A high-standard farmland construction timing optimization method

Abstract

The application discloses a high-standard farmland construction time sequence optimization method, relates to the field of agricultural information technology, and comprises the following steps: superimposing a permanent basic farmland distribution layer and a high-standard farmland distribution layer to identify a region of the permanent basic farmland which has not been built into high-standard farmland; obtaining multi-source basic data in the region, adopting an S-G filtering LAI average value to represent grain yield; constructing a high-standard farmland construction ecological resilience evaluation index system; calculating the combined weight of each evaluation index according to the combination of an entropy weight method and a CRITIC method, establishing a set pair analysis model to calculate farmland ecological resilience; obtaining the spatial interaction relationship between grain yield and farmland ecological resilience based on a bivariate local spatial autocorrelation analysis method, and combining a self-organizing mapping neural network and a K-means method to identify a priority plot of high-standard farmland construction and form a construction time sequence arrangement and spatial layout optimization scheme. The application can solve the problem of the priority sequence of high-standard farmland construction.

Description

Technical Field

[0001] This invention relates to the field of agricultural information technology, specifically to a method for optimizing the timing of high-standard farmland construction. Background Technology

[0002] Existing technologies face a dual bottleneck: Spatially, traditional site selection methods rely on single indicators such as land flatness and soil fertility, failing to systematically couple multi-source heterogeneous data (such as remote sensing, topography, and meteorology) to construct a comprehensive evaluation system covering both grain yield and farmland ecological resilience. Simultaneously, they neglect the assessment of the proximity between measured farmland status indicators and the optimal high-standard farmland construction, resulting in insufficient accuracy in identifying priority construction areas. Temporally, the lack of an optimization model integrating productivity enhancement and ecological resilience makes it difficult to coordinate construction batches through clustering algorithms, impacting the construction and management of high-standard farmland.

[0003] Specifically, on the one hand, spatial assessment lacks a systematic framework, making it difficult to integrate the synergistic relationship between grain production capacity representation and ecological resilience, and neglecting the interactive effect of bivariate spatial autocorrelation, resulting in insufficient basis for plot priority decision-making; on the other hand, the temporal arrangement relies on a fixed decomposition model, without introducing an objective weighting model and cluster optimization mechanism, making it difficult to promote the phased and phased implementation of the transformation and upgrading of permanent basic farmland and build high-standard farmland. Summary of the Invention

[0004] In view of this, the present invention provides a method for optimizing the construction sequence of high-standard farmland to solve the related problems in the prior art.

[0005] This invention provides a method for optimizing the timing of high-standard farmland construction, comprising:

[0006] S1. Perform spatial overlay analysis on the permanent basic farmland distribution layer and the high standard farmland distribution layer to identify areas where high standard permanent basic farmland has not been built.

[0007] S2. Obtain multi-source basic data for areas where high-standard permanent basic farmland has not yet been built; wherein, the multi-source basic data includes: LAI data, soil fertility improvement data, drought and flood disaster resistance data, and land leveling data; and, reconstruct the LAI data using SG filtering, and calculate the average LAI value during the crop growing season in areas where high-standard permanent basic farmland has not yet been built; the average LAI value is used to characterize grain yield;

[0008] S3. Based on multi-source basic data, construct an evaluation index system for the ecological resilience of high-standard farmland construction; and calculate the weights of each evaluation index by combining the entropy weight method and the CRITIC method, and establish a set pair analysis model to calculate the ecological resilience of farmland.

[0009] S4. Based on the bivariate local spatial autocorrelation analysis method, the spatial interaction relationship between the grain yield and the farmland ecological resilience is obtained;

[0010] S5. Based on the spatial interaction relationship, combined with the self-organizing map neural network and the K-means method, priority plots for the construction of high-standard farmland in areas where high-standard permanent basic farmland has not yet been built are identified, and a time-series optimization scheme for the construction of high-standard farmland is formed.

