Monitoring point layout optimization method and system based on regional scale nitrogen leaching

Abstract

The invention discloses a monitoring point layout optimization method and system based on regional scale nitrogen leaching, and relates to the field of agricultural environment protection, and the method comprises the steps: obtaining a regional area and regional data; based on the regional data, respectively drawing a slope grade map, an underground water level grade map and a nitrogen accumulation map of the region; performing pixel alignment superposition and combination calculation on the gradient grade map, the underground water level grade map and the nitrogen accumulation map of the region to generate a plurality of basic units; performing initial layout on the monitoring points in each basic unit according to the area of the region, the barrier layer and a preset distance between the monitoring points under a constraint condition; constructing a target function of the monitoring points based on an average distance minimization criterion; and based on the objective function, optimizing the monitoring points in the initial layout by adopting a space simulated annealing algorithm to obtain an optimized layout of the monitoring points. According to the method, the monitoring precision of regional scale nitrogen leaching can be improved, and the monitoring well point location layout efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural environmental protection, and in particular to a monitoring point layout optimization method and system based on regional scale nitrogen leaching. BACKGROUND

[0002] The research scale of farmland nitrogen leaching monitoring mainly focuses on field scale and regional scale. At field scale, domestic and foreign scholars have carried out a large number of researches, and have used various technical means such as undisturbed soil column method, ceramic head lysimeter method, leaching disc (barrel) method and real-time monitoring method of nitrogen sensor to observe and analyze the nitrogen leaching process in detail. Field scale belongs to small scale, and it is relatively simple to analyze at small scale.

[0003] However, the monitoring research on regional scale nitrogen leaching is relatively scarce. This is mainly because regional scale monitoring faces many challenges: the monitoring range is wide, the terrain is significantly undulating, the soil types and land use methods are highly heterogeneous in space; at the same time, the underground water flow is complexly affected by geological structure, underground water level fluctuation and surface runoff, etc., making it difficult to accurately track and effectively monitor the nitrogen migration path. In addition, the spatial layout of monitoring points often has the problems of incomplete coverage and insufficient data representativeness, further exacerbating the difficulty of regional scale nitrogen leaching monitoring. SUMMARY

[0004] The purpose of the present application is to provide a monitoring point layout optimization method and system based on regional scale nitrogen leaching, which can improve the monitoring accuracy of regional scale nitrogen leaching and the efficiency of monitoring well point layout.

[0005] To achieve the above purpose, the present application provides the following solutions: In a first aspect, the present application provides a monitoring point layout optimization method based on regional scale nitrogen leaching, comprising: acquiring a region area and region data; based on the region data, drawing a slope grade map, a groundwater level grade map and a nitrogen accumulation map of the region respectively; performing image element alignment and combination calculation on the slope grade map, the groundwater level grade map and the nitrogen accumulation map of the region to generate a plurality of basic units; under constraint conditions, according to the region area, an obstacle layer and a preset monitoring point spacing, performing initial layout of monitoring points in each basic unit; the constraint condition is greater than a nitrogen accumulation threshold and less than a groundwater depth threshold; the obstacle layer is a layer on which monitoring points cannot be set; based on the minimum average distance criterion, constructing a target function of the monitoring points; based on the target function, using a spatial simulated annealing algorithm to optimize the monitoring points in the initial layout in each basic unit to obtain an optimized layout of the monitoring points.

[0006] In a second aspect, the application provides a monitoring well point layout optimization system based on regional scale nitrogen leaching, comprising: an acquisition module configured to acquire a region area and region data; a drawing module configured to draw a slope level map, a groundwater level map and a nitrogen accumulation map of the region based on the region data; a basic unit generation module configured to perform pixel-to-pixel overlay and combination calculation on the slope level map, the groundwater level map and the nitrogen accumulation map of the region to generate a plurality of basic units; a monitoring point number generation module configured to, under a constraint condition, perform initial layout of monitoring points in each basic unit according to the region area, an obstacle layer and a preset monitoring point spacing; the constraint condition is greater than a nitrogen accumulation threshold and less than a groundwater depth threshold; the obstacle layer is a layer in which monitoring points cannot be arranged; a construction module configured to construct a target function of the monitoring points based on an average distance minimization criterion; and an optimization module configured to optimize the monitoring points in the initial layout in each basic unit based on the target function using a spatial simulated annealing algorithm to obtain an optimized layout of the monitoring points.

[0007] According to the specific embodiments provided in the application, the application has the following technical effects.

