Soil lead element distribution monitoring method and system

Abstract

The invention provides a soil lead element distribution monitoring method and system, and the method comprises the steps: obtaining topographic feature variables, remote sensing index variables, human activity intensity variables and geological feature variables of a plurality of sampling points of a target monitoring region in a specified current monitoring period in a preset variable database, constructing a lead migration potential index, an enhanced vegetation coverage dynamic index and a soil erosion-lead migration coupling index, and obtaining an actual soil lead spatial distribution probability based on a preset soil lead element distribution monitoring model; according to the actual soil lead space distribution probability, based on a preset lead element early warning grading rule, carrying out early warning grading on the sampling points; and according to the early warning level of the sampling point, generating a corresponding lead element early warning instruction and transmitting the lead element early warning instruction to early warning equipment, so that the soil lead element distribution monitoring efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of lead element monitoring, and in particular to a method and system for monitoring the distribution of lead elements in soil. Background Art

[0002] Lead (Pb), a typical toxic heavy metal, accumulates in the environment, causing severe impacts on ecosystems and human health. Against the backdrop of rapid industrialization, the sources of lead pollution are becoming increasingly diverse, primarily from traffic exhaust deposition, smelter emissions, solid waste dumps, and mineral resource extraction. Its spatial distribution exhibits significant heterogeneity and spatial inhomogeneity.

[0003] Traditional methods rely on extensive field sampling and laboratory analysis to determine soil lead levels. While these methods offer excellent accuracy at point-level detection, the high cost of sampling and testing limits their application across large areas. Furthermore, data processing and analysis require significant time and human resources, resulting in inefficient monitoring of soil lead distribution. Summary of the Invention

[0004] Based on this, the object of the present invention is to provide a soil lead element distribution monitoring method and system that improves the efficiency of soil lead element distribution monitoring.

[0005] A method for monitoring the distribution of lead in soil comprises the following steps:

[0006] In a preset variable database, terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables of a plurality of sampling points in a target monitoring area during a specified current monitoring period are obtained, wherein the terrain characteristic variables include at least slope, slope length, soil permeability coefficient, and terrain moisture index; the remote sensing index variables include at least enhanced vegetation index and plant cover index; and the human activity intensity variables include at least land use type;

[0007] Obtaining the soil saturated hydraulic conductivity threshold value at the sampling point, combining the soil permeability coefficient and the terrain moisture index, analyzing the spatial redistribution capacity of topography-driven hydraulic erosion on soil lead, and obtaining a lead migration potential index;

[0008] Obtaining the maximum enhanced vegetation index and the minimum enhanced vegetation index of the sampling point in the current monitoring period, analyzing the effect of plant cover on lead absorption, and obtaining an enhanced vegetation cover dynamic index;

[0009] Obtaining the average rainfall and soil erodibility index of the sampling point during the current monitoring period;

[0010] Based on the average rainfall, soil erodibility index, slope length, slope gradient, plant cover index, and land use type, the driving effect of soil erosion on soil lead migration was analyzed to obtain a soil erosion-lead migration coupling index;

[0011] According to the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index and soil erosion-lead migration coupling index, based on a preset soil lead element distribution monitoring model, the actual soil lead spatial distribution probability is obtained;

[0012] According to the actual spatial distribution probability of soil lead, based on the preset lead element warning level classification rules, the sampling points are classified into warning levels;

[0013] According to the warning level of the sampling point, a corresponding lead element warning instruction is generated and the lead element warning instruction is transmitted to the warning device.

[0014] The present application also provides a soil lead element distribution monitoring system, comprising:

[0015] Variable acquisition module: used to obtain terrain characteristic variables, remote sensing index variables, human activity intensity variables and geological characteristic variables of several sampling points in the target monitoring area during the current monitoring period from a preset variable database, wherein the terrain characteristic variables include at least: slope, slope length, soil permeability coefficient and terrain moisture index; the remote sensing index variables include at least: enhanced vegetation index and plant cover index; the human activity intensity variables include at least: land use type;

[0016] A lead migration potential index acquisition module is used to obtain the soil saturated hydraulic conductivity threshold of the sampling point, and analyze the spatial redistribution capacity of soil lead due to topography-driven hydraulic erosion in combination with the soil permeability coefficient and the topographic moisture index to obtain the lead migration potential index;

[0017] Enhanced vegetation cover dynamic index acquisition module: used to obtain the maximum enhanced vegetation index and the minimum enhanced vegetation index of the sampling point in the current monitoring period, analyze the impact of plant cover on lead absorption, and obtain the enhanced vegetation cover dynamic index;

[0018] Environmental factor acquisition module: used to obtain the average rainfall and land erodibility index of the sampling point in the current monitoring period;

[0019] Soil erosion-lead migration coupling index acquisition module: used to analyze the driving effect of soil erosion on soil lead migration based on the average rainfall, land erodibility index, slope length, slope gradient, plant cover index, and land use type, and obtain the soil erosion-lead migration coupling index;

[0020] Actual soil lead content acquisition module: used to obtain the actual soil lead spatial distribution probability based on the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index and soil erosion-lead migration coupling index based on a preset soil lead element distribution monitoring model;

[0021] Warning level classification module: used to classify the sampling points into warning levels according to the actual soil lead spatial distribution probability and the preset lead element warning level classification rules;

[0022] The warning instruction transmission module is used to generate a corresponding lead element warning instruction according to the warning level of the sampling point and transmit the lead element warning instruction to the warning device.

[0023] Compared to existing technologies, this solution uses remote sensing and GIS technologies to acquire topographic characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables. It then constructs a lead migration potential index, which quantifies the spatial redistribution of lead by topographically driven hydraulic erosion; an enhanced vegetation cover dynamics index, which quantifies the impact of vegetation cover changes on lead absorption; and a soil erosion-lead migration coupling index, which quantifies the driving effect of soil erosion on lead migration. By combining topographic characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables, and based on a pre-constructed soil lead distribution monitoring model, the actual spatial distribution probability of soil lead is determined, thereby determining the soil lead risk probability in the target detection area. This improves the reliability of soil lead monitoring while, to a certain extent, reducing reliance on field sampling, thereby reducing the workload of manual field sampling, expanding the monitoring scope, and effectively improving the efficiency of soil lead content monitoring.

