Classified management and control method and system for heavy metal pollution of cultivated land and medium

Abstract

The invention provides a farmland heavy metal pollution classification management and control method and system and a medium, and relates to the technical field of environmental protection, and the method comprises the steps: obtaining remote sensing image data of a heavy metal pollution strict management and control region, and dividing the strict management and control region into a plurality of land parcels under different environmental conditions through an object-oriented method; constructing a plurality of suitability constraint conditions of the management and control measures of the strict management and control area according to the town distance, the industrial area distance, the gradient, the productivity, the management and control measures and the area variables; and taking the expenditure, the cultivated land area and the safety utilization rate of the management and control measures of the strict management and control areas as constraint conditions of the management and control measures of the strict management and control areas, and obtaining classified management and control measures for minimizing the total cost of the heavy metal pollution strict management and control areas in combination with a suitability constraint condition. According to the method, the partition and block management of the heavy metal polluted cultivated land can be realized.

Description

Technical Field

[0001] The present invention relates to the field of environmental protection technology, and in particular to a method, system and medium for classified control of heavy metal pollution in cultivated land. Background Art

[0002] Controlling heavy metal pollution in cultivated land has far-reaching significance for protecting ecosystem stability, ensuring the quality and safety of agricultural products, and maintaining human health. It also helps to achieve sustainable use of land resources and promote sustainable development.

[0003] At present, for plots of land contaminated by heavy metals, environmental monitoring agencies usually conduct on-site inspections, and the control measures for different heavy metal pollution categories are different. For example, in safe utilization areas, agronomic control measures such as low-accumulation variety substitution and soil pH adjustment are implemented; in strict control areas, the planting of edible crops is prohibited, and measures such as adjusting the planting structure and returning farmland to forest and grassland are implemented.

[0004] However, on-site inspections are time-consuming and inefficient, and are not suitable for large-scale, long-term supervision and management. The soil conditions and surrounding environment within the same area vary greatly, and the specific control measures that should be taken for each plot are relatively general and lack practicability. Summary of the invention

[0005] The present invention provides a method, system and medium for classified control of heavy metal pollution in cultivated land. The method is helpful to achieve the management of heavy metal polluted cultivated land by zoning and block.

[0006] The present invention provides a method for classified control of heavy metal pollution in cultivated land, comprising: Obtain remote sensing image data of the heavy metal pollution strict control area, divide the heavy metal pollution strict control area using object-oriented method, and obtain each plot of heavy metal pollution zone; Obtain the crop types and rotation patterns on each plot in the strictly controlled area, and determine the control measures for various strictly controlled areas, including changing land use types, adjusting planting structure and ecological land withdrawal; Taking the distance to town, distance to industrial area, slope and production capacity as the influencing factors of various control measures in strict control areas to construct multiple scenarios, taking the controllable area for implementing various control measures in each scenario as the area variable, and constructing multiple suitability constraints for control measures in strict control areas based on the scenarios, control measures and area variables; A multi-objective linear programming model was constructed, and the expenditure costs of various control measures in strict control areas were taken as the objective function of the multi-objective linear programming model. The cultivated land area and safe utilization rate were taken as constraints for the control measures in strict control areas. Combined with multiple suitability constraints, the multi-objective linear programming model was used to obtain classified control measures that minimized the total cost of strict control areas of heavy metal pollution under various scenarios.

[0007] Preferably, the method of dividing the heavy metal pollution strict control area by using an object-oriented method comprises the following steps: Perform multi-scale segmentation on remote sensing image data and generate image object layers at different segmentation scales, wherein the characteristics of the image objects after multi-scale segmentation include: spectrum, texture and geometry; Select the feature space and assign different weights to each feature to obtain the classification results of the land objects; According to the classification results of the ground objects, the hierarchical structure corresponding to the ground objects is obtained, and the image object layers are connected according to the hierarchical structure corresponding to the ground objects to obtain the various plots of heavy metal pollution zones.

[0008] Preferably, the multi-objective linear programming model is constructed, and the expenditure of various types of control measures in strict control areas is used as the objective function of the multi-objective linear programming model, including: Construct a multi-objective linear programming model: The expenditures of various control measures in strictly controlled areas are taken as the objective functions of the multi-objective linear programming model. The expenditures of control measures in strictly controlled areas include the expenditures of changing land use types, adjusting planting structures and ecological land withdrawal, which are respectively set as the objective functions F 1( X ), F 2( X )and F 3( X ),but: MinF 1( X )=∑ C 1i × X a ; MinF 2( X )=∑ C 2i × X b ; MinF 3( X )=∑ C 3i × X c ; Where: C 1i For the i The cost per unit area of ​​the land use type change control measures in the following scenarios: X a For the i The area of ​​polluted cultivated land that takes land use type change control measures under the following scenarios: a =3i -2; C 2i For the i The cost per unit area of ​​the measures to adjust the planting structure under the following scenarios: X b For the i The area of ​​polluted cultivated land that takes measures to adjust the planting structure under the following scenarios: b =3 i -1; C 3i For the i The cost per unit area of ​​ecological land conversion control measures under the following scenarios: X c For the i The area of ​​polluted farmland that adopts ecological land withdrawal control measures under the following scenarios: c =3 i ; The weight coefficients of the three objective functions are all 1 / 3, converting the multi-objective function into a single objective function: ; Construct the cultivated land area constraint condition, which is that the sum of cultivated land areas with various control measures is equal to the total cultivated land area in the strict control area; Construct a safe utilization rate constraint condition, which requires that the safe utilization rate of polluted cultivated land reaches or exceeds the preset standard; According to the constraints and suitability constraints, the classified control measures with the minimum total cost are obtained.

