Regulation and control method and system for As-polluted paddy field soil

Abstract

The invention discloses an As-polluted paddy field soil regulation and control method and system, and the method comprises the steps: firstly obtaining soil key factor data at two moments before and after regulation and control, generating paddy inorganic As prediction distribution diagrams based on a prediction model, and determining an out-of-limit boundary line; the method comprises the following steps: judging a spatial position relationship between front and rear boundary lines, if the rear boundary line is positioned on the inner side of the front boundary line, dividing an annular region between the two lines into a plurality of dynamic regulation and control sub-regions, and determining a priority sequence according to an average predicted value and regulation and control difficulty of each sub-region; if not, defining the overlapping region as a high-priority regulation and control region; and finally, according to a priority sequence or aiming at a high-priority region, based on the real-time soil key factor data and a preset regulation and control rule base, automatically generating and executing an accurate or composite regulation and control scheme. According to the method, the closed-loop dynamic precise regulation and control from risk prediction, region precise identification to intelligent prescription generation is realized, and the pertinence and efficiency of arsenic-polluted farmland safety management are remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of soil pollution remediation technology, and in particular relates to a method and system for regulating As-contaminated paddy field soil. Background Technology

[0002] Arsenic (As) is a toxic metallic element widely present in the environment. With the rapid development of industry and agriculture, soil arsenic pollution has become increasingly serious, especially in paddy field systems. Arsenic has high bioavailability, is easily absorbed by rice and accumulates in the grains, posing a serious threat to human health through the food chain. According to the "National Soil Pollution Status Survey Bulletin" released in 2014, the exceedance rate of arsenic in Chinese soil reached 2.7%. Therefore, the safe utilization and precise control of As-contaminated paddy fields to reduce the arsenic content in rice and ensure the safety of agricultural products is of significant practical importance.

[0003] Currently, remediation technologies for As contaminated soil mainly include physical, chemical, and biological remediation methods. In practical applications, chemical passivation / stabilization technology is widely used due to its low cost and relatively simple operation. However, existing technologies mainly rely on a few indicators such as total soil arsenic content and pH value for regulation, lacking a systematic consideration of arsenic migration and transformation in the soil-rice system. This leads to significant blind spots in regulation measures and unstable effects.

[0004] Furthermore, existing technologies mostly focus on the remediation of single points or small areas, lacking a systematic approach for dynamic, zoned, and graded precise control of large-scale polluted farmland. Typically, after the implementation of control measures, the effectiveness is only assessed by retesting the total arsenic content in the soil, failing to establish a closed-loop control system based on predictive models that encompasses "monitoring-prediction-decision-implementation-feedback," thus hindering the dynamic optimization of control measures.

[0005] Therefore, developing a method and system for regulating As-contaminated paddy field soil that can accurately predict the arsenic content of rice, intelligently divide the regulation area, and dynamically generate and optimize the regulation scheme is of great significance for improving the safe utilization efficiency of As-contaminated farmland and ensuring the quality and safety of rice. Summary of the Invention

[0006] This invention provides a method and system for regulating As-contaminated paddy field soil, aiming to solve the technical problems of blind regulation measures, lack of dynamic optimization, and inability to achieve large-scale precise zonal regulation in existing technologies.

[0007] In a first aspect, the present invention provides a method for regulating As-contaminated paddy field soil, comprising: Obtain the first soil key factor data of paddy field at the first moment before regulation, and generate the first predicted distribution map of inorganic As in paddy grains based on the first soil key factor data. Obtain the second soil key factor data of paddy field at the second time after regulation, and generate the second predicted distribution map of inorganic As in rice grains based on the second soil key factor data; Determine whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice. The first excess boundary line is the boundary of the region in the first inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold, and the second excess boundary line is the boundary of the region in the second inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold. If the second exceeding boundary line is located inside the first exceeding boundary line, the area between the second exceeding boundary line and the first exceeding boundary line is divided into multiple dynamic control sub-regions, wherein each dynamic control sub-region is divided based on the vertical distance between a point on the first exceeding boundary line and a corresponding point on the second exceeding boundary line. Based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, the priority control order of each dynamic control sub-region is determined, and a list of dynamic control sub-regions sorted by priority is obtained. According to the priority-sorted list of dynamic control sub-regions, a precise control scheme is generated sequentially based on the real-time soil key factor data in each dynamic control sub-region using a preset control rule library, and then the precise control scheme is executed.

[0008] Secondly, the present invention provides a soil conditioning system for As-contaminated paddy fields, comprising: The first acquisition module is configured to acquire the first soil key factor data of the paddy field at the first moment before regulation, and generate a first predicted distribution map of inorganic As in rice grains based on the first soil key factor data. The second acquisition module is configured to acquire the second soil key factor data of the paddy field at the second time after regulation, and generate a second predicted distribution map of inorganic As in rice based on the second soil key factor data. The judgment module is configured to determine whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice, wherein the first excess boundary line is the boundary of the region in the first inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold, and the second excess boundary line is the boundary of the region in the second inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold. The partitioning module is configured to divide the area between the second excess boundary line and the first excess boundary line into multiple dynamic control sub-regions if the second excess boundary line is located inside the first excess boundary line. Each dynamic control sub-region is partitioned based on the vertical distance between a point on the first excess boundary line and a corresponding point on the second excess boundary line. The determination module is configured to determine the priority control order of each dynamic control sub-region based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, thereby obtaining a list of dynamic control sub-regions sorted by priority. The generation module is configured to generate a list of dynamic control sub-regions sorted according to the priority, and sequentially generate a precise control scheme based on the real-time soil key factor data in each dynamic control sub-region using a preset control rule library, and execute the precise control scheme.