[0008] (1) High monitoring well point layout efficiency: the application accurately identifies and divides the basic units of the region by combining pixel-to-pixel overlay and combination calculation, the target function of the monitoring points and the spatial simulated annealing algorithm. The simulated annealing algorithm can efficiently search for a global optimal solution, avoiding the blindness and redundancy of the distribution of monitoring points in traditional methods, and significantly improving the efficiency of monitoring well layout.

[0009] (2) High monitoring accuracy: in the application, the constraint condition that the nitrogen accumulation threshold is greater than the groundwater depth threshold ensures that the monitoring points occupy a sufficient proportion in the key risk areas with high nitrogen accumulation and shallow groundwater depth. This targeted layout method avoids the data deviation problem caused by unreasonable monitoring point proportion in the past, effectively improving the accuracy and representativeness of the monitoring data.

[0010] (3) Strong spatial representativeness: by performing pixel-to-pixel overlay and combination calculation on the slope level map, the nitrogen accumulation map and the groundwater level map of the region, the spatial representativeness of the monitoring points in the generated basic units is effectively improved, ensuring that the obtained data can more accurately reflect the monitoring accuracy of nitrogen leaching at the regional scale. BRIEF DESCRIPTION OF DRAWINGS

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating a method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching in one embodiment of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] In one exemplary embodiment, such as Figure 1 As shown, a method for optimizing the layout of monitoring points for nitrogen leaching at the regional scale is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is described using a server as an example, and includes the following steps S1 to S6.

[0016] Step S1: Obtain the area and data of the region.

[0017] Further, obtaining the area of ​​the region specifically includes: acquiring region image data; performing spatial registration on the region image data to generate a polygonal shape with closed boundaries; and calculating the area of ​​the region using planar geometry methods based on the polygonal shape with closed boundaries.

[0018] Furthermore, the formula for calculating the area of ​​a region is as follows.

[0019] .

[0020] in, The area is the region. The number of vertices of the polygon; For the first The coordinates of the vertices of a polygonal shape along the X-axis; For the first The coordinates of the vertices of a polygonal shape along the Y-axis; For the first The coordinates of the vertices of a polygonal shape along the X-axis; For the first The coordinates of the vertices of a polygonal shape along the Y-axis.

[0021] Specifically, obtaining regional area and data is the first step in optimizing the deployment of monitoring points for nitrogen leaching groundwater in farmland. The aim is to provide data support and decision-making basis for subsequent monitoring point deployment through a comprehensive understanding of the target area. Obtaining the regional area involves: understanding the terrain undulations, slopes, and geomorphic units (such as plains, hills, and basins) by acquiring regional image data. The acquired regional image data consists of remote sensing images or UAV aerial images of the target area. Spatial registration of the images is performed using known ground control points to ensure consistency between the geographical location and the actual space. Subsequently, the boundary of the study area is digitally vectorized to generate a closed polygonal shape. Then, based on the constructed closed polygonal boundary, the regional area is calculated using planar geometry methods. Specifically, the planar coordinates of all vertices of the polygonal shape are extracted, and the area is calculated using the formula for calculating the regional area.

[0022] Step S2: Based on the regional data, draw the regional slope level map, groundwater level map and nitrogen accumulation map respectively.

[0023] Furthermore, the regional data includes: digital elevation model data, groundwater depth data of known observation points within the region, and nitrogen content of soil layers at preset depths of known observation points within the region. Step S2 specifically includes steps S21-S23.

[0024] Step S21: Based on the digital elevation model data, calculate the slope value of each grid cell within the area.

[0025] Specifically, the slope map is constructed based on Digital Elevation Model (DEM) data. It calculates the surface tilt (slope value) of each raster cell by analyzing the elevation differences between each raster cell and its neighboring cells. The specific method involves selecting eight neighboring cells around each raster cell as the center, estimating the horizontal and vertical elevation gradients using third-order finite difference or triangulation methods, and then calculating the slope value of that cell. Further, the formula for calculating the slope value of each raster cell within the region is as follows.

[0026] .

[0027] in, This represents the slope value. For digital elevation model data in rate of elevation change in a direction; rate of elevation change in a direction for digital elevation model data rate of elevation change in a direction.

[0028] Step S22: classifying the slope values by using the natural break classification method, dividing the slope levels, and drawing a slope level map according to the slope levels; the slope level map includes a flat slope map, an inclined slope map, and a steep slope map.

