Method for identifying community space evolution driving factor weight range

Abstract

The invention relates to a method for identifying a community spatial evolution driving factor weight range. The method comprises the following steps: acquiring first-stage spatial element data, second-stage spatial element data, spatial evolution driving factor data and third-stage spatial element data of at least two sample communities; calculating a space element transfer matrix according to the first-period space element data and the second-period space element data; calculating a driving factor weight data set according to the second-stage spatial element data and the spatial evolution driving factor data, and creating a suitability graph set according to the driving factor weight data set; simulating the third-period spatial evolution of the sample community according to the spatial element transfer matrix and the suitability atlas to obtain third-period spatial element simulation data of the sample community; and performing precision test on the third-period space element simulation data according to the third-period space element data to obtain the range of the third-period space evolution driving factor weight of the sample community. According to the method, the influence of space element types and driving factors on space evolution is comprehensively considered.

Description

Technical Field

[0001] The present invention belongs to the technical field of spatial evolution simulation, and in particular relates to a method for identifying the weight range of community spatial evolution driving factors. Background Art

[0002] As a spatial place, a community is a place where people live, interact and cooperate together. Changes in the community's spatial pattern are the result of the combined effect of multiple factors. By simulating the community's spatial layout, that is, changes in community spatial elements, and clarifying the correlation between community spatial elements and the driving factors of spatial element evolution, we can determine the direction of community space development and provide support for the scientific formulation of community space planning.

[0003] Existing spatial simulation related technologies use methods that couple models such as logistic regression, artificial neural networks, and multi-agent models with cellular automaton models, and focus the research objects mainly on the meso-scale and above, such as provinces, cities, and counties, or communities within a certain area such as provinces, cities, and counties. At the micro-scale, existing technologies have proposed relevant digital simulation methods from the perspectives of decision-making and behavior of different stakeholders, and the interaction between transportation and land use. However, there is a lack of research on the correlation between spatial elements and driving factors, and there are technical problems in the incomplete consideration of influencing factors. Summary of the invention

[0004] In view of the above analysis, an embodiment of the present invention aims to provide a method for identifying the weight range of community space evolution driving factors, so as to solve one or more of the above problems existing in the prior art.

[0005] The object of the present invention is achieved in that:

[0006] The first aspect of the present invention provides a method for identifying the weight range of community spatial evolution driving factors, comprising the following steps:

[0007] S1. Obtain the first-period spatial element data, the second-period spatial element data and spatial evolution driving factor data, and the third-period spatial element data of at least two sample communities;

[0008] S2. For each sample community, a spatial element transfer matrix is ​​calculated according to the first-phase spatial element data and the second-phase spatial element data;

[0009] S3, calculating a driving factor weight data set composed of spatial evolution driving factor weights corresponding to each spatial element according to the second-phase spatial element data and the spatial evolution driving factor data, and creating a suitability atlas composed of suitability images of each spatial element according to the driving factor weight data set;

[0010] S4, simulating the spatial evolution of the sample community in the third period according to the spatial element transfer matrix and the suitability atlas, and obtaining the spatial element simulation data of the sample community in the third period;

[0011] S5. Perform an accuracy check on the third-period spatial element simulation data according to the third-period spatial element data; if the accuracy is greater than the first preset threshold and less than the second preset threshold, return to step S3 to recalculate the spatial evolution driving factor weights corresponding to each spatial element; if the accuracy is greater than the second preset threshold, use the 3σ criterion to calculate the normal distribution of the driving factor weight data set to obtain the range of the third-period spatial evolution driving factor weights of the sample community.

[0012] Furthermore, the first-phase spatial element data, the second-phase spatial element data and the third-phase spatial element data all include residential land, industrial and mining land, cultivated land, forest land and land water areas that have undergone data preprocessing.

[0013] Furthermore, the second-phase spatial evolution driving factor data include constraints and decision variables, wherein the constraints include at least river waters, basic farmland, ancient trees, traditional buildings, family and religious belief buildings, and the decision variables include at least elevation, slope, distance from community main roads, distance from highways, and distance from industrial development areas.