[0009] Preferably, it also includes: using a decision tree model, taking the expenditure costs of various control measures in the strictly controlled areas as the objective function of the decision tree model, taking the cultivated land area and safe utilization rate as constraints for the control measures in the strictly controlled areas, combining multiple suitability constraints, and obtaining classified control measures that minimize the total cost of the strictly controlled areas of heavy metal pollution under various scenarios through a multi-objective linear programming model.

[0010] Preferably, the obtaining of the crop types and rotation patterns on each plot in the strictly controlled area includes: Collect multiple sample point data of remote sensing image data, and annotate the ground object type and crop rotation mode for each sample point data; Obtain spectral characteristic data of each sample point data, and calculate exponential characteristic data according to the spectral characteristic data; The extracted feature data and the labeled data of the sample points are used to train a random forest classification model. The trained random forest classification model is used to obtain the crop types and rotation patterns on each plot in the safe utilization area, and thus determine the various strict control measures in the control area to change the land use type and adjust the planting structure.

[0011] Preferably, the bands of the spectral characteristic data include: B, G, R, NIR, SWIR1 and SWIR2, and the index characteristic data include: NDVI, EVI, NDWI, LSWI, NDSI, NDSVI, NDTI, WDVI and NDFI9.

[0012] The present invention also provides a farmland heavy metal pollution classification control system, which is used to implement any of the farmland heavy metal pollution classification control methods described above, and the farmland heavy metal pollution classification control system includes: The plot division module is used to obtain remote sensing image data of the heavy metal pollution strictly controlled area, and divide the strictly controlled area into multiple plots with different environmental conditions using an object-oriented method; Plot analysis module, used to obtain crop types and rotation patterns on each plot in the strictly controlled area; Construct a constraint condition module, which is used to use the distance to town, the distance to industrial area, slope, and production capacity as influencing factors of the control measures in the strict control area, construct multiple scenarios, and use the controllable area for implementing various control measures in each scenario as the area variable in the constraint equation. According to the scenarios, control measures, and area variables, construct multiple suitability constraints for the control measures in the strict control area; The classification control module is used to take the expenditure costs, cultivated land area and safe utilization rate of various control measures in strict control areas as constraints of control measures in strict control areas, and combine them with suitability constraints to obtain classification control measures that minimize the total cost of strict control areas of heavy metal pollution.

[0013] The present invention also provides a computer-readable storage medium, on which a data processing program is stored. When the data processing program is executed by a processor, the steps of the method for classification and control of heavy metal pollution in cultivated land as described in any one of the above texts are implemented.

[0014] Compared with the prior art, the present invention divides different zones of the study area into individual plots, obtains the crop type and rotation pattern of each plot, establishes a multi-objective linear programming model, and combines classified control measures to minimize the cost of polluted cultivated land. The zoning and classified control methods can effectively achieve more adaptable supervision and management of plots under different conditions, the overall control feasibility is better, and the classified control measures effectively improve the control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of the method for classified control of heavy metal pollution in cultivated land according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] Example 1 The present invention provides a method for classifying and controlling heavy metal pollution in cultivated land, and the specific process is as follows: Figure 1 As shown, the following steps are included: Step S101, obtaining remote sensing image data of the heavy metal pollution strict control area, and dividing the strict control area into multiple plots with different environmental conditions using an object-oriented method.

[0018] This step is used to divide the heavy metal pollution zones into individual plots so that the soil conditions and surrounding environment within the same plot are consistent.

[0019] The object-oriented method is used to extract the boundaries of the plots in each heavy metal pollution zone. The object-oriented extraction of remote sensing information includes two processes: image segmentation and image classification. The former generates image objects and provides a basis for the latter.

[0020] The pollution of cultivated land soil and crops in the strictly controlled areas is quite serious, and it is usually impossible to grow edible crops. Depending on the specific situation of the polluted cultivated land, the land use type can be changed, the planting structure can be adjusted or ecological land can be retired.

[0021] Of course, the above-mentioned control measures depend on the specific pollution situation and relevant policies. The control measures themselves are not the core technical features provided by this application. Therefore, the specific possible methods adopted will not affect the evaluation of the creativity of this application.

[0022] The various plots of heavy metal pollution zoning obtained using object-oriented method include: Perform multi-scale segmentation on remote sensing image data and generate image object layers at different segmentation scales, wherein the features of image objects after multi-scale segmentation include: spectrum, texture, and geometry; Select the feature space and assign different weights to each feature to obtain the classification results of the land objects; According to the classification results of the ground objects, the hierarchical structure corresponding to the ground objects is obtained, and the image object layers are connected according to the hierarchical structure corresponding to the ground objects to obtain the various plots of heavy metal pollution zones.