[0009] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the As-contaminated paddy field soil regulation method according to any embodiment of the present invention.

[0010] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the As-contaminated paddy field soil regulation method according to any embodiment of the present invention.

[0011] The method and system for regulating As-contaminated paddy field soil in this application generate predicted distribution maps of inorganic As in rice and determine the boundary lines exceeding the standard based on a prediction model. By judging the spatial relationship between the front and rear boundary lines, if the rear boundary line is located inside the front boundary line, the annular area between the two lines is divided into multiple dynamic regulation sub-regions, and the priority order is determined according to the average predicted value and regulation difficulty of each sub-region. If not, the overlapping area is defined as a high-priority regulation area. Finally, according to the priority order or for high-priority areas, based on real-time soil key factor data and a preset regulation rule library, a precise or composite regulation scheme is automatically generated and executed. This achieves closed-loop dynamic precise regulation from risk prediction, precise regional identification to intelligent prescription generation, significantly improving the targeting and efficiency of safe remediation of arsenic-contaminated farmland. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart of a method for regulating As-contaminated paddy field soil according to an embodiment of the present invention; Figure 2 A structural block diagram of an As-contaminated paddy field soil regulation system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Please see Figure 1 The diagram shows a flowchart of a method for regulating As-contaminated paddy field soil according to this application.

[0016] like Figure 1 As shown, the specific steps of the As-contaminated paddy field soil remediation method include: Step S101: Obtain the first soil key factor data of the paddy field at the first moment before regulation, and generate the first predicted distribution map of inorganic As in rice grains based on the first soil key factor data.

[0017] In this step, the first soil key factor data of each monitoring point in the paddy field at the first moment before regulation are obtained. The first soil key factor data includes at least total soil As, pH, organic matter, available Si, available phosphorus and cation exchange capacity. The first soil key factor data of each monitoring point are input into the preset rice inorganic As prediction model to calculate the first rice inorganic As prediction value of each monitoring point. The rice inorganic As prediction model includes a prediction function based on multiple linear regression. Spatial interpolation calculations are performed on the predicted inorganic As values ​​of the first rice grain at each monitoring point to generate a continuous predicted distribution map of the first inorganic As values ​​of the first rice grain. The first boundary line exceeding the standard is determined according to the preset safety threshold. The first boundary line exceeding the standard is the contour line where the predicted inorganic As values ​​of the first rice grain are equal to the safety threshold.

[0018] In one specific embodiment, a systematic grid method was used to deploy monitoring points in the target paddy field. Typically, a 50m x 50m grid was used to ensure uniform coverage of the entire area to be evaluated. At each monitoring point, a soil sample from the 0-20cm topsoil layer was collected using a stainless steel soil auger. After thorough mixing, approximately 1kg was collected using the quartering method as the test sample. The collected soil samples underwent pretreatment, including natural air drying, grinding, and sieving (100 mesh). Six key factors were then determined according to national standard methods: total arsenic (using nitric acid-hydrofluoric acid digestion and atomic fluorescence spectrometry), pH (using the glass electrode method with a water-to-soil ratio of 2.5:1), organic matter content (using the potassium dichromate external heating method), available silicon (using acetate buffer extraction-silica molybdenum blue colorimetric method), available phosphorus (using sodium bicarbonate extraction-molybdenum antimony colorimetric method), and cation exchange capacity (CEC) (using the ammonium acetate exchange method). These results formed a "First Key Soil Factor Data" record for each monitoring point.

[0019] After obtaining the "first key soil factor data" from all monitoring points, these data were input one by one into a pre-set rice inorganic As prediction model. The core of this model is a multiple linear regression equation fitted with large sample data. For example, rice inorganic As (mg / kg) = 0.002755 × total soil As (mg / kg) + 0.007244 × pH value - 0.000182 × available Si (mg / kg) + 0.000165 × organic matter (g / kg) - 0.000182 × available phosphorus (mg / kg) - 0.002239 × cation exchange capacity (cmol+ / kg) + 0.141259 (This model is based on fitting of 2592 sets of soil-rice co-sampling data from ** province, R...). 2 =0.150, p<0.001). Substituting the measured values ​​of the six factors at each location into this equation, the predicted value of the first inorganic As in rice at that location can be calculated.

[0020] Subsequently, using the spatial analysis module of Geographic Information System (GIS) software (such as ArcGIS or QGIS), the predicted inorganic arsenic levels in rice and their geographic coordinates at all the aforementioned monitoring points were used as input data. Kriging interpolation was employed for spatial interpolation calculations. This method fully considers the spatial autocorrelation of the data, thereby generating a continuous distribution map (usually in raster data format) of the predicted inorganic arsenic levels in rice covering the entire paddy field area. In this distribution map, the inorganic arsenic limit for rice (e.g., 0.2 mg / kg) specified in the National Food Safety Standard for Limits of Contaminants in Food (GB 2762-2022) was used as the preset safety threshold. Contour lines where the predicted value is exactly equal to 0.2 mg / kg were extracted from the GIS; these contour lines were defined as the first exceedance boundary line. The area inside this boundary line represents a potentially high-risk area for predicted excessive inorganic arsenic content in rice, while the area outside represents the predicted acceptable area.

