Genetic optimization spatial layout method and system for cultivated land monitoring stations

Abstract

The invention belongs to the technical field of agricultural information and resource monitoring, and discloses a genetic optimization spatial layout method and system for cultivated land monitoring sites, and the method comprises the steps: obtaining the geographic information and soil index data of the cultivated land monitoring sites, and carrying out the normalization processing of the data; constructing a spatial heterogeneity comprehensive index, fusing the multi-index weight based on an entropy weight method, and calculating the spatial heterogeneity comprehensive index of each cultivated land monitoring station; according to the quantile of the spatial heterogeneity comprehensive index, performing farmland monitoring station heterogeneous grade division, and generating a Thiessen polygon quantitative monitoring range; and optimizing the cultivated land monitoring station layout through a genetic algorithm, and iteratively selecting an optimal cultivated land monitoring station space layout scheme. According to the genetic optimization spatial layout method and system for the cultivated land monitoring stations, multiple key indexes of soil and spatial distribution characteristics of the monitoring stations are comprehensively considered, a spatial heterogeneity comprehensive index is constructed, and monitoring station layout optimization is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural information and agricultural resource monitoring, and particularly relates to a genetic optimization spatial layout method and system for cultivated land monitoring stations. BACKGROUND

[0002] With the continuous advancement of agricultural modernization in China, cultivated land quality monitoring plays an increasingly important role in agricultural production. Soil data obtained through monitoring stations can provide scientific basis for agricultural production and food security. However, the current monitoring station layout has many problems, mainly reflected in the unreasonable layout of monitoring stations. The existing monitoring station layout is mostly selected based on experience or simple geographical zoning, lacking comprehensive consideration of soil characteristics and spatial heterogeneity. This layout method leads to a large number of blind areas or repeated coverage areas in the monitoring area, insufficient monitoring accuracy, and excessive number of monitoring stations, resulting in resource waste. These problems not only reduce the monitoring efficiency, but also increase the monitoring cost, affecting the accuracy and reliability of the monitoring data.

[0003] Currently, domestic and foreign researches on the layout of cultivated land quality monitoring stations mainly focus on the construction of monitoring index system, the improvement of monitoring technology, and the preliminary layout of monitoring stations. However, these researches mostly only focus on single index or local area monitoring, lacking comprehensive consideration of soil multi-index comprehensive characteristics and spatial heterogeneity. In practical application, the layout of monitoring stations mostly relies on experience or simple geographical zoning, failing to fully combine the spatial distribution characteristics and heterogeneity degree of soil. This experience-based layout method often cannot accurately identify high heterogeneity areas, leading to insufficient representativeness of monitoring data and difficulty in accurately reflecting the real situation of regional cultivated land quality. In addition, existing researches mostly stay at the theoretical level, with few practical schemes and limited application scope, making it difficult to meet the needs of large-scale cultivated land monitoring.

[0004] Therefore, there is an urgent need for a monitoring station layout optimization method that can comprehensively consider the spatial heterogeneity of soil multi-indexes to improve monitoring efficiency and data quality, and provide scientific basis for accurate monitoring and management of cultivated land quality. SUMMARY

[0005] The purpose of the present application is to provide a genetic optimization spatial layout method and system for cultivated land monitoring stations, which comprehensively considers the multiple key indicators of soil and the spatial distribution characteristics of monitoring stations, constructs a spatial heterogeneity comprehensive index, and realizes the optimization of monitoring station layout.

[0006] To achieve the above purpose, the present application provides a genetic optimization spatial layout method for cultivated land monitoring stations, comprising the following steps: Step S1, data acquisition and preprocessing: acquire the geographic information and soil index data of the cultivated land monitoring sites, and normalize the acquired data; Step S2, spatial heterogeneity comprehensive index construction: construct the spatial heterogeneity comprehensive index, fuse the multi-index weight based on the entropy weight method, and calculate the spatial heterogeneity comprehensive index of each cultivated land monitoring site; Step S3, heterogeneity grade division and spatial coverage modeling: according to the quantile of the spatial heterogeneity comprehensive index, the heterogeneity grade division of the cultivated land monitoring site is carried out, and the Thiessen polygon quantization monitoring range is generated; Step S4, genetic algorithm optimization: the genetic algorithm is used to optimize the layout of the cultivated land monitoring sites, and the optimal cultivated land monitoring site spatial layout scheme is selected through iteration.

