Plaque generation land utilization simulation method

Abstract

The invention provides a plaque generation land utilization simulation method, and relates to the technical field of geographic information science, and the method comprises the steps: obtaining initial land utilization data, and obtaining change raster data; random point sampling is carried out on the driving factor data and the change raster data to obtain sampling data; training a random forest model through the preprocessed sampling data; obtaining a development probability and a development potential map through the driving factor data and the random forest model; inputting the development potential map and the initial land utilization data into a CA model, and iteratively scanning each pixel of the initial land utilization data to obtain an overall probability; on the basis of the overall probability, a roulette mechanism and a threshold reduction rule are used for introducing competition of land utilization types, and a land utilization simulation diagram is obtained in combination with multi-type random plaque seeds, so that accurate simulation of changes of multi-type land utilization plaques and landscapes is realized, and meanwhile, the method is applied to future land utilization scenario prediction.

Description

Technical Field

[0001] The present application relates to the field of geographic information science and technology, and in particular to a patch generation land use simulation method. Background Art

[0002] In land use change simulation, geographic cellular automata can simulate the spatial distribution and evolution of land use types in order to better understand the mechanism and trend of land use change. It is the mainstream model for studying land use change simulation. Cellular automata is an important simulation tool that simulates a spatial system composed of many small units (cells). The state of each cell changes over time and is affected by its surrounding neighbors.

[0003] The important feature of cellular automata is that they operate in a bottom-up manner, that is, each cell interacts only with a limited number of cells around it, and forms global patterns through regular local behaviors. Compared with traditional mathematical models, cellular automata can simulate irregular and complex phenomena in a more intuitive way, and can be modeled with precision without loss of accuracy by computers to simulate the behavior of various natural systems. Through cellular automata, we can better understand how individual and local behaviors in complex systems produce globally ordered patterns.

[0004] Geographic cellular automata are a special form of cellular automata. They decompose spatial systems into regular geographic units with certain properties and states. Each unit can represent a specific land use type. Each cell has a neighborhood around it, which includes the cell itself and other cells adjacent to it. The size and shape of the neighborhood can be defined as needed. Common neighborhood shapes include four neighborhoods, eight neighborhoods, and twelve neighborhoods. The state of cells in cellular automata changes over time, and the rules of change are determined by transition rules. The transition rule is a function that defines how the next state of each cell is calculated based on the current state and the state of its neighbors. The transition rule is usually based on the neighborhood state of the cell and can be a simple local function or a more complex global function. By defining and designing the state, neighborhood, and transition rules of cellular automata, the evolution of land use change can be simulated.

[0005] At present, two transformation rule mining strategies are commonly used in geographic cellular automata: transformation analysis strategy (TAS) and pattern analysis strategy (PAS). The CA model based on TAS extracts all land use transformations between two periods of land use data, but analyzing all transformation types will increase the computational complexity of the CA model structure and reduce the flexibility and universality of the model.

[0006] The CA model based on PAS only uses one period of land use data to calculate the probability of occurrence of land use types in each unit, and determines the state of the future cell through competition between land use types. This avoids the situation in which the combination of transformation types increases exponentially with the increase in the number of land use types in the process of mining transformation rules. However, the CA model based on PAS itself lacks the ability to reveal how driving factors cause land use changes, because the model is not built based on historical "change" analysis. Therefore, the CA model based on PAS cannot obtain land use change rules for specific time intervals, such as the FLUS model, which lacks the ability to reveal how driving factors cause land use changes.

[0007] In addition, the existing models are not capable of simulating the evolution of land use patches. Vector-based CA cannot be used to simulate the dynamic changes of natural land use types (such as forests and grasslands). Grid-based CA models have difficulty in simulating the evolution of patches, and it is difficult for multi-category and multi-type patches to achieve synchronous evolution. For example, the Fore-SCE model has difficulty in dealing with the situation where there are many small patches, and the model is not a spatiotemporal dynamic model. Summary of the invention

[0008] The purpose of the present invention is to provide a patch generation land use simulation method to solve the limitations of the model used in traditional land use change simulation, such as the decrease in simulation accuracy due to error transmission, the inability to explore the potential factors of land use change, and the inability to dynamically simulate the generation and evolution of multiple types of land patches in time and space.