[0021] In summary, through systematic gridded sampling and standardized testing, multi-key factor data capable of comprehensively characterizing the bioavailability of arsenic in soil were obtained, overcoming the limitations of relying solely on a single total arsenic index for risk assessment. Furthermore, using a statistically significant predictive model built upon a large amount of real-world data, soil properties were quantitatively transformed into arsenic accumulation risk values ​​for rice, achieving precise prediction from "soil condition" to "agricultural product safety risk." Finally, advanced spatial interpolation techniques visualized the discrete point prediction results, spatially continuousizing them into a distribution map, and clearly delineated risk boundaries (the first exceedance boundary line) based on national food safety standards. This step provides a precise "risk map" for the entire control method, enabling subsequent identification, zoning, and prioritization of control areas to be based on scientific and objective spatial data. This fundamentally changes the extensive mode of "fuzzy judgment and experience-based decision-making" in traditional methods, laying the foundation for the entire precise control system.

[0022] Step S102: Obtain the second soil key factor data of the paddy field at the second time after regulation, and generate the second predicted distribution map of inorganic As in rice based on the second soil key factor data.

[0023] In this step, the gridded monitoring point layout of the paddy field at the second time after regulation and the second soil key factor data of each monitoring point are obtained. The second soil key factor data includes at least total soil As, pH, organic matter, available Si, available phosphorus and cation exchange capacity. The second soil key factor data of each monitoring point are input into the preset rice inorganic As prediction model to calculate the second rice inorganic As prediction value of each monitoring point. Spatial interpolation is performed on the predicted inorganic As values ​​of the second rice at each monitoring point to generate a continuous predicted distribution map of the second inorganic As values ​​of the second rice. The second exceedance boundary line is determined according to the preset safety threshold. The second exceedance boundary line is the contour line where the predicted inorganic As values ​​of the second rice are equal to the safety threshold.

[0024] In one specific embodiment, the target field is surveyed again at the second moment after a round of soil conditioning (such as applying a passivating agent, amendment, etc.) has been completed and has undergone sufficient action time (usually recommended to be a complete rice growth cycle or the stabilization period recommended in the conditioner instructions, such as 3-6 months).

[0025] The layout of monitoring points should, in principle, maintain spatial consistency with the gridded monitoring point layout in step S101 to ensure data comparability. Use GPS positioning equipment to accurately locate the coordinates of each sampling point at the first moment, and collect soil samples at the same locations. If the original locations cannot be accurately reproduced due to field operations or other reasons, alternative sampling can be conducted at locations near the original grid points with soil types and cultivation conditions that are basically consistent, and the updated coordinates should be recorded. Sample collection, processing, and pre-testing methods (total As, pH, organic matter, available Si, available phosphorus, and cation exchange capacity) must all be strictly consistent with step S101 to obtain comparable data on the second key soil factor. This data reflects the new state of soil environmental properties after the implementation of control measures.

[0026] Subsequently, the newly measured data of the six second key soil factors at each monitoring point were input again into the same preset rice inorganic arsenic prediction model as in step S101. The model was used to calculate the predicted value of the second inorganic arsenic in rice at each point under the current conditions. This predicted value characterizes the theoretical content of inorganic arsenic in rice under existing soil conditions and is a direct quantitative indicator for assessing whether the control measures have effectively reduced the risk of arsenic absorption in rice.

[0027] Next, using a geographic information system (GIS), spatial interpolation is performed on the predicted inorganic As (As) values ​​and coordinates of the rice at each location (it is recommended to use the same Kriging interpolation method and parameters as used to generate the first distribution map). This generates a new continuous spatial distribution map reflecting the current situation after regulation, namely the second predicted inorganic As distribution map of rice. Similarly, based on the same preset safety threshold (e.g., 0.2 mg / kg), contour lines where the predicted value equals this threshold are extracted from this second distribution map and defined as the second exceedance boundary line. This boundary line clearly delineates the area in the paddy field where the predicted arsenic content of rice may still exceed the standard after the previous round of regulation.

[0028] Step S103: Determine whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice, wherein the first excess boundary line is the boundary of the region in the first inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold, and the second excess boundary line is the boundary of the region in the second inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold.

[0029] After determining whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice, if the second excess boundary line is not located inside the first excess boundary line, the overlapping area between the second excess boundary line and the first excess boundary line is defined as a high-priority control area. The real-time soil key factor data in the high-priority control area are obtained, and the control priority order of each soil key factor is determined according to the preset correlation coefficient table. The preset correlation coefficient table defines the historical statistical correlation coefficient between each soil key factor and the inorganic As content of rice. The larger the absolute value of the historical statistical correlation coefficient, the higher the control priority of the factor corresponding to the historical statistical correlation coefficient. Based on the aforementioned regulation priority order and real-time soil key factor data, a composite regulation scheme for the high-priority regulation area is generated using a preset regulation rule library. The regulation rule library stores the conditioner types, basic dosages, and compatibility rules corresponding to different deviations of soil key factors. Generating the composite regulation scheme includes: according to the regulation priority order, sequentially matching the corresponding conditioner type and calculating the dosage from the regulation rule library for each deviation of soil key factor, and generating a complete composite regulation scheme based on the compatibility rules.

[0030] In practice, the first step is to perform spatial overlay analysis on the first predicted distribution map of inorganic As in rice generated in step S101 and the second predicted distribution map of inorganic As in rice generated in step S102 in a unified GIS platform.

[0031] Determining whether the second boundary line exceeding the standard is located inside the first boundary line exceeding the standard can be achieved by calculating the spatial topological relationship between the two boundary lines. Specifically, the first boundary line exceeding the standard is considered polygon A, and the second boundary line exceeding the standard is considered polygon B. Using the spatial relationship analysis function of GIS, it is determined whether polygon B is completely located inside polygon A, and whether the two overlap or intersect. If this condition is met, it is determined that "the second boundary line exceeding the standard is located inside the first boundary line exceeding the standard." If the two boundary lines intersect, have complex inclusion relationships (such as the second boundary line being outside the first boundary line in some areas), or are completely separated, it is determined that "it is not located inside."