[0007] Preferably, in step S1, the geographic information and soil index data of the cultivated land monitoring sites are acquired, and the acquired data is normalized, and the specific process is as follows: Step S11, the geographic information of the cultivated land monitoring sites includes latitude, longitude and elevation, and the regional monitoring site distribution is presented using ArcGIS software; the soil index data includes pH value, organic matter content, total nitrogen content, available phosphorus content and available potassium content; Step S12, each soil index is normalized to eliminate the influence of different soil index data dimension and order of magnitude difference, as shown below: , =1,2,…,n; =1,2,…,m; Wherein, is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the original value of the i-th soil index of the j-th cultivated land monitoring site; is the normalized value of the i-th soil index of the j-th cultivated land monitoring site; is the total number of cultivated land monitoring sites; is the number of soil indexes.

[0008] Preferably, in step S2, the spatial heterogeneity comprehensive index is constructed, the multi-index weight is fused based on the entropy weight method, and the spatial heterogeneity comprehensive index of each cultivated land monitoring site is calculated, and the specific process is as follows:​ Step S21, convert the soil index value of each cultivated land monitoring site into a relative proportion, calculate the proportion of the first cultivated land monitoring site under the first soil index Step S22, according to the relative proportion of the soil index of each cultivated land monitoring site, first quantify the dispersion degree of the soil index with entropy value, the entropy value of the first soil index Step S23, based on the weight of each soil index, calculate the spatial heterogeneity comprehensive index of the soil index of the cultivated land monitoring site As follows: ; As follows: As follows: ; Then, use the weight to reflect the importance of each soil index in the comprehensive evaluation, the weight of the first soil index As follows: ; Wherein, Satisfies ; Step S23, based on the weight of each soil index, calculate the spatial heterogeneity comprehensive index of the soil index of the cultivated land monitoring site As follows: ; Wherein, is the mean value of the soil index of all cultivated land monitoring sites is the amplification coefficient; is the translation coefficient. Preferably, in step S3, according to the quantile of the spatial heterogeneity comprehensive index, the heterogeneity grade of the cultivated land monitoring site is divided, and the Thiessen polygon quantification monitoring range is generated, and the specific process is as follows:

[0009] Step S31, according to the H value of the spatial heterogeneity comprehensive index, the cultivated land monitoring site is graded by using quantile method; Step S32, each cultivated land monitoring site is regarded as a geographic space point, and the Thiessen polygon is generated by using R language Package to visualize the coverage range of each cultivated land monitoring site. sf

[0010] Preferably, in step S31, the cultivated land monitoring site is graded by using quantile method, as follows: The cultivated land monitoring site with H value lower than 50% quantile is marked as low heterogeneity point; The cultivated land monitoring site with H value between 50% and 75% quantile is marked as medium heterogeneity point; ​​​The cultivated land monitoring site with H value higher than the 75% quantile is marked as a high heterogeneity site.