[0023] Through the above steps, the remote sensing image data is classified, and the classification results are used to obtain the various plots of heavy metal pollution zones. The object-oriented method is described in detail below.

[0024] Multi-scale segmentation uses a multi-scale segmentation algorithm to segment remote sensing images and generate image object layers. This process divides the image into regions of different sizes, each of which is considered an object. Segmentation at different scales can better capture the spatial information of the objects, thereby improving the accuracy of classification. Among them, each image object contains its spectral, texture and geometric characteristics.

[0025] Feature extraction and weight assignment,For each image object, the corresponding features need to be extracted from,its spectral, texture and geometric features.

[0026] Different features are given different weights based on their importance. For example, spectral features may have the greatest impact on object classification and thus may be given a higher weight, while texture and geometric features may be given a lower weight.

[0027] Object classification: Use the extracted features and weights to classify image objects. Various classification algorithms, such as support vector machines (SVM) and random forests, can be used to classify image objects according to the extracted features and classify them into different object types, such as buildings, vegetation, water bodies, etc.

[0028] Obtain the hierarchical structure corresponding to the features. Based on the feature classification results, a hierarchical structure corresponding to the features can be established. This hierarchical structure can be a tree structure, reflecting the hierarchical relationship between different feature types. For example, buildings can be divided into subcategories such as residential, commercial, and industrial, and vegetation can be divided into subcategories such as forests, grasslands, and farmlands, and so on. This hierarchical structure helps to organize and manage feature classification results and provides richer information to describe the spatial distribution and relationship of features.

[0029] Connect the image object layers, and connect the image object layers according to the hierarchical structure corresponding to the object classification results. In this way, the various plots of heavy metal pollution zones can be obtained, and each plot can be classified as a specific object type and has its characteristics and location information, that is, the soil conditions and surrounding environment in the same plot are consistent.

[0030] Step S102, taking the distance to town, the distance to industrial area, the slope, and the production capacity as the influencing factors of the control measures in the strictly controlled area, constructing multiple scenarios, taking the controllable area for implementing various control measures in each scenario as the area variable in the constraint equation, and constructing multiple suitability constraints for the control measures in the strictly controlled area based on the scenarios, control measures, and area variables.

[0031] Step S103, taking the expenditures, cultivated land area, and safe utilization rate of the control measures in various strict control areas as the constraints of the control measures in the strict control areas, and combining the suitability constraints, obtain the classified control measures that minimize the total cost of the strict control areas of heavy metal pollution. The above two steps are used to obtain the classified control measures that minimize the total cost of each plot in the heavy metal pollution zone.

[0032] The above scheme involves a multi-objective linear programming model, which is a mathematical optimization model used to solve decision-making problems that consider multiple objectives at the same time. In multi-objective linear programming, there are multiple objective functions, each of which needs to be minimized or maximized.

[0033] The multi-objective linear programming model has two or more objective functions, and all objective functions and constraints are linear. The multi-objective linear programming model is used to determine the classification control measures and their regions and areas for the cultivated land in the strict control area. There are many ways to control the polluted cultivated land in the strict control area. The costs of different control measures are different, and the impact on the cultivated land area, production capacity, etc. is also different. Therefore, the multi-objective linear programming model is used to weigh the costs of various control measures. Under the requirements of the constraints such as cultivated land area and safe utilization rate, the measures with the least total cost of cultivated land control in the strict control area are obtained.

[0034] Firstly, the distance to towns, distance to industrial areas, slope and production capacity are taken as influencing factors of control measures in strict control areas. Multiple scenarios are constructed, and the controllable area for implementing various control measures in each scenario is used as the area variable in the constraint equation. Based on the scenarios, control measures and area variables, multiple suitability constraints for control measures in strict control areas are constructed.

[0035] Furthermore, the expenditures, cultivated land area and safe utilization rate of various control measures in strict control areas are taken as constraints of control measures in strict control areas. Combined with the suitability constraints, classified control measures that minimize the total cost of strict control areas of heavy metal pollution are obtained, including: The expenditures of the control measures in the strict control area include: the expenditures of changing the land use type, adjusting the planting structure and ecological land withdrawal, which are set as the objective functions F 1( X ), F 2( X )and F 3( X ),but: MinF 1( X )=∑ C 1i × X a ; MinF 2(X )=∑ C 2i × X b ; MinF 3( X )=∑ C 3i × X c .

[0036] Where: C 1i For the i The cost per unit area of ​​the land use type change control measures in the following scenarios: X a For the i The area of ​​polluted cultivated land that takes land use type change control measures under the following scenarios: a =3 i -2; C 2i For the i The cost per unit area of ​​the measures to adjust the planting structure under the following scenarios: X b For the i The area of ​​polluted cultivated land that takes measures to adjust the planting structure under the following scenarios: b =3 i -1; C 3i For the i The cost per unit area of ​​ecological land conversion control measures under the following scenarios: X c For the i The area of ​​polluted farmland that adopts ecological land withdrawal control measures under the following scenarios: c =3 i .

[0037] The weight coefficients of the three objective functions are all 1 / 3, converting the multi-objective function into a single objective function: .