[0009] The above-mentioned purpose of the present application is achieved through the following technical solutions: S1: Obtain initial land use data; obtain change grid data through the initial land use data; Obtain a preset number of driving factors affecting land use and land cover changes to form driving factor data; S2: Perform random point sampling on the driving factor data and the change grid data to obtain sampling data; S3: Preprocess the sampled data; build a random forest model based on the random forest classification algorithm; train the random forest model using the preprocessed sampled data; S4: Input all driving factor data into the trained random forest model to obtain the development probability of each type of land use and the development potential map of each land use type in the region; S5: Construct a CA model based on a multi-type random patch seed mechanism; set the transformation matrix and neighborhood weights of the CA model; set the target number of pixels of the CA model according to the required area of ​​each land use type; S6: Input the development potential map and the initial land use data into the CA model, iteratively scan each pixel of the initial land use data, and obtain the land use type contained in the neighborhood and the proportion of each pixel in the neighborhood and the adaptive inertia coefficient; The overall probability of each land use type in each pixel is obtained by combining the land use types contained in the neighborhood, the proportion of the pixel in the neighborhood, the adaptive inertia coefficient, and the development probability of each type of land use. S7: Construct a roulette wheel through the overall probability; through the roulette wheel method, transform various land use types in the pixel area into the land use type that wins the competition; When the adjacent effect of a land use type is equal to 0, different types of random seeds are generated by calculating the overall probability; new land use types are generated through random seeds; S8: Based on the threshold decreasing rule, determine whether the conversion of the new land use type that wins the competition occurs; S9: Repeat steps S6 to S8 until the iteration reaches the target number of pixels, then stop the iteration and output the land use simulation map.

[0010] This application adopts the above technical solution to more accurately explore the relationship between driving factors and land use changes for two-category and multi-category land use change simulation problems through the combination of land expansion analysis strategy and random forest classification algorithm. By adopting a multi-type random patch seeding mechanism based on threshold descent, accurate simulation of changes in multi-class land use patches and landscapes is achieved, which more realistically reflects the land use change process and can more accurately simulate future land use scenarios.

[0011] Optionally, step S1 includes: S11: Acquire an initial land use classification image; perform format conversion or reclassification on the initial land use classification image to obtain initial land use data; the initial land use data includes: first-period land use data and second-period land use data; S12: extracting the changed part between the two periods of the initial land use data, that is, extracting the grids with changed states from the second period of land use data; S13: Extracting grids whose states have changed between the two periods, namely, changed grid data, based on the first period land use data and the second period land use data.

[0012] This application adopts the above technical solution and replaces the two-period sampling mode or one-period sampling mode commonly used in cellular automata by sampling the change results of two-period land use data. It effectively avoids the analysis of all types of transformation, thereby effectively simplifying the analysis process of land use change and has the ability to describe the characteristics of land use change within a specific time interval.

[0013] Optionally, step S2 includes: Using uniform sampling strategy or proportional sampling strategy, random point sampling is performed on driving factor data and change grid data to obtain sampling data. The sample formula after sampling is expressed as:

[0014] in Indicates The first sampling point is extracted Driver data; Indicates The data of the change grid data extracted from the sampling points; is transposed.

[0015] Optionally, step S3 includes: The sampled data is normalized, and the normalization formula is as follows:

[0016] in and Respectively represent The maximum and minimum values ​​of each driver; .

[0017] Optionally, step S3 further includes: The random forest classification algorithm is expressed as follows:

[0018] in is a constant, either 0 or 1; is a vector consisting of a preset number of driving factors; is the indicator function of the decision tree set; is a vector The prediction type of the nth decision tree; is the total count of the decision tree.

[0019] Optionally, step S6 includes: The overall probability synthesis formula is:

[0020] in is a random value from 0 to 1; For land use type Thresholds for generating new land use patches, which are mined by users; is the neighborhood function; A scanning window is constructed through the neighborhood function, and the number of various pixels in the scanning window is counted to measure the spatial mutual influence of various land use types; Neighborhood functions is defined as follows:

[0021] in Indicates the land use type at the last iteration within the n×n window The total number of grid cells occupied, is the weight between different land use types; Adaptive function The adaptive method is defined as follows:

[0022] in and It is Second and Land use type at iteration The difference between current quantities and future demand.