[0014] Further, calculating a spatial element transfer matrix according to the first-period spatial element data and the second-period spatial element data includes:

[0015] By comparing the first-period spatial element data with the second-period spatial element data, the number of spatial elements of each type transformed into other types of spatial elements is analyzed, the transformation probability is calculated based on the number of transformations, and the spatial element transfer matrix is ​​constructed based on the transformation probability.

[0016] Furthermore, the step of calculating a driving factor weight dataset composed of spatial evolution driving factor weights corresponding to each spatial element according to the second-period spatial element data and the spatial evolution driving factor data, and creating a suitability atlas composed of suitability images of each spatial element according to the driving factor weight dataset includes:

[0017] Based on the second-phase spatial element data, the decision variables and constraints corresponding to each spatial element are input into the multi-criteria evaluation model; the fuzzy geometric function method is used to standardize the decision variables in the spatial evolution driving factor data; the hierarchical analysis method is used to construct the importance judgment matrix, and the standardized decision variables are weighted according to the importance judgment matrix to obtain the driving factor weight data set; the suitability score of each pixel in the sample community is weighted according to the driving factor weight data set to obtain a suitability atlas composed of the suitability images of each spatial element.

[0018] Furthermore, simulating the spatial evolution of the sample community in the third phase according to the spatial element transfer matrix and the suitability atlas includes:

[0019] With one year as an iteration cycle, the first period of spatial element data as the starting year, and the annual interval between the first period of spatial element data and the third period of spatial element data as the number of iterations, the spatial element transfer matrix and the suitability atlas are input into the spatial evolution simulation model to iteratively simulate the third period of spatial element distribution, so as to obtain the third period of spatial element simulation data.

[0020] Furthermore, the performing accuracy check on the third-period spatial element simulation data according to the third-period spatial element data includes:

[0021] A confusion matrix is ​​constructed based on the third-period spatial element data and the third-period spatial element simulation data; the actual accuracy and expected accuracy are calculated based on the confusion matrix; the Kappa coefficient is calculated based on the actual accuracy and expected accuracy to represent the accuracy.

[0022] Furthermore, if the accuracy is greater than the first preset threshold and less than the second preset threshold, return to step S3 to recalculate the spatial evolution driving factor weights corresponding to each spatial element; if the accuracy is greater than the second preset threshold, the 3σ criterion is used to calculate the normal distribution of the driving factor weight data set to obtain the range of the spatial evolution driving factor weights of the sample community in the third period.

[0023] A second aspect of the present invention provides a device for identifying a weight range of a driving factor for community spatial evolution, comprising:

[0024] A data acquisition module is used to acquire the first-period spatial element data, the second-period spatial element data and the spatial evolution driving factor data, and the third-period spatial element data of at least two sample communities;

[0025] A transfer matrix calculation module, used for calculating, for each sample community, a spatial element transfer matrix according to the first-phase spatial element data and the second-phase spatial element data;

[0026] A suitability atlas creation module is used to calculate a driving factor weight data set composed of spatial evolution driving factor weights corresponding to each spatial element based on the second-phase spatial element data and the spatial evolution driving factor data, and to create a suitability atlas composed of suitability images of each spatial element based on the driving factor weight data set;

[0027] A spatial element simulation module is used to simulate the spatial evolution of the sample community in the third period according to the spatial element transfer matrix and the suitability atlas to obtain spatial element simulation data of the sample community in the third period;

[0028] The precision verification module performs precision verification on the third-period spatial element simulation data according to the third-period spatial element data; if the precision is greater than the first preset threshold and less than the second preset threshold, returns to step S3 to recalculate the spatial evolution driving factor weights corresponding to each spatial element; if the precision is greater than the second preset threshold, the 3σ criterion is used to calculate the normal distribution of the driving factor weight data set to obtain the range of the spatial evolution driving factor weights of the sample community in the third period.

[0029] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for identifying the weight range of driving factors of community space evolution described in any embodiment is implemented.

[0030] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for identifying the weight range of driving factors of community spatial evolution as described in any one of the embodiments.