[0038] The constraint condition for cultivated land area is that the sum of cultivated land areas subject to various control measures is equal to the total cultivated land area in the strict control area.

[0039] The safe utilization rate constraint condition is that the safe utilization rate of contaminated cultivated land reaches above the preset standard.

[0040] According to the constraints and suitability constraints, the classified control measures with the minimum total cost are obtained.

[0041] In the above steps, the constraints of cultivated land area, safe utilization rate and cultivated land productivity depend on the actual situation and are not the focus of the present invention.

[0042] When the heavy metal pollution of cultivated land is in the safe utilization area, it is necessary to obtain the crop types and rotation patterns on each plot in the strict control area.

[0043] Obtain the crop types and rotation patterns on each plot in the strictly controlled area including: Collect multiple sample point data of remote sensing image data, and annotate the ground object type and crop rotation mode for each sample point data; Obtain spectral characteristic data of each sample point data, and calculate exponential characteristic data according to the spectral characteristic data; The extracted feature data and the labeled data of the sample points are used to train the random forest classification model, and the crop types and rotation patterns on each plot are obtained using the trained random forest classification model.

[0044] Since crops are all grown on cultivated land and their textures are not very different, the image data after fusion of multiple features such as spectral features and index features are used to automatically classify the crop types in the study area.

[0045] Among them, the bands of spectral characteristic data include: B, G, R, NIR, SWIR1 and SWIR2, and the index characteristic data include: NDVI, EVI, NDWI, LSWI, NDSI, NDSVI, NDTI, WDVI, and NDFI9.

[0046] The specific implementation steps for obtaining the crop type and rotation pattern on each plot are shown in the following embodiments.

[0047] The second embodiment of the present application provides an example of classification control of heavy metal pollution in cultivated land in a strictly controlled area using the method of the first embodiment.

[0048] The study area is located in the hilly area of ​​southeastern my country. The land is relatively fragmented, and cultivated land is generally scattered among crisscrossing roads, river networks and residential areas. Based on high spatial resolution Google Earth image data, this example uses an object-oriented method in the E-Cognition software to extract the boundaries of land plots in typical locations such as areas with severe heavy metal pollution, areas with complex planting structures, and areas surrounding cities.

[0049] In the GEE platform, the random forest algorithm is used to identify the crop types and rotation patterns on cultivated land. Based on Sentinel-2 and Landsat-7 / 8 image data, the random forest algorithm is used, combined with the characteristics of crop types and classification sample points, to obtain the spatial distribution of crop types and rotation patterns in the study area, and verify the classification accuracy. The details are as follows: Since crops are all grown on cultivated land, the textures are not very different, so the image data after fusion of multiple features such as spectral features and index features are used to automatically classify the crop types in the study area. The spectral features include spectral features of six bands: B, G, R, NIR, shortwave infrared 1 (SWIR1) and shortwave infrared 2 (SWIR2). Based on the six bands, nine index features are calculated: NDVI, EVI, NDWI, land surface water index (LSWI), normalized snow cover index (NDSI), normalized difference senescent vegetation index (NDSVI), normalized difference tillage index (NDTI), weighted difference vegetation index (WDVI), and normalized difference flood index (NDFI).

[0050] According to relevant statistical data, the main crops in the study area are rice, rapeseed and wheat. Since rapeseed and wheat are winter crops grown on dry land and the harvest time is the first half of the year, this embodiment uses remote sensing images from the first half of the year to divide dryland crops into three categories: rapeseed, wheat and others. Since rice grows in paddy fields and is divided into single-season rice and double-season rice, this embodiment uses remote sensing images throughout the year to divide paddy field crops into early rice, middle rice, late rice, double-season rice and other five categories. Since there is crop rotation in the study area, this embodiment further obtains seven major planting structures according to the geographical location and growth period of the crops: rice-oil rotation, rice-wheat rotation, single-season rice, double-season rice, rapeseed, wheat and other crops. Based on the crop sample points collected on the spot, combined with the high-resolution images of Sentinel-2 and GoogleEarth, a total of 705 sample point data were collected, including 109 rapeseed samples, 104 wheat samples, 65 early rice samples, 119 middle rice samples, 59 late rice samples, and 98 double-season rice samples. Each type of sample is randomly divided into training samples and verification samples in a ratio of approximately 7:3.

[0051] As shown in Table 1, the overall accuracy (OA) of the dryland crop classification in the study area is 86.05%, and the Kappa coefficient is 0.7873, indicating a high degree of consistency and a high degree of accuracy in the classification results. Among them, rapeseed has the highest user accuracy, reaching 90.91%, and wheat has the highest mapping accuracy, reaching 89.66%.

[0052] Table 1 Statistics of dryland crop mapping accuracy

[0053] As shown in Table 2, the overall accuracy (OA) of paddy field crop classification in the study area is 82.68%, and the Kappa coefficient is 0.7803, indicating a high degree of consistency and a high degree of accuracy in classification. Among them, the user accuracy of late rice is the highest, reaching 88.89%, and the mapping accuracy of mid-season rice is the highest, reaching 86.11%.