[0029] Specifically, after the slope values are calculated, all the slope values are grouped by using the natural break classification method. This method can maximize the difference between groups and reduce the dispersion within groups, achieving the optimal grading effect. Finally, the slope is divided into three levels, i.e., a flat slope map (small slope, gentle terrain), an inclined slope map (moderate slope, potential increase in leaching and runoff risk), and a steep slope map (large slope, which may cause rapid runoff and soil leaching), wherein the angle range of the flat slope area is 0-5°, the angle range of the inclined slope area is 5-15°, and the angle range of the steep slope area is > 15°.

[0030] Step S23: based on the groundwater depth data of the known observation points in the region and the nitrogen content of different soil layers at a preset depth of the known observation points in the region, the Kriging interpolation method is used to obtain a groundwater level map and a nitrogen accumulation map; the groundwater level map includes a shallow buried area map, a medium buried area map, and a deep buried area map; and the nitrogen accumulation map includes a low content area map, a moderate content area map, and a high content area map.

[0031] Specifically, the groundwater depth data of the known observation points in the region is obtained from the water conservancy department, the environmental protection department, the geological department, and the like, and the long-term observation data of the groundwater monitoring wells in the research region are obtained, and the hydrogeological report, the environmental impact assessment report, and the like are consulted to determine the groundwater type (phreatic water, confined water), the aquifer thickness, the buried depth, and the water level dynamic change.

[0032] Specifically, the nitrogen content of different soil layers at a preset depth of the known observation points in the region is preferentially obtained from the national or local soil database (such as the China Soil Database, the Second National Soil Survey Data, and the like) to obtain the soil type and nitrogen content data of the region. If the public data is insufficient, sampling points can be uniformly arranged in the region, and stratified sampling can be performed, and the nitrogen content of each soil layer in the range of 0-2m is recorded for subsequent nitrogen accumulation analysis.

[0033] Further, step S23 specifically includes steps S231-S239.

[0034] Step S231: based on the groundwater depth data of the known observation points in the region, a groundwater variogram model is established.

[0035] Specifically, based on the groundwater depth data of known observation points in the region, an experimental variogram is obtained; the experimental variogram is then fitted to obtain a groundwater variogram model.

[0036] The experimental variability function is as follows.

[0037] .

[0038] .

[0039] in, Let be the experimental variability function, representing the distance between two observation points. The expected value of the difference between the variable values ​​reflects how spatial correlation changes with distance; The distance is The number of all observation point pairs, where two observation points constitute one observation point pair; This represents the total number of known observation points within the region. For the first Groundwater depth data at known observation points; For the first Groundwater depth data at known observation points; The distance between observation point pairs; For the first The x-coordinates of the known observation points; No. The ordinates of the known observation points; For the first The x-coordinates of the known observation points; No. The ordinates of the known observation points.

[0040] A set of data points obtained from the experimental variogram. To determine a unique groundwater variability model (mainly the spherical model, Gaussian model or exponential model).

[0041] Step S232: Based on the groundwater variogram model, interpolate the groundwater depth data of unknown observation points in the region to obtain the groundwater depth data of unknown observation points in the region.

[0042] Specifically, based on the groundwater variogram model, a set of Kriging equations is constructed to determine the weighting coefficients for known points. Then, combined with the known burial depth values, a weighted calculation is performed to estimate the groundwater burial depth data for unknown observation points.

[0043] Among them, the interpolation of the first Unknown observation points The groundwater depth value needs to be calculated using a variogram model to determine the relationships between observation points and between known observation points and the first observation point. unknown observation points The spatial structure of unknown observation points is constructed as follows .

[0044] .

[0045] .

[0046] The groundwater depth data of the unknown observation points are calculated by using the linear combination formula for interpolation. The groundwater depth data of the unknown observation points are calculated by using the linear combination formula for interpolation.

[0047] .

[0048] wherein, The greater the density of interpolation, the greater the value of n; Each unknown observation point requires a set of weights for Kriging interpolation, indicating the Kriging weight of the i-th known observation point corresponding to the j-th unknown observation point, representing the influence coefficient of each known observation point on the result; is the experimental variogram value between the i-th observation point and the j-th unknown observation point; is the Lagrange multiplier corresponding to the j-th unknown point , used to ensure that the sum of the weights is 1; is the groundwater depth data of the j-th unknown observation point ; and is the Kriging weight of the i-th known observation point corresponding to the j-th unknown observation point.

