the bare soil image is subjected to DS correction and first-order derivative spectrum transformation to obtain a bare soil image after first-order derivative spectrum transformation;

[0010] Based on the soil samples, ground hyperspectral reflectance data of the sampling points, soil heavy metal content, and GF-5 remote sensing image hyperspectral reflectance data are obtained;

[0011] Taking the ground hyperspectral reflectance data as the standard, performing DS correction on the GF-5 remote sensing image hyperspectral reflectance data, and performing first-order derivative spectral transformation on the GF-5 remote sensing image hyperspectral reflectance data after DS correction;

[0012] The hyperspectral reflectance data of GF-5 remote sensing images after first-order derivative spectral transformation were screened by Boruta algorithm, and combined with the soil heavy metal content to build a heavy metal inversion model;

[0013] Based on the heavy metal inversion model, the bare soil image after the first-order derivative spectrum transformation is predicted to obtain the spatial distribution map of heavy metal content pollution, and complete the quantitative inversion of heavy metal content.

[0014] Preferably, the method for performing DS correction on the GF-5 remote sensing image hyperspectral reflectance data comprises: obtaining DS-corrected GF-5 remote sensing image hyperspectral reflectance data based on a conversion matrix and a residual matrix of ground hyperspectral reflectance data and GF-5 remote sensing image hyperspectral reflectance data, and the calculation formula is as follows:

[0015] X Lab =X GF-5 B+E,

[0016] X′ GF-5 =X GF-5 B+E,

[0017] Among them, X Lab Represents the original ground hyperspectral reflectance data of the sample point, X GF-5 Represents the GF-5 remote sensing image hyperspectral reflectance data of the sample point, B is X Lab and X GF-5 The transformation matrix, E is the residual matrix, X' GF-5 Represents the GF-5 remote sensing image hyperspectral reflectance data after DS conversion.

[0018] Preferably, the method of screening the GF-5 remote sensing image hyperspectral reflectance data after the first-order derivative spectrum transformation by the Boruta algorithm includes:

[0019] The hyperspectral reflectance data of GF-5 remote sensing images after first-order derivative spectral transformation are randomly shuffled as original features to obtain shadow features;

[0020] Based on the shadow features and the original features, a random forest model is constructed and trained;

[0021] Based on the trained random forest model, the importance scores of the original feature and the shadow feature are calculated and compared respectively. When the comparison result of the importance scores meets the preset requirements, the hyperspectral feature band as the important feature is obtained.

[0022] Preferably, the method for constructing a heavy metal inversion model includes: inputting the hyperspectral characteristic band as an independent variable and the soil heavy metal content as a dependent variable into an XGBoost model to construct a heavy metal inversion model based on XGBoost.

[0023] Preferably, the method for constructing the XGBoost model includes:

[0024] A loss function is established based on the actual value of soil heavy metal content and the predicted value of soil heavy metal content predicted by the decision tree;

[0025] Based on the loss function and the regularization term of the decision tree, an objective function of the XGBoost model is obtained;

[0026] Approximating the loss function using a second-order Taylor expansion based on gradient boosting to obtain an approximation of the objective function;

[0027] Based on the approximation of the objective function, the optimal weights of the decision tree leaf nodes in the regularization term are calculated, and based on the optimal weights, the leaf node splitting gains are calculated to obtain the optimal splitting points, thereby completing the construction of the XGBoost model.

[0028] The invention discloses a system for quantitatively inverting heavy metal content by combining GF-5 remote sensing images with ground soil hyperspectral images, and a method for implementing the system includes:

[0029] The collection module is used to collect soil samples at preset sampling points and download the GF-5 remote sensing images of the sampling points.

[0030] A bare soil image acquisition module, used to obtain a bare soil image based on the normalized vegetation index value of the GF-5 remote sensing image, and perform DS correction and first-order derivative spectrum transformation on the bare soil image to obtain a bare soil image after first-order derivative spectrum transformation;

[0031] A data acquisition module, for obtaining ground hyperspectral reflectance data, soil heavy metal content and GF-5 remote sensing image hyperspectral reflectance data of the sampling point based on the soil sample;

[0032] A data transformation module is used to perform DS correction on the GF-5 remote sensing image hyperspectral reflectance data based on ground hyperspectral reflectance data, and perform first-order derivative spectral transformation on the GF-5 remote sensing image hyperspectral reflectance data after DS correction;

[0033] The inversion model building module is used to filter the GF-5 remote sensing image hyperspectral reflectance data after the first-order derivative spectrum transformation through the Boruta algorithm, and build a heavy metal inversion model in combination with the soil heavy metal content;

[0034] The prediction module is used to predict the bare soil image after the first-order derivative spectrum transformation based on the heavy metal inversion model, obtain the spatial distribution map of heavy metal content pollution, and complete the quantitative inversion of heavy metal content.