[0054] Table 2 Statistics of paddy field crop mapping accuracy

[0055] This embodiment uses a multi-objective linear programming model to determine the classification control measures and their regions and areas for the farmland in the strict control area. There are multiple control methods for polluted farmland in the strict control area. The costs of different control measures vary, and the impacts on the farmland area, production capacity, etc. are also different. Therefore, a multi-objective linear programming model is used to weigh the costs of various control measures. Under the requirements of satisfying the constraints of farmland area, safe utilization rate, etc., a measure plan with the least total cost of farmland control in the strict control area is obtained.

[0056] The soil and crops in the strictly controlled areas are seriously polluted, and it is usually impossible to continue to grow edible crops. Depending on the specific situation of the polluted cultivated land, the land use type can be changed, the planting structure can be adjusted, or ecological land reclamation can be implemented. If the land use type of the polluted cultivated land is changed to construction land, the land compensation fee, resettlement subsidy, and compensation for young crops and ground attachments should be compensated to all the original farmers or rural village-level collective economic organizations, and the new land users need to pay the paid use fee for the newly added construction land. The land compensation fee and resettlement subsidy will be affected by the location and production capacity; the compensation fee for young crops and ground attachments is mainly affected by production capacity; the paid use fee for the newly added construction land is mainly affected by the location. If the planting structure of the polluted cultivated land is adjusted to plant non-edible economic crops such as mulberry, hemp, flowers, and seedlings, the crop replanting subsidy and field infrastructure management and maintenance fees should be compensated to all the original farmers or rural village-level collective economic organizations. The crop replanting subsidy will be affected by the location and production capacity; the field infrastructure management and maintenance fees will be affected by the terrain and production capacity. If the polluted farmland is ecologically retired and farmland is returned to forest and grassland, the construction and maintenance fees (including construction costs and operating costs), garden planting and technical and economic inputs (including garden construction costs, land rent, seedling costs, labor costs, fertilizers, pesticides, irrigation equipment, mulch and other material costs) of returning farmland to forest and grassland should be compensated to all individual farmers or rural village-level collective economic organizations of the original farmland. The construction and maintenance fees of returning farmland to forest and grassland will be affected by the location and terrain fluctuations; the garden construction costs are mainly affected by the degree of terrain fluctuations; the land rent and labor costs are mainly affected by the location; the fertilizer, pesticide, irrigation equipment, mulch and other material costs are mainly affected by production capacity.

[0057] All three types of control measures will reduce the planting area of ​​grain crops and cash crops, thereby reducing grain production capacity. In accordance with the principle of "returning as much as possible, replenishing as much as possible" to ensure the production capacity and safety of cultivated land, the quality of unused, inefficiently used, idle, damaged, degraded non-cultivated land, inefficiently used, and residual forest land, with a focus on medium and low-yield fields, can be improved in areas where polluted cultivated land is located. The cost of quality improvement will be affected by the location of the cultivated area, terrain undulations and production capacity.

[0058] According to the influencing factors of measures in the strict control area, 16 scenarios are set to analyze the different scenarios of polluted cultivated land in the strict control area under the constraints of various influencing factors and the possible control measures, as shown in the table below. The polluted cultivated land area corresponding to each scenario is used as the controllable area variable for various measures in the constraint equation, as shown in the table below. Combined with the cost of taking control measures, the constraints of cultivated land area, safe utilization rate and production capacity are further analyzed, and 48 decision variables are selected, including all measures that may be taken for all polluted cultivated land in the strict control area, as shown in Table 3.

[0059] Table 3 Control measures for different scenarios of polluted cultivated land in strict control areas under the constraints of various influencing factors

[0060] Since excessive use of certain control measures may lead to the loss of other types of farmland control in the strictly controlled area, it is necessary to weigh different control measures when taking control measures for polluted farmland, such as the balance between adjusting the planting structure and ecological land withdrawal. The costs of changing the land use type, adjusting the planting structure, and ecological land withdrawal in the strictly controlled area are set as the objective functions. F 1( X ), F 2( X )and F 3( X ), then: MinF 1( X )=∑ C 1i × X a ; MinF 2( X )=∑ C 2i × X b ; MinF 3( X )=∑ C 3i × X c ; Where: C 1i For the i The cost per unit area of ​​the land use type change control measures in the following scenarios: X a For the i The area of ​​polluted cultivated land that takes land use type change control measures under the following scenarios: a =3 i -2; C2i For the i The cost per unit area of ​​the measures to adjust the planting structure under the following scenarios: X b For the i The area of ​​polluted cultivated land that takes measures to adjust the planting structure under the following scenarios: b =3 i -1; C 3i For the i The cost per unit area of ​​ecological land conversion control measures under the following scenarios: X c For the i The area of ​​polluted farmland that adopts ecological land withdrawal control measures under the following scenarios: c =3 i .

[0061] The weights of the three objective functions are linearly weighted and summed to 1. Since the probability of taking these three types of control measures for polluted farmland is the same, the weight coefficients are all 1 / 3. Based on this, the multi-objective function can be converted into a single objective function for solution: MinF ( X )= MinF 1( X )+ MinF 2( X )+ MinF 3( X ).

[0062] According to the constraints of cultivated land area, safe utilization rate and cultivated land productivity in the first embodiment, combined with the suitability constraints of urban distance, industrial area distance, slope and healthy productivity status when formulating various cultivated land management and control measures, 18 constraint equations are set, see Table 4.

