Farmland cadmium content grading methods and systems, electronic devices, and storage media

By using a geographically weighted regression model and hotspot analysis, the spatial heterogeneity of cadmium content in farmland was identified, and differentiated soil sludge content thresholds were established. This solved the problem of poor applicability of thresholds for cadmium pollution zoning in farmland in existing technologies, and achieved the accuracy and scientific nature of cadmium content classification in farmland.

CN123120089APending Publication Date: 2026-11-17TECH CENT FOR SOIL AGRI & RURAL ECOLOGY & ENVIRONMENT MINIST OF ECOLOGY & ENVIRONMENT
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611260913.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-19
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing methods for safe planting zones in farmland contaminated with cadmium ignore the spatial correlation between soil cadmium content and crop cadmium content, resulting in poor threshold applicability and making it difficult to achieve accurate zoning and efficient management.

Method used

By employing a geographically weighted regression model combined with hotspot analysis, spatial hotspots for cadmium accumulation in soil and crops were identified. Local regression coefficients were constructed, and differentiated safe thresholds for soil cadmium content were established based on spatial characteristics and regression relationships.

Benefits of technology

Precisely characterizing the local response relationship between soil cadmium content and crop absorption avoids misjudgment or over-remediation due to "one-size-fits-all" standards, and enhances the spatial relevance and scientific basis of farmland heavy metal pollution risk assessment and hierarchical management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123120089A_ABST
    Figure CN123120089A_ABST
Patent Text Reader

Abstract

This invention relates to the field of pollution control, and provides a method and system for grading cadmium content in farmland, electronic equipment, and storage media. The method includes: collecting soil and crop samples from the farmland to be tested, obtaining data on the physicochemical properties and cadmium content of the soil, and data on the cadmium content in the crops; performing hotspot analysis to spatially cluster hotspot areas; constructing a geographically weighted regression model, using soil cadmium content as the independent variable and crop cadmium content as the dependent variable, and calculating the local regression coefficient for each spatial location; comprehensively determining the final zoning of the farmland to be tested; and formulating a corresponding safe threshold for soil cadmium content for each final zoning. This invention addresses the shortcomings of existing methods, which suffer from poor threshold applicability and low safe utilization efficiency due to neglecting the spatial correlation differences between soil cadmium content and crop cadmium content. The solution proposed in this application can consider the spatial heterogeneity of the soil-crop system and dynamically determine the safe threshold for each zoning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of pollution control technology, and in particular to a method and system for grading cadmium content in farmland, electronic equipment, and storage medium. Background Technology

[0002] Cadmium (Cd) is one of the most harmful heavy metals in farmland soil, readily entering the food chain through the soil-crop system and causing damage to the human kidneys and bones. While there are clear limits on the Cd content in soil and rice for human health, in practical applications, defining safe planting zones solely based on total soil Cd levels presents the following significant problems: 1. High Spatial Variables in Bioavailability: High total soil Cd levels do not necessarily lead to excessive Cd levels in crops. Factors such as soil pH, organic matter, and iron and manganese oxide content significantly affect the bioavailability of Cd. For example, in calcareous soils, Cd is strongly adsorbed, and crops absorb very little; while in acidic soils, even with low soil Cd levels, crops may still exceed safe limits. Using a uniform threshold for total soil Cd levels can lead to either "over-remediation" or "over-application." 2. Spatial heterogeneity is ignored: Traditional methods neglect the spatial variation of the correlation between soil Cd and crop Cd. In areas with complex geological backgrounds and diverse human activities, the relationship between the two may change drastically over short distances, and global thresholds cannot reflect this difference; 3. Low efficiency in zoning decision-making: Existing methods cannot effectively distinguish between "high-risk areas requiring strict control", "medium-risk areas requiring key attention" and "low-risk areas that can be safely utilized", making it difficult for governments and enterprises to formulate precise planting structure adjustment plans. Summary of the Invention

[0003] This invention provides a method and system for classifying cadmium content in farmland, an electronic device, and a storage medium to address the shortcomings of existing methods for safe planting zones in farmland contaminated with cadmium, which suffer from poor threshold applicability and low safety utilization efficiency due to neglecting the spatial correlation differences between soil cadmium content and crop cadmium content. The solution proposed in this application can take into account the spatial heterogeneity of the soil-crop system and can dynamically determine the safety threshold for each zone.