[0031] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0032] The method for identifying the weight range of driving factors of community spatial evolution provided by the present invention simulates the third-period spatial evolution process based on the spatial element transfer matrix and suitability atlas of the sample community, comprehensively considers the influence of spatial element types and driving factors on spatial evolution, and obtains the reasonable range of the weights of the driving factors of the third-period spatial evolution through precision testing, thereby providing support for subsequent community spatial planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this specification. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0034] Figure 1 A flowchart of a method for identifying weight ranges of driving factors for community spatial evolution provided in Example 1 of the present invention;

[0035] Figure 2 A schematic diagram of a device for identifying the weight range of driving factors for community spatial evolution provided in Example 2 of the present invention;

[0036] Figure 3 This is a schematic diagram of the electronic device architecture provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. It should be noted that, in the absence of conflict, the embodiments and features in the embodiments disclosed in this disclosure can be combined, separated, interchanged and / or rearranged with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0038] Example 1

[0039] A specific embodiment of the present invention, as Figure 1 As shown, a method for identifying the weight range of community spatial evolution driving factors is disclosed, comprising the following steps:

[0040] S1. Obtain the first-period spatial element data, the second-period spatial element data and spatial evolution driving factor data, and the third-period spatial element data of at least two sample communities.

[0041] In this embodiment, the first-phase spatial element data, the second-phase spatial element data and the third-phase spatial element data all include residential land, industrial and mining land, cultivated land, forest land and land water area that have undergone data preprocessing.

[0042] For example, data collection, field investigation, semi-structured interviews, etc., combined with manual visual interpretation of Google Earth historical images, can be used to draw the spatial element dwg data of the two sample communities in 2010, 2015 and 2020 based on the current topographic map using AutoCAD software, and then the dwg data can be processed through the following steps:

[0043] (I) The spatial element dwg data of the three phases were imported into ArcGIS software in order of residential land, industrial and mining land, cultivated land, forest land, and land water area through the area element type;

[0044] (II) Merge the imported spatial elements into layers and number each spatial element, so that the spatial elements of the same category have the same number;

[0045] (III) Use the surface-to-raster tool in ArcGIS software to convert the format. In order to make the simulation results more realistic, the pixel size of all raster images in the sample needs to be set to 1m×1m. In addition, since the raster data lacks a spatial coordinate system, it is necessary to use data with spatial information, such as using elevation data for mask extraction and projection coordinate system conversion.

[0046] (IV) Since the spatial element distribution data and the elevation data do not completely overlap, it is necessary to use a raster calculator to calculate the overlapping part of the two layers, and perform mask extraction again to obtain the spatial element distribution raster data, and then convert the raster data into ASCII data;

[0047] (V) Import the three-phase spatial element ASCII data into the IDRISI software. Since the data will be recognized as continuous data by the IDRISI software after import, it is necessary to reclassify it, convert it into discrete data, and add the name of the spatial element distribution image legend.

[0048] In this embodiment, the second-phase spatial evolution driving factor data includes constraints and decision variables, wherein the constraints include at least river waters, basic farmland, ancient trees, traditional buildings, family and religious belief buildings; and the decision variables include at least elevation, slope, distance from community main roads, distance from highways, and distance from industrial development areas.

[0049] Specifically, the constraint condition refers to the factors that are not allowed to be occupied during the spatial evolution of the selected sample. The data type is a logical value, which has only two types: 1 (suitable) and 0 (unsuitable). The weights of the constraint conditions in the present invention are all 0, among which, river waters refer to water source protection areas within which spatial evolution cannot be carried out, and the value is 0; basic farmland refers to permanent basic farmland within which spatial evolution cannot be carried out, and the value is 0; ancient trees refer to ancient trees within the vertical projection of the crown of the tree, and the value is 0; traditional buildings refer to traditional dwellings and public buildings with preservation value within the building red line, and the value is 0; family and religious belief buildings refer to temples, ancestral halls and other building land red lines within which spatial evolution cannot be carried out, and the value is 0;

[0050] Decision variables refer to variables that need to adjust parameters according to the comprehensive situation of the selected samples to affect the results of spatial evolution. They usually include factors such as topography, road accessibility, and the data type is continuous value. Among them, elevation refers to the elevation range of the vast majority of distribution areas within the larger area where the community is located. Slope refers to the slope range of the vast majority of distribution areas within the larger area where the community is located. Distance from the main road of the community refers to the closer to the main road of the community, the higher the accessibility. Whether it is proportional to the suitability of community construction depends on the actual situation of the community. Distance from the highway refers to the closer to the highway, the higher the accessibility. Whether it is proportional to the suitability of community construction depends on the actual situation of the community. Distance from the industrial development area refers to the distance to the large-scale park or individual factory / workshop mainly engaged in industrial and trade processing and manufacturing.