[0011] Preferably, in step S4, the cultivated land monitoring site layout is optimized by a genetic algorithm, and the optimal cultivated land monitoring site spatial layout scheme is iteratively selected. The genetic algorithm optimization includes scheme initialization, scheme coding, fitness calculation, selection, crossover and mutation operations. Step S41, based on the original cultivated land monitoring site layout, an initial scheme is generated, and the number of schemes is P; scheme 0 is the coordinate set of the original cultivated land monitoring site: ; Wherein, represents the longitude and latitude coordinates of the cultivated land monitoring site ; is the longitude coordinate; is the latitude coordinate; The remaining schemes are generated by difference disturbance: with a probability Remove low heterogeneity sites; with Randomly generate new cultivated land monitoring sites within the high heterogeneity Thiessen polygon, and verify by GIS space that the new cultivated land monitoring sites are in the cultivated land area, and delete the new cultivated land monitoring sites in the non-cultivated land area; Step S42, encode the cultivated land monitoring site layout scheme as a real number vector; each site layout scheme is a sequence, as shown below: ; Wherein, is used to identify the cultivated land monitoring site type: 0 indicates low heterogeneity, 1 indicates medium heterogeneity, and 2 indicates high heterogeneity; Step S43, for each layout scheme, calculate the fitness to evaluate the layout quality, as shown below: ; Wherein, is the total area of the high heterogeneity Thiessen polygon; is the total area of the region; is the number of low heterogeneity cultivated land monitoring sites; is the maximum distance from any point to the nearest cultivated land monitoring site; is the reference distance; is the high heterogeneity area coverage weight; is the low heterogeneity site quantity weight; is the spatial coverage uniformity weight; Step S44, parent selection and crossover mutation are performed in the cultivated land monitoring site layout scheme. Step S45, iteration of the genetic algorithm is performed, and a stop condition for running the genetic algorithm is set, i.e., a maximum number of iterations is reached or the layout schemes of the cultivated land monitoring sites are all the same, and the spatial optimization layout scheme of the cultivated land monitoring sites is completed.

[0012] Preferably, in step S44, parent selection and crossover mutation are performed in the layout scheme of the cultivated land monitoring sites, and the specific process is as follows: Step S441, for the i-th layout scheme, a selection probability is allocated according to the fitness proportion, as shown below: Among them, represents the selection probability of the i-th layout scheme; represents the fitness of the i-th layout scheme; represents the sum of the fitness of all layout schemes; the selection probability of each layout scheme is mapped to a cumulative probability axis in the interval [0, 1] in order, to form a virtual roulette wheel; Step S442, a uniform random number r in the interval [0, 1] is generated, and the corresponding scheme is selected according to the interval of the roulette wheel in which the value of r falls; Step S443, based on the crossover operator, two different parent schemes are randomly selected for crossover, and for high-heterogeneity points, the same type of cultivated land monitoring sites in the two schemes are aligned according to the principle of nearest neighbor matching of the longitude and latitude of the cultivated land monitoring sites, and the longitude and latitude coordinates of all high-heterogeneity cultivated land monitoring sites matched are executed by simulated binary crossover, as shown below: Among them, and represent the child scheme; and represent the parent scheme; is a random number between 0 and 1; is a crossover distribution index; is a crossover distribution coefficient; Step S444, based on the mutation operator, each child scheme is subjected to mutation operation: Deletion mutation, i.e., probability p d : a low-heterogeneity cultivated land monitoring site is randomly deleted, i.e. ; New mutation, i.e., probability p n : a cultivated land monitoring site is randomly added in the high-heterogeneity area, and the coordinates are uniformly distributed within the high-heterogeneity Thiessen polygon; if the coordinates after mutation fall into non-cultivated land, the operation is re-generated or cancelled.

[0013] ​​​​​A genetic optimization space layout system of cultivated land monitoring stations comprises the following modules: A data acquisition and preprocessing module is configured to collect geographical information of the laid cultivated land monitoring stations and soil index data of the stations and to preprocess the data. The geographical information comprises longitude, latitude and elevation, and the soil index data comprises pH value, organic matter content, total nitrogen content, available phosphorus content and available potassium content. A space heterogeneity comprehensive index construction module is configured to determine the soil index weight of each monitoring station based on an entropy weight method and to construct a space heterogeneity comprehensive index. A heterogeneity grade division and space coverage modeling module is configured to divide the monitoring stations into heterogeneity grades according to the space heterogeneity comprehensive index of each monitoring station and the corresponding quantile and to quantify the monitoring range through a Thiessen polygon. A genetic algorithm optimization module comprises station scheme initialization, scheme coding, fitness calculation, selection, crossover and mutation operator design and iteration to select a spatial optimization layout scheme of the cultivated land monitoring stations.

[0014] Therefore, the genetic optimization space layout method and system of the cultivated land monitoring stations are adopted to comprehensively consider various key indicators of the soil and the spatial distribution characteristics of the monitoring stations, construct a space heterogeneity comprehensive index and realize layout optimization of the monitoring stations.