[0024] In order to provide a clearer understanding of the present application, the specific implementation methods of the present application will be described below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flow chart of a method for monitoring soil lead distribution is provided for this application;

[0026] Figure 2 This is a flow chart of a method for obtaining a soil erosion-lead migration coupling index in a soil lead element distribution monitoring method of this application;

[0027] Figure 3 This is a flow chart of a method for obtaining the actual spatial distribution probability of soil lead in a soil lead element distribution monitoring method of this application;

[0028] Figure 4A flow chart of a method for screening terrain characteristic variables, remote sensing index variables, human activity intensity variables and geological characteristic variables in a soil lead element distribution monitoring method of this application;

[0029] Figure 5 This is a flow chart of a method for constructing a soil lead element distribution monitoring model in a soil lead element distribution monitoring method of this application;

[0030] Figure 6 A flow chart of a method for obtaining an improved decision tree model in a soil lead element distribution monitoring method for this application;

[0031] Figure 7 This is a flow chart of a method for constructing the spatial weighted loss function in a soil lead element distribution monitoring method of this application;

[0032] Figure 8 This is a schematic diagram of a soil lead distribution monitoring system for this application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0034] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations in the flowcharts may be implemented out of sequence, and steps that do not have a logical contextual relationship may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the contents of this application, may add one or more other operations to the flowcharts, or may remove one or more operations from the flowcharts.

[0035] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] Example 1

[0037] See also Figure 1 , Figure 1This is a flow chart of a method for monitoring the distribution of lead in soil. This application provides a method for monitoring the distribution of lead in soil, specifically comprising the following steps:

[0038] S1: Obtaining, from a preset variable database, terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables of a plurality of sampling points in a target monitoring area during a specified current monitoring period, wherein the terrain characteristic variables include at least slope, slope length, soil permeability, and terrain moisture index; the remote sensing index variables include at least enhanced vegetation index and plant cover index; and the human activity intensity variables include at least land use type;

[0039] S2: Obtaining the soil saturated hydraulic conductivity threshold of the sampling point, combining the soil permeability coefficient and the terrain moisture index, analyzing the spatial redistribution capacity of topography-driven hydraulic erosion on soil lead, and obtaining the lead migration potential index;

[0040] S3: Obtaining the maximum enhanced vegetation index and the minimum enhanced vegetation index of the sampling point in the current monitoring period, analyzing the effect of plant cover on lead absorption, and obtaining an enhanced vegetation cover dynamic index;

[0041] S4: Obtaining the average rainfall and soil erodibility index of the sampling point in the current monitoring period;

[0042] S5: Analyze the driving effect of soil erosion on soil lead migration based on the average rainfall, soil erodibility index, slope length, slope gradient, plant cover index, and land use type to obtain a soil erosion-lead migration coupling index;

[0043] S6: Obtaining the actual soil lead spatial distribution probability based on a preset soil lead element distribution monitoring model according to the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index, and soil erosion-lead migration coupling index;

[0044] S7: classifying the sampling points into warning levels according to the actual spatial distribution probability of soil lead and a preset lead element warning level classification rule;

[0045] S8: Generate a corresponding lead element warning instruction according to the warning level of the sampling point and transmit the lead element warning instruction to the warning device.

[0046] The soil lead distribution monitoring method of the present invention can be executed by a computer system comprising a variable database server, a data acquisition server, and a soil lead distribution analysis server. The variable database server is configured to construct a variable database that stores several sets of historical natural factor variables, historical human factor variables, historical lead content data, actual historical natural factor variables, actual human factor variables, and variable datasets for the target monitoring area.

[0047] The data acquisition server is used to obtain terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, soil saturated hydraulic conductivity threshold, average rainfall and land erodibility index of several sampling points in the target monitoring area from the variable database server, and send them to the soil lead element distribution analysis server for processing.

[0048] The soil lead element distribution analysis server executes the soil lead element distribution monitoring method of the present invention to calculate the lead migration potential index, the enhanced vegetation cover dynamic index and the soil erosion-lead migration coupling index, and combines terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables. Based on the pre-constructed soil erosion-lead migration coupling index, the actual soil lead spatial distribution probability is obtained to complete the monitoring of the soil lead element in the target monitoring area.

[0049] This scheme uses remote sensing and GIS technologies to obtain terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables. The lead migration potential index is constructed to quantify the spatial redistribution capacity of lead due to terrain-driven hydraulic erosion; the enhanced vegetation cover dynamic index is constructed to quantify the impact of vegetation cover changes on lead absorption; and the soil erosion-lead migration coupling index is constructed to quantify the driving effect of soil erosion on lead migration. Combining terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables, based on a pre-constructed soil lead distribution monitoring model, the actual soil lead spatial distribution probability is obtained, thereby determining the soil lead risk probability in the target detection area. This can improve the reliability of soil lead monitoring while reducing reliance on field sampling to a certain extent, thereby reducing the workload of manual field sampling, expanding the monitoring scope, and effectively improving the monitoring efficiency of soil lead content.

[0050] Regarding step S1, in this embodiment, the terrain characteristic variables include: elevation, slope, slope length, curvature, terrain moisture index, soil permeability coefficient, terrain position index, and surface roughness. The elevation, slope, slope length, curvature, terrain moisture index, terrain position index, and surface roughness are acquired using GIS technology and stored in the variable database server. The soil permeability coefficient can be acquired from a database of a relevant geographic department in the target monitoring area and stored in the variable database server.