[0049] Step S233: Based on the groundwater depth data of the known observation points in the region and the groundwater depth data of the unknown observation points in the region, a groundwater depth raster map is generated.

[0050] Specifically, the grid size (such as 10m x 10m) is set according to the research accuracy requirement, and the region is divided into a two-dimensional regular grid according to the grid size. According to the groundwater depth data of the known observation points in the region and the groundwater depth data of the unknown observation points in the region, the groundwater depth data of each grid center point in the two-dimensional regular grid is determined by interpolation, thereby generating a groundwater depth raster map.

[0051] ​​​​​​​​​​Step S234: Divide the groundwater depth grid map according to the preset range of groundwater depth data and draw a groundwater level map.

[0052] Specifically, the groundwater depth data from known observation points within the region are first compiled into a data table, and its completeness and logical consistency are checked. Outliers that significantly deviate from the regional trend are removed to ensure data reliability. Kriging interpolation is then used to spatially fit the groundwater level data. This includes: analyzing the differences in water levels between known observation points based on their depth data, establishing a suitable groundwater variability model (such as a spherical model, Gaussian model, or exponential model), and fitting the spatial variation structure of the data; based on the groundwater variability model, interpolation calculations are performed on the groundwater depth data from unknown observation points throughout the region to generate a continuously distributed groundwater depth raster map. Based on the preset range of groundwater depth data, the groundwater depth raster map is divided into three levels: shallow buried area (groundwater level is close to the surface, with a high risk of pollution), medium buried area (groundwater is relatively deep, with a medium pollution potential), and deep buried area (groundwater is at a greater depth, with a weaker nitrogen migration capacity). The preset range for the shallow buried area is 0–2m, the preset range for the medium buried area is 2–5m, and the preset range for the deep buried area is >5m.

[0053] Step S235: Based on the nitrogen content of different soil layers at preset depths of known observation points within the region, calculate the cumulative nitrogen content at preset depths of known observation points within the region.

[0054] Specifically, based on the nitrogen content (unit: g / kg) and soil bulk density (unit: g / cm³) of different soil layers at known observation points in each region... 3 ) and soil layer thickness (unit: cm), calculate the nitrogen accumulation (kg / ha) within the preset depth range of 0–2m, the specific calculation formula is as follows.

[0055] ; in, This refers to the cumulative amount of nitrogen. For the first Soil nitrogen content in each soil layer; For the first The soil bulk density of each soil layer; For the first The thickness of each soil layer; 10 is the unit conversion factor.

[0056] Step S236: Based on the preset depth nitrogen accumulation of known observation points in the region, establish a nitrogen accumulation variability function model.

[0057] Step S237: Based on the nitrogen accumulation amount variogram model, the nitrogen accumulation amount of the preset depth of the unknown observation points in the region is interpolated and calculated to obtain the nitrogen accumulation amount of the preset depth of the unknown observation points in the region.

[0058] Step S238: Based on the nitrogen accumulation amount of the preset depth in the region and the nitrogen accumulation amount of the preset depth of the unknown observation points in the region, a nitrogen accumulation grid map is generated.

[0059] Specifically, steps S236-S238, the established experimental variogram refers to steps S231-S233.

[0060] Step S239: According to the preset range of nitrogen accumulation amount, the nitrogen accumulation grid map is divided, and a nitrogen accumulation map is drawn.

[0061] Specifically, the calculated nitrogen accumulation amount of the preset depth of the known observation points in the region is taken as input data, and the Kriging interpolation method is used for spatial fitting. The specific operation steps are: according to the nitrogen accumulation amount of the preset depth of the known observation points in the region, the spatial variability of the nitrogen accumulation amount between each known observation point is analyzed, a suitable nitrogen content variogram model (such as spherical model, exponential model or Gaussian model) is selected and fitted, based on the nitrogen content variogram model, the nitrogen accumulation amount of the non-sampling position in the study area is interpolated and calculated, the prediction and estimation are realized, and a continuous distribution of nitrogen accumulation grid map layer is generated. According to the preset range of nitrogen accumulation amount, the nitrogen accumulation grid map is divided, and the results are divided into three levels of low content area, medium content area and high content area, wherein the preset range of low content area is <400 kg / ha, the preset range of medium content area is 400-1000 kg / ha, and the preset range of high content area is >1000 kg / ha.

[0062] Step S3: The pixel alignment superposition and combination calculation of the slope grade map, the groundwater level grade map and the nitrogen accumulation map of the region are performed to generate a plurality of basic units.