[0015] The application can not only scientifically determine the layout position of the monitoring stations according to the soil data and avoid resource waste caused by unreasonable station layout but also realize global optimization through the genetic algorithm and ensure the optimality of the monitoring station layout.

[0016] In addition, the application quantifies the monitoring range through the Thiessen polygon, intuitively displays the coverage area of each monitoring station and provides an important reference for reasonable layout of the monitoring stations. The method improves the monitoring accuracy in the high-heterogeneity area, reduces the number of inefficient stations, effectively reduces the monitoring cost, improves the monitoring efficiency, provides a powerful guarantee for improvement of the cultivated land quality and efficient management of agricultural production and helps the national strategy of food security.

[0017] The technical solutions of the application are further described below with reference to the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a flowchart of the genetic optimization space layout method of the cultivated land monitoring stations of the application; Figure 2 is a monitoring station distribution map of a selected region of the application; Figure 3 is a heterogeneity grade division result map of the monitoring stations of the application; Figure 4 is a monitoring site monitoring range map of the application; Figure 5 is a specific flowchart of the application applying a genetic optimization algorithm; Figure 6 is a monitoring site distribution map optimized by the genetic algorithm of the application; Figure 7 is a module schematic diagram of a cultivated land monitoring site genetic optimization spatial layout system of the application. DETAILED DESCRIPTION

[0019] The technical solutions of the application are further described below through the drawings and examples.

[0020] As shown in the drawings, Figure 1 a cultivated land monitoring site genetic optimization spatial layout method, comprising the following steps: Step S1, data acquisition and preprocessing: acquiring geographic information and soil index data of the cultivated land monitoring site, and performing normalization processing on the acquired data; Step S2, spatial heterogeneity comprehensive index construction: constructing a spatial heterogeneity comprehensive index, fusing multi-index weights based on an entropy weight method, and calculating the spatial heterogeneity comprehensive index of each cultivated land monitoring site; Step S3, heterogeneity grade division and spatial coverage modeling: performing heterogeneity grade division of the cultivated land monitoring site according to the quantile of the spatial heterogeneity comprehensive index, and generating a Thiessen polygon quantization monitoring range; Step S4, genetic algorithm optimization: optimizing the layout of the cultivated land monitoring site through a genetic algorithm, and iteratively selecting an optimal cultivated land monitoring site spatial layout scheme.

[0021] Example 1 In view of the problems of unreasonable cultivated land monitoring site layout, repeated coverage of the monitoring area, insufficient monitoring precision, and excessive number of monitoring sites leading to resource waste, a cultivated land monitoring site genetic optimization spatial layout method is proposed. Under the condition of considering cost and efficiency, a region and the number of monitoring sites in the region are given, based on the geographic information and soil index data of the monitoring sites, the optimal layout of the monitoring sites in the region is quickly realized, so that the monitoring sites can cover all key soil characteristic regions of the region as much as possible, the monitoring precision is improved, and the inefficient coverage region is reduced.

[0022] The cultivated land monitoring site genetic optimization spatial layout method of the application comprises the following steps: Step S1, acquiring geographic information and soil index data of the cultivated land monitoring site, and performing normalization processing on the acquired data.

[0023] Step S11: Obtain the geographical information of farmland monitoring stations, including latitude, longitude, and elevation, and use ArcGIS software to present the distribution of regional monitoring stations; soil index data include pH value, organic matter content, total nitrogen content, available phosphorus content, and available potassium content, etc.

[0024] In this embodiment, the geographic latitude and longitude information of some farmland monitoring stations in Gongzhuling is obtained, and ArcGIS software is used to present the distribution of farmland monitoring stations in the region, such as... Figure 2 As shown.

[0025] Step S12: Normalize each soil index to eliminate the impact of differences in the dimensions and orders of magnitude of different soil index data, as shown below: , =1,2,…,n; =1,2,…,m; in, For the first The first cultivated land monitoring station The original values ​​of each soil index; For the first The set of raw values ​​of a soil index from all farmland monitoring stations; For the first The minimum value of a soil index among all farmland monitoring stations; For the first The maximum value of each soil index across all farmland monitoring stations; For the first The first cultivated land monitoring station Normalized values ​​of each soil index; This represents the total number of farmland monitoring stations. This represents the number of soil indicators.