[0035] Preferably, the inversion model building module includes a band screening unit for screening the GF-5 remote sensing image hyperspectral reflectance data after the first-order derivative spectrum transformation through the Boruta algorithm; the band screening unit includes:

[0036] The shadow feature acquisition subunit is used to randomly shuffle the hyperspectral reflectance data of the GF-5 remote sensing image after the first-order derivative spectrum transformation as the original feature to obtain the shadow feature;

[0037] A random forest construction subunit, used to construct and train a random forest model based on the shadow features and the original features;

[0038] The importance evaluation subunit is used to calculate and compare the importance scores of the original feature and the shadow feature based on the trained random forest model, and when the comparison result of the importance scores meets the preset requirements, the hyperspectral feature band as the important feature is obtained.

[0039] Preferably, in the inversion model construction module, the hyperspectral characteristic band is used as an independent variable, and the soil heavy metal content is input into the XGBoost model as a dependent variable to construct a heavy metal inversion model based on XGBoost.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] (1) High efficiency and accuracy: By combining GF-5 remote sensing images with ground soil hyperspectral data, the present invention can quickly and accurately invert the heavy metal content in the soil, overcoming the time-consuming and high-cost problems of traditional soil detection methods, thereby achieving large-scale environmental monitoring.

[0042] (2) Feature optimization: The present invention uses the DS algorithm to correct the hyperspectral data and uses the Boruta algorithm to screen out key feature bands to ensure the reliability and accuracy of the inversion results. The Boruta algorithm effectively reduces the impact caused by band redundancy; by correcting the GF-5 image spectrum, the problem of poor GF-5 image spectrum quality is solved.

[0043] (3) Spatial distribution visualization: With the help of the XGBoost model, the present invention can not only predict the content of heavy metals in soil, but also generate a spatial distribution map of heavy metal pollution, providing intuitive and easy-to-understand information for environmental management and ecological restoration, and supporting decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0045] Figure 1 This is a flow chart of a method for quantitatively inverting heavy metal content by combining GF-5 remote sensing images with ground soil hyperspectral spectrum according to an embodiment of the present invention;

[0046] Figure 2 The following are examples of the spectral effects before and after DS correction according to the embodiment of the present invention; wherein (a) is the original laboratory spectrum; (b) is the original GF-5 spectrum; (c) is the GF-5 spectrum after DS correction;

[0047] Figure 3 This is an example of the first-order derivative spectrum transformation and characteristic band selection results of the embodiment of the present invention;

[0048] Figure 4 This is a spatial distribution diagram of heavy metal zinc pollution in an embodiment of the present invention;

[0049] Figure 5 This is a spatial distribution diagram of heavy metal lead pollution in an embodiment of the present invention;

[0050] Figure 6 This is a spatial distribution diagram of heavy metal nickel pollution in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] Embodiment 1

[0054] like Figure 1 As shown, a quantitative inversion method for heavy metal content combining GF-5 remote sensing images and ground soil hyperspectral includes the following steps:

[0055] S1: Collect soil samples at preset sampling points and download GF-5 remote sensing images of the sampling points. In this embodiment, the surrounding area of ​​a mining area is used as the experimental point, and 83 5-20 cm surface soils are collected in farmland, mountains, roads and other places accessible to researchers. The number and GPS coordinates of each sample are recorded, and the collected samples are brought back to the laboratory. At the same time, the GF-5 remote sensing images covering the sampling point range are downloaded.

[0056] S2: Based on the normalized vegetation index value of the GF-5 remote sensing image, a bare soil image is obtained, and the bare soil image is subjected to DS correction and first-order derivative spectral transformation to obtain a bare soil image after first-order derivative spectral transformation.