[0063] Specifically, the slope grade map, the groundwater depth grade map and the nitrogen accumulation grade map of the region are analyzed by pixel alignment superposition on the grid basis. By combining the classification coding of each pixel in the three layers, a unique identifier (such as slope grade Figure 1 - groundwater depth grade map 2 - nitrogen accumulation grade map 3 corresponding number 123) is formed, so as to divide the region into 3x3x3=27 basic units, each unit represents a specific natural geographical and nitrogen environmental combination type, which serves as the basis for the partition of the subsequent monitoring point layout.

[0064] Step S4: Under constraints, based on the area, obstacle layer, and preset monitoring point spacing, initially lay out the monitoring points in each basic unit; the constraints are greater than the nitrogen accumulation threshold and less than the groundwater depth threshold; the obstacle layer is a layer where monitoring points cannot be set.

[0065] Specifically, based on the area and in accordance with the "Technical Standards for Geological Survey of China Geological Survey" (DD06-2014), while also referencing similar studies at home and abroad or empirical data on the spatial influence radius of pollution sources, it is recommended that the horizontal length and vertical length of the area be 1 / 10 of the preset monitoring point spacing. Within the boundary of the study area, a regular rectangular grid is constructed at the set spacing, with the grid center point serving as the initial candidate set of monitoring points. Simultaneously, obstacle layers such as water bodies, roads, and buildings (e.g., vector boundaries) are introduced, and points intersecting with these layers are removed, retaining only points located within the effective area. The number of points falling within this area is the number of monitoring points. Based on the area weight of the basic unit, a proportional allocation method is used to distribute the divided monitoring points. Furthermore, constraints are added to consider areas with high nitrogen leaching risk in farmland and areas with shallow groundwater depth. Specifically, the number of monitoring points within areas with nitrogen accumulation (>1000 kg / ha, i.e., high nitrogen accumulation areas) and groundwater depth (<2 m, i.e., shallow groundwater areas) must not be less than 30%~50% of the total number of monitoring points.

[0066] Furthermore, the formula for calculating the number of monitoring points within each basic unit is as follows.

[0067] .

[0068] st .

[0069] in, For the first The number of monitoring points within each basic unit; For the first The area of ​​each basic unit; The area is the region. is the total number of monitoring points; st is the constraint condition; For the first The basic unit belongs to the high-content area map; For the first Number of monitoring points in each basic unit; This is a constraint scaling factor.

[0070] Step S5: Construct the objective function for the monitoring points based on the average distance minimization criterion.

[0071] Furthermore, the expression for the objective function is as follows.

[0072] .

[0073] in, The objective function is... For the first The initial number of monitoring points for each basic unit; The serial number of the monitoring point; The distance is Euclidean. For the first basic unit One monitoring point; Distance monitoring points within the basic unit The nearest monitoring point.

[0074] Specifically, when setting up monitoring points, if there is no prior knowledge, the geographical layout is optimized based on the Minimizations of the Mean of Shortest Distances (MMSD) criterion. The MMSD criterion takes into account the uniform distribution of sample points, so as not to lose some important information. This criterion minimizes the Euclidean distance between any point in the basic unit and the nearest monitoring point, so as to avoid the monitoring points being too concentrated or sparse, thereby improving the representativeness of the monitoring data.

[0075] Step S6: Based on the objective function, the spatial simulated annealing algorithm is used to optimize the monitoring points in the initial layout of each basic unit to obtain the optimized layout of the monitoring points.

[0076] Furthermore, step S6 specifically includes steps S61-S63.

[0077] Step S61: Initialize annealing parameters; annealing parameters include: initial temperature, cooling rate and termination iteration condition.

[0078] Step S62: For the set of monitoring points in the initial layout of each basic unit, under the constraints, generate a set of disturbance monitoring points in the basic unit using a disturbance method, and calculate the objective function of the set of monitoring points and the objective function of the set of disturbance monitoring points respectively.

[0079] Step S63: Based on the objective function of the monitoring point set, the objective function of the disturbance monitoring point set, and the current iteration temperature, the monitoring points in the initial layout within each basic unit are optimized using the Metropolis criterion until the termination iteration condition is met, thus completing the optimized layout of the monitoring points. The termination iteration condition is that the current iteration temperature is less than the temperature threshold. The current iteration temperature is determined based on the initial temperature, cooling rate, and number of iterations.