[0032] When it is determined that "not located on the inner side", it means that the pollution range has not shrunk as expected after regulation, and there may even be new pollution diffusion points or "island" phenomenon caused by uneven regulation. At this time, the overlapping area between the first and second exceeding boundary lines is calculated by using the spatial overlay calculation function of GIS (such as the "intersection" operation). This overlapping area is the core area where the risk has not been eliminated or may even worsen after regulation, and is automatically defined as a high-priority regulation area.

[0033] Subsequently, enhanced monitoring of this high-priority control area was immediately initiated. Real-time soil data on six key factors were collected by densely distributing monitoring points or utilizing pre-defined grid monitoring sites within the area. Simultaneously, a pre-defined correlation coefficient table was invoked. This table, based on historical large-sample data, clearly defines the historical statistical correlation coefficients between each factor and the inorganic As content in rice. For example: cation exchange capacity (-0.159), available phosphorus (-0.116), available Si (-0.114), pH (0.061), and organic matter (-0.050). Based on this correlation coefficient table, the six key factors were automatically sorted in descending order of absolute correlation coefficient values, generating a control priority order (e.g., cation exchange capacity > available phosphorus > available Si > pH > organic matter). This order reflects the potential impact of controlling each soil factor on reducing arsenic content in rice.

[0034] Next, the regulation priority order and real-time soil key factor data in the high-priority regulation area will be input into a pre-set regulation rule base. This regulation rule base is a structured knowledge base, the core of which includes: Factor-conditioner mapping table: Defines the type of conditioner to be matched when a factor (such as cation exchange capacity) is below or above its preset standard range (e.g., bentonite or humic acid modifiers are recommended for low cation exchange capacity).

[0035] Dosage Calculation Model: For each conditioner, a built-in formula calculates the basic dosage based on the degree of deviation (the difference between the measured value and the standard value). For example, the recommended dosage of bentonite (kg / acre) = K × (standard cation exchange capacity value - measured cation exchange capacity value), where K is an empirical coefficient.

[0036] Compatibility rule library: Defines the rules to be followed when different conditioners are applied at the same time to avoid antagonistic effects or adverse reactions (for example, lime and certain phosphate conditioners need to be applied separately or the pH order needs to be adjusted).

[0037] The process of generating a composite control scheme is executed automatically by the system: According to the order of regulation priority, the factors with the highest priority (such as cation exchange capacity) are treated first. Determine whether the measured value of the factor deviates from its preset standard range and the direction of deviation (e.g., too low); Based on the direction and degree of deviation, the preferred type of conditioner is matched from the factor-conditioner mapping table, and the initial dosage is calculated using the dosage calculation model; Next, the next highest priority factors (such as available phosphorus) are processed. After processing all priority factors, a list containing various conditioners and their initial dosages is obtained.

[0038] Finally, the system calls upon the compatibility rule base to perform compatibility checks and optimizations on the conditioner combinations in the list. This includes adjusting the application order, correcting dosage adjustments needed due to chemical interactions, or replacing antagonistic conditioners. After optimization and integration, the final compound control scheme is output. This scheme clearly specifies the types of conditioners to be applied in high-priority control areas, their precise dosages, the order of application or mixing requirements, and recommended application methods (such as broadcasting, tillage depth, etc.).

[0039] Step S104: If the second exceeding boundary line is located inside the first exceeding boundary line, the area between the second exceeding boundary line and the first exceeding boundary line is divided into multiple dynamic control sub-regions. Each dynamic control sub-region is divided based on the vertical distance between a point on the first exceeding boundary line and a corresponding point on the second exceeding boundary line.

[0040] In this step, multiple dividing points are selected at preset intervals along the first boundary line that exceeds the standard. Draw a perpendicular line from each dividing point to the first boundary line of the excess, and extend each perpendicular line to intersect the second boundary line of the excess, thus obtaining the corresponding intersection point; The area enclosed by two adjacent vertical lines, the line segment between two adjacent dividing points on the first over-limit boundary line, and the line segment between two adjacent intersection points on the second over-limit boundary line is defined as a dynamic control sub-region. Repeat the operation for all division points to divide the entire annular region between the second and first out-of-limit boundary lines into multiple continuous dynamic control sub-regions.

[0041] In one specific embodiment, in areas where the control measures have achieved initial results (i.e., the pollution range has been reduced), a refined spatial unit division is carried out to lay the foundation for subsequent implementation of gradient and differentiated precise control measures.

[0042] First, the vector data of the first and second boundary lines (inner boundaries) that have been determined are imported. On the first boundary line, a series of equally spaced dividing points are automatically generated at a preset fixed distance (e.g., 50 meters). This preset interval can be adjusted according to the actual size of the field and the required management precision. The smaller the interval, the more sub-areas are divided, and the more refined the management.

[0043] Next, at each segmentation point, the system calculates the tangent direction of the first exceeding boundary line at that point and automatically generates a normal direction perpendicular to the tangent. A perpendicular line is then drawn inwards along this direction. Each perpendicular line extends inwards (i.e., towards the center of the contaminated area) until it intersects the second exceeding boundary line, and this intersection point is recorded. This forms a series of radial line segments pointing from the outer boundary to the inner boundary.

[0044] Subsequently, polygon construction is performed. Two adjacent perpendicular lines, the line segment between these two perpendicular lines on the first over-limit boundary line (i.e., the boundary part between two adjacent dividing points), and the line segment between these two perpendicular lines on the second over-limit boundary line (i.e., the boundary part between two adjacent intersection points) are connected together. These four line segments together form a closed polygonal region, which the system defines as a dynamically adjustable sub-region. This dynamically adjustable sub-region appears as an approximately trapezoidal or fan-shaped strip.