[0051] It should be noted that the second-phase spatial evolution driving factor data also needs to be processed. The steps are similar to those for spatial element data processing and will not be repeated here.

[0052] S2. For each sample community, a spatial element transfer matrix is ​​calculated according to the first-phase spatial element data and the second-phase spatial element data.

[0053] In this embodiment, step S2 specifically includes:

[0054] By comparing the first-period spatial element data with the second-period spatial element data, the number of spatial elements of each type transformed into other types of spatial elements is analyzed, the transformation probability is calculated based on the number of transformations, and the spatial element transfer matrix is ​​constructed based on the transformation probability.

[0055] For example, the following table is used to show the number of changes in residential land, industrial and mining land, cultivated land, forest land and land waters from the first period to the second period in a sample community;

[0056] Residential land Industrial and mining land arable land woodland Land waters Residential land 800 100 50 30 20 Industrial and mining land 10 200 80 50 10 arable land 120 80 600 200 100 woodland 30 50 40 300 200 Land waters 10 20 40 60 500

[0057] For example, for residential land, the probability of remaining residential land is 80%, the probability of being converted into industrial and mining land is 10%, the probability of being converted into cultivated land is 5%, the probability of being converted into forest land is 3%, and the probability of being converted into land water is 2%. The transformation probabilities of other spatial elements are calculated in turn, and the spatial element transfer matrix is ​​composed of the transformation probabilities of all spatial elements.

[0058] S3. Calculate a driving factor weight data set composed of the spatial evolution driving factor weights corresponding to each spatial element based on the second-phase spatial element data and the spatial evolution driving factor data, and create a suitability atlas composed of the suitability images of each spatial element based on the driving factor weight data set.

[0059] In this embodiment, step S3 specifically includes:

[0060] S31, based on the second-phase spatial element data, inputting the decision variables and constraints corresponding to each spatial element into the multi-criteria evaluation model;

[0061] S32, using a fuzzy geometric function method to standardize the decision variables in the spatial evolution driving factor data;

[0062] Exemplarily, an S-shaped monotone decreasing function with different parameters is used to represent elevation, a J-shaped monotone decreasing function represents slope, distance from community main road, and distance from highway, and an S-shaped monotone increasing function represents distance from industrial development area, so as to normalize the decision variables.

[0063] S33, constructing an importance judgment matrix using the hierarchical analysis method, calculating the weights of the standardized decision variables according to the importance judgment matrix, and obtaining a driving factor weight data set;

[0064] Specifically, the analytic hierarchy process was used to calculate the weights of each decision variable based on the five spatial element types of residential land, industrial and mining land, cultivated land, forest land and terrestrial water in each sample community, and then form a driving factor weight data set.

[0065] S34. Calculate the suitability score of each pixel in the sample community according to the driving factor weight dataset to obtain a suitability atlas consisting of suitability images of various spatial elements.

[0066] Specifically, the suitability scores of each pixel corresponding to each driving factor are weighted and summed according to the weights to obtain the suitability image, which is expressed as follows:

[0067] S(x,y)=w1·f1(x,y)+w2·f2(x,y)+…+w n ·f n (x,y)

[0068] Among them, S(x,y) represents the suitability score of the pixel with coordinates (x,y) in the image, w1,w2,...,w n Represents the weight of each driving factor, f1(x,y),f2(x,y),...,f n (x,y) represents the suitability score of each driving factor corresponding to the pixel with coordinates (x,y) in the image.

[0069] S4. Simulate the spatial evolution of the sample community in the third period according to the spatial element transfer matrix and the suitability atlas to obtain the spatial element simulation data of the sample community in the third period.

[0070] In this embodiment, step S4 specifically includes:

[0071] With one year as an iteration cycle, the first period of spatial element data as the starting year, and the annual interval between the first period of spatial element data and the third period of spatial element data as the number of iterations, the spatial element transfer matrix and the suitability atlas are input into the spatial evolution simulation model to iteratively simulate the third period of spatial element distribution, so as to obtain the third period of spatial element simulation data.