[0051] The remote sensing index variables include: NIR, RED, BLUE, NDSI, BI, SI, SWIR1 / NIR ratio, SWIR2 / Red ratio, B11-B4 difference, B8A / B11 ratio, Enhanced Vegetation Index, and Plant Cover Index. The NDSI, BI, SI, SWIR1 / NIR ratio, SWIR2 / Red ratio, B11-B4 difference, and B8A / B11 ratio can be obtained through remote sensing technology and stored in the variable database server.

[0052] According to NIR, RED, and BLUE, based on the enhanced vegetation index calculation formula, the enhanced vegetation index is obtained:

[0053]

[0054] Wherein, EVI is the enhanced vegetation index, NIR is the reflectance of the near-infrared band, RED is the reflectance of the red light band, and BLUE is the reflectance of the blue light band.

[0055] The vegetation coverage factor can be based on an empirical formula of remote sensing index. Taking the normalized vegetation index of the sampling point as an example, the vegetation coverage factor can be calculated by the following formula:

[0056]

[0057] Where v is the vegetation coverage factor, NDVI is the normalized vegetation index of the sampling point, and NDVI is the soil The normalized difference vegetation index (NDVI) of the bare soil or low vegetation cover area at the sampling point is soil is the normalized vegetation index of the complete vegetation cover at the sampling point.

[0058] In other embodiments, the near-infrared band reflectance of the bare soil or low vegetation coverage area and the near-infrared band reflectance of the complete vegetation coverage area at the sampling point may be obtained, and the vegetation coverage factor may be calculated based on the following formula:

[0059]

[0060] Where v is the vegetation coverage factor, NIR is the near infrared band reflectance of the sampling point, and NIR soil NIR is the near-infrared reflectance of the bare soil or low vegetation cover area at the sampling point. soil is the near-infrared reflectance of the complete vegetation coverage at the sampling point.

[0061] The human activity intensity variables include at least: land use type, road density, residential area density, population density, night light intensity, industrial and mining enterprise distribution density, agricultural cultivated area proportion and built-up area proportion, which can be obtained through GIS and remote sensing technology, or obtained from the database that manages the target monitoring area and stored in the variable database server.

[0062] The geological characteristic variables include: natural neighbor weighted interpolation of lead mine points, natural neighbor weighted interpolation of zinc mine points, natural neighbor weighted interpolation of silver mine points, natural neighbor weighted interpolation of copper mine points, natural neighbor weighted interpolation of pyrite mine points and natural neighbor weighted interpolation of polymetallic mine points, etc., which are obtained from the database of the geological and mineral resources department that manages the target monitoring area and stored in the variable database server.

[0063] After obtaining the terrain characteristic variables, remote sensing index variables, human activity intensity variables and geological characteristic variables, they are all uniformly resampled to a spatial resolution of 30 meters, and are subjected to standardization and normalization processing such as Z-score processing or Min-Max processing to eliminate dimensional differences.

[0064] In other embodiments, the terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables may be adaptively adjusted according to actual lead element monitoring requirements.

[0065] In step S2, the soil saturated hydraulic conductivity threshold is used to describe the water conductivity of the soil under saturation. It can be obtained from the soil database of the relevant geographical department and stored in the variable database server. The soil saturated hydraulic conductivity threshold of the sampling point is obtained, combined with the soil permeability coefficient and the terrain moisture index, to analyze the spatial redistribution capacity of soil lead due to terrain-driven hydraulic erosion, and obtain the lead migration potential index, including:

[0066] According to the soil permeability coefficient, the terrain moisture index and the soil saturated hydraulic conductivity threshold, based on a preset soil lead migration potential calculation formula, the lead migration potential index is obtained:

[0067]

[0068] Where, T Pbis the lead migration potential index, TWI is the terrain wetness index, R is the soil permeability coefficient, is the soil saturated hydraulic conductivity threshold.

[0069] In step S3, for the same sampling point, the value of the Enhanced Vegetation Index may vary due to factors such as the vegetation growth cycle, seasonal changes, and weather conditions. By monitoring and analyzing the EVI values ​​at different time points during the same monitoring cycle at the same sampling point, the maximum and minimum Enhanced Vegetation Indexes can be obtained.

[0070] The obtaining of the maximum enhanced vegetation index and the minimum enhanced vegetation index of the sampling point in the current monitoring period, analyzing the effect of plant cover on lead absorption, and obtaining the enhanced vegetation cover dynamic index includes:

[0071] VD=EVI max -EVI min / EVI max +EVI min

[0072] Where VD is the enhanced vegetation cover dynamic index, EVI max is the maximum enhanced vegetation index, EVI min is the minimum enhanced vegetation index.

[0073] For steps S4 and S5, the average rainfall can be obtained from rainfall data of a local meteorological station in the target monitoring area. The soil erodibility index can be obtained from a local soil database in the target area.

[0074] Please also see Figure 2 , Figure 2 This is a flow chart of a method for obtaining a soil erosion-lead migration coupling index in a soil lead distribution monitoring method of this application. The method analyzes the driving effect of soil erosion on soil lead migration based on the average rainfall, soil erodibility index, slope length, slope gradient, plant cover index, and land use type to obtain the soil erosion-lead migration coupling index, including:

[0075] S51: Obtaining a corresponding land use type value according to the land use type and based on a preset land use type value mapping rule;

[0076] S52: Based on the slope length and slope, and based on a preset formula, the driving effect of soil erosion on lead migration is analyzed to obtain slope length and slope variables:

[0077]

[0078] Wherein, TP is the slope length and slope variable, length is the slope length, slope is the slope, z and c are the preset first and second empirical coefficients respectively;

[0079] S53: normalizing the average rainfall and the soil erodibility index respectively to obtain a standard average rainfall and a standard soil erodibility index;

[0080] S54: Multiplying the standard average rainfall, standard soil erodibility index, slope length and slope variable, plant cover index and land use type assignment in sequence to obtain the soil erosion-lead migration coupling index.

[0081] In step S51, the land use type includes forest land and cultivated land. If the land use type is forest land, the land use type is assigned a value of 0.1; if the land use type is cultivated land, the land use type is assigned a value of 0.5. Of course, in other embodiments, the land use types can be appropriately expanded and the land use type assignments can be adaptively adjusted based on actual lead monitoring requirements.

