A method of validating a land use simulation space of a ca model

Abstract

The embodiment of the application discloses a method for verifying land use simulation space of a CA model, and relates to the technical field of geographic simulation. The method comprises the following steps: acquiring initial land use data and final land use data of a research area during simulation by a CA model, and acquiring simulation land use data output by the model; converting the initial land use data, the final land use data and the simulation land use data into corresponding matrices respectively; inputting the matrices into a Fuzzy FoM model to calculate evaluation parameters of the CA model and output evaluation results. The evaluation parameters are calculated by comparing the cells with changes in the matrices corresponding to the initial land use data, the final land use data and the simulation land use data. The changes of the cells in the three kinds of land use data are compared, and the position fuzziness is combined, so that the accuracy of the CA model and the capturing ability of spatial autocorrelation and heterogeneity can be quantified, which is helpful to guide the improvement direction of the CA model.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of geographic simulation, in particular to a method for verifying land use simulation space of a CA model. BACKGROUND

[0002] A cellular automaton (CA) is a "bottom-up" model for simulating discrete spatial and temporal complexity phenomena through local operations. Because of its open structure, the CA can be integrated with other models to simulate and predict land use evolution. The CA has been widely used to simulate the spatio-temporal evolution of complex nonlinear systems and is very suitable for simulating and predicting complex geographical processes. The spatial autocorrelation and heterogeneity capturing ability of the model has been the focus of current research.

[0003] However, the current CA model has the following shortcomings in quantifying its spatial autocorrelation and heterogeneity capturing ability:

[0004] (1) The traditional cell-by-cell checking method ignores the ability of the model in capturing spatial autocorrelation and heterogeneity;

[0005] (2) The traditional Kappa coefficient is questioned by the academic community for evaluating the accuracy of the model. By comparing examples of evaluating the accuracy of the model in land use simulation and remote sensing neighborhood, the Kappa coefficient has certain misleading, which can lead to the real accuracy of the model being less than the evaluation accuracy, especially when evaluating the simulation results of the region with less land use change.

[0006] Therefore, there is an urgent need for a new method to solve the above problems, to quantify the spatial autocorrelation and heterogeneity capturing ability of the land use change simulation model, and to better evaluate the simulation results of the model for land use change. SUMMARY

[0007] The embodiments of the application provide a method for verifying land use simulation space of a CA model, which can correctly evaluate the accuracy of the model while quantifying the capturing ability of the CA model for spatial autocorrelation and heterogeneity. The technical solution is as follows:

[0008] In a first aspect, the embodiments of the application provide a method for verifying land use simulation space of a CA model, characterized in that it comprises:

[0009] S1 obtaining initial land use data and final land use data of a study area during simulation by the CA model, and obtaining simulation land use data output by the CA model;

[0010] S2 converts the initial land use data, the final land use data and the simulated land use data into corresponding matrices respectively, wherein a matrix element corresponds to a cell, and a matrix space corresponds to a cell space;

[0011] S3 inputs each matrix into a Fuzzy FoM model, calculates the evaluation parameters of the CA model through the Fuzzy FoM model, and outputs the evaluation result of the CA model based on the evaluation parameters.

[0012] In an optional implementation of the first aspect, step S1 specifically includes the following steps.

[0013] S101 performs rasterization processing on the initial land use data, the final land use data and the simulated land use data respectively to obtain corresponding land use raster data.

[0014] S102 assigns a value of 0 to the grid of the marginal non-research area of all the land use raster data.

[0015] In an optional implementation of the first aspect, step S2 specifically includes the following steps.

[0016] All the land use raster data are converted into land use state matrices respectively, a corresponding land use type is determined according to each element in the land use state matrix corresponding to a cell, and each element in the land use state matrix is assigned a value based on the land use type.

[0017] The land use type includes cultivated land, forest land, grassland, water area, construction land and unused land, wherein the cultivated land is assigned a value of 1, the forest land is assigned a value of 2, the grassland is assigned a value of 3, the water area is assigned a value of 4, the construction land is assigned a value of 5, and the unused land is assigned a value of 6.