[0057] Specifically, the GF-5 remote sensing image applied for is preprocessed with ENVI software for radiation calibration, atmospheric correction and orthorectification, and the band range of the GF-5 remote sensing image is resampled to 400-2450nm based on the original ground hyperspectral reflectance data in step 1; then the normalized difference vegetation index (NDVI) value of the image is calculated, and Python programming is used to extract the GF-5 image with NDVI < 0.4 as the bare soil area. The NDVI is calculated using the following formula:

[0058]

[0059] Among them, Band431 is the near-infrared band, and Band297 is the red light band;

[0060] Then, according to the GPS coordinates of the sampling points, the ENVI software was used to extract the hyperspectral reflectance data of the bare soil image at the corresponding location.

[0061] The bare soil image after DS correction was transformed by first-order derivative spectrum in ENVI software to ensure that the inverted image and the modeling band values ​​were of the same order of magnitude. The transformed image was used for subsequent prediction of heavy metal content.

[0062] S3: Based on soil samples, obtain the ground hyperspectral reflectance data of the sampling points, soil heavy metal content and GF-5 remote sensing image hyperspectral reflectance data.

[0063] Specifically, the collected soil samples were removed of weeds, stones and other impurities, dried naturally, ground with a grinder and sieved through a 100-mesh sieve, and then measured with an ASD spectrometer to obtain the hyperspectral reflectance data of the soil samples, and the X-ray fluorescence spectrometer (XRF) was used to measure the heavy metal content of the soil samples. The bands with large noise and unstable spectral data at 350-399 and 2451-2500nm in the ground hyperspectral reflectance data measured by ASD were removed, and then the remaining 2051 bands were SG smoothed, and the smoothed data were used as the original ground spectral reflectance data. The heavy metal content measured by XRF was tested for partial distribution, and if the heavy metal content was partial distribution, partial distribution correction was performed.

[0064] S4: Taking the ground hyperspectral reflectance data as the standard, the GF-5 remote sensing image hyperspectral reflectance data is DS corrected, and the first-order derivative spectral transformation of the DS-corrected GF-5 remote sensing image hyperspectral reflectance data is performed with the help of Python.

[0065] Figure 2 In the figure, (a) is the original laboratory spectrum; (b) is the original GF-5 spectrum; (c) is the GF-5 spectrum after DS correction. A further implementation method is that the method for DS correction of GF-5 remote sensing image hyperspectral reflectance data includes: based on the conversion matrix of ground hyperspectral reflectance data and GF-5 remote sensing image hyperspectral reflectance data and the residual matrix, the GF-5 remote sensing image hyperspectral reflectance data after DS correction is obtained, and the calculation formula is as follows:

[0066] X Lab =X GF-5 B+E,

[0067] X′ GF-5 =X GF-5 B+E,

[0068] Among them, X Lab Represents the original ground hyperspectral reflectance data of the sample point, X GF-5 Represents the GF-5 remote sensing image hyperspectral reflectance data of the sample point, B is X Lab and X GF-5 The transformation matrix, E is the residual matrix, X' GF-5Represents the GF-5 remote sensing image hyperspectral reflectance data after DS conversion. Among them, 70% of the original ground hyperspectral reflectance data and GF-5 hyperspectral reflectance data are selected to calculate DS parameters B and E.

[0069] S5: The hyperspectral reflectance data of GF-5 remote sensing images after first-order derivative spectral transformation were screened by Boruta algorithm, and combined with the soil heavy metal content to construct a heavy metal inversion model.

[0070] like Figure 3 As shown, a further implementation method is that the method of screening the GF-5 remote sensing image hyperspectral reflectance data after the first-order derivative spectrum transformation by the Boruta algorithm includes:

[0071] The hyperspectral reflectance data of GF-5 remote sensing images after first-order derivative spectral transformation are randomly shuffled as original features to obtain shadow features;

[0072] Build and train a random forest model based on shadow features and original features;

[0073] Based on the trained random forest model, the importance scores of the original feature and the shadow feature are calculated and compared respectively. If the importance score of the original feature is significantly higher than the score of the shadow feature, the feature is considered "important". If the importance score of the original feature is not higher than the score of the shadow feature, the feature is considered "unimportant". When the comparison result of the importance score meets the above preset requirements, the hyperspectral feature band as the important feature is obtained, and the unimportant features are eliminated. The present invention uses Python programming to call the boruta package to realize feature band selection.