[0011] In one optional implementation, S1 specifically includes:

[0012] The permanent basic farmland distribution layer and the high-standard farmland distribution layer are spatially overlaid. The high-standard farmland distribution layer is removed from the permanent basic farmland distribution layer by GIS difference operation, and the permanent basic farmland distribution layer that has not been built to a high standard is output.

[0013] In one optional implementation, the soil fertility improvement data includes: soil organic matter, total soil nitrogen content, total soil phosphorus content, soil texture, soil pH value, and soil bulk density;

[0014] The drought and flood disaster mitigation data includes: key climate factors, SPEI index, and distance to rivers and reservoirs;

[0015] The land leveling data includes: dimensional index, elevation, slope, topographic relief, effective soil layer thickness, and road accessibility.

[0016] In one optional implementation, the SPEI index is calculated using temperature and precipitation data obtained from the China Meteorological Administration Data Sharing Service Network; the key climate factors are obtained by performing correlation analysis between LAI data and 19 bioclimatic variables, sorting them from high to low correlation, and selecting the top 5 bioclimatic variables.

[0017] In one optional implementation, S3 includes:

[0018] S31. Based on soil fertility improvement data, drought and flood disaster resistance data, and land leveling data, construct an ecological resilience evaluation index system for high-standard farmland construction; wherein, the ecological resilience evaluation index system for high-standard farmland construction includes the name of each evaluation index, the corresponding index value, the source type, and the index type to which it belongs; the index type is used to characterize the correlation between the index value corresponding to the evaluation index and the ecological resilience of farmland;

[0019] S32. Based on the correlation between the index values ​​corresponding to each evaluation indicator and the ecological resilience of farmland, the index values ​​corresponding to each evaluation indicator are standardized to obtain the standardized values ​​corresponding to each evaluation indicator.

[0020] S33. Based on S32, calculate the combined weight of each evaluation index by combining the entropy weight method and the CRITIC method.

[0021] S34. Based on S33, establish a set pair analysis model; and calculate the farmland ecological resilience of each unit to be evaluated according to the set pair analysis model.

[0022] In one optional implementation, S34 includes:

[0023] The evaluation of the ecological resilience of high-standard farmland is denoted as... ;in, To evaluate the set of schemes, The total number of evaluation schemes; For the evaluation index set, The total number of evaluation indicators; For the set of units to be evaluated, For the first One unit to be evaluated, The total number of units to be evaluated; within the same unit, the optimal evaluation index among the various evaluation schemes is determined to form the optimal scheme set. The worst evaluation index among all evaluation schemes constitutes the worst-case scheme set. ;

[0024] ;

[0025] in, , These represent the degree of similarity and the degree of opposition between the optimal and worst solution sets, respectively. , The first p Evaluation indicators With sets [ The degree of similarity and opposition, For the first The weight of each evaluation indicator;

[0026] Evaluation scheme With the optimal solution set Relative closeness for:

[0027] ;

[0028] in, For the evaluation scheme set One evaluation scheme, .

[0029] In one optional implementation, the standardization process for the evaluation indicators is as follows:

[0030] When the correlation between the evaluation index value and the farmland ecological resilience is positive, the formula for calculating the standardized value is:

[0031] ;

[0032] When the correlation between the evaluation index value and farmland ecological resilience is negative, the formula for calculating the standardized value is:

[0033] ;

[0034] When the degree of closeness between the indicator value corresponding to the evaluation indicator and the set threshold meets the set limit, the formula for calculating the standardized value is:

[0035] ;

[0036] in, For the first The indicator values ​​corresponding to each evaluation indicator; For multiple units to be evaluated The maximum value; For multiple units to be evaluated The minimum value; To set a threshold; This is a comparison operation between the maximum and minimum values.

[0037] In one alternative implementation, S4 includes:

[0038] GeoDA software was used to perform bivariate local spatial autocorrelation analysis on the target evaluation unit to obtain the spatial interaction relationship between the farmland ecological resilience of the target evaluation unit and the grain yield of other surrounding evaluation units; the spatial interaction relationship includes four types: high-high region, high-low region, low-high region, and low-low region.

