Digital twinborn-based rural construction land scale prediction method

Abstract

The invention relates to the technical field of land planning and prediction, and particularly discloses a digital twinborn-based rural construction land scale prediction method, which comprises the following steps of: collecting geographic information data of N alternative villages to construct a terrain twinborn model of each alternative village; based on the terrain twinborn model of each alternative country, extracting each environment parameter corresponding to each alternative country; analyzing the expansion possibility of the construction land of each alternative country, and identifying the expansion area of each alternative country corresponding to each future time point; therefore, the target expanded villages are screened out, centralized resources are facilitated for key development, the efficiency and effect of village construction are improved, and regional balanced development can be promoted. The method is helpful for evaluating the development potential of each country, and also can provide a scientific basis for reasonable configuration of land resources.

Description

Technical Field

[0001] The present invention belongs to the technical field of land use planning and prediction, and relates to a method for predicting the scale of rural construction land based on digital twins. Background Art

[0002] The scale forecast of rural construction land is extremely necessary and important in modern society. With the growth of population and the acceleration of urbanization, the demand for land in rural areas is increasing. Through accurate forecasting, the waste and unreasonable use of land resources can be avoided and the sustainable development of land resources can be ensured. Secondly, the scale forecast of rural construction land is helpful to improve rural infrastructure and public services. By predicting future land demand, necessary infrastructure such as roads, water, electricity, and communications can be planned and constructed in advance, thereby improving the quality of life of rural residents and promoting the development of the rural economy.

[0003] The current technology still has certain limitations in selecting target expansion villages. It is impossible to effectively screen the target expansion villages by analyzing the alternative villages. To a certain extent, it is not conducive to improving the selection efficiency and intelligence level of target expansion villages. It cannot effectively guarantee the comprehensiveness of the selection of target expansion villages, and cannot effectively guarantee the scientificity and reliability of the selection of target expansion villages. It also cannot provide accurate data for the follow-up and cannot improve the accuracy of the selection of target expansion villages. Summary of the invention

[0004] In view of the above problems existing in the prior art, the present invention provides a rural construction land scale prediction method based on digital twins, which is used to solve the above technical problems.

[0005] In order to achieve the above purpose and other purposes, the technical solution adopted by the present invention is as follows: The present invention provides a method for predicting the scale of rural construction land based on digital twins, which comprises the following steps: Step 1: Collect geographic information data of N candidate villages, and construct a terrain twin model of each candidate village; Step 2: Based on the terrain twin model of each candidate village, extract the environmental parameters corresponding to each candidate village; Step 3: Analyze the possibility of expansion of construction land for each candidate village, and identify the expansion area of ​​each candidate village at each future time point; Step 4: Based on the expansion area of ​​each candidate village at each future time point, select the target expansion village.

[0006] In the preferred technical solution of the present application, the geographic information data of each candidate village includes altitude, slope, vegetation coverage area, geographical location superiority and population size.

[0007] In the preferred technical solution of this application, a terrain twin model of each candidate village is constructed, including: Interpolate the altitude and slope data of each candidate village to fill in missing values ​​and eliminate noise; classify and filter the vegetation coverage data to determine the distribution of different types of vegetation; spatially register the geographic location superiority data of each candidate village to ensure spatial consistency between different data layers; and spatially process the population data of each candidate village; The altitude and slope data of each candidate village are integrated through the GIS platform to generate a three-dimensional terrain model of each candidate village; the vegetation coverage area data is superimposed on the three-dimensional terrain model of each candidate village to generate a terrain model with real vegetation coverage area; the geographical location superiority data of each candidate village is combined to enrich the details of the model; finally, the population data of each candidate village is combined with the model to generate a terrain twin model of each candidate village.

[0008] Verify the constructed terrain twin models of each candidate village, and verify and calibrate the models; conduct field surveys on the actual geographic information data of each candidate village, and revise and adjust the terrain twin models of each candidate village based on the data.

[0009] In the preferred technical solution of this application, the environmental parameters corresponding to each candidate village are extracted, including: Each environmental parameter is specifically divided into patch density assessment coefficient, landscape shape assessment coefficient and patch cohesion assessment coefficient; Based on the terrain twin model of each candidate village, the total number of land patches M and the area of ​​each land patch in each candidate village are obtained. ,perimeter and frequency , i is the number of each candidate village, i=1,2,...N, j is the number of each land patch, j=1,2,...M; Thus, the patch density assessment coefficients corresponding to each candidate village are obtained in turn. , Landscape shape evaluation coefficient and plaque binding evaluation coefficient , is the total area of ​​the i-th alternative village.