[0072] Exemplarily, a cellular automaton and a Markov model are combined as a spatial evolution simulation model. The input of the model is the spatial element transfer matrix and suitability atlas of each sample community. Taking the first period of spatial element data as the spatial element data of 2010 and the second period of spatial element data as the spatial element data of 2015 as an example, the model simulates the spatial evolution process in 2020 and outputs the spatial element simulation data of each sample community in 2020, that is, the third period of spatial element simulation data.

[0073] S5. Perform an accuracy check on the third-period spatial element simulation data according to the third-period spatial element data; if the accuracy is greater than the first preset threshold and less than the second preset threshold, return to step S3 to recalculate the spatial evolution driving factor weights corresponding to each spatial element; if the accuracy is greater than the second preset threshold, use the 3σ criterion to calculate the normal distribution of the driving factor weight data set to obtain the range of the third-period spatial evolution driving factor weights of the sample community.

[0074] In this embodiment, step S5 specifically includes:

[0075] S51, constructing a confusion matrix according to the third-period spatial element data and the third-period spatial element simulation data;

[0076] Exemplarily, the confusion matrix is ​​represented by the third-period spatial element simulation data and the third-period spatial element data (actual data) as follows:

[0077] Data Type 1 Data Type 2 … Data Type n Data Type 1 <![CDATA[a 11 ]]> <![CDATA[a 12 ]]> … <![CDATA[a 1n ]]> Data Type 2 <![CDATA[b 21 ]]> <![CDATA[b 22 ]]> … <![CDATA[b 2n ]]> … … … … … Data Type n <![CDATA[m n1 ]]> <![CDATA[m n2 ]]> … <![CDATA[m nn ]]>

[0078] Among them, a 11 Indicates the number of pixels whose type is 1 in the third-period spatial element simulation data and whose actual type is 1 in the third-period spatial element data. 12 It indicates the number of pixels whose type is 1 in the third-period spatial element simulation data and whose actual type is 2 in the third-period spatial element data, and so on;

[0079] S52, calculating the actual accuracy and the expected accuracy according to the confusion matrix;

[0080] Specifically, the actual accuracy P0 is the sum of the elements on the diagonal of the confusion matrix divided by the total number of pixels, expressed as:

[0081] Expected accuracy P e The actual frequency of each type is multiplied by the actual accuracy and then added together, expressed as:

[0082]

[0083] Where q = a 11 +a 12 +...+a 1n +b 21 +b 22 +...+b 2n +...+m nn .

[0084] S53. Calculate the Kappa coefficient based on the actual accuracy and the expected accuracy to indicate the accuracy, as shown below:

[0085]

[0086] S54, calculating the normal distribution of the driving factor weight data set using the 3σ criterion;

[0087] Specifically, it is assumed that the data obeys the normal distribution. The normal distribution has two parameters, namely the mean μ and the standard deviation σ. For a random variable that obeys the normal distribution, its mean μ determines the overall position of the normal distribution. The closer the variable is to the mean μ, the greater the probability of the variable appearing. The standard deviation σ describes the degree of dispersion of the data distribution. The larger σ is, the more discrete the data distribution is. Conversely, the more concentrated the data distribution is. For the 3σ criterion, the probability that the value is distributed within (μ-σ,μ+σ) is 0.6826, the probability that the value is distributed within (μ-2σ,μ+2σ) is 0.9554, and the probability that the value is distributed within (μ-3σ,μ+3σ) is 0.99. 74. Since the data distributed in (μ-3σ, μ+3σ) accounts for 99.74% of the total data, the interval (μ-3σ, μ+3σ) can basically be regarded as the actual possible value interval of the random variable, that is, the 3σ criterion of the normal distribution; however, this embodiment calculates the value range of the community space evolution driving factor weight data with a greater probability of appearing based on the weights of all spatial element driving factors in the sample space evolution simulation process, rather than calculating the value range that can cover all weight data; therefore, according to the meaning of the normal distribution position parameter μ, this embodiment recognizes the values ​​distributed in (μ-σ, μ+σ) as the driving factor weight range.