[0026] In this embodiment, 30 farmland monitoring stations were set up, and 5 soil indicators were established.

[0027] Step S2: Construct a spatial heterogeneity comprehensive index. Based on the entropy weight method, integrate the weights of multiple indicators to calculate the spatial heterogeneity comprehensive index of each farmland monitoring station.

[0028] Step S21: Convert the soil index values ​​of each farmland monitoring station into relative weights, and calculate the first... The first soil index The proportion of individual farmland monitoring stations As shown below: ; Step S22: Based on the relative proportions of soil indicators at each farmland monitoring station, firstly, the dispersion of soil indicators is quantified using entropy values. Entropy value of each soil index As follows: ; Then, the weight reflects the importance of each soil index in the comprehensive evaluation, the weight of the first Soil index As follows: ; Wherein, Satisfies .

[0029] Step S23, based on the weight of each soil index, calculate the spatial heterogeneity comprehensive index of the soil index of the cultivated land monitoring site As follows: ; Wherein, The mean value of the soil index of all cultivated land monitoring sites ; And Empirical scaling factor; Amplification coefficient, enhance the identification sensitivity of high heterogeneity area; Translation coefficient, prevent zero interference.

[0030] Step S3, according to the quantile of spatial heterogeneity comprehensive index, the heterogeneity grade of cultivated land monitoring site is divided, and the thiesen polygon quantization monitoring range is generated.

[0031] Step S31, according to the H value of spatial heterogeneity comprehensive index, the cultivated land monitoring site is classified by quantile method, as Figure 3 As follows: The cultivated land monitoring site with H value lower than 50% quantile is marked as "low heterogeneity point"; The cultivated land monitoring site with H value between 50% and 75% quantile is marked as "medium heterogeneity point"; The cultivated land monitoring site with H value higher than 75% quantile is marked as "high heterogeneity point".

[0032] Step S32, each cultivated land monitoring site is regarded as a geographic space point, and the thiesen polygon is generated by using R language sf Package according to the longitude and latitude coordinates of the site, the coverage range of each cultivated land monitoring site is visualized, as Figure 4 As follows:

[0033] Step S4, the genetic algorithm is used to optimize the layout of the cultivated land monitoring site, and the optimal cultivated land monitoring site spatial layout scheme is selected by iteration. The genetic algorithm optimization includes scheme initialization, scheme coding, fitness calculation, selection, crossover and mutation operation, asFigure 5 are shown.

[0034] Step S41, scheme initialization.

[0035] Based on the current original cultivated land monitoring site layout, an initial scheme is generated, and the number of schemes is P, which is set to 200. Among them, scheme 0 is the coordinate set of the original cultivated land monitoring site: ; Among them, represents the longitude and latitude coordinates of the cultivated land monitoring site ; is the longitude coordinate; is the latitude coordinate.

[0036] The remaining schemes are generated by difference disturbance: with a probability Remove low-heterogeneous points; with Randomly generate new cultivated land monitoring sites within the high-heterogeneous point Thiessen polygon, and through GIS spatial verification, the newly added cultivated land monitoring sites are in the cultivated land area such as non-road, non-water area, and the newly added cultivated land monitoring sites in non-cultivated land area are deleted.

[0037] Step S42, scheme encoding.

[0038] The cultivated land monitoring site layout scheme is encoded to represent it as a real number vector. Each site layout scheme is a sequence, as shown below: ; Among them, is used to identify the cultivated land monitoring site type: 0 represents low heterogeneity, 1 represents medium heterogeneity, and 2 represents high heterogeneity.

[0039] Step S43, fitness calculation.

[0040] For each layout scheme, the fitness is calculated to evaluate the layout quality, as shown below: ; Among them, is the total area of the high-heterogeneous Thiessen polygon; is the total area of the region; is the number of low-heterogeneous cultivated land monitoring sites; is the maximum distance from any point to the nearest cultivated land monitoring site; is the reference distance; is the high-heterogeneous area coverage weight, is the low-heterogeneous site quantity weight, is the spatial coverage uniformity weight, which are all calibrated through pre-experiments; Step S44, parent selection and crossover mutation in the farmland monitoring station layout scheme.