[0074] A further implementation method is that the method for constructing a heavy metal inversion model includes: inputting the hyperspectral characteristic band as an independent variable and the soil heavy metal content as a dependent variable into the XGBoost model to construct a heavy metal inversion model based on XGBoost. Subsequently, the bare soil image after the first-order derivative transformation is input into the trained heavy metal inversion model, and then the bare soil image is processed in blocks, and the heavy metal content value of the bare soil image is predicted in blocks; finally, the predicted image is imported into ArcMap for thematic mapping of the spatial distribution of heavy metal content pollution.

[0075] A further implementation method is that the method for constructing the XGBoost model includes:

[0076] Based on the actual value of soil heavy metal content and the predicted value of soil heavy metal content predicted by the decision tree, a loss function is established; based on the loss function and the regularization term of the decision tree, the objective function of the XGBoost model is obtained.

[0077] Specifically, the objective function of XGBoost can be summarized as follows:

[0078]

[0079] in, is the loss function, which represents the actual value y i With the predicted value The predicted value here is the error between the previous round of predictions. and the prediction of the current tree (f t (x i )) is composed of. Ω(f t ) is a regularization term for the tree, which is used to control the complexity of the model and prevent overfitting.

[0080] The loss function is approximated using the second-order Taylor expansion based on gradient boosting to obtain the approximation of the objective function; specifically, in order to optimize the objective function, XGBoost uses the second-order Taylor expansion to approximate the loss function. That is, the error is quadratically approximated using the first-order derivative (Gradient) and the second-order derivative (Hessian) of the loss function. This enables the model to quickly find the optimal solution. The approximate objective function is:

[0081]

[0082] in, is the first-order gradient, which represents the gradient of the loss function; is the second-order gradient, which represents the curvature of the loss function; Ω(f t ) is the regularization term of the tree, which is used to control the complexity of the tree.

[0083] Based on the approximation of the objective function, the optimal weights of the decision tree leaf nodes in the regularization term are calculated, and based on the optimal weights, the leaf node split gain is calculated to obtain the optimal split point and complete the construction of the XGBoost model. Specifically, XGBoost regularizes the complexity of each tree, and the regularization term is in the form of:

[0084]

[0085] Where: T is the number of leaf nodes in the tree; w j is the weight of the jth leaf node; γ controls the penalty for the number of leaf nodes, and λ controls the penalty for the weight.

[0086] According to the approximate formula of Taylor expansion, XGBoost calculates the optimal weight w for each leaf node. j To optimize the model. The formula for calculating the optimal weight is:

[0087]

[0088] Among them, ∑ i∈j g i is the first-order gradient sum of all samples in the jth leaf node; ∑ i∈j h i is the second-order gradient sum of all samples in the jth leaf node; λ is the regularization parameter used to control the weight of the leaf node.

[0089] In order to select the best split point, XGBoost calculates the change (gain) of the objective function before and after the split. The formula for calculating the gain is:

[0090]

[0091] Where L and R represent the left child node and right child node after the split respectively. i∈L g i and∑ i∈R g i is the sum of the first-order gradients in the left and right child nodes; ∑ i∈L h i and∑ i∈R h i is the sum of the second-order gradients within the left and right child nodes; γ is the leaf node penalty term; this formula indicates that if a split can bring enough gain (i.e., reduce the loss), the split will be performed.

[0092] XGBoost optimizes the model by continuously iterating and generating new trees. Each round of iteration calculates the residual, fits the tree, updates the leaf node weights, calculates the gain, and so on until the loss function can no longer be significantly reduced.

[0093] S6: Based on the heavy metal inversion model, the bare soil image after the first-order derivative spectrum transformation is predicted to obtain the spatial distribution map of heavy metal content pollution and complete the quantitative inversion of heavy metal content. Figure 4 , Figure 5 , Figure 6 shown.