[0063] Table 4 Constraint equation statistics

[0064] The total controlled area of ​​cultivated land in the strictly controlled area is 952.77hm 2 , its heavy metal pollution and planting structure are relatively complex. This embodiment adopts a multi-objective linear programming model to classify and control the cultivated land in the strict control area according to information such as distance from towns, distance from industrial areas, slope, and healthy production capacity status.

[0065] The decision variable values ​​when the objective function is optimally solved are obtained using the Excel planning and solving function, as shown in Table 5. The polluted cultivated land in scenarios 2, 4, 6, 7 and 8 adopts the control measure of changing the land use type, the polluted cultivated land in scenarios 1, 3, 9, 11, 13 and 15 adopts the control measure of adjusting the planting structure, and the polluted cultivated land in scenarios 5, 10, 12, 14 and 16 adopts the control measure of ecological land withdrawal. Combining the distance from towns and industrial areas, terrain, healthy production capacity conditions and other conditions of each scenario, it can be concluded that: polluted cultivated land located around towns and industrial areas will be classified as a change of land use type, and with reference to the approval process for conversion of agricultural land, it can apply for approval to change to construction land to support local construction land needs; polluted cultivated land located in grain production functional areas, important agricultural product production protection areas, plain areas, and with good healthy production capacity conditions will be classified as an adjustment of planting structure, and planting structure adjustments will be implemented according to local conditions to plant fiber crops (such as cotton, hemp, and mulberry), flower seedlings, energy crops (such as yellow-veined camphor and switchgrass), and other non-edible economic crops to achieve efficient utilization; polluted cultivated land located in low hills and gentle slopes with poor healthy production capacity conditions will be classified as an ecological land conversion category, and after applying for approval in accordance with regulations, it will be converted to ecological land and returned to forest and grassland to promote ecological environmental protection.

[0066] Table 5 Decision variable values ​​when the objective function is optimal

[0067] According to the control measures taken for polluted farmland in each scenario of the strict control area, the cultivated land area with the same control measure type is summed up, as shown in Table 6. For polluted farmland in the strict control area, the area that needs to take control measures to adjust the planting structure is the largest, up to 517.37 hm 2 , accounting for 54.30% of the cultivated land area in the strict control area, more than half of which are scattered throughout the study area, especially in the central region. The area of ​​polluted cultivated land that needs to take control measures to change the land use type is the smallest, at 168.72hm 2 , accounting for 17.71%, concentrated in the urban area in the middle of the study area. The area of ​​polluted farmland that needs to take ecological land reclamation control measures is 266.67hm 2 , accounting for 27.99% of the cultivated land area in the strict control area, and is concentrated in the higher terrain area in the central and western part of the study area.

[0068] Table 6 Area and proportion of each type of control measures

[0069] Heavy metal pollution zones also include priority protection areas and safe utilization areas. The cleanliness and health of cultivated land in priority protection areas are generally high. Crops in the area are all pollution-free, and most of the soil is pollution-free, with a small amount of slight pollution. For cultivated land with no pollution in both soil and crops, it is directly classified as permanent basic farmland for continuous protection, such as adopting green production technology to further improve the productivity and health of cultivated land. For cultivated land with slight soil pollution and no pollution in crops, appropriate agronomic control measures such as soil testing and formula fertilization are adopted to reduce the degree of heavy metal pollution in the soil, and at the same time, green prevention and control, cultivated land conservation and other technologies are assisted to improve the quality of cultivated land; the heavy metal pollution and planting structure in the safe utilization area are complex. According to information such as crop pollution level, soil pollution level, soil pH, planted crop type and major soil pollutants, the cultivated land in the safe utilization area can be classified and controlled. For specific control measures, see below.

[0070] In the method for classified control of heavy metal pollution in cultivated land of the first embodiment, steps S102 and S103 may also adopt the following technical solution: using a decision tree model to obtain classified control measures for each plot in the heavy metal pollution strict control area.

[0071] The decision tree model is a method of classifying data based on a tree structure formed by knowledge. It is highly similar to a flowchart in structure and has the advantages of strong readability and fast classification speed. The top node of the decision tree is the root node of the tree, the branch represents the test output, the leaf node represents the category, and the non-leaf node represents the attribute test. A series of classification rules are generated through learning and induction, so each path from the root node to the leaf node is a classification rule.

[0072] The third embodiment of the present invention provides a method for obtaining classification control measures for each plot of land in a heavy metal pollution safe utilization area by using a decision tree.