[0023] Optionally, step S7 includes: The threshold decreasing rule, the formula is as follows:

[0024]

[0025] in, The decreasing threshold The attenuation coefficient, Random values ​​that follow a normal distribution; is the decreasing threshold; is the number of attenuation times; is the decreasing step length; Defines whether land use type k is allowed to be converted to type The transformation matrix of represents the random forest probability, i.e., pixel Developed into type probability.

[0026] This application adopts the above technical solution and adopts a multi-type random patch seeding mechanism based on threshold reduction. This mechanism generates seeds using the Monte Carlo method and proposes a threshold reduction rule for a competitive process to limit the organic growth and spontaneous growth of all land use types. This can dynamically simulate the generation and evolution of any type of land patches in time and space, more realistically reflect the land use change process, and more accurately simulate future land use scenarios.

[0027] This application adopts the above technical solution and adopts a multi-type random patch seeding mechanism based on threshold reduction. This mechanism generates seeds using the Monte Carlo method and proposes a threshold reduction rule for a competitive process to limit the organic growth and spontaneous growth of all land use types. This can dynamically simulate the generation and evolution of any type of land patches in time and space, more realistically reflect the land use change process, and more accurately simulate future land use scenarios.

[0028] A computer-readable storage medium stores instructions, which, when executed, execute a patch generation land use simulation method.

[0029] The beneficial effects of the technical solution provided by this application are: It integrates the ability of cellular automata (CA) to simulate complex spatiotemporal evolution processes and the advantage of simulating competition among multiple land use types, and overcomes the inherent defects of traditional cellular automata by integrating advantages. It adopts a rule mining framework based on land expansion analysis strategy to realize the intelligent calculation of the development probability of land use types. The framework adopts the random forest classification (RFC) algorithm to reveal the potential driving factors of land use changes. In addition, it adopts a multi-type random patch seeding mechanism based on threshold descent to realize the accurate simulation of changes in multiple land use patches and landscapes. Compared with traditional models, it has practical advantages such as higher accuracy, suitability for multiple scales, low data requirements, fewer parameters, simple operation, fast speed, more accurate landscape simulation results, and more rigorous mining of driving factors. In summary, the present invention integrates the advantages of the old model and eliminates error transmission; introduces the random forest classification algorithm to calculate the development probability of various types of land use, and combines the land expansion analysis strategy to explore the driving factors of land use change; then uses the roulette mechanism and the threshold descent rule to introduce the competition of land use types, and combines multiple types of random patch seeds to achieve accurate simulation of changes in multiple types of land use patches and landscapes and simultaneously apply it to future land use scenario prediction; finally, it makes up for the defects of the old model and obtains simulation results with higher accuracy than the old model. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The present application will be further described below with reference to the accompanying drawings and embodiments, in which: Figure 1 is a flow chart in an embodiment of the present application; Figure 2 It is the initial land use classification map in 2003 in the embodiment of the present application; Figure 3 is a schematic diagram of driving factors of various land use changes in the embodiments of the present application; Figure 4 is a schematic diagram of the development probability of various types of land use output by the random forest in the embodiment of the present application; Figure 5 It is a simulation result diagram in the embodiment of the present application; Figure 6 This is a schematic diagram of the comparison of the actual land use change distribution in 2013 in the embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to have a clearer understanding of the technical features, purposes and effects of the present application, the specific implementation methods of the present application are now described in detail with reference to the accompanying drawings.

[0032] An embodiment of the present application provides a patch generation land use simulation method.

[0033] Please refer to Figure 1 , Figure 1 : is a flow chart of a patch generation land use simulation method in an embodiment of the present application, comprising: S1: Obtain initial land use data; obtain change grid data through the initial land use data; Obtain a preset number of driving factors affecting land use and land cover changes to form driving factor data; S2: Perform random point sampling on the driving factor data and the change grid data to obtain sampling data; S3: Preprocess the sampled data; build a random forest model based on the random forest classification algorithm; train the random forest model using the preprocessed sampled data; S4: Input all driving factor data into the trained random forest model to obtain the development probability of each type of land use and the development potential map of each land use type in the region; Specifically, the output of the random forest in this example is Figure 4 Development potential of the seven land use types shown.