[0004] This invention provides a method for grading cadmium content in farmland, comprising: Soil and crop samples were collected from the farmland to be tested, and the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, were obtained through laboratory testing. Hotspot analysis was performed on soil cadmium content data and crop cadmium content data to identify spatial hotspots of cadmium accumulation in soil and crops. A geographically weighted regression model was constructed, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, to calculate the local regression coefficient for each spatial location. By combining the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients, the final zoning of the farmland to be tested is determined comprehensively. For each final zone, a corresponding safe threshold for soil cadmium content is established based on spatial characteristics and regression relationships.

[0005] According to the farmland cadmium content grading method provided by the present invention, the step of formulating a corresponding safe threshold for soil cadmium content for each final zone based on spatial characteristics and regression relationships further includes: Using the confusion matrix, the accuracy, misjudgment rate, and omission rate of the obtained soil cadmium content threshold were calculated. By adjusting the soil cadmium content threshold, the accuracy rate, false positive rate, and omission rate all meet the set standards.

[0006] According to the method for grading cadmium content in farmland provided by the present invention, the setting criteria include: The accuracy rate reaches the preset accuracy rate threshold. Alternatively, the rate of increase in the accuracy rate reaches a pre-set growth rate threshold.

[0007] According to the method for grading farmland cadmium content provided by this invention, the construction of a geographically weighted regression model, using soil cadmium content as the independent variable and crop cadmium content as the dependent variable, and calculating the local regression coefficient for each spatial location, includes: Construct the following regression equation: in, It is the value of the dependent variable corresponding to the i-th sampling position. It is the value of the independent variable corresponding to the i-th sampling position. It is the y-intercept. Let i be the regression coefficients estimated for the independent variables at i locations. It is an error term; By adding geographical location to the regression equation using a geographic weighted regression model, the following formula is satisfied: in, and Let be the coordinates of the i-th sampling position. It is the intercept at the i-th sampling position. It is the regression coefficient of the independent variable at the i-th sampling position; The regression coefficients are estimated according to the following formula: Where X is the... The corresponding matrix, Y is The corresponding matrix, This is the weight matrix; Using the Pearson correlation coefficient calculation formula, the local regression coefficients are obtained, satisfying the following formula: in, R² is generated for each point in the GWR model.

[0008] According to the method for classifying cadmium content in farmland provided by the present invention, the step of combining the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients to comprehensively determine the final zoning of the farmland to be tested includes: Interpolate the local regression coefficients to divide the clustering areas of the farmland to be tested; Based on the magnitude and direction of the local regression coefficients and the hotspot distribution of cadmium in the soil, the farmland to be tested is divided into zones.

[0009] According to the method for classifying cadmium content in farmland provided by the present invention, the farmland to be tested is divided into high-risk areas, high bioavailability concern areas, and low bioavailability concern areas. The high-risk area corresponds to a high-value cluster of cadmium in the soil and crops of the farmland to be tested. The local regression coefficient is also high. The soil of the farmland to be tested corresponding to the high bioavailability interest area is clustered as a low-value cluster area, and the crops are clustered as a high-value cluster area. The local regression coefficient is low, and the soil physicochemical property data characterize high cadmium bioavailability. The soil clusters of the farmland to be tested corresponding to the low bioavailability concern area are high-value clusters, and the crop clusters are low-value clusters. The local regression coefficients are low, and the soil physicochemical property data indicate low cadmium bioavailability.

[0010] According to the farmland cadmium content grading method provided by the present invention, the step of formulating a corresponding safe threshold for soil cadmium content for each final zone based on spatial characteristics and regression relationships includes: A univariate linear regression model was established between soil cadmium content data and crop cadmium content data of the farmland to be tested. Based on the crop cadmium content data, the soil cadmium content threshold of the farmland to be tested in high-risk areas was determined. Based on the cumulative probability distribution of cadmium enrichment coefficients in crops, the soil cadmium content threshold for farmland under test in high bioavailability interest areas was determined. A neural network model is applied, using the soil physicochemical properties of the farmland to be tested as the model input data, to predict the soil cadmium function of the farmland to be tested and determine the soil cadmium content threshold of the farmland to be tested in the low bioavailability concern area.