[0010] In the preferred technical solution of this application, the possibility of expansion of each alternative rural construction land is analyzed, including: Obtain the rural expansion impact index corresponding to geographic information data; Combined with the patch density assessment coefficient, landscape shape assessment coefficient and patch integration assessment coefficient corresponding to each candidate village, the expansion potential assessment coefficient of each candidate village is comprehensively calculated. , is the rural expansion impact index corresponding to the geographic information data, They are the weight factors corresponding to the patch density assessment coefficient, landscape shape assessment coefficient, patch integration assessment coefficient and rural expansion impact index.

[0011] In a preferred technical solution of this application, obtaining the rural expansion impact index corresponding to the geographic information data includes: Extract the altitude, slope, vegetation coverage, geographical location and population of each expanded village from the historical database; The altitude of each expanded village To standardize the process, , get the standardized altitude of each expanded village ; d is the number of each expanded village, d=1,2,...D; Similarly, the standardized slope, standardized vegetation coverage, standardized geographical location superiority and standardized population of each expanded village are obtained; Determine the weight of each geographic information data, and take the weighted sum of the standardized altitude, standardized slope, standardized vegetation coverage area, standardized geographical location superiority and standardized population size of each expanded village with the corresponding weight to obtain the rural expansion impact index corresponding to the geographic information data.

[0012] In the preferred technical solution of the present application, the weight factors corresponding to the patch density assessment coefficient, the landscape shape assessment coefficient, the patch integration assessment coefficient and the rural expansion impact index are specifically calculated as follows: Obtain the initial patch density assessment coefficient of each expanded village at each expansion , initial landscape shape evaluation coefficient and initial plaque binding evaluation coefficient , k is the number of expansion times, k=1,2,...B; Get the expansion frequency of each expanded village at each expansion ; By analyzing the formula The correlation coefficient between the initial patch density assessment coefficient of the expanded villages at each expansion and the expansion frequency was obtained by analysis. , sum them up to get the sum of the correlation coefficients between the initial patch density assessment coefficient and the expansion frequency corresponding to the expanded village ; Similarly, the sum of the correlation coefficients of the initial landscape shape assessment coefficient and the initial patch integration assessment coefficient corresponding to the expanded village and the expansion frequency are calculated and recorded as and ; Obtain the initial altitude, initial slope, initial vegetation coverage, initial geographical location superiority and initial population of each expanded village at each expansion, calculate the initial rural expansion impact index of each expanded village at each expansion, and similarly calculate the sum of the correlation coefficients between the initial rural expansion impact index and the expansion frequency of the expanded village ; Then solve the weight factor corresponding to the plaque density assessment coefficient ; Weight factor corresponding to the landscape shape assessment coefficient ; Weight factor corresponding to the plaque binding evaluation coefficient ; Weight factor corresponding to the rural expansion impact index .

[0013] In the preferred technical solution of this application, the expansion area of ​​each candidate village corresponding to each future time point is identified, including: Based on the expansion potential evaluation coefficient of each candidate village, select the villages to be expanded; Each rural area to be expanded is divided into a number of cells, and each cell has a corresponding initial state, where the initial state value is divided into 0 and 1; 0 represents undeveloped land, and 1 represents construction land; Divide each rural area to be expanded into a number of cells and number them in sequence, 1, 2, ...u, ...q; Indicates that at the current time point t, the initial state of the u-th cell corresponding to the f-th prepared expansion village, It indicates the number of construction land cells in the neighborhood of the u-th cell corresponding to the f-th village to be expanded at the current time point t, where f is the number of the village to be expanded; Then establish the state transition rules for the corresponding cells of each prepared expansion village ; n is the number of preset intervals h between the current time point t and each future time point, and h is the preset interval length; The expansion area of ​​each planned expansion village corresponding to each future time point is calculated , is an indicator function that takes the value 1 when its condition is true, otherwise it is 0.

[0014] In the preferred technical solution of this application, target expansion villages are selected, including: Get the expansion area of ​​each planned expansion village at each future time point , calculate the expansion rate of each planned expansion village at each future time point , The fth prepared expansion village corresponds to the t+(n+1)th The expansion area at h future time points; The expansion rates of each planned expansion village corresponding to each future time point are averaged and calculated to obtain the average expansion rate of each planned expansion village corresponding to the future time point. The planned expansion villages are ranked based on the average expansion rate, and the planned expansion village with the highest average expansion rate at the future time point is selected as the target expansion village.