[0045] The system repeats the above operations (generating perpendicular lines, finding intersections, and constructing polygons) on all the dividing points on the first boundary line exceeding the standard. Finally, the entire annular region between the first boundary line exceeding the standard and the second boundary line exceeding the standard is systematically and seamlessly divided into a series of continuously arranged dynamic control sub-regions. Each sub-region carries spatial gradient information from the outer boundary (predicted pollution risk is higher) to the inner boundary (predicted pollution risk is close to meeting the standard).

[0046] In summary, the design of each dynamic regulation sub-region naturally includes a complete spatial spectrum from relatively high pollution risk (near the original outer boundary) to significantly reduced risk (near the new inner boundary). This division method ensures that when conducting soil diagnosis and scheme formulation within the sub-region, this spatial gradient characteristic can be fully considered and utilized, thereby formulating more targeted gradient regulation strategies, such as taking different intensities of conditioning measures for different locations within the same sub-region. These predefined dynamic control sub-regions become the objective objects for comprehensive evaluation and priority ranking in the subsequent step S105. The average predicted value and control difficulty coefficient of each sub-region can be calculated independently, so as to scientifically determine which sub-region is the most urgent and which sub-region has the best cost-effectiveness ratio. This allows limited human, material and financial resources to be accurately allocated to the most needed and effective spatial units according to a clear priority order, which greatly improves the efficiency and effectiveness of the overall control project.

[0047] Step S105: Based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, determine the priority control order of each dynamic control sub-region to obtain a list of dynamic control sub-regions sorted by priority.

[0048] In this step, the priority control order of each dynamic control sub-region is determined based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, resulting in a list of dynamic control sub-regions sorted by priority, including: Calculate the average predicted value of inorganic As in rice for each dynamic control sub-region, where the average predicted value of inorganic As in rice is the arithmetic mean of the predicted values ​​of inorganic As in rice at all monitoring points within the dynamic control sub-region. Calculate the control difficulty coefficient for each dynamic control sub-region. The control difficulty coefficient is determined based on the comprehensive deviation of key soil factors within the dynamic control sub-region from preset standard values. The calculation formula is as follows: , Where D represents the difficulty coefficient of regulation. To dynamically regulate the average value of the i-th key soil factor within the sub-region, To dynamically regulate the preset standard value of the i-th key soil factor within a sub-region, To dynamically adjust the weighting coefficient of the i-th key soil factor within a sub-region, The total number of key soil factors; The comprehensive score for each dynamically regulated sub-region is calculated using the following expression: S = α × P + β × D, In the formula, S is the comprehensive score, P is the average predicted value of inorganic As in rice in the dynamic regulation sub-region, D is the regulation difficulty coefficient of the dynamic regulation sub-region, α and β are the preset weight coefficients, and α+β=1. All dynamic control sub-regions are sorted according to their comprehensive scores from highest to lowest to obtain a list of dynamic control sub-regions sorted by priority.

[0049] Step S106: According to the priority-sorted list of dynamic control sub-regions, a precise control scheme is generated sequentially based on the real-time soil key factor data in each dynamic control sub-region using a preset control rule library, and the precise control scheme is executed.

[0050] In this step, real-time soil key factor data within the current dynamic regulation sub-region are obtained. The real-time soil key factor data includes at least total soil As, pH, organic matter, available Si, available phosphorus, and cation exchange capacity. The real-time soil key factor data and the preset correlation coefficients between each soil key factor and rice inorganic As are input into the preset regulation rule library. The regulation rule base matches the most suitable combination of conditioners and calculates the recommended dosage based on the deviation degree of each key soil factor in the real-time key soil factor data and the regulation influence weight represented by the absolute value of the corresponding correlation coefficient, generating a precise regulation plan that includes conditioner type, dosage, application time and application method.

[0051] In one specific embodiment, after obtaining the list of dynamically controlled sub-regions sorted by priority, the sequential execution process is initiated. The specific implementation method is as follows: First, for the current sub-region requiring dynamic control, sampling tasks are automatically planned and assigned based on its spatial boundary coordinates. Using mobile terminal devices (such as tablets with a dedicated app), field workers or drones / robots navigate to this sub-region and collect surface soil samples according to a pre-set sampling plan (e.g., a five-point method or a system grid method). The samples are then rapidly processed on-site or sent back to the laboratory, where real-time data on key soil factors are measured using standard methods. These factors include six indicators: total As, pH, organic matter, available Si, available phosphorus, and cation exchange capacity. This data represents the latest background condition of the sub-region before control measures are implemented and forms the basis for generating targeted solutions.

[0052] Subsequently, this batch of real-time soil key factor data, along with the historical statistical correlation coefficient table of each soil key factor and inorganic As in rice pre-stored in the database, is input into the preset regulation rule library. This correlation coefficient table is the same as that used in step S103, which clarifies the influence weight of each factor on arsenic accumulation in rice (e.g., the correlation coefficient of cation exchange capacity is -0.159, with the highest weight).

[0053] The decision engine of the regulatory rule base is then activated, executing the following intelligent matching and calculation process: Deviation Calculation and Diagnosis: The rule base contains preset standard ranges for various key soil factors (such as the suitable range of pH being 6.5-7.5, and the target value of cation exchange capacity being ≥20 cmol+ / kg). Real-time data is compared with the corresponding standard values ​​one by one to calculate the degree of deviation for each factor (for example, if the measured pH is 5.5, the deviation is 1.0 unit below the lower limit of the standard; if the measured cation exchange capacity is 15 cmol+ / kg, the deviation is 5 units below the standard value).