[0082] In step S52, the first and second empirical coefficients are dynamically determined based on the slope. Specifically, if the slope is greater than 5%, the first empirical coefficient is determined to be 0.6; otherwise, the first empirical coefficient is determined to be 0.3. If the slope is greater than 5%, the second empirical coefficient is determined to be 1.2; otherwise, the first empirical coefficient is determined to be 0.2. By analyzing the potential impact of soil erosion, the driving effect of soil erosion on lead migration can be assessed. In areas with a high soil erosion-lead migration coupling index, it indicates that the terrain conditions in that area have a strong driving effect on soil erosion and lead migration.

[0083] In step S54, the soil erosion-lead migration coupling index is obtained by sequentially multiplying the standard average rainfall, the standard soil erodibility index, the slope length and gradient variable, the plant cover index, and the land use type assignment according to the following formula:

[0084] SEPI=P·E·TP·V·C

[0085] Wherein, SEPI is the soil erosion-lead migration coupling index, P is the standard average rainfall, TP is the slope length and slope variable, V is the vegetation cover index, C is the land use type assignment, and E is the standard land erodibility index.

[0086] For step S6, please also refer to Figure 3 , Figure 3This is a flow chart of a method for obtaining the actual soil lead spatial distribution probability in a soil lead element distribution monitoring method of this application. The method, based on the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index, and soil erosion-lead migration coupling index, obtains the actual soil lead spatial distribution probability based on a preset soil lead element distribution monitoring model, including:

[0087] S61: Obtaining, from the variable database, historical soil lead content, historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, historical geological characteristic variables, historical lead migration potential index, historical enhanced vegetation cover dynamic index, and historical soil erosion-lead migration coupling index at the sampling point during a historical monitoring period;

[0088] S62: Analyze and screen the correlation between the historical terrain characteristic variable, the historical remote sensing index variable, the historical human activity intensity variable, and the historical geological characteristic variable and the historical soil lead content, respectively, to obtain screened terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables;

[0089] S63: Obtain the screened terrain characteristic variables, remote sensing index variables, human activity intensity variables and geological characteristic variables of the sampling point in the current monitoring period, combine the lead migration potential index, enhanced vegetation cover dynamic index and soil erosion-lead migration coupling index, and obtain the actual soil lead content based on the soil lead element distribution monitoring model.

[0090] For step S62, see Figure 4 , Figure 4 This is a flow chart of a method for screening terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables in a soil lead distribution monitoring method of this application. The method analyzes and screens the correlation between the historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables and the historical soil lead content, and obtains the screened terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables, including:

[0091] S621: Calculating partial correlation coefficients between the historical terrain characteristic variables, the historical remote sensing index variables, the historical human activity intensity variables, and the historical geological characteristic variables and the historical soil lead content, and eliminating characteristic variables whose partial correlation coefficients are less than a preset partial correlation coefficient threshold;

[0092] S622: Calculating the rank correlation coefficient between the historical terrain characteristic variable, the historical remote sensing index variable, the historical human activity intensity variable, the historical geological characteristic variable, and the historical soil lead content, and eliminating characteristic variables whose rank correlation coefficients are greater than a preset rank correlation coefficient threshold;

[0093] S623: Calculate the variance collision factor between the historical terrain characteristic variable, the historical remote sensing index variable, the historical human activity intensity variable, the historical geological characteristic variable, and the historical soil lead content, and eliminate the characteristic variables whose variance collision factor is greater than a preset variance collision factor threshold.

[0094] For steps S621-S623, the partial correlation coefficient threshold is 0.5, the rank correlation coefficient threshold is 0.05, and the variance collision factor threshold is 10. Of course, in other embodiments, the partial correlation coefficient threshold, the rank correlation coefficient threshold, and the variance collision factor threshold are adaptively modified according to actual lead element monitoring requirements.

[0095] For step S63, see Figure 5 , Figure 5 This is a flow chart of a method for constructing a soil lead element distribution monitoring model in a soil lead element distribution monitoring method of this application. Constructing the soil lead element distribution monitoring model includes:

[0096] S631: Obtaining a soil lead spatial heterogeneity classification label result based on the historical soil lead content and the historical soil pH value by performing a combined classification operation of multiple threshold intervals;

[0097] S632: Optimizing the decision tree model using a priority-weighted splitting criterion based on the lead adsorption-migration correlation to obtain an improved decision tree model;

[0098] S633: Using the historical soil pH value and the screened historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables as independent variables, and the soil lead spatial heterogeneity classification label results as dependent variables, construct a training set and a validation set with preset proportions;

[0099] S634: using the independent variables of the training set as input data, and obtaining a hierarchical prediction result of soil lead spatial heterogeneity corresponding to the training set based on the improved decision tree model;

[0100] S635: Based on a preset spatial weighted loss function, calculating the error between the soil lead spatial heterogeneity classification prediction result of the training set and the soil lead spatial heterogeneity classification label result corresponding to the training set as the training set loss value;

[0101] S636: Adjusting the maximum number of trees, learning rate, regularization parameter, and tree depth of the improved decision tree model according to the training loss value;

[0102] S637: Using the independent variables of the validation set as input data, and based on the adjusted improved decision tree model, obtaining a hierarchical prediction result of the spatial heterogeneity of soil lead in the validation set;

[0103] S638: Based on the spatial weighted loss function, calculating the error between the soil lead spatial heterogeneity classification prediction result of the validation set and the soil lead spatial heterogeneity classification label result corresponding to the validation set as the validation set loss value;

[0104] S639: When the validation set loss value meets a predetermined validation loss threshold range, the soil lead element distribution monitoring model is obtained.