[0018] In an optional implementation of the first aspect, step S3 specifically includes the following steps.

[0019] S301 extracts first cells from all the matrices through a first mask, calculates the attribution degree of each cell by taking each first cell as the center of a distance attenuation function, extracts second cells from all the matrices through a second mask, and extracts the attribution degree of the second cells;

[0020] S302 calculates the sum of the attribution degrees of all the second cells, and calculates the evaluation parameters based on the sum of the attribution degrees.

[0021] The first cell is a cell in which the land use type changes during the simulation period and the CA model simulation error occurs; and the second cell is a cell in which the land use type in the initial land use data and the final land use data is not l, and the simulated land use type in the simulated land use data is l.

[0022] In an optional implementation of the first aspect, the first cells are extracted based on all the matrices by using the first mask in step S301, and the following formula is applied:

[0023]

[0024] If the calculated value is 1, the corresponding cell is extracted as the first cell. If the calculated value is 1, the corresponding cell is extracted as the first cell.

[0025] The belonging degree of each cell is calculated by taking each first cell as the center of the distance attenuation function, and the following formula is applied:

[0026]

[0027] wherein, is the first mask for the land use type l at the (i, j) position, is the land use type corresponding to the (i, j) position in the initial land use data, is the land use type corresponding to the (i, j) position in the final land use data, is the land use type corresponding to the (i, j) position in the simulated land use data, and f(·) is a Gaussian distance attenuation function and d is the Euclidean distance from the (i, j) position to the center cell.

[0028] In an optional implementation of the first aspect, the second cells are extracted based on all the matrices by using the second mask in step S301, and the following formula is applied:

[0029]

[0030] If the calculated value is 1, the corresponding cell is extracted as the second cell. If the calculated value is 1, the corresponding cell is extracted as the second cell.

[0031] The second cells are retained by using the second mask, and the belonging degrees corresponding to the second cells are obtained.

[0032] The sum of the belonging degrees of all the second cells is calculated, and the following formula is applied:

[0033]

[0034] Wherein, E represents the sum of the attribution degree of all spatial autocorrelation and heterogeneity cells in the study area, num represents the number of land use types, represents the maximum value of the attribution degree of the cell of land use type l at the (i, j) position in all Gaussian distance decay functions, represents the second mask for land use type l at the (i, j) position.

[0035] In an optional implementation of the first aspect, the evaluation parameter is calculated based on the sum of the attribution degrees in step S302, and the formula is applied:

[0036]

[0037] The evaluation result of the CA model is output based on the evaluation parameter in step S3, and specifically includes the following steps:

[0038] The Fuzzy FoM is visualized, and a distribution map of the accuracy of the CA model in simulating the land use types in the study area is output;

[0039] Wherein, FoM fuzzy is the value of the evaluation parameter, A is the area where the actual land use type changes but the simulation result fails to correctly simulate; B is the area where both the actual land use and the simulation result change and are correctly simulated; C is the area where both the actual land use and the simulation result change but the simulation is incorrect; D represents the area where the actual land use type does not change but the simulation result does not change.

[0040] In the second aspect, the embodiments of the present application further provide a device for verifying the land use simulation space of a CA model, comprising:

[0041] A data acquisition module is configured to acquire initial land use data and final land use data of a study area during simulation by the CA model, and acquire simulation land use data output by the CA model;

[0042] A data processing module is configured to convert the initial land use data, the final land use data and the simulation land use data into corresponding matrices respectively, wherein the matrix elements correspond to cells, and the matrix space corresponds to the cell space.

[0043] An evaluation module is configured to input each matrix into a Fuzzy FoM model, calculate the evaluation parameter of the CA model through the Fuzzy FoM model, and output the evaluation result of the CA model based on the evaluation parameter.

[0044] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the method provided by the first aspect of the embodiments of the present application or any of the implementation manners of the first aspect when executing the program.