[0080] Specifically, the simulated annealing algorithm is a general optimization algorithm, which firstly sets a high initial temperature and gives a cooling rate of temperature, and then searches around to find the optimal solution of the objective function. The advantage of this algorithm is that it can jump out of the local optimal solution and find the global optimal solution. The spatial simulation algorithm is suitable for the case of known research area with a small amount of sample data and semi-variogram model representing the spatial characteristics of the monitoring point attribute. It is a random calculation technique that can effectively avoid local optimization and become a combination optimization algorithm converging to the global optimum, and has no strict requirements for the initial state of the research object, and can be used to solve complex deterministic optimization combination problems. The specific steps are as follows.

[0081] Step 1: initialize annealing parameters, including initial temperature , cooling rate β (0 β <1) and termination iteration condition, etc.

[0082] Step 2: set all monitoring points in the initial layout in the first basic unit as set , and execute the objective function .

[0083] Step 3: generate a disturbed monitoring point set based on set using a disturbance method, and set the disturbed monitoring point set as set , and execute the objective function , wherein the disturbance method includes but is not limited to the following three operations, specifically including addition, deletion and replacement, etc., and any operation or combination thereof can be used to generate the disturbed monitoring point set.

[0084] Among them, the addition of monitoring points: in the basic unit, a set of several monitoring points is randomly generated according to the constraint condition, and is added to the current layout set to form the disturbed monitoring point set .

[0085] Delete monitoring points: in the basic unit, a set of several monitoring points is randomly selected from the current layout set according to the constraint condition, and is removed to form the disturbed monitoring point set .

[0086] Replace the monitoring points: in the basic unit, a set of several monitoring points is randomly selected from the current layout according to the constraint condition, and is replaced by a set of new monitoring points randomly generated in the basic unit to form the disturbed monitoring point set .

[0087] ​After the perturbation operation is completed, a perturbation monitoring point set is obtained . Then, the objective function value of the perturbation solution is calculated .

[0088] Step 4: Compare the objective function of the monitoring point set and the objective function of the perturbation monitoring point set , and use the Metropolis criterion to determine whether to accept the set .

[0089] Specifically, if the new solution is better than the current solution, the new solution is accepted unconditionally. This means (i.e., the set has a smaller objective function value, indicating that the layout of the monitoring points is more uniform). If , the new solution is accepted with a probability, which is calculated by the Metropolis criterion, and the acceptance probability depends on the difference in the objective function and the current "temperature" state. That is, the set is accepted with a probability , where is the iteration temperature of the th iteration.

[0090] Step 5: Determine whether the termination iteration condition is met (the current iteration temperature is less than the temperature threshold ), if not, calculate the iteration temperature of the th iteration, and continue to repeat step 3, otherwise complete the optimization and output the optimized layout of the monitoring points.

[0091] The monitoring point layout optimization method based on regional scale nitrogen leaching proposed in the present application has the following beneficial effects: (1) By performing pixel alignment and combination calculation on the regional slope level map, groundwater level level map, and nitrogen accumulation map, the basic unit of the region is accurately laid out, and then combined with the objective function of the monitoring point and the spatial simulation annealing algorithm, the global optimal solution is efficiently searched, avoiding the blindness and redundancy of the distribution of monitoring points in traditional methods, and significantly improving the efficiency of monitoring well layout.

[0092] (2) In the initial layout, the constraint condition of being greater than the nitrogen accumulation threshold and less than the groundwater depth threshold is used to ensure that the monitoring points in the key risk areas with high nitrogen accumulation and shallow groundwater depth occupy a sufficient proportion, effectively avoiding the data deviation problem caused by unreasonable monitoring point proportion in the past, and improving the accuracy and representativeness of the monitoring data of the monitoring points.

[0093] ​(3) By pixel-to-pixel overlay and combination calculation of the slope grade map, nitrogen accumulation map and groundwater level grade map of the region, the topography, soil nitrogen distribution and groundwater depth variation in the region are comprehensively considered, and a plurality of basic units are generated according to the grades of each map, so that each basic unit generated represents a specific natural geographical and nitrogen environment combination type, the spatial representativeness of the monitoring points is effectively improved, and the monitoring accuracy of nitrogen leaching at the regional scale can be more accurately reflected.

[0094] (4) The finally optimized monitoring points can provide scientific support for precise evaluation and evolution trend prediction of groundwater nitrogen pollution, and provide more systematic and efficient decision-making basis for regional agricultural nitrogen management and groundwater pollution prevention and control.