[0015] As described above, the method for predicting the scale of rural construction land based on digital twins provided by the present invention has at least the following beneficial effects: (1) The method for predicting the scale of rural construction land based on digital twins provided by the present invention can provide a scientific and systematic method for rural planning and development by collecting geographic information data of N candidate villages and constructing a terrain twin model of each candidate village. The terrain twin model can accurately simulate and reproduce the topography of each village, so that planners can more intuitively understand the geographical characteristics and environmental conditions of each village. This accurate terrain simulation not only helps to identify the advantages and disadvantages of the terrain, but also provides a reliable data basis for the subsequent extraction of environmental parameters.

[0016] (2) The embodiment of the present invention can predict the expansion area of ​​each village at different future time points by analyzing the expansion possibility of each candidate village construction land. This prediction not only helps to evaluate the development potential of each village, but also provides a scientific basis for the rational allocation of land resources. By identifying the possible expansion areas of each village in the future, planners can formulate land use plans in advance to avoid resource waste and environmental damage caused by disorderly expansion; this not only helps to concentrate resources for key development and improve the efficiency and effectiveness of rural construction, but also promotes balanced regional development and narrows the urban-rural gap. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 It is a schematic diagram of the connection of each step of the method of the present invention. DETAILED DESCRIPTION

[0019] The above contents in combination with the implementation of the present invention are merely examples and explanations of the concept of the present invention. The technical personnel in the relevant technical field may make various modifications or supplements to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

[0020] Example 1 See also Figure 1 As shown, a method for predicting the scale of rural construction land based on digital twins includes the following steps: Step 1: Collect geographic information data of N candidate villages, and construct a terrain twin model of each candidate village; Based on the above scheme, the geographic information data of each candidate village includes altitude, slope, vegetation coverage area, geographical location superiority and population size.

[0021] The superiority of geographical location refers to the position of a region in geographical space and its related natural, economic and social characteristics, which have an impact on the region's development potential, economic activities, social structure and other aspects; specifically, it may include natural location factors: including climate conditions, hydrological resources, etc.; economic location factors: involving transportation conditions, labor supply, technological level, etc.

[0022] Altitude data can be obtained through digital elevation models (DEM), which are usually collected through satellite remote sensing, LiDAR or drone aerial photography. Slope data is obtained by spatial analysis of altitude data. Vegetation coverage area data can be classified and analyzed through remote sensing images. Common remote sensing data sources include Landsat, Sentinel, etc. The superiority of geographical location involves information such as geographical coordinates, transportation network, water source distribution, etc., which can be integrated through the geographic information system (GIS) platform. Population data can be obtained through statistical data from the National Bureau of Statistics or local governments.

[0023] Based on the above schemes, a terrain twin model of each candidate village is constructed, including: Interpolate the altitude and slope data of each candidate village to fill in missing values ​​and eliminate noise; classify and filter the vegetation coverage data to determine the distribution of different types of vegetation; spatially register the geographic location superiority data of each candidate village to ensure spatial consistency between different data layers; and spatially process the population data of each candidate village; The altitude and slope data of each candidate village are integrated through the GIS platform to generate a three-dimensional terrain model of each candidate village; the vegetation coverage area data is superimposed on the three-dimensional terrain model of each candidate village to generate a terrain model with real vegetation coverage area; the geographical location superiority data of each candidate village is combined to enrich the details of the model; finally, the population data of each candidate village is combined with the model to generate a terrain twin model of each candidate village.

[0024] Verify the constructed terrain twin models of each candidate village, and verify and calibrate the models; conduct field surveys on the actual geographic information data of each candidate village, and revise and adjust the terrain twin models of each candidate village based on the data.

[0025] Step 2: Based on the terrain twin model of each candidate village, extract the environmental parameters corresponding to each candidate village; Based on the above scheme, the environmental parameters corresponding to each candidate village are extracted, including: Each environmental parameter is specifically divided into patch density assessment coefficient, landscape shape assessment coefficient and patch cohesion assessment coefficient; Based on the terrain twin model of each candidate village, the total number of land patches M and the area of ​​each land patch in each candidate village are obtained. ,perimeter and frequency , i is the number of each candidate village, i=1,2,...N, j is the number of each land patch, j=1,2,...M; Based on the terrain twin model of each candidate village, a reverse digital terrain model (RDTM) of each candidate village is established, with the average elevation of the DTM as the benchmark; in the reverse digital terrain model of each candidate village, the elevation maximum points of each candidate village are extracted, and these points are the key to identifying patches; three terrain factors, namely elevation, terrain undulation and slope, are selected, and the weights of these terrain factors are determined by the entropy weight method; the weighted method is used to obtain the comprehensive membership of the terrain factors, and the threshold is determined by the comprehensive membership of the multi-window terrain factors; thereby locating the position of each land patch in each candidate village, and further obtaining the area and perimeter of each land patch in each candidate village.