[0011] This invention also provides a cadmium content grading system for farmland, which applies a cadmium content grading method for farmland, including: The data acquisition module is used to collect soil and crop samples from the farmland to be tested, and to obtain data on the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, through laboratory testing. The hotspot analysis module is used to perform hotspot analysis on soil cadmium content data and crop cadmium content data respectively, and to identify spatial hotspot areas of cadmium accumulation in soil and crops. The weighted regression module is used to construct a geographic weighted regression model, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, to calculate the local regression coefficient for each spatial location. The farmland zoning module is used to combine the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients to comprehensively determine the final zoning of the farmland to be tested. The threshold determination module is used to formulate corresponding safe thresholds for soil cadmium content for each final partition based on spatial characteristics and regression relationships.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the above-described methods for grading cadmium content in farmland.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for grading cadmium content in farmland.

[0014] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described methods for grading cadmium content in farmland.

[0015] The method for classifying cadmium content in farmland provided by this invention, by coupling a geographically weighted regression model with hotspot analysis technology, not only breaks through the limitation of traditional global regression ignoring spatial heterogeneity and accurately characterizes the local response relationship between soil cadmium content and crop uptake, but also identifies farmland zones dominated by different ecological processes based on statistical significance. This allows for the tailoring of differentiated soil cadmium content thresholds for each zone, effectively avoiding misjudgments or over-remediation caused by a "one-size-fits-all" standard. It significantly improves the spatial relevance and scientific basis of heavy metal pollution risk assessment and graded management, providing reliable technical support for precision agriculture and soil health management. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort.

[0017] Figure 1 This is a schematic flowchart of the method for grading cadmium content in farmland provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the cadmium content grading system for farmland provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the physical structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0019] Figure 1 This is a schematic flowchart of the method for grading cadmium content in farmland provided in an embodiment of the present invention.

[0020] like Figure 1 As shown, this embodiment provides a method for grading cadmium content in farmland, including: Step 101: Collect soil and crop samples from the farmland to be tested, and obtain data on the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, through laboratory testing. In practical applications, soil physicochemical properties can include pH value, TFe2O3 (total iron oxide) content, Corg. (organic carbon) content, CaO (calcium oxide) content, etc.

[0021] After obtaining the above data, logarithmic transformation or normal score transformation can be performed on the data to make it conform to a normal distribution, so as to meet the needs of subsequent processing steps.

[0022] Step 102: Perform hotspot analysis on soil cadmium content data and crop cadmium content data respectively to identify spatial hotspot areas of cadmium accumulation in soil and crops. Specifically, the strength and direction of the spatial correlation between soil cadmium content and crop cadmium content can be initially determined based on the magnitude and sign of the local regression coefficients. Subsequently, hotspot analysis (such as the Getis-OrdGi* statistic) is performed on the local regression coefficients to identify statistically significant high-value clusters (hotspots) and low-value clusters (colds). Hotspot areas correspond to strong positive correlations, while coldspot areas correspond to weak or negative correlations.

[0023] Step 103: Construct a geographically weighted regression model with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, and calculate the local regression coefficient for each spatial location. The local regression coefficient reflects the strength and direction of the correlation between cadmium content in farmland and cadmium content in crops. In practice, the following regression equation can be constructed: in, It is the value of the dependent variable corresponding to the i-th sampling position. It is the value of the independent variable corresponding to the i-th sampling position. It is the y-intercept. Let be the regression coefficient estimated for the independent variable at the i-th position. This is the error term.

[0024] By adding geographical location to the regression equation using a geographic weighted regression model, the following formula is satisfied: in, and Let be the coordinates of the i-th sampling position. It is the intercept at the i-th sampling position. It is the regression coefficient of the independent variable at the i-th sampling position.

[0025] The regression coefficients are estimated according to the following formula: Where X is the... The corresponding matrix, Y is The corresponding matrix, This is the weight matrix; Using the Pearson correlation coefficient calculation formula, the local regression coefficients are obtained, satisfying the following formula: in, R² is generated for each point in the GWR model.