[0041] Step S441, first, for the first layout scheme, the selection probability is allocated according to the fitness proportion, as follows: ; Wherein, represents the selection probability of the first layout scheme; represents the fitness of the first layout scheme; represents the sum of the fitness of all layout schemes, P=200. The selection probability of each layout scheme is mapped to a cumulative probability axis in the interval [0,1] in order, forming a virtual "roulette".

[0042] Step S442, secondly, a uniform random number r in the interval [0,1] is generated, and the corresponding scheme is selected according to the interval of the roulette in which the value of r falls. Repeat the random roulette selection 200 times to retain high-quality schemes into the next generation and ensure scheme diversity.

[0043] Step S443, then, based on the crossover operator, randomly select two different parent schemes for crossover. For high-heterogeneity points, align the same type of farmland monitoring stations in the two schemes according to the nearest neighbor matching principle of farmland monitoring station longitude and latitude, and perform simulated binary crossover on the longitude and latitude coordinates of all matched high-heterogeneity farmland monitoring stations, as follows: ; Wherein, and represent the child scheme; and represent the parent scheme; is a random number between 0 and 1; is a crossover distribution index (usually 5) used to control the concentration of child individuals around parent individuals; is a crossover distribution coefficient used to control the degree of deviation of child individuals from parent individuals.

[0044] Step S444, finally, based on the mutation operator, perform mutation operation on each child scheme: Delete mutation probability : randomly delete a low-heterogeneity farmland monitoring station ( ); Add mutation probability : randomly add farmland monitoring stations in high-heterogeneity areas, with coordinates uniformly distributed within the high-heterogeneity Thiessen polygon; if the coordinates after mutation fall into non-farmland, regenerate or cancel the operation.

[0045] Step S45, iteration of the genetic algorithm is performed, a stop condition for running the genetic algorithm is set, i.e., a maximum number of iterations is reached or all farmland monitoring station layout schemes are the same, and the best spatial optimization layout scheme of the farmland monitoring station is completed, as shown in Figure 6 .

[0046] Embodiment 2 As shown in Figure 7 , the application further provides a genetic optimization spatial layout system of a farmland monitoring station, comprising the following modules: A data acquisition and preprocessing module is configured to collect geographic information of the laid farmland monitoring station and soil index data of each station, and to preprocess the data.

[0047] The geographic information includes longitude, latitude and elevation, and the soil index data includes pH value, organic matter content, total nitrogen content, available phosphorus content and available potassium content.

[0048] A spatial heterogeneity comprehensive index construction module is configured to determine the soil index weight of each monitoring station based on an entropy weight method, and to construct a spatial heterogeneity comprehensive index.

[0049] A heterogeneity grade division and spatial coverage modeling module is configured to divide the monitoring stations into heterogeneity grades according to the spatial heterogeneity comprehensive index and the corresponding quantile of each monitoring station, and to quantify the monitoring range through a Thiessen polygon.

[0050] A genetic algorithm optimization module includes station scheme initialization, scheme coding, fitness calculation, design of selection, crossover and mutation operators, and iteration to select the best spatial optimization layout scheme of the farmland monitoring station.

[0051] The specific implementation modes of the modules correspond to the steps, and the application will not be described.

[0052] In summary, the application adopts the above-mentioned genetic optimization spatial layout method and system of a farmland monitoring station, comprehensively considers various key indicators of the soil and spatial distribution characteristics of the monitoring station, constructs a spatial heterogeneity comprehensive index, and realizes layout optimization of the monitoring station.

[0053] The application can not only scientifically determine the layout position of the monitoring station according to the soil data, avoid resource waste caused by unreasonable station layout, but also realize global optimization through the genetic algorithm, and ensure the optimality of the monitoring station layout.

[0054] In addition, the present application visually displays the coverage area of each monitoring station by the Tyson polygon visual monitoring range, and provides an important reference for the reasonable layout of the monitoring station. This method improves the monitoring accuracy of the high-heterogeneous area, reduces the number of inefficient stations, effectively reduces the monitoring cost, improves the monitoring efficiency, and provides a strong guarantee for agricultural production and food safety monitoring management.