[0039] The formula for calculating the spatial interaction relationship is:

[0040] ;

[0041] in, I The global autocorrelation coefficient is a bivariate coefficient. t For the total number of grid cells, This is the spatial weight matrix; and These are the variables: farmland ecological resilience In grid Values ​​and grain yield In grid The value; This represents the variance of farmland ecological resilience and grain yield.

[0042] In one optional implementation, S5 includes:

[0043] S51. Set the high-high area as a high priority construction area, the high-low and low-high areas as secondary priority construction areas, and the low-low area as a non-priority construction area.

[0044] S52. Using self-organizing mapping neural networks and K-means, the standardized values ​​corresponding to each evaluation index are clustered into three main areas: soil fertility improvement, drought and flood resistance, and land leveling.

[0045] S53. Based on S52 and S53, a time-series optimization scheme for high-standard farmland construction is obtained.

[0046] The present invention has the following beneficial effects:

[0047] This invention addresses the issue of prioritizing high-standard farmland construction. Spatially, it establishes a comprehensive evaluation model driven by the fusion of multi-source heterogeneous data. By coupling data from remote sensing imagery, topography, meteorological factors, and soil moisture, it establishes a dual-objective collaborative framework for grain production capacity and ecological resilience. Bivariate spatial autocorrelation analysis is used to analyze the spatial interaction effects of evaluation indicators, enabling precise identification of priority construction areas. Temporally, it employs an entropy weighting method-multiple correlation coefficient integrated weighting model to objectively quantify the weights of indicators such as production capacity enhancement potential and ecological resilience, generating a phased construction sequence for high-standard farmland and achieving effective, phased advancement of permanent basic farmland transformation. Attached Figure Description

[0048] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating a method for optimizing the timing of high-standard farmland construction according to an embodiment of the present invention.

[0050] Figure 2 This is a correlation diagram between bioclimatic variables and LAI according to an embodiment of the present invention;

[0051] Figure 3 This is a bivariate local spatial autocorrelation plot according to an embodiment of the present invention;

[0052] Figure 4This is a priority sequence diagram for the construction of high-standard farmland according to an embodiment of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] like Figure 1 As shown, this invention provides a method for optimizing the timing of high-standard farmland construction, comprising:

[0055] Step S1: Perform spatial overlay analysis on the permanent basic farmland distribution layer and the high standard farmland distribution layer to identify areas where high standard permanent basic farmland has not been built.

[0056] In one optional implementation, step S1 specifically includes:

[0057] The permanent basic farmland distribution layer and the high-standard farmland distribution layer are spatially overlaid. The high-standard farmland distribution layer is removed from the permanent basic farmland distribution layer by GIS difference operation, and the permanent basic farmland distribution layer that has not been built to a high standard is output.

[0058] Preferably, step S1 can be performed on a geographic information system (GIS) platform or a remote sensing data processing platform for spatial overlay analysis.

[0059] Using ArcGIS as an example, firstly, a permanent basic farmland distribution layer is imported into ArcGIS as the first data layer (A), and a high-standard farmland distribution layer is imported as the second data layer (B). The first data layer (A) contains the boundary range and attribute information of the permanent basic farmland, and the second data layer (B) contains the boundary range and attribute information of the high-standard farmland. Then, ArcGIS's "Erase Tool" is called, with the first data layer (A) as the input feature and the second data layer (B) as the eraser feature, to perform a spatial difference operation, generating a difference result layer (C). Finally, the difference result layer (C) is defined as the "Permanent Basic Farmland Distribution Layer Not Yet Built to High Standards," which contains the boundary range and attribute information of permanent basic farmland that has not met the high-standard farmland construction standards, thus obtaining the areas of permanent basic farmland not yet built to high standards.