[0073] The decision tree model is used to determine the classification control measures and their regions and areas for cultivated land in safe utilization areas. There are great differences in crop pollution, soil pollution, soil pH, crop types and major soil pollutants in the contaminated cultivated land in the safe utilization area, and the corresponding control measures are also very different. The cultivated land in the safe utilization area can adopt the following measures depending on the specific pollution situation. If there is heavy metal pollution in crops, low-accumulation varieties of crops can be used to replace the planted varieties. If there is heavy metal pollution in the soil, measures can be taken according to the type of cultivated land and its main pollutant types. For rice fields contaminated by Cd, Hg, Pb, and As, water control method can be adopted; for rice fields contaminated by Cd and Pb, leaf barrier control method can be adopted; for rice fields contaminated by Cd and Hg, organic material regulation method can be adopted; for farmland contaminated by Cd, Hg, and Pb, in-situ passivation method can be adopted; for farmland contaminated by Cd, Zn, and As, plant absorption method can be adopted. For the acidity and alkalinity of the soil, lime or gypsum regulation method can be adopted. The optimized fertilization method is usually used in conjunction with other measures and is applicable to all soils and crops contaminated by heavy metals. In addition, deep tillage, microbial remediation, and straw removal can be used in conjunction with other measures according to the actual situation of heavy metal pollution in the soil. Some classification rules of the decision tree are shown in Table 7.

[0074] Table 7 Partial classification rules of decision tree

[0075] The total controlled area of ​​cultivated land in the safe utilization zone is 4650.28hm 2 , a total of seven control technologies based on the idea of ​​"VIP+n" integrated technology are adopted, see Table 8. V (variety) refers to the replacement of low-accumulation varieties; I (irrigation) refers to the optimization of water and fertilizer regulation; P (pH) refers to the regulation of soil acidity and alkalinity; n refers to the adoption of other composite measures such as leaf surface control. "VIP" technology includes two specific measures. The area of ​​cultivated land pollution control using this technology is the largest, which is 2218.56hm 2 , accounting for 47.70%, almost half of the cultivated land in the safe utilization area, and is obviously concentrated in the central region. The control area of ​​the "lime / gypsum adjustment + optimized fertilization" measure is 1638.26hm 2 , accounting for 35.23%, the highest proportion in the control area of ​​specific measures, and widely distributed in the study area, scattered in the northern region. 2 Neutral soils need to be replaced with low-accumulation varieties and water and fertilizer regulation should be optimized. Another 7.27hm 2 Neutral soil requires water control, leaf barrier control and organic material adjustment. The control area of ​​"IP+n" technology and "P+n" technology is not much different, about 250hm 2, mainly distributed in the north-central region. The control area using only other composite measures is relatively small, including 127.78hm 2 of cultivated land only needs optimized fertilization, 34.57hm 2 of cultivated land only needs to be planted with hyperaccumulators, 3.90hm 2 The cultivated land needs to be optimized for fertilization and in situ passivation.

[0076] Table 8 Control technology

[0077] The methods of classified control measures for priority protection areas can be referred to the above technical solution and will not be repeated here.

[0078] A fourth embodiment of the present invention provides a system for classifying and controlling heavy metal pollution in cultivated land, and the system for classifying and controlling heavy metal pollution in cultivated land comprises: The plot division module is used to obtain remote sensing image data of the heavy metal pollution strictly controlled area, and divide the strictly controlled area into multiple plots with different environmental conditions using an object-oriented method; Plot analysis module, used to obtain crop types and rotation patterns on each plot in the strictly controlled area; Construct a constraint condition module, which is used to use the distance to town, the distance to industrial area, slope, and production capacity as influencing factors of the control measures in the strict control area, construct multiple scenarios, and use the controllable area for implementing various control measures in each scenario as the area variable in the constraint equation. According to the scenarios, control measures, and area variables, construct multiple suitability constraints for the control measures in the strict control area; The classification control module is used to take the expenditure costs, cultivated land area and safe utilization rate of various control measures in strict control areas as constraints of control measures in strict control areas, and combine them with suitability constraints to obtain classification control measures that minimize the total cost of strict control areas of heavy metal pollution.

[0079] The fifth embodiment of the present invention provides a computer-readable storage medium, on which a data processing program is stored. When the data processing program is executed by a processor, the steps of the method for classified control of heavy metal pollution in cultivated land as described in any of the above items are implemented.

[0080] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for classified control of heavy metal pollution in cultivated land, characterized in that: include: Obtain remote sensing image data of the heavy metal pollution strict control area, divide the heavy metal pollution strict control area using object-oriented method, and obtain each plot of heavy metal pollution zone; Obtain the crop types and rotation patterns on each plot in the strictly controlled area, and determine the control measures for various strictly controlled areas, including changing land use types, adjusting planting structure and ecological land withdrawal; Taking the distance to town, distance to industrial area, slope and production capacity as the influencing factors of various control measures in strict control areas to construct multiple scenarios, taking the controllable area for implementing various control measures in each scenario as the area variable, and constructing multiple suitability constraints for control measures in strict control areas based on the scenarios, control measures and area variables; A multi-objective linear programming model was constructed, and the expenditure costs of various control measures in strict control areas were taken as the objective function of the multi-objective linear programming model. The cultivated land area and safe utilization rate were taken as constraints for the control measures in strict control areas. Combined with multiple suitability constraints, the multi-objective linear programming model was used to obtain classified control measures that minimized the total cost of strict control areas of heavy metal pollution under various scenarios.