[0045] In a fourth aspect, a non-transitory computer-readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the method provided by the first aspect of the embodiments of the present application or any of the implementation manners of the first aspect.

[0046] The technical solutions provided by some embodiments of the present application have at least the following beneficial effects:

[0047] (1) The Fuzzy FoM model provided by the present application introduces location fuzziness when simulating land use data, that is, a certain degree of attribution is given within a certain range, so as to capture the spatial autocorrelation and heterogeneity characteristics, and the degree of attribution is quantified by establishing a Gaussian distance decay function, which is very suitable for land use simulation research.

[0048] (2) The Fuzzy FoM model provided by the present application calculates the evaluation parameters by comparing the cells with changes in the matrices corresponding to the initial, final and simulated land use data. By comparing the changes of the cells in the three kinds of land use data and combining the location fuzziness, the accuracy of the CA model and the capturing ability of the CA model to spatial autocorrelation and heterogeneity can be quantified, which is helpful to guide the improvement direction of the CA model. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the present application or related art, the following will briefly introduce the drawings needed to be used in the embodiments or related art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0050] Figure 1 is a flowchart of a method for verifying the land use simulation space of the CA model provided by the embodiments of the present application;

[0051] Figure 2 is a schematic diagram of processing by using a mask in the embodiments of the present application;

[0052] Figure 3 is a schematic diagram of the evaluation results of Fuzzy FoM taking Beijing as an example in the embodiments of the present application;

[0053] Figure 4Schematic diagram of the evaluation results of Fuzzy FoM using Wuhan as an example in the embodiments of the present application;

[0054] Figure 5 Schematic diagram of a device for verifying a land use simulation space of a CA model provided in an embodiment of the present application;

[0055] Figure 6 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0057] The terms "including" and "having," and any variations thereof, in the specification and claims of this application and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to the process, method, product, or apparatus.

[0058] It should be noted that the terms "first" and "second" used in this application are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the terms "first" and "second" may interchangeably represent a specific order or precedence, where permitted. It should be understood that the objects distinguished by "first" and "second" may interchangeably represent a specific order or precedence, where appropriate, such that the embodiments of the present application described herein can be implemented in an order other than that described or illustrated herein.

[0059] The present application is described in detail below with reference to specific embodiments.

[0060] Next, combine Figure 1 , introduces a method for verifying the land use simulation space of the CA model provided by the embodiment of this application. Figure 1 , Figure 1 The following is a flow chart showing a method for verifying the land use simulation space of the CA model provided by an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0061] S1 obtains initial land use data and final land use data of a research area during simulation of the CA model, and obtains simulated land use data output by the CA model;

[0062] S2 converts the initial land use data, the final land use data and the simulated land use data into corresponding matrices respectively, wherein a matrix element corresponds to a cell, and a matrix space corresponds to a cell space;

[0063] S3 inputs each matrix into a Fuzzy FoM model, calculates an evaluation parameter of the CA model through the Fuzzy FoM model, and outputs an evaluation result of the CA model based on the evaluation parameter.

[0064] In some embodiments, step S1 specifically includes the following steps:

[0065] S101 rasterizes the initial land use data, the final land use data and the simulated land use data respectively to obtain corresponding land use raster data;

[0066] S102 assigns a value of 0 to a grid of a marginal non-research area of all the land use raster data.

[0067] Specifically, the initial land use data can be understood as actual land use data in an initial stage of simulation of the research area by the CA model, the final land use data can be understood as actual land use data in a final stage of simulation of the research area by the CA model, and the simulated land use data can be understood as simulation result data of the research area by the CA model.

[0068] Specifically, in S101, the initial, final and simulated land use raster data can be aligned according to actual geographic coordinates of each grid.

[0069] In some embodiments, step S2 specifically includes the following steps:

[0070] converts all the land use raster data into land use state matrices respectively, determines a corresponding land use type according to a cell corresponding to each element in the land use state matrix, and assigns a value to each element in the land use state matrix based on the land use type;

[0071] The land use type includes cultivated land, forest land, grassland, water area, construction land and unused land, and the cultivated land is assigned a value of 1, the forest land is assigned a value of 2, the grassland is assigned a value of 3, the water area is assigned a value of 4, the construction land is assigned a value of 5, and the unused land is assigned a value of 6.