[0055] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit them, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that: it can still modify or equivalently replace the technical solutions of the present application, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. A genetically optimized spatial layout method for farmland monitoring stations, characterized in that, Includes the following steps: Step S1, Data Acquisition and Preprocessing: Acquire geographic information and soil index data of farmland monitoring stations, and normalize the acquired data; Step S2, Construction of Spatial Heterogeneity Composite Index: A spatial heterogeneity composite index is constructed by integrating multiple indicator weights using the entropy weight method. The specific process is as follows: Step S21: Convert the soil index values ​​of each farmland monitoring station into relative weights, and calculate the first... The first soil index The proportion of individual farmland monitoring stations As shown below: ； Step S22: Based on the relative proportions of soil indicators at each farmland monitoring station, firstly, the dispersion of soil indicators is quantified using entropy values. Entropy values ​​of soil indicators As shown below: ； Next, weights are used to reflect the importance of each soil indicator in the comprehensive evaluation. Weights of each soil index As shown below: ； in, satisfy ; Step S23: Based on the weights of each soil index, calculate the comprehensive index of spatial heterogeneity of soil indices at farmland monitoring stations. As shown below: ； in, Soil indicators for all farmland monitoring stations The mean; This is the magnification factor; The translation coefficient; Step S3, Heterogeneity Classification and Spatial Coverage Modeling: Based on the quantiles of the spatial heterogeneity comprehensive index, the heterogeneity levels of farmland monitoring stations are classified, and the Thiessen polygon is used to quantify the monitoring range. The specific process is as follows: Step S31: Based on the H value of the spatial heterogeneity comprehensive index, the quantile method is used to classify the farmland monitoring stations; Step S32: Treat each farmland monitoring station as a geospatial point, and based on the latitude and longitude coordinates of that station, use the R language... sf The package generates Thiessen polygons to visualize the coverage of each farmland monitoring station; Step S4, Genetic Algorithm Optimization: The layout of farmland monitoring stations is optimized using a genetic algorithm, and the optimal spatial layout scheme of farmland monitoring stations is selected iteratively. Genetic algorithm optimization includes scheme initialization, scheme encoding, fitness calculation, selection, crossover and mutation operations; Step S41: Based on the existing farmland monitoring station layout, generate an initial scheme, with P schemes; Scheme 0 is the coordinate set of the original farmland monitoring stations: ； in, Indicates farmland monitoring stations latitude and longitude coordinates; Longitude coordinates; Latitude coordinates; The remaining schemes are generated through difference perturbations: in probability Remove low heterogeneous points; New farmland monitoring stations are randomly generated within the Thiessen polygon with high heterogeneity. The newly added farmland monitoring stations are verified by GIS spatial verification to be located in farmland areas other than roads and water bodies. New farmland monitoring stations in non-farmland areas are deleted. Step S42: Encode the layout scheme of the farmland monitoring stations, representing it as a real number vector; each station layout scheme is a sequence, as shown below: ； in, Used to identify the type of farmland monitoring station: 0 indicates low heterogeneity, 1 indicates medium heterogeneity, and 2 indicates high heterogeneity; Step S43: For each layout scheme, calculate the fitness. To assess layout quality, as shown below: ； in, The total area of ​​the highly heterogeneous Thiessen polygon; The total area of ​​the region; The number of monitoring stations for low-heterogeneous cultivated land; The maximum distance from any point to the nearest farmland monitoring station; For reference distance; Weights are assigned to cover highly heterogeneous regions; Weighting based on the number of heterogeneous sites; Weights for spatial coverage uniformity; Step S44: Perform parent selection and crossover variation in the farmland monitoring station layout scheme; Step S45: Iterate the genetic algorithm and set the stopping condition for the genetic algorithm, that is, reach the maximum number of iterations or all farmland monitoring station layout schemes are the same, and complete the spatial optimization layout scheme of farmland monitoring stations.