[0088] S55. According to the normal distribution obtained in step S54, the maximum and minimum values ​​of the driving factor weights corresponding to each spatial element in the third period of spatial evolution of the sample community are calculated, and the range of the driving factor weights of the third period of spatial evolution of the sample community is constructed.

[0089] It should be noted that the first preset threshold and the second preset threshold involved in the present invention can be set to any number between 0 and 1 according to actual conditions, and the present invention does not limit this.

[0090] In some embodiments, if the accuracy is less than the first threshold, it indicates that the data of the second-period spatial evolution driving factor may be missing or other abnormal conditions exist, and the data needs to be reacquired.

[0091] Compared with the prior art, the method for identifying the weight range of driving factors of community spatial evolution provided in this embodiment simulates the third-period spatial evolution process based on the spatial element transfer matrix and suitability atlas of the sample community, comprehensively considers the impact of spatial element types and driving factors on spatial evolution, and obtains the reasonable range of weights of the driving factors of the third-period spatial evolution through precision testing, thereby providing support for subsequent community spatial planning.

[0092] Example 2

[0093] This embodiment provides a device for identifying the weight range of community space evolution driving factors, such as Figure 2 As shown, including:

[0094] A data acquisition module is used to acquire the first-period spatial element data, the second-period spatial element data and the spatial evolution driving factor data, and the third-period spatial element data of at least two sample communities;

[0095] A transfer matrix calculation module, used for calculating a spatial element transfer matrix according to the first-phase spatial element data and the second-phase spatial element data;

[0096] A suitability atlas creation module is used to calculate a driving factor weight data set composed of spatial evolution driving factor weights corresponding to each spatial element based on the second-phase spatial element data and the spatial evolution driving factor data, and to create a suitability atlas composed of suitability images of each spatial element based on the driving factor weight data set;

[0097] A spatial element simulation module is used to simulate the spatial evolution of the sample community in the third period according to the spatial element transfer matrix and the suitability atlas to obtain spatial element simulation data of the sample community in the third period;

[0098] The precision verification module performs precision verification on the third-period spatial element simulation data according to the third-period spatial element data; if the precision is greater than the first preset threshold and less than the second preset threshold, returns to step S3 to recalculate the spatial evolution driving factor weights corresponding to each spatial element; if the precision is greater than the second preset threshold, the 3σ criterion is used to calculate the normal distribution of the driving factor weight data set to obtain the range of the spatial evolution driving factor weights of the sample community in the third period.

[0099] Example 3

[0100] This embodiment provides an electronic device, such as Figure 3 As shown, it includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, it implements the method for identifying the weight range of the driving factor of community space evolution as described in any of the above embodiments.

[0101] Example 4

[0102] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for identifying the weight range of the driving factor of community space evolution as described in any of the above embodiments is implemented.

[0103] Computer readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0104] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0105] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0106] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying the weight range of driving factors of community spatial evolution, characterized in that: The following steps are involved: S1. Obtain the first-period spatial element data, the second-period spatial element data and spatial evolution driving factor data, and the third-period spatial element data of at least two sample communities; S2. For each sample community, a spatial element transfer matrix is ​​calculated according to the first-phase spatial element data and the second-phase spatial element data; S3, calculating a driving factor weight data set composed of spatial evolution driving factor weights corresponding to each spatial element according to the second-phase spatial element data and the spatial evolution driving factor data, and creating a suitability atlas composed of suitability images of each spatial element according to the driving factor weight data set; S4, simulating the spatial evolution of the sample community in the third period according to the spatial element transfer matrix and the suitability atlas, and obtaining the spatial element simulation data of the sample community in the third period; S5, performing an accuracy test on the third-period spatial element simulation data according to the third-period spatial element data; if the accuracy is greater than the first preset threshold and less than the second preset threshold, returning to step S3 to recalculate the spatial evolution driving factor weights corresponding to each spatial element; If the accuracy is greater than the second preset threshold, the 3σ criterion is used to calculate the normal distribution of the driving factor weight data set to obtain the range of the driving factor weights of the third period of spatial evolution of the sample community.

2. The method for identifying the weight range of driving factors of community spatial evolution according to claim 1, characterized in that: The first phase spatial element data, the second phase spatial element data and the third phase spatial element data all include residential land, industrial and mining land, cultivated land, forest land and land water areas that have undergone data preprocessing.