[0072] It can be understood that each grid can be regarded as a cell, and the coordinates of the center point of the cell can be selected as the coordinates of the corresponding cell. Each element in the matrix corresponds to the position coordinates of the cell according to the row and column where the element is located.

[0073] In some embodiments, step S3 specifically comprises the following steps:

[0074] S301 extracts first cells on the basis of all matrices through a first mask, and calculates the attribution degree of each cell by taking each first cell as the center of a distance decay function. Second cells are extracted on the basis of all matrices through a second mask, and the attribution degrees of the second cells are extracted.

[0075] S302 calculates the sum of the attribution degrees of all the second cells, and calculates an evaluation parameter based on the sum of the attribution degrees.

[0076] The first cells are cells in which the land use type changes during the simulation, and the CA model simulates errors. The second cells are cells in which the land use type is not l in the initial land use data and the final land use data, and the simulated land use type is l in the simulated land use data.

[0077] Specifically, in step S301, first cells are extracted on the basis of all matrices through a first mask, and the formula is applied:

[0078]

[0079] If If the calculated value is 1, the corresponding cell is extracted as a first cell.

[0080] The attribution degree of each cell is calculated by taking each first cell as the center of a distance decay function, and the formula is applied:

[0081]

[0082] wherein, is a first mask for the land use type l at the (i, j) position, is the land use type corresponding to the (i, j) position in the initial land use data, is the land use type corresponding to the (i, j) position in the final land use data, is the land use type corresponding to the (i, j) position in the simulated land use data, and f(·) is a Gaussian distance decay function, and d is the Euclidean distance of the (i, j) position from the center cell.

[0083] It should be noted that the degree of belonging can be understood as the tendency of surrounding cells to correctly simulate the first cell, and the higher the value of the degree of belonging, the higher the probability that the CA model correctly simulates the land use type of each cell. It can be understood that when calculating the distance based on the Gaussian distance decay function, only the degree of belonging of the cells within the decay radius range is calculated.

[0084] In step S301, the second cell is extracted based on all the matrices through the second mask, and the formula is applied:

[0085]

[0086] If If the calculated value is 1, the corresponding cell is extracted as the second cell;

[0087] The second cell is retained through the second mask, and the degree of belonging corresponding to the second cell is obtained;

[0088] The sum of the degrees of belonging of all the second cells is calculated, and the formula is applied:

[0089]

[0090] Wherein, E represents the sum of the degrees of belonging of all the spatial autocorrelation and heterogeneity cells in the study area, num represents the number of land use types, represents the maximum value of the degree of belonging of the cell with land use type l at position (i,j) in all Gaussian distance decay functions, represents the second mask for land use type l at position (i,j).

[0091] Exemplarily, as shown in Figure 2 is a schematic diagram for extracting the cells for calculating the degree of belonging using the first mask Mask I and Mask II. Figure 2 In the embodiment, it can be found that there are three cells whose land use type in the initial land use map is forest land, and whose land use type in the final land use map is construction land, but whose land use type in the final simulation result is forest land. Therefore, the three cells can be extracted through the first mask; then the degrees of belonging of other cells around the three cells can be calculated. Specifically, the Euclidean distance of each cell position from the center cell can be calculated by applying the Gaussian distance decay function in the above embodiment, and then the values of the degrees of belonging of each cell within the decay radius can be calculated, and the degrees of belonging can be divided into three categories of high degree of belonging, low degree of belonging and no degree of belonging according to the size of the degree of belonging value. Subsequently, the second cell is derived through the second mask, that is, the cell which is forest land in the initial and final land use maps but is simulated as construction land by the CA model, and the degree of belonging of the selected second cell is extracted.