[0105] For step S631, the combined classification operation based on multiple threshold intervals is specifically: the soil lead content [0-70) mg / kg and PH≤5.5, [0-90) mg / kg and 5.5<PH≤6.5, [0-120) mg / kg and 6.5<PH≤7.5, [0-170) mg / kg and PH>7.5 is assigned the label "Level 0", and those that do not meet the above conditions are "Level 1".

[0106] For step S632, please also refer to Figure 6 , Figure 6 This is a flow chart of a method for obtaining an improved decision tree model in a soil lead distribution monitoring method of this application. The decision tree model is optimized based on a priority-weighted splitting criterion of lead adsorption-migration correlation to obtain an improved decision tree model, including:

[0107] S632a: Calculating the Pearson correlation coefficients between the filtered historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables and the historical soil lead content, respectively, to obtain a lead adsorption correlation degree set;

[0108] S632b: Calculating the rank correlation coefficients between the filtered historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables and the historical soil lead content, respectively, to obtain a lead migration correlation degree set;

[0109] S632c: Calculate the priority of each of the filtered historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables based on the lead adsorption correlation degree set and the lead migration correlation degree set and a preset splitting priority function:

[0110] Prior(v)=w1·IP (v)+w2·I S (v)

[0111] Where Prior(v) is the priority of the vth feature variable, I P (v) is the Pearson correlation coefficient of the vth characteristic variable in the lead adsorption correlation set, I S (v) is the rank correlation coefficient of the vth characteristic variable in the lead migration correlation set, wherein the characteristic variables include the historical terrain characteristic variable, the historical remote sensing index variable, the historical human activity intensity variable, and the historical geological characteristic variable after screening, w1 is the first weight coefficient, w2 is the second weight coefficient, and w1+w2=1;

[0112] S632d: Modify the splitting principle of the decision tree model according to the priorities of the filtered historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables to obtain the improved decision tree model:

[0113] Advanced_information_gain=information_gain·Prior(v)

[0114] In the formula, Advanced_information_gain is the improved information gain of the improved decision tree model, information_gain is the original information gain of the decision tree model, Prior(v) is the priority of the vth feature variable, and the feature variables include the screened historical terrain feature variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological feature variables.

[0115] In steps S632a and S632b, the lead adsorption correlation set is constructed to represent the correlation between the historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables and lead adsorption. The lead migration correlation set is constructed to represent the driving effect of the historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables on lead migration.

[0116] For step S632c, the search domains of the first weight coefficient and the second weight coefficient are both: [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0], and satisfy w1+w2=1.

[0117] In step S633, the preset ratio is 70% of the training set and 30% of the validation set. In other embodiments, a 70% training set, a 15% validation set, and a 15% test set can be constructed, with the test set used to test the accuracy of the soil lead distribution monitoring model. Alternatively, the soil lead distribution monitoring model can be constructed using a ten-fold cross-validation method.

[0118] For steps S634-S638, see Figure 7 , Figure 7 This is a flow chart of a method for constructing the spatial weighted loss function in a soil lead element distribution monitoring method of this application. Constructing the spatial weighted loss function includes:

[0119] S63a: Calculate the Euclidean distance between each of the sampling points to obtain a sampling point distance matrix;

[0120] S63b: According to the sampling point matrix, the spatial weights of the sampling points are adjusted based on a spatial kernel function to obtain a spatial weight matrix. The spatial kernel function is:

[0121]

[0122] Where w mn is the spatial weight of the mth sampling point relative to the nth sampling point in the spatial weight matrix, d mn is the Euclidean distance between the mth sampling point and the nth sampling point in the sampling point distance matrix, and σ is the preset optimal spatial attenuation coefficient;

[0123] S63c: Normalizing the spatial weight matrix to obtain a normalized spatial weight matrix;

[0124] S63d: Perform spatial weighting processing on the original loss function according to the normalized spatial weight matrix to obtain the spatial weighted loss function:

[0125]

[0126] Where WL is the spatial weighted loss function, w i is the comprehensive spatial weight of the i-th sampling point, Loss(·) is the original loss function, y i The soil lead spatial heterogeneity classification prediction result of the training set or the soil lead spatial heterogeneity classification prediction result of the validation set for the i-th sampling point; It is the soil lead spatial heterogeneity classification label result corresponding to the training set of the i-th sampling point or the soil lead spatial heterogeneity classification label result corresponding to the validation set.

[0127] In step S63a, the Euclidean distance between each of the sampling points is calculated based on the following formula to obtain the sampling point distance matrix:

[0128]

[0129] Where, d mn is the sampling point distance matrix, which represents the distance between the mth sampling point and the nth sampling point, (x m ,y m ) is the coordinate of the mth sampling point, (x n ,y n ) is the coordinate of the nth sampling point.

[0130] For step S63b, determining the optimal spatial attenuation coefficient includes: constructing a list of spatial attenuation coefficient candidate values ​​such as [100, 200, 500, 1000], and for each spatial attenuation coefficient candidate value in the list of spatial attenuation coefficient candidate values, selecting the spatial attenuation coefficient candidate value that maximizes the determination coefficient of the soil lead spatial heterogeneity classification prediction result of the calculated training set and the soil lead spatial heterogeneity classification label result corresponding to the training set, or selecting the spatial attenuation coefficient candidate value that maximizes the determination coefficient of the soil lead spatial heterogeneity classification prediction result of the calculated validation set and the soil lead spatial heterogeneity classification label result corresponding to the validation set as the optimal spatial attenuation coefficient.

[0131] In step S63c, the spatial weight matrix is ​​normalized based on the following formula to obtain a normalized spatial weight matrix:

[0132]

[0133] Where, is the normalized spatial weight matrix, w mn is the spatial weight matrix.

[0134] For step S63d, the comprehensive spatial weight of the sampling point reflects the relative importance of the i-th sampling point in space, w i The values ​​can be obtained from the spatial weight matrix w mn Specifically, w i It can be the average of the spatial weights of sampling point i and all other sampling points. Of course, other aggregation methods can also be used according to the actual lead element monitoring needs.