[0054] Weighting and Factor Ranking: The system comprehensively evaluates factors by combining their degree of deviation and the absolute value of their correlation coefficients (regulatory influence weights). Factors with large deviations and high influence weights are assigned a higher regulatory urgency score. For example, if a subregion simultaneously exhibits severely low cation exchange capacity (large deviation) and low pH (moderate deviation), the system will identify cation exchange capacity as the primary regulatory target for that subregion due to its higher influence weight.

[0055] Conditioner Matching and Dosage Calculation: Based on the above diagnostic results, the rule base calls its core "factor-measure-dosage" knowledge graph. This knowledge graph stores a large amount of agronomic knowledge in the form of "IF-THEN" rules, such as: "IF Cation Exchange Capacity < Target Value X AND Deviation ΔCEC, THEN Bentonite is recommended, with a base dosage of Y0 kg / acre, and the final dosage is adjusted according to ΔCEC and weighting coefficients as Y = Y0 + k1 * ΔCEC * |correlation coefficient|". The system matches the most suitable conditioner type (such as lime for pH adjustment, silicon-calcium fertilizer for Si supplementation, humic acid for organic matter increase, and CEC) based on the specific circumstances of each factor to be adjusted, and calculates the recommended dosage through a built-in quantitative model. This model not only considers the deviation but also incorporates correction parameters such as soil texture and target crop.

[0056] Solution Integration and Optimization: The system integrates the control measures (types and dosages of conditioners) for each factor. During this process, the compatibility rule module in the rule base checks the compatibility between different conditioners to prevent chemical reactions that reduce effectiveness or cause harm, and optimizes the application sequence. Finally, it packages and generates a precise control plan for the current sub-region. This plan is output in the form of clear operation instructions, explicitly listing the types of conditioners required, their precise dosages, recommended application times (e.g., basal application or top dressing), and specific application methods (e.g., spreading followed by tilling, diluting with water and spraying, etc.).

[0057] In summary, the method presented in this application constructs and applies a rice inorganic arsenic prediction model based on multiple key factors, accurately mapping soil properties to agricultural product safety risks, overcoming the blindness of traditional methods that rely solely on total soil arsenic and pH values ​​for judgment. By comparing risk distribution maps before and after regulation, it intelligently identifies dynamic changes in pollution range and, based on spatial geometric rules, finely divides pollution shrinkage areas into multiple dynamic regulation sub-units, or precisely locates complex problem areas requiring key attention, achieving precise focusing of regulation targets from "surface" to "point." Furthermore, by integrating the pollution degree, regulation difficulty, and historical influence weights of various soil factors in each sub-region, a scientific and quantitative regulation priority ranking and decision-making mechanism is established, ensuring optimal allocation of limited resources. Finally, with the help of an intelligent regulation rule library integrating agronomic knowledge and compatibility rules, it can automatically generate quantitative, personalized, and highly operable precise regulation or composite regulation schemes for each smallest management unit, thus forming a complete dynamic closed-loop precision governance system of "monitoring-prediction-zoning-decision-execution." This system significantly improves the targeting, effectiveness, and resource utilization efficiency of the safe utilization of arsenic-contaminated paddy fields, realizing a fundamental shift from experience-based extensive management to data-driven intelligent decision-making, and is of great value in ensuring the quality and safety of agricultural products and the sustainable use of farmland.

[0058] Please see Figure 2 The diagram shows a structural block diagram of an As-contaminated paddy field soil regulation system according to this application.

[0059] like Figure 2 As shown, the As-contaminated paddy field soil regulation system 200 includes a first acquisition module 210, a second acquisition module 220, a judgment module 230, a division module 240, a determination module 250, and a generation module 260.

[0060] The first acquisition module 210 is configured to acquire the first soil key factor data of the paddy field at the first moment before regulation, and generate a first predicted distribution map of inorganic As in rice based on the first soil key factor data; the second acquisition module 220 is configured to acquire the second soil key factor data of the paddy field at the second moment after regulation, and generate a second predicted distribution map of inorganic As in rice based on the second soil key factor data; the judgment module 230 is configured to judge whether the second exceedance boundary line in the second predicted distribution map of inorganic As in rice is located inside the first exceedance boundary line in the first predicted distribution map of inorganic As in rice, wherein the first exceedance boundary line is the boundary of the area in the first predicted distribution map of inorganic As in rice where the predicted value of inorganic As in rice exceeds the safety threshold, and the second exceedance boundary line is the area in the second predicted distribution map of inorganic As in rice where the predicted value of inorganic As in rice exceeds the safety threshold. Boundary; Division module 240, configured to divide the area between the second and first excess boundary lines into multiple dynamic control sub-regions if the second excess boundary line is located inside the first excess boundary line, wherein each dynamic control sub-region is divided based on the vertical distance between a point on the first excess boundary line and a corresponding point on the second excess boundary line; Determination module 250, configured to determine the priority control order of each dynamic control sub-region based on the average predicted value of rice inorganic As and the control difficulty coefficient of the dynamic control sub-regions, thereby obtaining a list of dynamic control sub-regions sorted by priority; Generation module 260, configured to generate a precise control scheme based on the real-time soil key factor data within each dynamic control sub-region according to the priority-sorted list of dynamic control sub-regions, using a preset control rule library, and execute the precise control scheme.