[0026] Thus, the patch density assessment coefficients corresponding to each candidate village are obtained in turn. , Landscape shape evaluation coefficient and plaque binding evaluation coefficient , is the total area of ​​the i-th alternative village.

[0027] Step 3: Analyze the possibility of expansion of construction land for each candidate village, and identify the expansion area of ​​each candidate village at each future time point; Based on the above options, the feasibility of expanding the alternative rural construction land is analyzed, including: Obtain the rural expansion impact index corresponding to geographic information data; Combined with the patch density assessment coefficient, landscape shape assessment coefficient and patch integration assessment coefficient corresponding to each candidate village, the expansion potential assessment coefficient of each candidate village is comprehensively calculated. , is the rural expansion impact index corresponding to the geographic information data, They are the weight factors corresponding to the patch density assessment coefficient, landscape shape assessment coefficient, patch integration assessment coefficient and rural expansion impact index.

[0028] Based on the above scheme, the rural expansion impact index corresponding to the geographic information data is obtained, including: Extract the altitude, slope, vegetation coverage, geographical location and population of each expanded village from the historical database; The altitude of each expanded village To standardize the process, , get the standardized altitude of each expanded village ; d is the number of each expanded village, d=1,2,...D; Similarly, the standardized slope, standardized vegetation coverage, standardized geographical location superiority and standardized population of each expanded village are obtained; Determine the weight of each geographic information data, and take the weighted sum of the standardized altitude, standardized slope, standardized vegetation coverage area, standardized geographical location superiority and standardized population size of each expanded village with the corresponding weight to obtain the rural expansion impact index corresponding to the geographic information data.

[0029] The calculation method of the weight of each geographic information data is the same as the calculation method of the weight factor corresponding to the patch density assessment coefficient.

[0030] Based on the above scheme, the weight factors corresponding to the patch density assessment coefficient, landscape shape assessment coefficient, patch integration assessment coefficient and rural expansion impact index are calculated as follows: Obtain the initial patch density assessment coefficient of each expanded village at each expansion , initial landscape shape evaluation coefficient and initial plaque binding evaluation coefficient , k is the number of expansion times, k=1,2,...B; Calculate the population growth rate and land use change rate of each expanded village in each expansion; use a multivariate regression model

[0031] The population growth rate and land use change rate of each expanded village in each historical expansion are put back into the multivariate regression model to obtain the constant term The value and regression coefficient and 2, and the population growth rate and land use change rate of each expanded village during each expansion were introduced into the multivariate regression model to obtain the expansion frequency of each expanded village during each expansion.

[0032] Get the expansion frequency of each expanded village at each expansion ; By analyzing the formula The correlation coefficient between the initial patch density assessment coefficient of the expanded villages at each expansion and the expansion frequency was obtained by analysis. , sum them up to get the sum of the correlation coefficients between the initial patch density assessment coefficient and the expansion frequency corresponding to the expanded village ; Similarly, the sum of the correlation coefficients of the initial landscape shape assessment coefficient and the initial patch integration assessment coefficient corresponding to the expanded village and the expansion frequency are calculated and recorded as and ; Obtain the initial altitude, initial slope, initial vegetation coverage, initial geographical location superiority and initial population of each expanded village at each expansion, calculate the initial rural expansion impact index of each expanded village at each expansion, and similarly calculate the sum of the correlation coefficients between the initial rural expansion impact index and the expansion frequency of the expanded village ; Then solve the weight factor corresponding to the plaque density assessment coefficient ; Weight factor corresponding to the landscape shape assessment coefficient ; Weight factor corresponding to the plaque binding evaluation coefficient ; Weight factor corresponding to the rural expansion impact index .