[0135] The original loss function is a root mean square error calculation formula. In other embodiments, a determination coefficient calculation formula can also be selected as the original loss function.

[0136] For steps S7 and S8, the actual soil lead spatial distribution probability is the average value of the voting results of all decision trees in the soil lead element distribution monitoring model on the lead element distribution risk of the sampling point. Each decision tree independently judges the sampling point and outputs a binary classification result, that is, it determines whether the sampling point belongs to a high-risk area for lead pollution (marked as 1) or a non-high-risk area (marked as 0). The actual soil lead spatial distribution probability finally output by the model is the arithmetic mean of the voting results of all decision trees. Since the voting result of each tree is only 0 or 1, the value range of the actual soil lead spatial distribution probability is a continuous value between 0 and 1. The larger the value, the higher the possibility that the model determines that the sampling point belongs to a high-risk area for lead pollution.

[0137] The specific rule for classifying the lead element warning level is as follows: when the actual spatial distribution probability of soil lead is greater than 0.5, the warning level of the sampling point is classified as level 1. When the actual spatial distribution probability of soil lead is less than 0.5, the warning level of the sampling point is classified as level 2.

[0138] The lead element warning instruction includes the generation time, warning level and specific instructions, etc. The warning instruction can be transmitted to the warning device via wired or wireless means. The warning device receives and parses the lead element warning instruction, identifies the sampling point location, warning level and specific instructions, and triggers the corresponding alarm mechanism according to the warning level. Specifically, when the warning level is a level one warning, the warning device should immediately trigger a strong sound and light alarm to remind relevant personnel to take emergency measures; when the warning level is a level two warning, the warning device can trigger a milder alarm, such as a flashing indicator light or a short buzzer sound, to remind relevant personnel to pay attention.

[0139] Regarding the specific instructions, when the warning level is level one, the instructions are to conduct a detailed survey of the area surrounding the sampling point to identify potential pollution sources; strengthen soil and groundwater monitoring in the area and increase the monitoring frequency; and prepare to take necessary pollution control and remediation measures. When the warning level is level two, the instructions are to continue to monitor the lead contamination status of the sampling point; regularly conduct soil and groundwater monitoring and maintain the monitoring frequency; and conduct daily inspections of potential pollution sources in the surrounding area.

[0140] Of course, in other embodiments, the lead element warning instruction may be adaptively adjusted according to actual lead element monitoring requirements.

[0141] Example 2

[0142] See also Figure 8 , Figure 8 This is a schematic diagram of a soil lead element distribution monitoring system of the present application. The present application also provides a soil lead element distribution monitoring system, including:

[0143] Variable acquisition module 1: used to obtain terrain characteristic variables, remote sensing index variables, human activity intensity variables and geological characteristic variables of several sampling points in the target monitoring area during the current monitoring period from a preset variable database, wherein the terrain characteristic variables include at least: slope, slope length, soil permeability coefficient and terrain moisture index; the remote sensing index variables include at least: enhanced vegetation index and plant cover index; the human activity intensity variables include at least: land use type;

[0144] Lead migration potential index acquisition module 2: used to obtain the soil saturated hydraulic conductivity threshold of the sampling point, combine the soil permeability coefficient and the terrain moisture index, analyze the spatial redistribution capacity of soil lead caused by terrain-driven hydraulic erosion, and obtain the lead migration potential index;

[0145] Enhanced vegetation cover dynamic index acquisition module 3: used to obtain the maximum enhanced vegetation index and the minimum enhanced vegetation index of the sampling point in the current monitoring period, analyze the impact of plant cover on lead absorption, and obtain the enhanced vegetation cover dynamic index;

[0146] Environmental factor acquisition module 4: used to obtain the average rainfall and soil erodibility index of the sampling point in the current monitoring period;

[0147] Soil erosion-lead migration coupling index acquisition module 5: used to analyze the driving effect of soil erosion on soil lead migration based on the average rainfall, land erodibility index, slope length, slope gradient, plant cover index, and land use type, and obtain the soil erosion-lead migration coupling index;

[0148] Actual soil lead content acquisition module 6: used to obtain the actual soil lead spatial distribution probability based on the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index and soil erosion-lead migration coupling index based on a preset soil lead element distribution monitoring model;

[0149] Warning level classification module 7: used to classify the sampling points into warning levels according to the actual soil lead spatial distribution probability and the preset lead element warning level classification rules;

[0150] The warning instruction transmission module 8 is used to generate a corresponding lead element warning instruction according to the warning level of the sampling point and transmit the lead element warning instruction to the warning device.

[0151] It should be noted that the data obtained by the soil lead element distribution monitoring system provided in this application when implementing a soil lead element distribution monitoring method are stored one-to-one in the storage of this system. When relevant calculations are required, the data required for the calculation can be directly obtained from the storage.

[0152] It should also be noted that the soil lead distribution monitoring system provided in the above embodiment, when implementing a soil lead distribution monitoring method, is merely illustrated by the division of the aforementioned functional modules. In actual applications, the aforementioned functions can be assigned to different functional modules as needed, i.e., the internal structure of the device can be divided into different functional modules to perform all or part of the functions described above. Furthermore, the soil lead distribution monitoring system provided in the above embodiment shares the same concept as the soil lead distribution monitoring method in Example 1. The implementation process is detailed in the method embodiments and will not be further elaborated here.

[0153] Based on the same inventive concept, the present application also provides an electronic device, which can be a terminal device such as a server, desktop computing device, or mobile computing device (e.g., laptop computing device, handheld computing device, tablet computer, netbook, etc.). The device includes one or more processors and a memory, wherein the processor is configured to execute a program to implement the soil lead distribution monitoring method; and the memory is configured to store a computer program executable by the processor.