[0094] Embodiment 2

[0095] A system for quantitatively inverting heavy metal content by combining GF-5 remote sensing images with ground soil hyperspectral images of the present invention is used to implement the method described in Example 1, including:

[0096] A collection module, used to collect soil samples at preset sampling points and download GF-5 remote sensing images of the sampling points;

[0097] The bare soil image acquisition module is used to obtain the bare soil image based on the normalized vegetation index value of the GF-5 remote sensing image, and perform DS correction and first-order derivative spectrum transformation on the bare soil image to obtain the bare soil image after the first-order derivative spectrum transformation;

[0098] The data acquisition module is used to obtain the ground hyperspectral reflectance data of the sampling point, the soil heavy metal content and the GF-5 remote sensing image hyperspectral reflectance data based on soil samples;

[0099] The data transformation module is used to perform DS correction on the hyperspectral reflectance data of the GF-5 remote sensing image based on the ground hyperspectral reflectance data, and perform first-order derivative spectral transformation on the GF-5 remote sensing image hyperspectral reflectance data after DS correction;

[0100] The inversion model building module is used to filter the GF-5 remote sensing image hyperspectral reflectance data after the first-order derivative spectrum transformation through the Boruta algorithm, and build a heavy metal inversion model in combination with the soil heavy metal content;

[0101] The prediction module is used to predict the bare soil image after the first-order derivative spectrum transformation based on the heavy metal inversion model, obtain the spatial distribution map of heavy metal content pollution, and complete the quantitative inversion of heavy metal content.

[0102] A further implementation method is that the inversion model construction module includes a band screening unit for screening the GF-5 remote sensing image hyperspectral reflectance data after the first-order derivative spectrum transformation through the Boruta algorithm; the band screening unit includes:

[0103] The shadow feature acquisition subunit is used to randomly shuffle the hyperspectral reflectance data of the GF-5 remote sensing image after the first-order derivative spectrum transformation as the original feature to obtain the shadow feature;

[0104] A random forest construction subunit is used to construct and train a random forest model based on shadow features and original features;

[0105] The importance evaluation subunit is used to calculate and compare the importance scores of the original feature and the shadow feature based on the trained random forest model, and when the comparison result of the importance scores meets the preset requirements, the hyperspectral feature band as the important feature is obtained.

[0106] A further implementation method is that, in the inversion model construction module, the hyperspectral characteristic band is used as an independent variable, and the soil heavy metal content is used as a dependent variable to input into the XGBoost model to construct a heavy metal inversion model based on XGBoost.

[0107] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A quantitative inversion method for heavy metal content combining GF-5 remote sensing images and ground soil hyperspectral, characterized in that: The following steps are involved: Collect soil samples from preset sampling points and download GF-5 remote sensing images of the sampling points; Based on the normalized vegetation index value of the GF-5 remote sensing image, a bare soil image is obtained, and the bare soil image is subjected to DS correction and first-order derivative spectrum transformation to obtain a bare soil image after first-order derivative spectrum transformation; Based on the soil samples, ground hyperspectral reflectance data of the sampling points, soil heavy metal content, and GF-5 remote sensing image hyperspectral reflectance data are obtained; Taking the ground hyperspectral reflectance data as the standard, performing DS correction on the GF-5 remote sensing image hyperspectral reflectance data, and performing first-order derivative spectral transformation on the GF-5 remote sensing image hyperspectral reflectance data after DS correction; The hyperspectral reflectance data of GF-5 remote sensing images after first-order derivative spectral transformation were screened by Boruta algorithm, and combined with the soil heavy metal content to build a heavy metal inversion model; Based on the heavy metal inversion model, the bare soil image after the first-order derivative spectrum transformation is predicted to obtain the spatial distribution map of heavy metal content pollution, and complete the quantitative inversion of heavy metal content.

2. The method for quantitatively inverting heavy metal content by combining GF-5 remote sensing images and ground soil hyperspectral according to claim 1, characterized in that: The method for performing DS correction on the GF-5 remote sensing image hyperspectral reflectance data includes: obtaining DS-corrected GF-5 remote sensing image hyperspectral reflectance data based on the conversion matrix and residual matrix of the ground hyperspectral reflectance data and the GF-5 remote sensing image hyperspectral reflectance data, and the calculation formula is as follows: X Lab =X GF-5 B+E, X′ GF-5 =X GF-5 B+E, Among them, X Lab Represents the original ground hyperspectral reflectance data of the sample point, X GF-5 Represents the GF-5 remote sensing image hyperspectral reflectance data of the sample point, B is X Lab and X GF-5 The transformation matrix, E is the residual matrix, X' GF-5 Represents the GF-5 remote sensing image hyperspectral reflectance data after DS conversion.