[0092] Finally, the cells that are simulated correctly and the cells that have a degree of belonging and are within the decay radius are superimposed to generate a visualization map of the Fuzzy FoM as shown in Figure 2 The visualization map obtained by traversing each grid of each land use type is the final evaluation result distribution map of the CA model simulation of the study area.

[0093] In some embodiments, the evaluation parameter is calculated based on the sum of the degree of belonging in step S302, and the formula is applied:

[0094]

[0095] The evaluation result of the CA model is output based on the evaluation parameter in step S3, which specifically includes the following steps:

[0096] The Fuzzy FoM is visualized, and the accuracy distribution map of the CA model simulation of the land use type in the study area is output;

[0097] Wherein, FoM fuzzy is the value of the evaluation parameter, A is the area where the actual land use type changes, but the simulation result fails to simulate correctly; B is the area where both the actual land use and the simulation result change and are simulated correctly; C is the area where both the actual land use and the simulation result change, but the simulation is incorrect; D represents the area where the actual land use type does not change, but the simulation result does not change.

[0098] In some embodiments, the land use data and simulation results of Beijing and Wuhan from 2000 to 2010 can be taken as examples to analyze the accuracy evaluation results of Fuzzy FoM as shown in Figures 3-4 , wherein Figure 3 is a schematic diagram of the evaluation results of Fuzzy FoM taking Beijing as an example, Figure 4 is a schematic diagram of the evaluation results of Fuzzy FoM taking Wuhan as an example. To obtain the training data required for the experiment, the ArcGIS tool can be used to perform spatial overlay analysis on the land use data, extract urban land use change and spatial variable data, and perform data standardization processing and spatial projection.

[0099] Specifically, the construction and operation of the evaluation index of the spatial autocorrelation and heterogeneity of the land use simulation of the CA model are realized in the Matlab2022b environment. The computer is configured as Intel i7-10 generation, 32G memory, and 6G 6500XT graphics card. In order to show the capturing ability of Fuzzy FoM for spatial autocorrelation and heterogeneity, the artificial neural network (ANN) CA, PLUS model, ASHN(G)-CA and ASHN(E)-CA are compared.

[0100] Table 1 Evaluation of simulation accuracy of land use change in Beijing and Wuhan

[0101]

[0102] Table 1 shows that in Beijing, the FoM value of the ANN-CA model is 0.2564, which is higher than that of the PLUS model of 0.1071, and the Fuzzy FoM value of the PLUS model is improved by 0.1699 compared with its FoM value, which is significantly higher than that of the ANN-CA model of 0.0673. This shows that the ANN-CA model has a greater advantage in modeling accuracy, while the PLUS model has a stronger ability to capture spatial features. In addition, the comparison of the accuracy of the models in Wuhan area shows that the performance of the ANN-CA model has decreased sharply compared with Beijing, while the accuracy gap of the PLUS model is smaller. In addition, the Fuzzy FoM enhancement of the PLUS model is more obvious in both study areas, indicating that the PLUS model is more stable and skilled in capturing spatial autocorrelation and heterogeneity in land use change simulation. The gap between the two models is more obvious, and in the two study areas, the FoM value of the ASHN(E) model is slightly lower than that of the ASHN(G). However, the Fuzzy FoM value of the ASHN(E) model increases from 0.085 to 0.1006, which is higher than that of the ASHN(G) model of 0.044 to 0.0771. Therefore, the ASHN-CA(E) model has advantages in both model accuracy and spatial feature capture.

[0103] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the method embodiment of the present application.

[0104] Next, please refer to Figure 5A structural diagram of an apparatus for verifying a land use simulation space of a CA model is provided for an example embodiment of the present application. The apparatus can be realized by software, hardware or a combination of both as all or part of a terminal, and can also be integrated as an independent module on a server. The apparatus for verifying a land use simulation space of a CA model in the embodiments of the present application can be applied to a terminal or cloud, and the apparatus 50 includes a data acquisition module 501, a data processing module 502 and an evaluation module 503, wherein:

[0105] The data acquisition module 501 is configured to acquire initial land use data and final land use data of a research area during simulation by the CA model, and acquire simulation land use data output by the CA model;

[0106] The data processing module 502 is configured to convert the initial land use data, the final land use data and the simulation land use data into corresponding matrices respectively, wherein a matrix element corresponds to a cell, and a matrix space corresponds to a cell space;

[0107] The evaluation module 503 is configured to input each matrix into a Fuzzy FoM model, calculate an evaluation parameter of the CA model by the Fuzzy FoM model, and output an evaluation result of the CA model based on the evaluation parameter.