[0060] Step S2: Obtain multi-source basic data for areas where high-standard permanent basic farmland has not yet been built; the multi-source basic data includes: LAI data (leaf area index), soil fertility improvement data, drought and flood disaster resistance data, and land leveling data; and reconstruct the LAI data using SG filtering to calculate the average LAI value during the crop growing season in areas where high-standard permanent basic farmland has not yet been built; the average LAI value is used to characterize grain yield.

[0061] Preferably, when removing the high-standard farmland distribution layer from the permanent basic farmland distribution layer, it is also necessary to remove sloping farmland with an inclination of more than 25 degrees, strictly controlled farmland, ecological protection red lines, and layers of farmland converted to forest, grassland, lake, or pasture, as these areas are strictly restricted from the construction of high-standard farmland.

[0062] For sloping farmland with an incline of 25 degrees or more, ASTER GDEM 30M resolution digital elevation data can be obtained from the geospatial data cloud. In the GIS platform, select 3D analyst tools→Raster surface→Slope to generate slope data. Set the data above 25 degrees to 0. Use a raster calculator to multiply the data with the distribution layer of permanent basic farmland that has not been built to a high standard, and remove sloping farmland with an incline of 25 degrees or more.

[0063] In one alternative implementation, the soil fertility enhancement data includes: soil organic matter, total soil nitrogen content, total soil phosphorus content, soil texture, soil pH, and soil bulk density; the drought and flood disaster resistance data includes: key climate factors, SPEI index (i.e., standardized precipitation evapotranspiration index), and distance to rivers and reservoirs; the land leveling data includes: sub-dimension index, elevation, slope, topographic relief, effective soil layer thickness, and road accessibility.

[0064] Preferably, LAI data can be collected in Google Earth Engine from the MCD15A3H dataset of the main crop growing season in areas where high-standard permanent basic farmland has not been built. This dataset contains LAI data with a spatial resolution of 500m and a temporal resolution of 8 days.

[0065] In one alternative implementation, the SPEI index is calculated using temperature and precipitation data obtained from the China Meteorological Administration Data Sharing Service Network; the key climate factors are obtained by performing correlation analysis between the LAI data and 19 bioclimatic variables, sorting them from high to low correlation, and selecting the top 5 bioclimatic variables.

[0066] Specifically, the calculation process for the SPEI index is as follows:

[0067] First, download monthly temperature and precipitation data from meteorological stations and use ANUSPLIN software to interpolate and obtain monthly potential evapotranspiration (PET). Second, install GDAL in Anaconda and call the corresponding function in Climate_Indices to calculate SPEI and obtain the raster-scale SPEI index.

[0068] It should be noted that when optimizing the construction timeline of standard farmland in areas where high-standard permanent basic farmland has not yet been built, the areas where high-standard permanent basic farmland has not yet been built need to be divided into multiple grids (plots), with each grid serving as an evaluation unit (for subsequent analysis and processing), and multi-source basic data should be acquired on a grid-by-grid basis.

[0069] There are a total of 19 bioclimatic variables (including extreme or limiting environmental factors), such as... Figure 2 The figures shown represent annual average temperature (Bio_1), average daily temperature range (Bio_2), isotherm (Bio_3), temperature seasonality (Bio_4), maximum temperature of the hottest month (Bio_5), minimum temperature of the coldest month (Bio_6), annual temperature range (Bio_7), average temperature of the wettest season (Bio_8), average temperature of the driest season (Bio_9), average temperature of the hottest season (Bio_10), average temperature of the coldest season (Bio_11), annual precipitation (Bio_12), precipitation of the wettest month (Bio_13), precipitation of the driest month (Bio_14), precipitation seasonality (Bio_15), precipitation of the wettest season (Bio_16), precipitation of the driest season (Bio_17), precipitation of the hottest season (Bio_18), and precipitation of the coldest season (Bio_19). Then, Spearman correlation analysis was performed on all 19 bioclimatic variables with LAI data, and they were ranked from high to low correlation. Finally, the top 5 bioclimatic variables were selected as key climate factors (those with the highest correlation).