[0154] The present application may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-usable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. The information can be computer-executable instructions, and the computer-executable instructions can execute the soil lead distribution monitoring method. Examples of computer storage media include but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0155] The present application is not limited to the above-mentioned embodiments. If various changes or modifications to the present application do not depart from the spirit and scope of the present application, and if these changes and modifications fall within the claims of the present application and the scope of equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A method for monitoring soil lead distribution, characterized in that: The following steps are involved: In a preset variable database, terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables of a plurality of sampling points in a target monitoring area during a specified current monitoring period are obtained, wherein the terrain characteristic variables include at least slope, slope length, soil permeability coefficient, and terrain moisture index; the remote sensing index variables include at least enhanced vegetation index and plant cover index; and the human activity intensity variables include at least land use type; Obtaining the soil saturated hydraulic conductivity threshold value at the sampling point, combining the soil permeability coefficient and the terrain moisture index, analyzing the spatial redistribution capacity of topography-driven hydraulic erosion on soil lead, and obtaining a lead migration potential index; Obtaining the maximum enhanced vegetation index and the minimum enhanced vegetation index of the sampling point in the current monitoring period, analyzing the effect of plant cover on lead absorption, and obtaining an enhanced vegetation cover dynamic index; Obtaining the average rainfall and soil erodibility index of the sampling point during the current monitoring period; Based on the average rainfall, soil erodibility index, slope length, slope gradient, plant cover index, and land use type, the driving effect of soil erosion on soil lead migration was analyzed to obtain a soil erosion-lead migration coupling index; According to the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index and soil erosion-lead migration coupling index, based on a preset soil lead element distribution monitoring model, the actual soil lead spatial distribution probability is obtained; According to the actual spatial distribution probability of soil lead, based on the preset lead element warning level classification rules, the sampling points are classified into warning levels; According to the warning level of the sampling point, a corresponding lead element warning instruction is generated and the lead element warning instruction is transmitted to the warning device.

2. The method for monitoring soil lead distribution according to claim 1, wherein: The method of obtaining the actual soil lead spatial distribution probability based on the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index, and soil erosion-lead migration coupling index and a preset soil lead element distribution monitoring model according to the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index, and soil erosion-lead migration coupling index comprises: Obtaining, from the variable database, historical soil lead content, historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, historical geological characteristic variables, historical lead migration potential index, historical enhanced vegetation cover dynamic index, and historical soil erosion-lead migration coupling index at the sampling point during a historical monitoring period; Analyzing and screening the correlation between the historical terrain characteristic variables, the historical remote sensing index variables, the historical human activity intensity variables, and the historical geological characteristic variables and the historical soil lead content, respectively, to obtain screened terrain characteristic variables, remote sensing index variables, human activity intensity variables, and geological characteristic variables; The screened terrain characteristic variables, remote sensing index variables, human activity intensity variables and geological characteristic variables of the sampling points in the current monitoring period are obtained, and the actual soil lead content is obtained based on the soil lead element distribution monitoring model in combination with the lead migration potential index, enhanced vegetation cover dynamic index and soil erosion-lead migration coupling index.

3. The method for monitoring soil lead distribution according to claim 2, wherein: The historical topographic characteristic variables include: historical soil pH value; Constructing the soil lead element distribution monitoring model includes: According to the historical soil lead content and the historical soil pH value, a combined classification operation of multiple threshold intervals is performed to obtain a hierarchical label result of the spatial heterogeneity of soil lead; The decision tree model was optimized based on the priority weighted splitting criterion of lead adsorption-migration correlation to obtain an improved decision tree model. The historical soil pH value and the screened historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables are used as independent variables, and the soil lead spatial heterogeneity classification label results are used as dependent variables to construct a training set and a validation set with preset proportions; Using the independent variables of the training set as input data, and based on the improved decision tree model, obtaining a hierarchical prediction result of soil lead spatial heterogeneity corresponding to the training set; Based on a preset spatial weighted loss function, the error between the soil lead spatial heterogeneity classification prediction result of the training set and the soil lead spatial heterogeneity classification label result corresponding to the training set is calculated as the training set loss value; Adjusting the maximum number of trees, learning rate, regularization parameter, and tree depth of the improved decision tree model according to the training loss value; Using the independent variables of the validation set as input data, and based on the adjusted improved decision tree model, obtaining a hierarchical prediction result of the spatial heterogeneity of soil lead in the validation set; Based on the spatial weighted loss function, calculating the error between the soil lead spatial heterogeneity classification prediction result of the validation set and the soil lead spatial heterogeneity classification label result corresponding to the validation set as the validation set loss value; When the validation set loss value meets a predetermined validation loss threshold range, the soil lead element distribution monitoring model is obtained.

4. The method for monitoring soil lead distribution according to claim 3, wherein: The decision tree model is optimized based on the priority weighted splitting criterion of the lead adsorption-migration correlation to obtain an improved decision tree model, including: Calculating the Pearson correlation coefficients between the screened historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables and the historical soil lead content to obtain a lead adsorption correlation degree set; Calculating the rank correlation coefficients between the screened historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables and the historical soil lead content, respectively, to obtain a lead migration correlation set; According to the lead adsorption correlation set and the lead migration correlation set, based on a preset splitting priority function, the priorities of the filtered historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables are calculated: Prior(v)=w1·I p (v)+w2·I S (v) Where Prior(v) is the priority of the vth feature variable, I P (v) is the Pearson correlation coefficient of the vth characteristic variable in the lead adsorption correlation set, I S (v) is the rank correlation coefficient of the vth characteristic variable in the lead migration correlation set, wherein the characteristic variables include the historical terrain characteristic variable, the historical remote sensing index variable, the historical human activity intensity variable, and the historical geological characteristic variable after screening, w1 is the first weight coefficient, w2 is the second weight coefficient, and w1+w2=1; According to the priorities of the filtered historical terrain characteristic variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological characteristic variables, the splitting principle of the decision tree model is modified to obtain the improved decision tree model: Advanced_information_gain=information_gain·Prior(v) In the formula, Advanced_information_gain is the improved information gain of the improved decision tree model, information_gain is the original information gain of the decision tree model, Prior(v) is the priority of the vth feature variable, and the feature variables include the screened historical terrain feature variables, historical remote sensing index variables, historical human activity intensity variables, and historical geological feature variables.