[0034] S5: Construct a CA model based on a multi-type random patch seed mechanism; set the transformation matrix and neighborhood weights of the CA model; set the target number of pixels of the CA model according to the required area of ​​each land use type; S6: Input the development potential map and the initial land use data into the CA model, iteratively scan each pixel of the initial land use data, and obtain the land use type contained in the neighborhood and the proportion of each pixel in the neighborhood and the adaptive inertia coefficient; The overall probability of each land use type in each pixel is obtained by combining the land use types contained in the neighborhood, the proportion of the pixel in the neighborhood, the adaptive inertia coefficient, and the development probability of each type of land use. S7: Construct a roulette wheel through the overall probability; through the roulette wheel method, transform various land use types in the pixel area into the land use type that wins the competition; When the adjacent effect of a land use type is equal to 0, different types of random seeds are generated by calculating the overall probability; new land use types are generated through random seeds; S8: Based on the threshold decreasing rule, determine whether the conversion of the new land use type that wins the competition occurs; S9: Repeat steps S6 to S8 until the iteration reaches the target number of pixels, then stop the iteration and output the land use simulation map.

[0035] Specifically, Figure 1 The models in this paper include a transformation rule mining framework (LEAS) module based on the land expansion analysis strategy and a CA model (CARS) module based on the multi-type random patch seed mechanism.

[0036] Step S1 includes: S11: Acquire an initial land use classification image; perform format conversion or reclassification on the initial land use classification image to obtain initial land use data; the initial land use data includes: first-period land use data and second-period land use data; S12: extracting the changed part between the two periods of the initial land use data, that is, extracting the grids with changed states from the second period of land use data; S13: Extracting grids whose states have changed between the two periods, namely, changed grid data, based on the first period land use data and the second period land use data.

[0037] Specifically, Figure 2 To collect the initial land-use change data, Landsat images were classified into seven land-use types, including built-up areas, cultivated land, deciduous broad-leaved forest, evergreen broad-leaved forest, grassland, water bodies, and bare land. Figure 3The raster maps of various driving factors used in this example include: Wuhan city elevation, Wuhan city slope, Wuhan city soil type, Wuhan city average annual precipitation, Wuhan city average annual temperature, Wuhan city adjacent open water, Wuhan city expressway linear vector, Wuhan city railway linear vector, Wuhan city traffic main road vector, Wuhan city traffic secondary road vector, Wuhan city traffic tertiary road vector, Wuhan city adjacent high-speed rail station, Wuhan city adjacent government, Wuhan city GDP data, Wuhan city population data.

[0038] Step S2 includes: Using uniform sampling strategy or proportional sampling strategy, random point sampling is performed on driving factor data and change grid data to obtain sampling data. The sample formula after sampling is expressed as:

[0039] in Indicates The first sampling point is extracted Driver data; Indicates The data of the change grid data extracted from the sampling points; is transposed.

[0040] Specifically, the uniform sampling strategy makes the sampling points of each land use type consistent, which is suitable for areas with large differences in the areas of different land use types; the proportional sampling method makes the proportion of sampling points of each land use type to the total sampling points consistent with the ratio of each initial land use type to the regional area, with a small amount of calculation, and is suitable for sampling in larger scale areas.

[0041] Step S3 includes: The sampled data is normalized, and the normalization formula is as follows:

[0042] in and Respectively represent The maximum and minimum values ​​of each driver; .

[0043] Step S3 also includes: The random forest classification algorithm is expressed as follows:

[0044] in is a constant, either 0 or 1; is a vector consisting of a preset number of driving factors; is the indicator function of the decision tree set; is a vector The prediction type of the nth decision tree; is the total count of the decision tree.

[0045] Specifically, this example uses the random forest algorithm to mine the mapping relationship between the development and changes of urban functional land type k and driving factors . It is a binary classifier, so the value of d is either 0 or 1.

[0046] Step S6 includes: The overall probability synthesis formula is:

[0047] in is a random value from 0 to 1; For land use type Thresholds for generating new land use patches, which are mined by users; is the neighborhood function; A scanning window is constructed through the neighborhood function, and the number of various pixels in the scanning window is counted to measure the spatial mutual influence of various land use types; Neighborhood functions is defined as follows:

[0048] in Indicates the land use type at the last iteration within the n×n window The total number of grid cells occupied, is the weight between different land use types; Adaptive function The adaptive method is defined as follows:

[0049] in and It is Second and Land use type at iteration The difference between current quantities and future demand.