[0026] Step 104: Combine the soil cadmium distribution zones obtained from hotspot analysis with local regression coefficients to comprehensively determine the final zones of the farmland to be tested; In practical applications, geological background information (such as parent material type, soil pH, iron and manganese oxide content, etc.) can be superimposed to comprehensively determine the final zoning of the farmland to be tested. If a region has a significantly positive local regression coefficient and is in a hotspot cluster, it is classified as a high-risk area with a strong positive correlation, indicating that soil cadmium content directly dominates crop cadmium content and requires strict control.

[0027] If a region has a local regression coefficient that is weakly positive or negative and is in a cold cluster, but the geological background shows that the soil pH is low and iron and manganese oxides are lacking (cadmium bioavailability is high), it is classified as a high bioavailability concern area. Even if the soil cadmium content is not high, crops are still at risk of exceeding the standard.

[0028] If the local regression coefficient of a certain area is weakly positive or negative, and the geological background shows that the soil pH is high and rich in iron and manganese oxides or carbonates (cadmium bioavailability is inhibited), it is classified as a low bioavailability concern area, and can be safely planted under monitoring.

[0029] Step 105: For each final zone, based on spatial characteristics and regression relationships, formulate corresponding safe thresholds for soil cadmium content.

[0030] In this step, different methods can be selected to determine the soil cadmium content based on the different zones determined above. Specifically, for high-risk areas, since the cadmium content data of farmland is directly related to the cadmium content data of crops, a univariate linear regression model can be established between the cadmium content data of the farmland to be tested and the cadmium content data of crops. Based on the cadmium content data of crops, the soil cadmium content threshold of the farmland to be tested in high-risk areas can be determined. For areas of high bioavailability concern, the "Species Sensitivity Distribution (SSD) method" is applied—avoiding the hidden risks of "high-yield cultivation in low-yield soils"—based on the cumulative probability distribution of cadmium enrichment coefficients in crops, to determine the soil cadmium content threshold for farmland in these high-bioavailability concern areas. Although the total soil cadmium content in this zone is not high, its bioavailability is extremely high, posing a significant risk of crop absorption. In this case, the linear relationship between soil and crop has collapsed; if regression is used to force a reverse calculation, the sample size will be insufficient or the residuals will be extremely large, resulting in a highly unstable threshold. Therefore, instead of establishing a linear equation between soil and crop, the enrichment coefficients of a large number of plots in the area are statistically analyzed. For example, the median quantile of protecting 90% of the plots can be selected as the threshold. This "probabilistic protection" approach can effectively cover those extremely sensitive plots where "soil cadmium is low but the enrichment coefficient is extremely high."

[0031] For areas of concern with low bioavailability, the local regression coefficients show weak or negative correlations, and the geological background is favorable (high pH, ​​rich in iron and manganese oxides / carbonates). In this case, using linear regression would ignore the interactions between factors (e.g., the synergistic inhibition of cadmium by CaO increasing pH), leading to overly conservative thresholds that limit production. Using species sensitivity distribution methods would waste known key physicochemical data. Therefore, a neural network regression model is introduced, utilizing its powerful nonlinear fitting capability. By using the aforementioned key factors as input layers, a "dynamic virtual benchmark" is trained, truly achieving "maximization of planting space under safe monitoring."

[0032] In practical applications, after determining the soil cadmium content threshold, the calculated threshold can be verified, including the following steps: Using the confusion matrix, the accuracy, misjudgment rate, and omission rate of the obtained soil cadmium content threshold were calculated. By adjusting the soil cadmium content threshold, the accuracy rate, false positive rate, and omission rate all meet the set standards.

[0033] In summary, the method for grading cadmium content in farmland provided in this application has at least the following beneficial effects: 1. Improved the accuracy of safe planting zoning: Through spatial correlation analysis, spatial differences in Cd migration and transformation in the soil-crop system were identified, avoiding over-remediation or over-management problems caused by "one-size-fits-all" thresholds.

[0034] 2. It has enabled refined management of farmland: the study area has been divided into high-risk control zones, high bioavailability focus zones, and low-risk safety zones, which has significantly reduced the cost of governance.

[0035] 3. Enhanced scientific rigor and adaptability of the method: For the dominant control factors (linear relationships, probability distributions, nonlinear multi-factor coupling) in different regions, a matching mathematical model is adopted, making the threshold determination process more theoretically grounded and practically operable.