5. The method for monitoring soil lead distribution according to claim 3, wherein: Constructing the spatial weighted loss function includes: Calculating the Euclidean distance between each of the sampling points to obtain a sampling point distance matrix; According to the sampling point matrix, the spatial weights of the sampling points are adjusted based on the spatial kernel function to obtain a spatial weight matrix. The spatial kernel function is: Where w mn is the spatial weight of the mth sampling point relative to the nth sampling point in the spatial weight matrix, d mn is the Euclidean distance between the mth sampling point and the nth sampling point in the sampling point distance matrix, and σ is the preset optimal spatial attenuation coefficient; Normalizing the spatial weight matrix to obtain a normalized spatial weight matrix; Calculating the average spatial weight of any sampling point and each adjacent sampling point according to the normalized spatial weight matrix to obtain the comprehensive spatial weight of the sampling point; According to the normalized spatial weight matrix, the original loss function is spatially weighted to obtain the spatial weighted loss function: Where WL is the spatial weighted loss function, w i is the comprehensive spatial weight of the i-th sampling point, Loss(·) is the original loss function, y i The soil lead spatial heterogeneity classification prediction result of the training set or the soil lead spatial heterogeneity classification prediction result of the validation set for the i-th sampling point; It is the soil lead spatial heterogeneity classification label result corresponding to the training set of the i-th sampling point or the soil lead spatial heterogeneity classification label result corresponding to the validation set.

6. The method for monitoring soil lead distribution according to claim 1, wherein: The driving effect of soil erosion on soil lead migration is analyzed based on the average rainfall, soil erodibility index, slope length, slope gradient, plant cover index, and land use type to obtain a soil erosion-lead migration coupling index, including: According to the land use type, based on the preset land use type assignment mapping rule, a corresponding land use type assignment is obtained; According to the slope length and slope, based on the preset formula, the driving effect of soil erosion on lead migration is analyzed to obtain the slope length and slope variables: TP=(length / 22.13) z ·(sinslope / 0.0896) c Wherein, TP is the slope length and slope variable, length is the slope length, slope is the slope, z and c are the preset first and second empirical coefficients respectively; Normalizing the average rainfall and the land erodibility index respectively to obtain a standard average rainfall and a standard land erodibility index; The soil erosion-lead migration coupling index is obtained by sequentially multiplying the standard average rainfall, standard land erodibility index, slope length and slope variable, plant cover index and land use type assignment.

7. The method for monitoring soil lead distribution according to claim 1, wherein: The obtaining of the maximum enhanced vegetation index and the minimum enhanced vegetation index of the sampling point in the current monitoring period, analyzing the effect of plant cover on lead absorption, and obtaining the enhanced vegetation cover dynamic index includes: According to the maximum enhanced vegetation index and the minimum enhanced vegetation index, based on the preset enhanced vegetation coverage, the enhanced vegetation coverage dynamic index is obtained: VD=EVI max -HOUSE min / HOUSE max +HOUSE min Where VD is the enhanced vegetation cover dynamic index, EVI max is the maximum enhanced vegetation index, EVI min is the minimum enhanced vegetation index.

8. The method for monitoring soil lead distribution according to claim 1, wherein: The soil saturated hydraulic conductivity threshold of the sampling point is obtained, and combined with the soil permeability coefficient and the terrain moisture index, the spatial redistribution capacity of soil lead caused by terrain-driven hydraulic erosion is analyzed to obtain the lead migration potential index, including: According to the soil permeability coefficient, the terrain moisture index and the soil saturated hydraulic conductivity threshold, based on a preset soil lead migration potential calculation formula, the lead migration potential index is obtained: Where, T Ob is the lead migration potential index, TWI is the terrain wetness index, R is the soil permeability coefficient, is the soil saturated hydraulic conductivity threshold.

9. A soil lead element distribution monitoring system, characterized in that: include: Variable acquisition module: used to obtain terrain characteristic variables, remote sensing index variables, human activity intensity variables and geological characteristic variables of several sampling points in the target monitoring area during the current monitoring period from a preset variable database, wherein the terrain characteristic variables include at least: slope, slope length, soil permeability coefficient and terrain moisture index; the remote sensing index variables include at least: enhanced vegetation index and plant cover index; the human activity intensity variables include at least: land use type; A lead migration potential index acquisition module is used to obtain the soil saturated hydraulic conductivity threshold of the sampling point, and analyze the spatial redistribution capacity of soil lead due to topography-driven hydraulic erosion in combination with the soil permeability coefficient and the topographic moisture index to obtain the lead migration potential index; Enhanced vegetation cover dynamic index acquisition module: used to obtain the maximum enhanced vegetation index and the minimum enhanced vegetation index of the sampling point in the current monitoring period, analyze the impact of plant cover on lead absorption, and obtain the enhanced vegetation cover dynamic index; Environmental factor acquisition module: used to obtain the average rainfall and land erodibility index of the sampling point in the current monitoring period; Soil erosion-lead migration coupling index acquisition module: used to analyze the driving effect of soil erosion on soil lead migration based on the average rainfall, land erodibility index, slope length, slope gradient, plant cover index, and land use type, and obtain the soil erosion-lead migration coupling index; Actual soil lead content acquisition module: used to obtain the actual soil lead spatial distribution probability based on the terrain characteristic variables, remote sensing index variables, human activity intensity variables, geological characteristic variables, lead migration potential index, enhanced vegetation cover dynamic index and soil erosion-lead migration coupling index based on a preset soil lead element distribution monitoring model; Warning level classification module: used to classify the sampling points into warning levels according to the actual soil lead spatial distribution probability and the preset lead element warning level classification rules; The warning instruction transmission module is used to generate a corresponding lead element warning instruction according to the warning level of the sampling point and transmit the lead element warning instruction to the warning device.

10. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a method for monitoring the distribution of lead in soil as claimed in any one of claims 1 to 8 is implemented.

Images