[0050] The threshold decreasing rule, the formula is as follows:

[0051]

[0052] in, The decreasing threshold The attenuation coefficient, Random values ​​that follow a normal distribution; is the decreasing threshold; is the number of attenuation times; is the decreasing step length; Defines whether land use type k is allowed to be converted to type The transformation matrix of represents the random forest probability, i.e., pixel Developed into type probability.

[0053] This application provides an embodiment as follows: The research object is set as Wuhan, the capital of Hubei Province. Wuhan is located in the central part of Hubei Province. The total area of ​​the city is about 8494 square kilometers. It is a megacity in central China. The test data used in this study area are: the land use data of Wuhan in 2003 and 2013 are used as the initial data for simulation, and the corresponding Landsat images in 2003 and 2013 are classified by decision trees. The land use change data interpreted from the Landsat images of Wuhan in 2013 are used as verification data. The land use change data of Wuhan in 2003 and the data in 2013 have the same land use classification system. All regional data files must be unified into raster images of the same scale to facilitate homogeneous analysis at the pixel scale. According to the research experience of land use change simulation combined with the historical data and existing data of Wuhan, a total of fifteen driving factors of land use / land cover change are selected in this example. The driving factors are: Wuhan city elevation, Wuhan city slope, Wuhan city soil type, Wuhan city average annual precipitation, Wuhan city average annual temperature, Wuhan city adjacent to open water, Wuhan city highway linear vector, Wuhan city railway linear vector, Wuhan city traffic main road vector, Wuhan city traffic secondary road vector, Wuhan city traffic tertiary road vector, Wuhan city adjacent to high-speed rail station, Wuhan city adjacent to government, Wuhan city GDP data, Wuhan city population data.

[0054] The main reason for selecting Wuhan as the research object in the present invention is that Wuhan is located in the middle reaches of the Yangtze River, with a gross domestic product (GDP) of 91.3 billion U.S. dollars in 2011, ranking 13th among all cities in China, and is an important transportation hub and economic center. Wuhan has superior geographical conditions, is located at the confluence of the Yangtze River and the Han River, and has abundant natural resources such as forests, minerals, water resources, etc. Water bodies occupy a large area of ​​Wuhan, forests are mainly distributed in hilly areas, and natural vegetation is mainly composed of deciduous broad-leaved trees. Wuhan has experienced rapid urban development in the past decade, resulting in extensive expansion of built-up area land (from 4.19×104 hectares in 1988 to 49.39×104 hectares in 2011), encroaching on surrounding land with ecological value (i.e., cultivated land, woodland, grassland and water surface). Studying the potential causes of land use changes in Wuhan and determining the sustainable land use plan in Wuhan are of great significance to its urban development. The study area includes 11 of the 13 districts in Wuhan, covering the central metropolitan area.

[0055] Step 1: Convert or reclassify the initial land use classification image to obtain initial land use data; select several driving factors that affect land use / land cover changes to form driving force data; overlay the land use data of the two periods and extract the changed parts between the two periods, that is, extract the grids with changed status from the second period of land use data.

[0056] Step 2: Perform random point sampling on the driving force data and the change grid data output by S1, and select the sampling method according to the characteristics of the initial land use data. The model provides two sampling methods: 1. Uniform sampling strategy; 2. Proportional sampling strategy. In this example, the uniform sampling strategy is used to make the sampling points of various land use types consistent, and the sampling points are extracted Figure 2 Land expansion results data and Figure 3 The driving force data in , the sampling rate is set to 0.01.

[0057] Step 3: Use the random forest algorithm to train the sampled data, set the training parameters and sampling rate, and then train the regression tree. In this example, the number of decision trees is set to 20; the maximum number of features of the random forest model is set to 16, which is equal to the number of driving factors.

[0058] Step 4: Input all driving force data into the trained random forest and output the development potential of each land use type in the region.