[0033] Based on the above schemes, the expansion area of ​​each candidate village corresponding to each future time point is identified, including: Based on the expansion potential evaluation coefficient of each candidate village, select the villages to be expanded; Each rural area to be expanded is divided into a number of cells, and each cell has a corresponding initial state, where the initial state value is divided into 0 and 1; 0 represents undeveloped land, and 1 represents construction land; Divide each rural area to be expanded into a number of cells and number them in sequence, 1, 2, ...u, ...q; Indicates that at the current time point t, the initial state of the u-th cell corresponding to the f-th prepared expansion village, It indicates the number of construction land cells in the neighborhood of the u-th cell corresponding to the f-th village to be expanded at the current time point t, where f is the number of the village to be expanded; Then establish the state transition rules for the corresponding cells of each prepared expansion village ; n is the number of preset intervals h between the current time point t and each future time point, and h is the preset interval length; The state transition rule is that the condition for an undeveloped land cell (state 0) to be converted into a construction land cell (state 1) is that at least three of its neighbors are construction land cells (state 1).

[0034] The expansion area of ​​each planned expansion village corresponding to each future time point is calculated , is an indicator function that takes the value 1 when its condition is true, otherwise it is 0.

[0035] Indicator function Used to check whether each cell is in the construction land cell (state 1). If the state of cell p at the current time point t is 1, the indicator function is 1; otherwise the indicator function is 0; The summation operation traverses the entire grid and counts the number of cells that are in the rural land state; the counted number of rural land cells is multiplied by the area of ​​each cell to obtain the expansion area of ​​each candidate village corresponding to each future time point.

[0036] Step 4: Based on the expansion area of ​​each candidate village at each future time point, select the target expansion village.

[0037] Based on the above options, we selected target villages for expansion, including: Get the expansion area of ​​each planned expansion village at each future time point , calculate the expansion rate of each planned expansion village at each future time point , The fth prepared expansion village corresponds to the t+(n+1)th The expansion area at h future time points; The expansion rates of each planned expansion village corresponding to each future time point are averaged and calculated to obtain the average expansion rate of each planned expansion village corresponding to the future time point. The planned expansion villages are ranked based on the average expansion rate, and the planned expansion village with the highest average expansion rate at the future time point is selected as the target expansion village.

[0038] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0039] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0040] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0041] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting the scale of rural construction land based on digital twins, characterized in that: include: Collect geographic information data of N candidate villages, and construct terrain twin models of each candidate village; Based on the terrain twin model of each candidate village, the environmental parameters corresponding to each candidate village are extracted; Analyze the possibility of expansion of construction land in each candidate village, and identify the expansion area of ​​each candidate village at each future time point; Based on the expansion area of ​​each candidate village at each future time point, the target expansion villages are selected.

2. According to a method for predicting the scale of rural construction land based on digital twins according to claim 1, it is characterized in that: The geographic information data of each candidate village includes altitude, slope, vegetation coverage area, geographical location superiority and population size.

3. According to a method for predicting the scale of rural construction land based on digital twins according to claim 2, it is characterized in that: Construct terrain twin models for each candidate village, including: Interpolate the altitude and slope data of each candidate village to fill in missing values ​​and eliminate noise; classify and filter the vegetation coverage data to determine the distribution of different types of vegetation; spatially register the geographic location superiority data of each candidate village to ensure spatial consistency between different data layers; and spatially process the population data of each candidate village; The altitude and slope data of each candidate village are integrated through the GIS platform to generate a three-dimensional terrain model of each candidate village; the vegetation coverage area data is superimposed on the three-dimensional terrain model of each candidate village to generate a terrain model with real vegetation coverage area; the geographical location superiority data of each candidate village is combined to enrich the details of the model; finally, the population data of each candidate village is combined with the model to generate a terrain twin model of each candidate village; Verify the constructed terrain twin models of each candidate village, and verify and calibrate the models; conduct field surveys on the actual geographic information data of each candidate village, and revise and adjust the terrain twin models of each candidate village based on the data.

4. The method for predicting the scale of rural construction land based on digital twin according to claim 1 is characterized in that: Extract the environmental parameters corresponding to each candidate village, including: Each environmental parameter is specifically divided into patch density assessment coefficient, landscape shape assessment coefficient and patch cohesion assessment coefficient; Based on the terrain twin model of each candidate village, the total number of land patches M and the area of ​​each land patch in each candidate village are obtained. ,perimeter and frequency , i is the number of each candidate village, i=1,2,...N, j is the number of each land patch, j=1,2,...M; Thus, the patch density assessment coefficients corresponding to each candidate village are obtained in turn. , Landscape shape evaluation coefficient and plaque binding evaluation coefficient , is the total area of ​​the i-th alternative village.