[0108] It should be noted that the apparatus 50 provided in the above embodiments is only exemplified by the above division of functional modules when performing the method for verifying a land use simulation space of a CA model, and in actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the apparatus provided in the above embodiments and the method for verifying a land use simulation space of a CA model belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be described here.

[0109] The embodiments of the present application also provide an electronic device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method of any of the above embodiments when executing the program.

[0110] Please refer to Figure 6 A structural block diagram of an electronic device is provided for an embodiment of the present application.

[0111] As shown in Figure 6 The electronic device 600 includes a processor 601 and a memory 602.

[0112] In the embodiments of the present application, the processor 601 is the control center of the computer system, which can be a processor of a physical machine or a processor of a virtual machine. The processor 601 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 601 can be implemented in at least one of the hardware forms of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array).

[0113] The processor 601 can also include a main processor and a coprocessor. The main processor is a processor for processing data in a wake-up state, also known as a CPU (Central Processing Unit). The coprocessor is a low-power processor for processing data in a standby state.

[0114] The memory 602 can include one or more computer-readable storage media, which can be non-transitory. The memory 602 can also include a high-speed random access memory and a nonvolatile memory such as one or more disk storage devices, flash storage devices. In some embodiments of the present application, the non-transitory computer-readable storage medium in the memory 602 is used to store at least one instruction for being executed by the processor 601 to implement the method in the embodiments of the present application.

[0115] In some embodiments, the electronic device 600 further includes a peripheral device interface 603 and at least one peripheral device 604. The processor 601, the memory 602, and the peripheral device interface 603 can be connected through a bus or a signal line. Each peripheral device 604 can be connected to the peripheral device interface 603 through a bus, a signal line, or a circuit board. Specifically, the peripheral device interface 603 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 601 and the memory 602.

[0116] In some embodiments of the present application, the processor 601, the memory 602, and the peripheral device interface 603 are integrated on the same chip or circuit board; in some other embodiments of the present application, any one or two of the processor 601, the memory 602, and the peripheral device interface 603 can be implemented on a separate chip or circuit board. The embodiments of the present application do not make specific limitations in this regard.

[0117] The electronic device structure block diagram shown in the embodiments of the present application does not constitute a limitation on the electronic device 600, and the electronic device 600 can include more or fewer components than shown, or combine certain components, or use a different arrangement of components.

[0118] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the steps of the method of any of the preceding embodiments. The computer readable storage medium can include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, micro-drives, and magneto-optical disks, ROM, RAM, EPROM, EEPROM, DRAM, VRAM, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0119] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary universal hardware platforms, and of course can also be implemented by hardware. Based on such an understanding, the above technical solutions, essentially or in terms of related art, can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0120] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of validating a land use simulation space of a CA model, characterized in that, The method comprises the following steps: S1: obtaining initial land use data and final land use data of a study area during simulation of the CA model, and obtaining simulated land use data output by the CA model; S2: converting the initial land use data, the final land use data and the simulated land use data into corresponding matrices respectively, wherein a matrix element corresponds to a cell, and a matrix space corresponds to a cell space; S3: inputting each matrix into a Fuzzy FoM model to obtain an evaluation parameter of the CA model by the Fuzzy FoM model, and outputting an evaluation result of the CA model based on the evaluation parameter, which comprises the following steps: S301: extracting first cells from all matrices based on a first mask, taking each first cell as the center of a distance attenuation function to calculate the belonging degree of each cell, and extracting second cells from all matrices based on a second mask to extract the belonging degree of the second cells; S302: calculating the sum of the belonging degrees of all the second cells, and applying the formula: to obtain the evaluation parameter based on the sum of the belonging degrees. ； Step S1 specifically comprises the following steps: ； wherein E represents the sum of the attribution degree of all the cells with spatial autocorrelation and heterogeneity in the study area, num represents the number of land use types, represents the land use type at the location is l the maximum value of the attribution degree of the cell in all the Gaussian distance decay functions; the first cell is the cell in which the land use type changes during the simulation, and the CA model simulation error, the second cell is the cell in which the land use type is not l in the initial land use data and the final land use data, and the simulated land use type in the simulation land use data is l ; FoM_fuzzy is the value of the evaluation parameter, A is the area in which the actual land use type changes, but the simulation result fails to correctly simulate; B is the area in which both the actual land use and the simulation result change and are correctly simulated; C is the area in which both the actual land use and the simulation result change, but the simulation is incorrect; and D represents the area in which the actual land use type does not change, but the simulation result does not change.