[0070] Preferably, Bio_5, Bio_8, Bio_10, Bio_16 and Bio_18 are selected as key climate factors.

[0071] In addition, the distance to the river and reservoir is determined by using the "Euclidean distance" tool in ArcGIS to obtain the buffer raster data of the river and reservoir. The "zonal statistics" tool is then used to perform distance statistics to obtain the minimum distance from each unit to be evaluated to the river and reservoir.

[0072] The dimensionality index is calculated using Fragstats software. The larger the dimensionality, the more complex the shape of the unit (plot) to be evaluated. The closer the value is to 1, the stronger the self-similarity of the plot, the more regular the shape, and the simpler it is, thus indicating that it is more susceptible to interference.

[0073] (1);

[0074] in, For the first The dimensions of each plot of land, For the first The perimeter of each plot of land, For the first The area of ​​each plot of land.

[0075] Road accessibility was assessed using the Near tool in ArcGIS → Analysis Tools → Proximity to obtain the minimum distance from each unit to the road.

[0076] Step S3: Based on multi-source basic data, construct an evaluation index system for the ecological resilience of high-standard farmland construction; and calculate the weights of each evaluation index by combining the entropy weight method and the CRITIC method, and establish a set pair analysis model to calculate the ecological resilience of farmland.

[0077] In one optional implementation, step S3 includes:

[0078] S31. Based on soil fertility improvement data, drought and flood disaster resistance data, and land leveling data, construct an ecological resilience evaluation index system for high-standard farmland construction.

[0079] As shown in Table 1, the evaluation index system for the ecological resilience of high-standard farmland construction includes the name of each evaluation index, its corresponding index value, source type, and index type. The index type is used to characterize the correlation between the index value corresponding to the evaluation index and the ecological resilience of farmland.

[0080] Table 1

[0081] ;

[0082] Specifically, the types of indicators can include positive indicators, negative indicators, and neutral indicators. Positive indicators indicate a positive correlation between the indicator value corresponding to the target evaluation indicator and the ecological resilience of farmland. Negative indicators indicate a negative correlation between the indicator value corresponding to the target evaluation indicator and the ecological resilience of farmland. Neutral indicators indicate how close the indicator value corresponding to the target evaluation indicator is to a set threshold. The closer the indicator value is to the threshold, the closer the evaluation target is to the ideal.

[0083] S32. Based on the correlation between the index values ​​corresponding to each evaluation indicator and the ecological resilience of farmland, the index values ​​corresponding to each evaluation indicator are standardized to obtain the standardized values ​​corresponding to each evaluation indicator.

[0084] In one optional implementation, the standardization process for the evaluation indicators is as follows:

[0085] When the correlation between the evaluation index value and the farmland ecological resilience is positive, the formula for calculating the standardized value is:

[0086] (2);

[0087] When the correlation between the evaluation index value and farmland ecological resilience is negative, the formula for calculating the standardized value is:

[0088] (3);

[0089] When the degree of closeness between the indicator value corresponding to the evaluation indicator and the set threshold meets the set limit, the formula for calculating the standardized value is:

[0090] (4);

[0091] in, For the first The indicator values ​​corresponding to each evaluation indicator; For multiple units to be evaluated The maximum value; For multiple units to be evaluated The minimum value; To set a threshold; This is a comparison operation between the maximum and minimum values.

[0092] S33. Based on step S32, calculate the combined weights of each evaluation index by combining the entropy weight method and the CRITIC method. ;in, W The set of combined weights for each evaluation indicator. For the first The combined weights of the evaluation indicators .

[0093] Preferably, the weights of each evaluation index are determined by a combination of the entropy weight method and the CRITIC method, and the combined weights are calculated using a multiplicative synthesis method, as follows:

[0094] (5);

[0095] in, For the first The combined weights of each evaluation indicator; The first one obtained by the entropy weight method The weight values ​​of each evaluation indicator; The first CRITIC method obtained The weight values ​​of each evaluation indicator.