3. The method for identifying the weight range of driving factors of community spatial evolution according to claim 1, characterized in that: The second phase of spatial evolution driving factor data includes constraints and decision variables, wherein the constraints include at least river waters, basic farmland, ancient trees, traditional buildings, family and religious belief buildings, and the decision variables include at least elevation, slope, distance from community main roads, distance from highways, and distance from industrial development areas.

4. The method for identifying the weight range of driving factors of community spatial evolution according to claim 1, characterized in that: Calculating a spatial element transfer matrix according to the first-period spatial element data and the second-period spatial element data includes: By comparing the first-period spatial element data with the second-period spatial element data, the number of spatial elements of each type transformed into other types of spatial elements is analyzed, the transformation probability is calculated based on the number of transformations, and the spatial element transfer matrix is ​​constructed based on the transformation probability.

5. The method for identifying the weight range of driving factors of community spatial evolution according to claim 3, characterized in that: The step of calculating a driving factor weight dataset composed of spatial evolution driving factor weights corresponding to each spatial element according to the second-phase spatial element data and the spatial evolution driving factor data, and creating a suitability atlas composed of suitability images of each spatial element according to the driving factor weight dataset includes: Based on the second-phase spatial element data, the decision variables and constraints corresponding to each spatial element are input into the multi-criteria evaluation model; Using fuzzy geometric function method to standardize the decision variables in the spatial evolution driving factor data; The importance judgment matrix is ​​constructed using the hierarchical analysis method. The weights of the standardized decision variables are calculated based on the importance judgment matrix to obtain the driving factor weight data set. The suitability score of each pixel in the sample community is calculated based on the driving factor weight dataset to obtain a suitability atlas consisting of the suitability images of each spatial element.

6. The method for identifying the weight range of driving factors of community spatial evolution according to claim 5, characterized in that: The simulating the spatial evolution of the sample community in the third phase according to the spatial element transfer matrix and the suitability atlas includes: With one year as an iteration cycle, the first period of spatial element data as the starting year, and the annual interval between the first period of spatial element data and the third period of spatial element data as the number of iterations, the spatial element transfer matrix and the suitability atlas are input into the spatial evolution simulation model to iteratively simulate the third period of spatial element distribution, so as to obtain the third period of spatial element simulation data.

7. The method for identifying the weight range of driving factors of community spatial evolution according to claim 6, characterized in that: The performing accuracy check on the third-period spatial element simulation data according to the third-period spatial element data comprises: Construct a confusion matrix based on the third-period spatial element data and the third-period spatial element simulation data; Calculate the actual accuracy and expected accuracy based on the confusion matrix; The Kappa coefficient is calculated based on the actual accuracy and the expected accuracy to indicate the accuracy.

8. A device for identifying the weight range of driving factors of community spatial evolution, characterized in that: The device comprises: A data acquisition module is used to acquire the first-period spatial element data, the second-period spatial element data and the spatial evolution driving factor data, and the third-period spatial element data of at least two sample communities; A transfer matrix calculation module, used for calculating, for each sample community, a spatial element transfer matrix according to the first-phase spatial element data and the second-phase spatial element data; A suitability atlas creation module is used to calculate a driving factor weight data set composed of spatial evolution driving factor weights corresponding to each spatial element based on the second-phase spatial element data and the spatial evolution driving factor data, and to create a suitability atlas composed of suitability images of each spatial element based on the driving factor weight data set; A spatial element simulation module is used to simulate the spatial evolution of the sample community in the third period according to the spatial element transfer matrix and the suitability atlas to obtain spatial element simulation data of the sample community in the third period; The precision verification module performs precision verification on the third-period spatial element simulation data according to the third-period spatial element data; if the precision is greater than the first preset threshold and less than the second preset threshold, returns to step S3 to recalculate the spatial evolution driving factor weights corresponding to each spatial element; if the precision is greater than the second preset threshold, the 3σ criterion is used to calculate the normal distribution of the driving factor weight data set to obtain the range of the spatial evolution driving factor weights of the sample community in the third period.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for identifying the weight range of the driving factor of community space evolution as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the method for identifying the weight range of community space evolution driving factors as described in any one of claims 1 to 7 is implemented.

Images