[0036] 4. It ensures the quality and safety of agricultural products while avoiding excessive investment in low-risk land.

[0037] The cadmium content grading system for farmland provided by this invention is described below. The cadmium content grading system for farmland described below can be referred to in correspondence with the cadmium content grading method for farmland described above.

[0038] Figure 2 This is a schematic diagram of the cadmium content grading system for farmland provided in an embodiment of the present invention.

[0039] like Figure 2 As shown, the farmland cadmium content grading system provided in this embodiment includes: The data acquisition module 201 is used to collect soil and crop samples from the farmland to be tested, and to obtain data on the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, through laboratory testing. Hotspot analysis module 202 is used to perform hotspot analysis on soil cadmium content data and crop cadmium content data respectively, and to identify spatial hotspot areas of cadmium accumulation in soil and crops. The weighted regression module 203 is used to construct a geographic weighted regression model, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, to calculate the local regression coefficient for each spatial location. Farmland zoning module 204 is used to combine the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients to comprehensively determine the final zoning of the farmland to be tested; The threshold determination module 205 is used to formulate a corresponding safe threshold for soil cadmium content for each final partition based on spatial characteristics and regression relationships.

[0040] The specific implementation method of the farmland cadmium content grading system provided in this embodiment can be implemented with reference to the above embodiment, and will not be repeated here.

[0041] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. The processor 310, communications interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions stored in the memory 330 to execute a method for grading cadmium content in farmland, which includes: Soil and crop samples were collected from the farmland to be tested, and the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, were obtained through laboratory testing. Hotspot analysis was performed on soil cadmium content data and crop cadmium content data to identify spatial hotspots of cadmium accumulation in soil and crops. A geographically weighted regression model was constructed, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, to calculate the local regression coefficient for each spatial location. By combining the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients, the final zoning of the farmland to be tested is determined comprehensively. For each final zone, a corresponding safe threshold for soil cadmium content is established based on spatial characteristics and regression relationships.

[0042] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0043] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the farmland cadmium content grading method provided by the above methods, the method comprising: Soil and crop samples were collected from the farmland to be tested, and the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, were obtained through laboratory testing. Hotspot analysis was performed on soil cadmium content data and crop cadmium content data to identify spatial hotspots of cadmium accumulation in soil and crops. A geographically weighted regression model was constructed, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, to calculate the local regression coefficient for each spatial location. By combining the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients, the final zoning of the farmland to be tested is determined comprehensively. For each final zone, a corresponding safe threshold for soil cadmium content is established based on spatial characteristics and regression relationships.

[0044] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the farmland cadmium content grading method provided by the above methods, the method comprising: Soil and crop samples were collected from the farmland to be tested, and the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, were obtained through laboratory testing. Hotspot analysis was performed on soil cadmium content data and crop cadmium content data to identify spatial hotspots of cadmium accumulation in soil and crops. A geographically weighted regression model was constructed, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, to calculate the local regression coefficient for each spatial location. By combining the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients, the final zoning of the farmland to be tested is determined comprehensively. For each final zone, a corresponding safe threshold for soil cadmium content is established based on spatial characteristics and regression relationships.

[0045] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0046] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for grading cadmium content in farmland, characterized in that, include: Soil and crop samples were collected from the farmland to be tested, and the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, were obtained through laboratory testing. Hotspot analysis was performed on soil cadmium content data and crop cadmium content data to identify spatial hotspots of cadmium accumulation in soil and crops. A geographically weighted regression model was constructed, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, to calculate the local regression coefficient for each spatial location. By combining the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients, the final zoning of the farmland to be tested is determined comprehensively. For each final zone, a corresponding safe threshold for soil cadmium content is established based on spatial characteristics and regression relationships.

2. The method for grading cadmium content in farmland according to claim 1, characterized in that, For each final zone, based on spatial characteristics and regression relationships, a corresponding safe threshold for soil cadmium content is established, which further includes: Using the confusion matrix, the accuracy, misjudgment rate, and omission rate of the obtained soil cadmium content threshold were calculated. By adjusting the soil cadmium content threshold, the accuracy rate, false positive rate, and omission rate all meet the set standards.