2. The method for classified control of heavy metal pollution in cultivated land according to claim 1, characterized in that: The method of dividing the heavy metal pollution strict control area by using the object-oriented method includes the following steps: Perform multi-scale segmentation on remote sensing image data and generate image object layers at different segmentation scales, wherein the characteristics of the image objects after multi-scale segmentation include: spectrum, texture and geometry; Select the feature space and assign different weights to each feature to obtain the classification results of the land objects; According to the classification results of the ground objects, the hierarchical structure corresponding to the ground objects is obtained, and the image object layers are connected according to the hierarchical structure corresponding to the ground objects to obtain the various plots of heavy metal pollution zones.

3. The method for classified control of heavy metal pollution in cultivated land according to claim 1, characterized in that: The multi-objective linear programming model is constructed, and the expenditure of various control measures in the strict control area is used as the objective function of the multi-objective linear programming model, including: Construct a multi-objective linear programming model: The expenditures of various control measures in strictly controlled areas are taken as the objective functions of the multi-objective linear programming model. The expenditures of control measures in strictly controlled areas include the expenditures of changing land use types, adjusting planting structures and ecological land withdrawal, which are respectively set as the objective functions F 1( X ), F 2( X )and F 3( X ),but: MinF 1( X )=∑ C 1i × X a ； MinF 2( X )=∑ C 2i × X b ； MinF 3( X )=∑ C 3i × X c ； Where: C 1i For the i The cost per unit area of ​​the land use type change control measures in the following scenarios: X a For the i The area of ​​polluted cultivated land that takes land use type change control measures under the following scenarios: a =3 i -2; C 2i For the i The cost per unit area of ​​the measures to adjust the planting structure under the following scenarios: X b For the i The area of ​​polluted cultivated land that takes measures to adjust the planting structure under the following scenarios: b =3 i -1; C 3i For the i The cost per unit area of ​​ecological land conversion control measures under the following scenarios: X c For the i The area of ​​polluted farmland that adopts ecological land withdrawal control measures under the following scenarios: c =3 i ; The weight coefficients of the three objective functions are all 1 / 3, converting the multi-objective function into a single objective function: ； Construct the cultivated land area constraint condition, which is that the sum of cultivated land areas with various control measures is equal to the total cultivated land area in the strict control area; Construct a safe utilization rate constraint condition, which requires that the safe utilization rate of polluted cultivated land reaches or exceeds the preset standard; According to the constraints and suitability constraints, the classified control measures with the minimum total cost are obtained.

4. The method for classified control of heavy metal pollution in cultivated land according to claim 1, characterized in that: Also includes: Using the decision tree model, the expenditure costs of various control measures in strict control areas are taken as the objective function of the decision tree model, and the cultivated land area and safe utilization rate are taken as constraints for the control measures in strict control areas. Combined with multiple suitability constraints, a multi-objective linear programming model is used to obtain classified control measures that minimize the total cost of strict control areas of heavy metal pollution under various scenarios.

5. The method for classified control of heavy metal pollution in cultivated land according to claim 1, characterized in that: The acquisition of crop types and rotation patterns on each plot in the strictly controlled area includes: Collect multiple sample point data of remote sensing image data, and annotate the ground object type and crop rotation mode for each sample point data; Obtain spectral characteristic data of each sample point data, and calculate exponential characteristic data according to the spectral characteristic data; The extracted feature data and the labeled data of the sample points are used to train a random forest classification model. The trained random forest classification model is used to obtain the crop types and rotation patterns on each plot in the safe utilization area, and thus determine the various strict control measures in the control area to change the land use type and adjust the planting structure.

6. The method for classified control of heavy metal pollution in cultivated land according to claim 5, characterized in that: The bands of the spectral characteristic data include: B, G, R, NIR, SWIR1 and SWIR2, and the index characteristic data include: NDVI, EVI, NDWI, LSWI, NDSI, NDSVI, NDTI, WDVI and NDFI9.

7. A classification and control system for heavy metal pollution in cultivated land, characterized in that: Used to implement the method for classified control of heavy metal pollution in cultivated land as described in any one of claims 1 to 6, the classified control system for heavy metal pollution in cultivated land comprises: The land parcel division module is used to obtain remote sensing image data of the heavy metal pollution strict control area, divide the heavy metal pollution strict control area using an object-oriented method, and obtain the various land parcels of the heavy metal pollution zone; The plot analysis module is used to obtain the crop types and rotation patterns on each plot in the strictly controlled area, and determine the control measures for various strictly controlled areas, including changing the land use type, adjusting the planting structure and ecological land withdrawal; Construct a constraint condition module, which is used to construct multiple scenarios by taking town distance, industrial zone distance, slope and production capacity as influencing factors of various control measures in strict control areas, taking the controllable area for implementing various control measures in each scenario as the area variable, and constructing multiple suitability constraints for control measures in strict control areas based on the scenarios, control measures and area variables; The classification control module is used to take the expenditure of various control measures in strict control areas as the objective function of the multi-objective linear programming model, and take the cultivated land area and safe utilization rate as the constraints of the control measures in the strict control areas. Combined with multiple suitability constraints, the multi-objective linear programming model is used to obtain the classification control measures that minimize the total cost of the strict control areas of heavy metal pollution under various scenarios.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a data processing program, and when the data processing program is executed by the processor, the steps of the method for classification and control of heavy metal pollution in cultivated land as described in any one of claims 1 to 6 are implemented.

Images