2. The method of validating the land use simulation space of a CA model according to claim 1, wherein, S101: performing rasterization processing on the initial land use data, the final land use data and the simulated land use data to obtain corresponding land use raster data; S102: assigning the grid of the marginal non-study area of all the land use raster data to 0. Step S2 specifically comprises the following steps:

3. The method of validating the land use simulation space of a CA model according to claim 2, wherein, S201: converting all the land use raster data into land use state matrices, determining the corresponding land use type according to the cell corresponding to each element in the land use state matrix, and assigning each element in the land use state matrix based on the land use type; The land use type comprises cultivated land, forest land, grassland, water area, construction land and unused land, wherein the cultivated land is assigned to 1, the forest land is assigned to 2, the grassland is assigned to 3, the water area is assigned to 4, the construction land is assigned to 5, and the unused land is assigned to 6. In step S301, the first cells are extracted from all the matrices based on the first mask, and the formula is applied:

4. The method of validating the land use simulation space of a CA model according to claim 1, wherein, In step S301, the second cells are extracted from all the matrices based on the second mask, and the formula is applied: ； If If the calculated value is 1, the corresponding cell is extracted as the first cell. The second cells are retained by the second mask, and the belonging degree corresponding to the second cells is obtained; ； wherein, is a first mask for land use type at location l , is a land use type in initial land use data corresponding to location is a land use type in final land use data corresponding to location is a land use type in simulated land use data corresponding to location is a Gaussian distance decay function, d is is the Euclidean distance from the center cell at location h is the decay radius of the distance decay function.

5. The method of validating the land use simulation space of a CA model according to claim 4, wherein, In step S3, the evaluation result of the CA model is output based on the evaluation parameter, which specifically comprises the following steps: ； If If the calculated value is 1, the corresponding cell is extracted as the second cell. The Fuzzy FoM is visualized, and a distribution map of the accuracy of the CA model in simulating the land use type in the study area is output. wherein, represents a second mask located at position for land use type l.

6. The method of validating the land use simulation space of a CA model according to claim 5, wherein, The device is used to implement the method for verifying the land use simulation space of the CA model according to any one of claims 1-6, and the device comprises: a data acquisition module configured to obtain initial land use data and final land use data of a study area during simulation of the CA model, and obtain simulated land use data output by the CA model; 7. An apparatus for validating a land use simulation space of a CA model, characterized by ​ ​ a data processing module, configured to convert the initial land use data, the final land use data and the simulated land use data into corresponding matrices respectively, wherein a matrix element corresponds to a cell, and a matrix space corresponds to a cell space; an evaluation module, configured to input each matrix into a Fuzzy FoM model, to calculate evaluation parameters of the CA model by the Fuzzy FoM model, and to output an evaluation result of the CA model based on the evaluation parameters.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the steps of the method of any one of claims 1 to 6 when executing the program. 9.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the steps of the method of any one of claims 1 to 6 when executed by the processor.

Images