[0061] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0062] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the As-contaminated paddy field soil regulation method in any of the above method embodiments. In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows: Obtain the first soil key factor data of paddy field at the first moment before regulation, and generate the first predicted distribution map of inorganic As in paddy grains based on the first soil key factor data. Obtain the second soil key factor data of paddy field at the second time after regulation, and generate the second predicted distribution map of inorganic As in rice grains based on the second soil key factor data; Determine whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice. The first excess boundary line is the boundary of the region in the first inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold, and the second excess boundary line is the boundary of the region in the second inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold. If the second exceeding boundary line is located inside the first exceeding boundary line, the area between the second exceeding boundary line and the first exceeding boundary line is divided into multiple dynamic control sub-regions, wherein each dynamic control sub-region is divided based on the vertical distance between a point on the first exceeding boundary line and a corresponding point on the second exceeding boundary line. Based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, the priority control order of each dynamic control sub-region is determined, and a list of dynamic control sub-regions sorted by priority is obtained. According to the priority-sorted list of dynamic control sub-regions, a precise control scheme is generated sequentially based on the real-time soil key factor data in each dynamic control sub-region using a preset control rule library, and then the precise control scheme is executed.

[0063] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of the As-contaminated paddy field soil conditioning system, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely configured relative to a processor, which can be connected to the As-contaminated paddy field soil conditioning system via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0064] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby implementing the As-contaminated paddy field soil regulation method described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the As-contaminated paddy field soil regulation system. The output device 340 may include a display screen or other display device.

[0065] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0066] In one implementation, the above-described electronic device is applied in an As-contaminated paddy field soil conditioning system for a client application, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Obtain the first soil key factor data of paddy field at the first moment before regulation, and generate the first predicted distribution map of inorganic As in rice grains based on the first soil key factor data. Obtain the second soil key factor data of paddy field at the second time after regulation, and generate the second predicted distribution map of inorganic As in rice grains based on the second soil key factor data; Determine whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice. The first excess boundary line is the boundary of the region in the first inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold, and the second excess boundary line is the boundary of the region in the second inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold. If the second exceeding boundary line is located inside the first exceeding boundary line, the area between the second exceeding boundary line and the first exceeding boundary line is divided into multiple dynamic control sub-regions, wherein each dynamic control sub-region is divided based on the vertical distance between a point on the first exceeding boundary line and a corresponding point on the second exceeding boundary line. Based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, the priority control order of each dynamic control sub-region is determined, and a list of dynamic control sub-regions sorted by priority is obtained. According to the priority-sorted list of dynamic control sub-regions, a precise control scheme is generated sequentially based on the real-time soil key factor data in each dynamic control sub-region using a preset control rule library, and then the precise control scheme is executed.

[0067] 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.

[0068] 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 regulating As-contaminated paddy field soil, characterized in that, include: Obtain the first soil key factor data of paddy field at the first moment before regulation, and generate the first predicted distribution map of inorganic As in paddy grains based on the first soil key factor data. Obtain the second soil key factor data of paddy field at the second time after regulation, and generate the second predicted distribution map of inorganic As in rice grains based on the second soil key factor data; Determine whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice. The first excess boundary line is the boundary of the region in the first inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold, and the second excess boundary line is the boundary of the region in the second inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold. If the second exceeding boundary line is located inside the first exceeding boundary line, the area between the second exceeding boundary line and the first exceeding boundary line is divided into multiple dynamic control sub-regions, wherein each dynamic control sub-region is divided based on the vertical distance between a point on the first exceeding boundary line and a corresponding point on the second exceeding boundary line. Based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, the priority control order of each dynamic control sub-region is determined, and a list of dynamic control sub-regions sorted by priority is obtained. According to the priority-sorted list of dynamic control sub-regions, a precise control scheme is generated sequentially based on the real-time soil key factor data in each dynamic control sub-region using a preset control rule library, and then the precise control scheme is executed.

2. The method for regulating As-contaminated paddy field soil according to claim 1, characterized in that, The step of generating the first predicted distribution map of inorganic As in rice based on the first soil key factor data includes: The first soil key factor data of each monitoring point in the paddy field at the first moment before regulation are obtained, wherein the first soil key factor data includes at least total soil As, pH, organic matter, available Si, available phosphorus and cation exchange capacity. The first soil key factor data of each monitoring point are input into the preset rice inorganic As prediction model to calculate the first rice inorganic As prediction value of each monitoring point. The rice inorganic As prediction model includes a prediction function based on multiple linear regression. Spatial interpolation calculations are performed on the predicted inorganic As values ​​of the first rice grain at each monitoring point to generate a continuous predicted distribution map of the first inorganic As values ​​of the first rice grain. The first boundary line exceeding the standard is determined according to the preset safety threshold. The first boundary line exceeding the standard is the contour line where the predicted inorganic As values ​​of the first rice grain are equal to the safety threshold.

3. The method for regulating As-contaminated paddy field soil according to claim 1, characterized in that, The step of generating a second predicted distribution map of inorganic As in rice based on the second soil key factor data includes: The gridded monitoring point layout and the second soil key factor data of each monitoring point were obtained in the paddy field at the second time after regulation. The second soil key factor data included at least total soil As, pH, organic matter, available Si, available phosphorus and cation exchange capacity. The second soil key factor data of each monitoring point are input into the preset rice inorganic As prediction model to calculate the second rice inorganic As prediction value of each monitoring point. Spatial interpolation is performed on the predicted inorganic As values ​​of the second rice at each monitoring point to generate a continuous predicted distribution map of the second inorganic As values ​​of the second rice. The second exceedance boundary line is determined according to the preset safety threshold. The second exceedance boundary line is the contour line where the predicted inorganic As values ​​of the second rice are equal to the safety threshold.