[0095] Based on the same inventive concept, the embodiments of the present application also provide a monitoring well point layout optimization system based on regional scale nitrogen leaching. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme described in the above method, so the specific limitations in one or more monitoring well point layout optimization system embodiments based on regional scale nitrogen leaching provided below can be referred to the limitations of the monitoring well point layout optimization method based on regional scale nitrogen leaching in the above, which will not be repeated here.

[0096] In an exemplary embodiment, a monitoring well point layout optimization system based on regional scale nitrogen leaching is provided, which includes: an acquisition module configured to acquire a region area and region data; a drawing module configured to draw a slope grade map, a groundwater level grade map and a nitrogen accumulation map of the region based on the region data, respectively; a basic unit generation module configured to perform pixel-to-pixel overlay and combination calculation on the slope grade map, the groundwater level grade map and the nitrogen accumulation map of the region to generate a plurality of basic units; a monitoring point number generation module configured to, under a constraint condition, perform initial layout of monitoring points in each basic unit according to the region area, an obstacle layer and a preset monitoring point spacing; the constraint condition is greater than a nitrogen accumulation threshold and less than a groundwater depth threshold; the obstacle layer is a layer on which monitoring points cannot be set; a construction module configured to construct a target function of the monitoring points based on an average distance minimization criterion; and an optimization module configured to optimize the monitoring points in the initial layout in each basic unit based on the target function by using a spatial simulated annealing algorithm to obtain an optimized layout of the monitoring points.

[0097] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0098] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to a memory, a database or other medium used in the embodiments provided in the present application can include at least one of a non-volatile and a volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical storage, a high-density embedded non-volatile memory, a resistive random access memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric random access memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0099] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0100] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0101] The principles and implementation modes of the present application are described by applying specific examples in the present application. The above-mentioned embodiments are only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range can be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A method for optimizing the layout of monitoring points for nitrogen leaching at the regional scale, characterized in that, The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching includes: Obtain the area and region data; Based on the regional data, slope grade map, groundwater level grade map and nitrogen accumulation map of the region were drawn respectively. Pixel alignment and combination calculations are performed on the slope level map, groundwater level map and nitrogen accumulation map of the region to generate multiple basic units; Under constraints, monitoring points are initially laid out in each basic unit based on the area, obstacle layer, and preset monitoring point spacing; the constraints are that nitrogen accumulation is greater than the nitrogen accumulation threshold and groundwater depth is less than the groundwater depth threshold; the obstacle layer is a layer where monitoring points cannot be set. Based on the criterion of minimizing average distance, construct the objective function for monitoring points; Based on the objective function, the spatial simulated annealing algorithm is used to optimize the monitoring points in the initial layout of each basic unit, resulting in an optimized layout of the monitoring points.

2. The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching according to claim 1, characterized in that, To obtain the area of ​​a region, specifically: Acquire regional image data; Spatial registration is performed on the image data of the region to generate a polygonal shape with closed boundaries; The area of ​​the region is calculated using a plane geometry method based on the polygonal shape with the closed boundary.

3. The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching according to claim 2, characterized in that, The formula for calculating the area of ​​the region is: ； in, The area is the region. The number of vertices of the polygon; For the first The coordinates of the vertices of a polygonal shape along the X-axis; For the first The coordinates of the vertices of a polygonal shape along the Y-axis; For the first The coordinates of the vertices of a polygonal shape along the X-axis; For the first The coordinates of the vertices of a polygonal shape along the Y-axis.

4. The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching according to claim 1, characterized in that, The regional data includes: digital elevation model data, groundwater depth data of known observation points in the region, and nitrogen content of soil layers at preset depths of known observation points in the region; Based on the regional data, slope level maps, groundwater level maps, and nitrogen accumulation maps for the region are drawn, specifically including: Based on the digital elevation model data, the slope value of each grid cell within the area is calculated; The slope values ​​are classified using the natural discontinuity classification method to determine slope grades, and slope grade maps are drawn based on these grades. The slope grade maps include: flat slope maps, sloping slope maps, and steep slope maps. Based on the groundwater depth data of known observation points in the region and the nitrogen content of soil layers at preset depths of known observation points in the region, the Kriging interpolation method is used to obtain groundwater level maps and nitrogen accumulation maps; the groundwater level maps include: shallow buried area maps, medium buried area maps and deep buried area maps; the nitrogen accumulation maps include: low content area maps, medium content area maps and high content area maps.