3. The method for quantitatively inverting heavy metal content by combining GF-5 remote sensing images and ground soil hyperspectral according to claim 1, characterized in that: The method of screening the hyperspectral reflectance data of GF-5 remote sensing images after the first-order derivative spectral transformation by Boruta algorithm includes: The hyperspectral reflectance data of GF-5 remote sensing images after first-order derivative spectral transformation are randomly shuffled as original features to obtain shadow features; Based on the shadow features and the original features, a random forest model is constructed and trained; Based on the trained random forest model, the importance scores of the original feature and the shadow feature are calculated and compared respectively. When the comparison result of the importance scores meets the preset requirements, the hyperspectral feature band as the important feature is obtained.

4. The method for quantitatively inverting heavy metal content by combining GF-5 remote sensing images and ground soil hyperspectral according to claim 3 is characterized in that: The method for constructing a heavy metal inversion model includes: inputting the hyperspectral characteristic band as an independent variable and the soil heavy metal content as a dependent variable into an XGBoost model to construct a heavy metal inversion model based on XGBoost.

5. The method for quantitatively inverting heavy metal content by combining GF-5 remote sensing images and ground soil hyperspectral according to claim 4, characterized in that: The XGBoost model construction method includes: A loss function is established based on the actual value of soil heavy metal content and the predicted value of soil heavy metal content predicted by the decision tree; Based on the loss function and the regularization term of the decision tree, an objective function of the XGBoost model is obtained; Approximating the loss function using a second-order Taylor expansion based on gradient boosting to obtain an approximation of the objective function; Based on the approximation of the objective function, the optimal weights of the decision tree leaf nodes in the regularization term are calculated, and based on the optimal weights, the leaf node splitting gains are calculated to obtain the optimal splitting points, thereby completing the construction of the XGBoost model.

6. A system for quantitatively inverting heavy metal content by combining GF-5 remote sensing images with ground soil hyperspectral, used to implement any one of the methods of claims 1-5, characterized in that: include: A collection module is used to collect soil samples at preset sampling points and download GF-5 remote sensing images of the sampling points; A bare soil image acquisition module, used to obtain a bare soil image based on the normalized vegetation index value of the GF-5 remote sensing image, and perform DS correction and first-order derivative spectrum transformation on the bare soil image to obtain a bare soil image after first-order derivative spectrum transformation; A data acquisition module, for obtaining ground hyperspectral reflectance data, soil heavy metal content and GF-5 remote sensing image hyperspectral reflectance data of the sampling point based on the soil sample; A data transformation module is used to perform DS correction on the GF-5 remote sensing image hyperspectral reflectance data based on ground hyperspectral reflectance data, and perform first-order derivative spectral transformation on the GF-5 remote sensing image hyperspectral reflectance data after DS correction; The inversion model building module is used to filter the GF-5 remote sensing image hyperspectral reflectance data after the first-order derivative spectrum transformation through the Boruta algorithm, and build a heavy metal inversion model in combination with the soil heavy metal content; The prediction module is used to predict the bare soil image after the first-order derivative spectrum transformation based on the heavy metal inversion model, obtain the spatial distribution map of heavy metal content pollution, and complete the quantitative inversion of heavy metal content.

7. The system for quantitatively inverting heavy metal content by combining GF-5 remote sensing images with ground soil hyperspectral according to claim 6, characterized in that: The inversion model building module includes a band screening unit for screening the GF-5 remote sensing image hyperspectral reflectance data after the first-order derivative spectrum transformation through the Boruta algorithm; the band screening unit includes: The shadow feature acquisition subunit is used to randomly shuffle the hyperspectral reflectance data of the GF-5 remote sensing image after the first-order derivative spectrum transformation as the original feature to obtain the shadow feature; A random forest construction subunit, used to construct and train a random forest model based on the shadow features and the original features; The importance evaluation subunit is used to calculate and compare the importance scores of the original feature and the shadow feature based on the trained random forest model, and when the comparison result of the importance scores meets the preset requirements, the hyperspectral feature band as the important feature is obtained.

8. The system for quantitatively inverting heavy metal content by combining GF-5 remote sensing images with ground soil hyperspectral according to claim 6, characterized in that: In the inversion model construction module, the hyperspectral characteristic band is used as an independent variable, and the soil heavy metal content is used as a dependent variable to input into the XGBoost model to construct a heavy metal inversion model based on XGBoost.

Images