[0096] S34. Based on S33, establish a set pair analysis model; and according to the set pair analysis model, calculate the farmland ecological resilience of each unit to be evaluated, that is, the relative fit of each unit to be evaluated with the optimal scheme set.

[0097] In one alternative implementation, S34 includes:

[0098] The evaluation of the ecological resilience of high-standard farmland is denoted as... ;in, To evaluate the set of schemes, The total number of evaluation schemes; For the evaluation index set, The total number of evaluation indicators; For the set of units to be evaluated, For the first One unit to be evaluated, The total number of units to be evaluated; within the same unit, the optimal evaluation index among the various evaluation schemes is determined to form the optimal scheme set. The worst evaluation index among all evaluation schemes constitutes the worst-case scheme set. ;

[0099] Set in The degree of connection on the surface is:

[0100] ;

[0101] in, For the first One evaluation scheme; , , These represent the similarity, difference, and opposition of the optimal and worst solution sets, respectively. , The first p Evaluation indicators With sets [ The degree of similarity and opposition, For the first The weight of each evaluation indicator;

[0102] Evaluation scheme With the optimal solution set Relative closeness That is, the ecological resilience of farmland is:

[0103] ;

[0104] reflect With the optimal solution set The degree of connectivity The larger the value, the closer the unit being evaluated is to the optimal solution, i.e. The higher the value, the greater the ecological resilience of high-standard farmland.

[0105] Step S4: Based on the bivariate local spatial autocorrelation analysis method, the spatial interaction relationship between grain yield and farmland ecological resilience is obtained.

[0106] In one alternative implementation, step S4 includes:

[0107] GeoDA software was used to perform bivariate local spatial autocorrelation analysis on the target evaluation unit to obtain the spatial interaction relationship between the farmland ecological resilience of the target evaluation unit and the grain yield of other surrounding evaluation units; the spatial interaction relationship includes four types: high-high region, high-low region, low-high region, and low-low region.

[0108] The formula for calculating the spatial interaction relationship is:

[0109] ;

[0110] in, I The global autocorrelation coefficient is a bivariate coefficient. t For the total number of grid cells, This is the spatial weight matrix; and These are the variables: farmland ecological resilience In grid Values ​​and grain yield In grid The value; The variances of farmland ecological resilience and grain yield are represented. The obtained bivariate local spatial autocorrelation plot is shown below. Figure 3 As shown.

[0111] Step S5: Based on spatial interaction relationships, combined with self-organizing map neural networks and K-means method, identify priority plots for high-standard farmland construction in areas where high-standard permanent basic farmland has not yet been built, and formulate a time-series optimization scheme for high-standard farmland construction.

[0112] In one alternative implementation, S5 includes:

[0113] S51. Set the high-high area as a high-priority construction area, the high-low and low-high areas as secondary-priority construction areas, and the low-low area as a non-priority construction area. Figure 4 As shown;

[0114] S52. Using self-organizing mapping neural networks and K-means, the standardized values ​​corresponding to each evaluation index are clustered into three main areas: soil fertility improvement, drought and flood resistance, and land leveling.

[0115] Specifically, a self-organizing mapping neural network and K-means were used. Self-organizing mapping analysis was performed using the Kohonen package in R, and K-means analysis was performed using SPSS. By clustering the standardized values ​​of the evaluation indicators for the three categories of soil fertility improvement, drought and flood resistance, and land leveling, the regions were divided into soil fertility improvement-dominant areas, drought and flood resistance-dominant areas, and land leveling-dominant areas.

[0116] S53. Based on S52 and S53, a time-series optimization scheme for high-standard farmland construction is obtained.