4. The method for regulating As-contaminated paddy field soil according to claim 1, characterized in that, After determining whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice, the method further includes: If the second exceeding boundary line is not located inside the first exceeding boundary line, then the overlapping area between the second exceeding boundary line and the first exceeding boundary line is defined as a high-priority control area. The real-time soil key factor data in the high-priority control area are obtained, and the control priority order of each soil key factor is determined according to the preset correlation coefficient table. The preset correlation coefficient table defines the historical statistical correlation coefficient between each soil key factor and the inorganic As content of rice. The larger the absolute value of the historical statistical correlation coefficient, the higher the control priority of the factor corresponding to the historical statistical correlation coefficient. Based on the aforementioned regulation priority order and real-time soil key factor data, a composite regulation scheme for the high-priority regulation area is generated using a preset regulation rule library. The regulation rule library stores the conditioner types, basic dosages, and compatibility rules corresponding to different deviations of soil key factors. Generating the composite regulation scheme includes: according to the regulation priority order, sequentially matching the corresponding conditioner type and calculating the dosage from the regulation rule library for each deviation of soil key factor, and generating a complete composite regulation scheme based on the compatibility rules.

5. The method for regulating As-contaminated paddy field soil according to claim 1, characterized in that, The step of dividing the area between the second exceeding boundary line and the first exceeding boundary line into multiple dynamic control sub-regions includes: Multiple dividing points are selected at preset intervals along the first boundary line that exceeds the standard. Draw a perpendicular line from each dividing point to the first boundary line of the excess, and extend each perpendicular line to intersect the second boundary line of the excess, thus obtaining the corresponding intersection point; The area enclosed by two adjacent vertical lines, the line segment between two adjacent dividing points on the first over-limit boundary line, and the line segment between two adjacent intersection points on the second over-limit boundary line is defined as a dynamic control sub-region. Repeat the operation for all division points to divide the entire annular region between the second and first out-of-limit boundary lines into multiple continuous dynamic control sub-regions.

6. The method for regulating As-contaminated paddy field soil according to claim 1, characterized in that, The priority control order of each dynamic control sub-region is determined based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, resulting in a list of dynamic control sub-regions sorted by priority, including: Calculate the average predicted value of inorganic As in rice for each dynamic control sub-region, where the average predicted value of inorganic As in rice is the arithmetic mean of the predicted values ​​of inorganic As in rice at all monitoring points within the dynamic control sub-region. Calculate the control difficulty coefficient for each dynamic control sub-region. The control difficulty coefficient is determined based on the comprehensive deviation of key soil factors within the dynamic control sub-region from preset standard values. The calculation formula is as follows: ， Where D represents the difficulty coefficient of regulation. To dynamically regulate the average value of the i-th key soil factor within the sub-region, To dynamically regulate the preset standard value of the i-th key soil factor within a sub-region, To dynamically adjust the weighting coefficient of the i-th key soil factor within a sub-region, The total number of key soil factors; The comprehensive score for each dynamically regulated sub-region is calculated using the following expression: S = α × P + β × D, In the formula, S is the comprehensive score, P is the average predicted value of inorganic As in rice in the dynamic regulation sub-region, D is the regulation difficulty coefficient of the dynamic regulation sub-region, α and β are the preset weight coefficients, and α+β=1. All dynamic control sub-regions are sorted according to their comprehensive scores from highest to lowest to obtain a list of dynamic control sub-regions sorted by priority.

7. The method for regulating As-contaminated paddy field soil according to claim 1, characterized in that, The process of generating a precise control scheme based on real-time soil key factor data within each dynamic control sub-region, using a pre-set control rule base, and executing the precise control scheme includes: Acquire real-time soil key factor data within the current dynamic regulation sub-region, wherein the real-time soil key factor data includes at least total soil As, pH, organic matter, available Si, available phosphorus, and cation exchange capacity; The real-time soil key factor data and the preset correlation coefficients between each soil key factor and rice inorganic As are input into the preset regulation rule library. The regulation rule base matches the most suitable combination of conditioners and calculates the recommended dosage based on the deviation degree of each key soil factor in the real-time key soil factor data and the regulation influence weight represented by the absolute value of the corresponding correlation coefficient, generating a precise regulation plan that includes conditioner type, dosage, application time and application method.

8. A soil conditioning system for As-contaminated paddy fields, characterized in that, include: The first acquisition module is configured to acquire the first soil key factor data of the paddy field at the first moment before regulation, and generate a first predicted distribution map of inorganic As in rice grains based on the first soil key factor data. The second acquisition module is configured to acquire the second soil key factor data of the paddy field at the second time after regulation, and generate a second predicted distribution map of inorganic As in rice based on the second soil key factor data. The judgment module is configured to determine whether the second excess boundary line in the second inorganic As prediction distribution map of rice is located inside the first excess boundary line in the first inorganic As prediction distribution map of rice, wherein the first excess boundary line is the boundary of the region in the first inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold, and the second excess boundary line is the boundary of the region in the second inorganic As prediction distribution map of rice where the predicted value of inorganic As in rice exceeds the safety threshold. The partitioning module is configured to divide the area between the second excess boundary line and the first excess boundary line into multiple dynamic control sub-regions if the second excess boundary line is located inside the first excess boundary line. Each dynamic control sub-region is partitioned based on the vertical distance between a point on the first excess boundary line and a corresponding point on the second excess boundary line. The determination module is configured to determine the priority control order of each dynamic control sub-region based on the average predicted value of inorganic As in rice and the control difficulty coefficient of the dynamic control sub-region, thereby obtaining a list of dynamic control sub-regions sorted by priority. The generation module is configured to generate a list of dynamic control sub-regions sorted according to the priority, and sequentially generate a precise control scheme based on the real-time soil key factor data in each dynamic control sub-region using a preset control rule library, and execute the precise control scheme.

9. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method according to any one of claims 1 to 7.

Images