2. The genetically optimized spatial layout method for farmland monitoring stations according to claim 1, characterized in that, In step S1, the geographical information and soil index data of the farmland monitoring stations are acquired, and the acquired data are normalized. The specific process is as follows: Step S11: Obtain the geographic information of farmland monitoring stations, including latitude, longitude, and elevation, and use ArcGIS software to present the distribution of regional monitoring stations; soil index data include pH value, organic matter content, total nitrogen content, available phosphorus content, and available potassium content; Step S12: Normalize each soil index to eliminate the impact of differences in the dimensions and orders of magnitude of different soil index data, as shown below: , =1,2,…,n; =1,2,…,m; in, For the first The first cultivated land monitoring station The original values ​​of each soil index; For the first The set of raw values ​​of a soil index from all farmland monitoring stations; For the first The minimum value of a soil index among all farmland monitoring stations; For the first The maximum value of each soil index across all farmland monitoring stations; For the first The first cultivated land monitoring station Normalized values ​​of each soil index; This represents the total number of farmland monitoring stations. This represents the number of soil indicators.

3. The genetically optimized spatial layout method for farmland monitoring stations according to claim 1, characterized in that, In step S31, the quantile method is used to classify the farmland monitoring stations, as shown below: Farmland monitoring stations with H values ​​below the 50th percentile are marked as low heterogeneous points; Farmland monitoring stations with H values ​​between the 50th and 75th percentiles are marked as heterogeneous points; Farmland monitoring stations with H values ​​higher than the 75th percentile are marked as high heterogeneous sites.

4. The genetic optimization spatial layout method for farmland monitoring stations according to claim 1, characterized in that, In step S44, parent selection and crossover mutation are performed in the farmland monitoring station layout scheme. The specific process is as follows: Step S441, for the first Each layout scheme is assigned a selection probability based on its fitness percentage, as shown below: ； in, Indicates the first The probability of selecting a layout scheme; Indicates the first The adaptability of each layout scheme; This represents the sum of fitness for all layout options; the selection probability of each layout option is sequentially mapped onto a cumulative probability axis in the interval [0,1], forming a virtual roulette wheel; Step S442: Generate a uniform random number r in the interval [0,1], and select the corresponding scheme based on the roulette interval in which the value of r falls; Step S443: Based on the crossover operator, randomly select two different parent schemes for crossover. For highly heterogeneous points, align the farmland monitoring stations of the same type in the two schemes according to the nearest neighbor matching principle of farmland monitoring stations by latitude and longitude. Perform simulated binary crossover on the latitude and longitude coordinates of all matched highly heterogeneous farmland monitoring stations, as shown below: ； in, and Indicates the offspring scheme; and Indicates the parent scheme; A random number between 0 and 1; The cross-distribution index; The cross-distribution coefficient; Step S444: Based on the mutation operator, perform mutation operation on each child scheme: Deletion mutation is probability Randomly delete a monitoring station for low-heterogeneous cultivated land, i.e. ; New mutations are probabilities : Randomly add farmland monitoring stations in highly heterogeneous areas, with coordinates evenly distributed within highly heterogeneous Thiessen polygons; if the coordinates fall into non-farmland after mutation, regenerate or cancel the operation.

5. A method for genetically optimized spatial layout of cultivated land monitoring stations according to any one of claims 1-4, characterized in that, A genetically optimized spatial layout system for a farmland monitoring station includes the following modules: The data acquisition and preprocessing module is used to collect the geographic information of the established farmland monitoring stations and the soil index data of each station, and to preprocess the data. The geographic information includes latitude and longitude, and elevation; the soil index data includes pH value, organic matter content, total nitrogen content, available phosphorus content, and available potassium content. The spatial heterogeneity comprehensive index construction module determines the weights of each soil indicator at the monitoring station based on the entropy weight method, and constructs the spatial heterogeneity comprehensive index. The heterogeneity classification and spatial coverage modeling module classifies the monitoring stations into heterogeneity levels based on the comprehensive spatial heterogeneity index of each monitoring station and its corresponding quantile, and quantifies the monitoring range using Thiessen polygons. The genetic algorithm optimization module includes site scheme initialization, scheme encoding, fitness calculation, design of selection, crossover and mutation operators, and iterative selection of spatial optimization layout schemes for farmland monitoring sites.

Images