[0117] For example, based on the priority division in step S51 and the cluster analysis results in step S52, a time-series plan of "three-level stages, three categories of leading projects, and five implementation steps" is constructed. In the near term (1-3 years), the focus is on high-priority construction areas, and the work is promoted in categories according to the soil fertility improvement leading area (60%), drought and flood disaster resistance leading area (30%), and land leveling leading area (10%). Core projects such as deep tillage, canal seepage prevention, and field consolidation are implemented, along with supporting technology pre-research such as organic fertilizer substitution and intelligent irrigation system pilot projects. In the medium term (4-6 years), basic capacity building such as straw return to the field experiment and ecological ditch pre-laying is carried out in secondary priority construction areas. In the long term (7-10 years), ecological restoration and smart farmland base station deployment are promoted in non-priority construction areas. The innovative plan establishes an "engineering package" system and a digital twin platform, and achieves dynamic adjustments through annual NDVI remote sensing monitoring and ESG evaluation system. It is expected to improve the quality of arable land by 3.8 levels, achieve 100% irrigation guarantee rate, and reduce carbon emission intensity by 45% within 10 years, forming a three-dimensional control plan that integrates space, time, and type.

[0118] In summary, this invention addresses the issue of prioritizing high-standard farmland construction. Spatially, it establishes a comprehensive evaluation model driven by the fusion of multi-source heterogeneous data. By coupling data from remote sensing imagery, topography, meteorological factors, and soil moisture, it establishes a dual-objective collaborative framework for grain production capacity and ecological resilience. Bivariate spatial autocorrelation analysis is used to analyze the spatial interaction effects of evaluation indicators, enabling precise identification of priority construction areas. Temporally, it employs an entropy weighting method-multiple correlation coefficient integrated weighting model to objectively quantify the weights of indicators such as production capacity enhancement potential and ecological resilience, generating a phased construction sequence for high-standard farmland and achieving effective, phased advancement of permanent basic farmland transformation.

[0119] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for optimizing the construction sequence of high-standard farmland, characterized in that, include: S1. Perform spatial overlay analysis on the permanent basic farmland distribution layer and the high standard farmland distribution layer to identify areas where high standard permanent basic farmland has not been built. S2. Obtain multi-source basic data for areas where high-standard permanent basic farmland has not yet been built; wherein, the multi-source basic data includes: LAI data, soil fertility improvement data, drought and flood disaster resistance data, and land leveling data; and, reconstruct the LAI data using SG filtering, and calculate the average LAI value during the crop growing season in areas where high-standard permanent basic farmland has not yet been built; the average LAI value is used to characterize grain yield; S3. Based on multi-source basic data, construct an evaluation index system for the ecological resilience of high-standard farmland construction; and calculate the weights of each evaluation index by combining the entropy weight method and the CRITIC method, and establish a set pair analysis model to calculate the ecological resilience of farmland. S3 includes: S31. Based on soil fertility improvement data, drought and flood disaster resistance data, and land leveling data, construct an ecological resilience evaluation index system for high-standard farmland construction; wherein, the ecological resilience evaluation index system for high-standard farmland construction includes the name of each evaluation index, the corresponding index value, the source type, and the index type to which it belongs; the index type is used to characterize the correlation between the index value corresponding to the evaluation index and the ecological resilience of farmland; S32. Based on the correlation between the index values ​​corresponding to each evaluation indicator and the ecological resilience of farmland, the index values ​​corresponding to each evaluation indicator are standardized to obtain the standardized values ​​corresponding to each evaluation indicator. S33. Based on S32, calculate the combined weight of each evaluation index by combining the entropy weight method and the CRITIC method. S34. Based on S33, establish a set pair analysis model; and calculate the farmland ecological resilience of each unit to be evaluated according to the set pair analysis model. S34 includes: The evaluation of the ecological resilience of high-standard farmland is denoted as... ;in, To evaluate the set of solutions, The total number of evaluation schemes; For the evaluation index set, The total number of evaluation indicators; For the set of units to be evaluated, For the first One unit to be evaluated, The total number of units to be evaluated; within the same unit, the optimal evaluation index among the various evaluation schemes is determined to form the optimal scheme set. The worst evaluation index among all evaluation schemes constitutes the worst-case scheme set. ; in, , These represent the degree of similarity and the degree of opposition between the optimal and worst solution sets, respectively. , The first Evaluation indicators With sets [ The degree of similarity and opposition, For the first The weight of each evaluation indicator; Evaluation scheme With the optimal solution set Relative closeness for: in, For the evaluation scheme set One evaluation scheme, ; S4. Based on the bivariate local spatial autocorrelation analysis method, the spatial interaction relationship between the grain yield and the farmland ecological resilience is obtained; S4 includes: GeoDA software was used to perform bivariate local spatial autocorrelation analysis on the target evaluation unit to obtain the spatial interaction relationship between the farmland ecological resilience of the target evaluation unit and the grain yield of other surrounding evaluation units; the spatial interaction relationship includes four types: high-high region, high-low region, low-high region, and low-low region. The formula for calculating the spatial interaction relationship is: in, The global autocorrelation coefficient is a bivariate coefficient. For the total number of grid cells, This is the spatial weight matrix; and These are the variables: farmland ecological resilience In grid Values ​​and grain yield In grid The value; The variance of farmland ecological resilience and grain yield; S5. Based on the spatial interaction relationship, combined with the self-organizing map neural network and the K-means method, priority plots for the construction of high-standard farmland in areas where high-standard permanent basic farmland has not yet been built are identified, and a time-series optimization scheme for the construction of high-standard farmland is formed. A three-tiered, three-category, and five-part implementation timeline is proposed. In the near term (1-3 years), the focus will be on high-priority development areas, with the implementation categorized into three areas: 60% for soil fertility improvement, 30% for drought and flood resistance, and 10% for land leveling.