3. The method for grading cadmium content in farmland according to claim 2, characterized in that, The setting criteria include: The accuracy rate reaches the preset accuracy rate threshold. Alternatively, the rate of increase in the accuracy rate reaches a pre-set growth rate threshold.

4. The method for grading cadmium content in farmland according to claim 1, characterized in that, The constructed geographic weighted regression model, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, calculates the local regression coefficients for each spatial location, including: Construct the following regression equation: in, It is the value of the dependent variable corresponding to the i-th sampling position. It is the value of the independent variable corresponding to the i-th sampling position. It is the y-intercept. Let i be the regression coefficients estimated for the independent variables at i locations. It is an error term; By adding geographical location to the regression equation using a geographic weighted regression model, the following formula is satisfied: in, and Let be the coordinates of the i-th sampling position. It is the intercept at the i-th sampling position. It is the regression coefficient of the independent variable at the i-th sampling position; The regression coefficients are estimated according to the following formula: Where X is the... The corresponding matrix, Y is The corresponding matrix, This is the weight matrix; Using the Pearson correlation coefficient calculation formula, the local regression coefficients are obtained, satisfying the following formula: in, R for each point generated by the GWR model 2 .

5. The method for grading cadmium content in farmland according to claim 1, characterized in that, The process of combining the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients to comprehensively determine the final zoning of the farmland to be tested includes: Interpolate the local regression coefficients to divide the clustering areas of the farmland to be tested; Based on the magnitude and direction of the local regression coefficients and the hotspot distribution of cadmium in the soil, the farmland to be tested is divided into zones.

6. The method for grading cadmium content in farmland according to claim 5, characterized in that, The farmland to be tested is divided into high-risk areas, high bioavailability concern areas, and low bioavailability concern areas. The high-risk area corresponds to a high-value cluster of cadmium in the soil and crops of the farmland to be tested. The local regression coefficient is also high. The soil of the farmland to be tested corresponding to the high bioavailability interest area is clustered as a low-value cluster area, and the crops are clustered as a high-value cluster area. The local regression coefficient is low, and the soil physicochemical property data characterize high cadmium bioavailability. The soil clusters of the farmland to be tested corresponding to the low bioavailability concern area are high-value clusters, and the crop clusters are low-value clusters. The local regression coefficients are low, and the soil physicochemical property data indicate low cadmium bioavailability.

7. The method for grading cadmium content in farmland according to claim 6, characterized in that, For each final zone, based on spatial characteristics and regression relationships, corresponding safe thresholds for soil cadmium content are established, including: A univariate linear regression model was established between soil cadmium content data and crop cadmium content data of the farmland to be tested. Based on the crop cadmium content data, the soil cadmium content threshold of the farmland to be tested in high-risk areas was determined. Based on the cumulative probability distribution of cadmium enrichment coefficients in crops, the soil cadmium content threshold for farmland under test in high bioavailability interest areas was determined. A neural network model is applied, using the soil physicochemical properties of the farmland to be tested as the model input data, to predict the soil cadmium function of the farmland to be tested and determine the soil cadmium content threshold of the farmland to be tested in the low bioavailability concern area.

8. A farmland cadmium content grading system, employing the farmland cadmium content grading method according to any one of claims 1-7, characterized in that, include: The data acquisition module is used to collect soil and crop samples from the farmland to be tested, and to obtain data on the physicochemical properties and cadmium content of the soil, as well as the cadmium content of the crops, through laboratory testing. The hotspot analysis module is used to perform hotspot analysis on soil cadmium content data and crop cadmium content data respectively, and to identify spatial hotspot areas of cadmium accumulation in soil and crops. The weighted regression module is used to construct a geographic weighted regression model, with soil cadmium content as the independent variable and crop cadmium content as the dependent variable, to calculate the local regression coefficient for each spatial location. The farmland zoning module is used to combine the soil cadmium distribution zoning obtained from hotspot analysis with local regression coefficients to comprehensively determine the final zoning of the farmland to be tested. The threshold determination module is used to formulate corresponding safe thresholds for soil cadmium content for each final partition based on spatial characteristics and regression relationships.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for grading the cadmium content of farmland as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for grading the cadmium content of farmland as described in any one of claims 1-7.