5. The method for predicting the scale of rural construction land based on digital twin according to claim 1 is characterized in that: Analyze the possibility of expansion of each alternative rural construction land, including: Obtain the rural expansion impact index corresponding to geographic information data; Combined with the patch density assessment coefficient, landscape shape assessment coefficient and patch integration assessment coefficient corresponding to each candidate village, the expansion potential assessment coefficient of each candidate village is comprehensively calculated. , is the rural expansion impact index corresponding to the geographic information data, They are the weight factors corresponding to the patch density assessment coefficient, landscape shape assessment coefficient, patch integration assessment coefficient and rural expansion impact index.

6. The method for predicting the scale of rural construction land based on digital twins according to claim 5 is characterized in that: Obtain the rural expansion impact index corresponding to geographic information data, including: Extract the altitude, slope, vegetation coverage, geographical location and population of each expanded village from the historical database; The altitude of each expanded village To standardize the process, , get the standardized altitude of each expanded village ; d is the number of each expanded village, d=1,2,...D; Similarly, the standardized slope, standardized vegetation coverage, standardized geographical location superiority and standardized population of each expanded village are obtained; Determine the weight of each geographic information data, and take the weighted sum of the standardized altitude, standardized slope, standardized vegetation coverage area, standardized geographical location superiority and standardized population size of each expanded village with the corresponding weight to obtain the rural expansion impact index corresponding to the geographic information data.

7. The method for predicting the scale of rural construction land based on digital twin according to claim 5 is characterized by: The weight factors corresponding to the patch density assessment coefficient, landscape shape assessment coefficient, patch integration assessment coefficient and rural expansion impact index are calculated as follows: Obtain the initial patch density assessment coefficient of each expanded village at each expansion , initial landscape shape evaluation coefficient and initial plaque binding evaluation coefficient , k is the number of expansion times, k=1,2,...B; Get the expansion frequency of each expanded village at each expansion ; By analyzing the formula The correlation coefficient between the initial patch density assessment coefficient of the expanded villages at each expansion and the expansion frequency was obtained by analysis. , sum them up to get the sum of the correlation coefficients between the initial patch density assessment coefficient and the expansion frequency corresponding to the expanded village ; Similarly, the sum of the correlation coefficients of the initial landscape shape assessment coefficient and the initial patch integration assessment coefficient corresponding to the expanded village and the expansion frequency are calculated and recorded as and ; Obtain the initial altitude, initial slope, initial vegetation coverage, initial geographical location superiority and initial population of each expanded village at each expansion, calculate the initial rural expansion impact index of each expanded village at each expansion, and similarly calculate the sum of the correlation coefficients between the initial rural expansion impact index and the expansion frequency of the expanded village ; Then solve the weight factor corresponding to the plaque density assessment coefficient ; Weight factor corresponding to the landscape shape assessment coefficient ; Weight factor corresponding to the plaque binding evaluation coefficient ; Weight factor corresponding to the rural expansion impact index .

8. The method for predicting the scale of rural construction land based on digital twin according to claim 1 is characterized in that: Identify the expansion area of ​​each candidate village at each future time point, including: Based on the expansion potential evaluation coefficient of each candidate village, select the villages to be expanded; Each rural area to be expanded is divided into a number of cells, and each cell has a corresponding initial state, where the initial state value is divided into 0 and 1; 0 represents undeveloped land, and 1 represents construction land; Divide each rural area to be expanded into a number of cells and number them in sequence, 1, 2, ...u, ...q; Indicates that at the current time point t, the initial state of the u-th cell corresponding to the f-th prepared expansion village, It indicates the number of construction land cells in the neighborhood of the u-th cell corresponding to the f-th village to be expanded at the current time point t, where f is the number of the village to be expanded; Then establish the state transition rules for the corresponding cells of each prepared expansion village ; n is the number of preset intervals h between the current time point t and each future time point, and h is the preset interval length; The expansion area of ​​each planned expansion village corresponding to each future time point is calculated , is an indicator function that takes the value 1 when its condition is true, otherwise it is 0.

9. The method for predicting the scale of rural construction land based on digital twins according to claim 8 is characterized in that: Select target villages for expansion, including: Get the expansion area of ​​each planned expansion village at each future time point , calculate the expansion rate of each planned expansion village at each future time point , The fth prepared expansion village corresponds to the t+(n+1)th The expansion area at h future time points; The expansion rates of each planned expansion village corresponding to each future time point are averaged and calculated to obtain the average expansion rate of each planned expansion village corresponding to the future time point. The planned expansion villages are ranked based on the average expansion rate, and the planned expansion village with the highest average expansion rate at the future time point is selected as the target expansion village.

Images