5. The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching according to claim 4, characterized in that, The formula for calculating the slope value of each grid cell within the area is as follows: ； in, This represents the slope value. For digital elevation model data in Rate of change of elevation in the direction; For digital elevation model data in Rate of change of elevation in the direction.

6. The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching according to claim 4, characterized in that, Based on the groundwater depth data of known observation points within the region and the nitrogen content of soil layers at preset depths at the known observation points within the region, the Kriging interpolation method is used to obtain a groundwater level map and a nitrogen accumulation map, specifically including: Based on the groundwater depth data of known observation points in the region, a groundwater variability function model is established. Based on the groundwater variogram model, the groundwater depth data of unknown observation points in the region are interpolated to obtain the groundwater depth data of unknown observation points in the region. A groundwater depth raster map is generated based on the groundwater depth data of known observation points and unknown observation points within the region. The groundwater depth grid map is divided according to the preset range of groundwater depth data, and a groundwater level map is drawn. Based on the nitrogen content of different soil layers at a preset depth of known observation points in the region, calculate the cumulative nitrogen content at the preset depth of known observation points in the region. A nitrogen accumulation variability function model is established based on the preset depth nitrogen accumulation of known observation points in the region. Based on the nitrogen accumulation variability function model, the nitrogen accumulation of different soil layers at a preset depth of unknown observation points in the region is interpolated to obtain the nitrogen accumulation of unknown observation points at a preset depth in the region. A nitrogen accumulation raster map is generated based on the preset depth nitrogen accumulation in the region and the preset depth nitrogen accumulation at unknown observation points in the region. The nitrogen accumulation raster is divided according to a preset range of nitrogen accumulation, and a nitrogen accumulation map is drawn.

7. The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching according to claim 1, characterized in that, The formula for calculating the number of monitoring points within each basic unit is as follows: ； s.t. ; in, For the first The number of monitoring points in each basic unit; For the first The area of ​​each basic unit; The area is the region. is the total number of monitoring points; st is the constraint condition; For the first The basic unit belongs to the high-content area map; For the first Number of monitoring points in each basic unit; This is a constraint scaling factor.

8. The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching according to claim 1, characterized in that, The expression for the objective function is: ； in, The objective function is... For the first The initial number of monitoring points for each basic unit; The serial number of the monitoring point; The distance is Euclidean. For the first basic unit One monitoring point; Distance monitoring points within the basic unit The nearest monitoring point.

9. The method for optimizing the layout of monitoring points based on regional-scale nitrogen leaching according to claim 1, characterized in that, Based on the objective function, the spatial simulated annealing algorithm is used to optimize the monitoring points in the initial layout within each basic unit, resulting in an optimized layout of the monitoring points, specifically including: Initialize the annealing parameters; the annealing parameters include: initial temperature, cooling rate, and termination iteration condition; For the set of monitoring points in the initial layout of each basic unit, under the constraints, a set of perturbation monitoring points is generated in the basic unit using a perturbation method, and the objective function of the set of monitoring points and the objective function of the set of perturbation monitoring points are calculated respectively. Based on the objective function of the set of monitoring points, the objective function of the set of disturbed monitoring points, and the current iteration temperature, the Metropolis criterion is used to optimize the monitoring points in the initial layout within each basic unit until the termination iteration condition is met, thus completing the optimized layout of the monitoring points. The termination iteration condition is that the current iteration temperature is less than a temperature threshold. The current iteration temperature is determined based on the initial temperature, cooling rate, and number of iterations.

10. A monitoring well location optimization system based on regional-scale nitrogen leaching, characterized in that, The monitoring well site layout optimization system based on regional-scale nitrogen leaching includes: The acquisition module is used to obtain the area and data of the region. The drawing module is used to draw the slope level map, groundwater level map and nitrogen accumulation map of the region based on the regional data. The basic unit generation module is used to perform pixel alignment overlay and combination calculations on the slope level map, groundwater level map and nitrogen accumulation map of the region to generate multiple basic units. The monitoring point number generation module is used to initially lay out the monitoring points in each basic unit under constraints, based on the area, obstacle layer, and preset monitoring point spacing; the constraints are greater than the nitrogen accumulation threshold and less than the groundwater depth threshold; the obstacle layer is a layer where monitoring points cannot be set. The building block is used to construct the objective function for monitoring points based on the average distance minimization criterion; The optimization module is used to optimize the monitoring points in the initial layout of each basic unit based on the objective function using the spatial simulated annealing algorithm, so as to obtain the optimized layout of the monitoring points.

Images