2. The method according to claim 1, characterized in that, S1 specifically includes: The permanent basic farmland distribution layer and the high-standard farmland distribution layer are spatially overlaid. The high-standard farmland distribution layer is removed from the permanent basic farmland distribution layer by GIS difference operation, and the permanent basic farmland distribution layer that has not been built to a high standard is output.

3. The method according to claim 1, characterized in that, The soil fertility improvement data includes: soil organic matter, total nitrogen content, total phosphorus content, soil texture, soil pH value, and soil bulk density; The drought and flood disaster mitigation data includes: key climate factors, SPEI index, and distance to rivers and reservoirs; The land leveling data includes: dimensional index, elevation, slope, topographic relief, effective soil layer thickness, and road accessibility.

4. The method according to claim 3, characterized in that, The SPEI index was calculated using temperature and precipitation data obtained from the China Meteorological Administration's data sharing service network. The key climate factors were obtained by performing correlation analysis between the LAI data and 19 bioclimatic variables, sorting them from high to low correlation, and selecting the top 5 bioclimatic variables.

5. The method according to claim 1, characterized in that, The standardization process for the evaluation indicators is as follows: When the correlation between the evaluation index value and the farmland ecological resilience is positive, the formula for calculating the standardized value is: When the correlation between the evaluation index value and farmland ecological resilience is negative, the formula for calculating the standardized value is: When the degree of closeness between the indicator value corresponding to the evaluation indicator and the set threshold meets the set limit, the formula for calculating the standardized value is: in, For the first The indicator values ​​corresponding to each evaluation indicator; For multiple units to be evaluated The maximum value; For multiple units to be evaluated The minimum value; To set a threshold; This is a comparison operation between the maximum and minimum values.

6. The method according to claim 1, characterized in that, S5 includes: S51. Set the high-high area as a high priority construction area, the high-low and low-high areas as secondary priority construction areas, and the low-low area as a non-priority construction area. S52. Using self-organizing mapping neural networks and K-means, the standardized values ​​corresponding to each evaluation index are clustered into three main areas: soil fertility improvement, drought and flood resistance, and land leveling. S53. Based on S52 and S53, a time-series optimization scheme for high-standard farmland construction is obtained.

Images