[0059] Step 5: Input the development potential map and initial land use data into the CA model module of the multi-type random patch seed mechanism, set the conversion matrix and neighborhood weight, and set the target number of pixels according to the required area of ​​each land use type, that is, the number of pixels required for each type of land use in the future; The image pixel of Wuhan area in this example is 100m, so the neighborhood range is selected as 3×3 Moore neighborhood. The simulation time of this example is from 2003 to 2013, so the number of target pixels is consistent with the classification image of each type of land use in 2013. When the area of ​​all land use types reaches their corresponding required area, the simulation stops automatically. The conversion matrix is ​​restricted to deciduous forests and towns that cannot be converted to other land uses, and evergreen forests cannot be converted to other land uses except cultivated land. The neighborhood weight value of each land use type can be determined based on expert knowledge and a series of model tests, ranging from 0-1.

[0060] Step 6: Iteratively scan the pixels of the initial land use data, and synthesize the overall probability of various land use types in the pixel by calculating the land use types contained in the neighborhood of the pixel and the proportion of the land use types in the neighborhood, the adaptive inertia coefficient and the development probability of each type of land use; in addition, when the pixel neighborhood probability is 0, the overall probability of this type of land use type is composed of the development probability, the adaptive inertia coefficient, the random number, and the growth threshold of this type of land use type.

[0061] In this example, a scanning window is constructed through the neighborhood function to count the number of pixels in the window and measure the spatial interaction of different land use types. The neighborhood rule is defined as follows:

[0062] in represents the total number of grid cells occupied by land use type k at the last iteration within the n×n window, is the weight between different land use types, because different land use types have different neighborhood effects. In this example, n=3 is taken to construct the Moore neighborhood.

[0063] According to an embodiment of the present invention, the overall probability synthesis formula for roulette is:

[0064] in is a random value from 0 to 1; is the threshold for generating new land use patches for land use type k, which is mined by users, is the domain function, is an adaptive function. The maximum threshold for the number of new seeds generated in this example is set to 0.0001, which means that only 0.01% of the cells can generate new patches. The definition is as follows:

[0065] in and It is Second and Land use type at iteration The difference between current quantities and future demand.

[0066] Step 7: The overall probability of various land use types on the pixel constitutes a roulette wheel. By using the roulette wheel method, various land use types in the region compete on the pixel. This method proposes a threshold decreasing mechanism: when a new land use type wins in a round of competition, a decreasing threshold is used to determine whether the conversion occurs. The decreasing threshold for generating new patches set in this example is 0.5, and the attenuation coefficient is set to 0.1.

[0067] Step 8: After iterating all valid pixels of an image, return to step 6 to refresh the land use change image and enter the next iteration, and calculate the difference to the target number of pixels. When the target number of pixels is reached, stop the iteration and output the results.

[0068] Figure 5 The final output land use simulation map is: Figure 6 To compare the simulation results of the new model with the previous old model, the models involved in the comparison are: the degraded PLUS model (I) (using PAS), the degraded PLUS model (II) (without the multi-type random patch seed mechanism) and the FLUS model (CA model based on artificial neural network).

[0069] The present application also discloses a computer-readable storage medium storing a plurality of instructions suitable for loading by a processor to execute the above-mentioned patch generation land use simulation method.

[0070] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0071] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A patch generation land use simulation method, characterized in that: The method comprises the following steps: S1: Obtain initial land use data; obtain change grid data through the initial land use data; Obtain a preset number of driving factors affecting land use and land cover changes to form driving factor data; S2: Perform random point sampling on the driving factor data and the change grid data to obtain sampling data; S3: Preprocess the sampled data; build a random forest model based on the random forest classification algorithm; train the random forest model using the preprocessed sampled data; S4: Input all driving factor data into the trained random forest model to obtain the development probability of each type of land use and the development potential map of each land use type in the region; S5: Construct a CA model based on a multi-type random patch seed mechanism; set the transformation matrix and neighborhood weights of the CA model; set the target number of pixels of the CA model according to the required area of ​​each land use type; S6: Input the development potential map and the initial land use data into the CA model, iteratively scan each pixel of the initial land use data, and obtain the land use type contained in the neighborhood and the proportion of each pixel in the neighborhood and the adaptive inertia coefficient; The overall probability of each land use type in each pixel is obtained by combining the land use types contained in the neighborhood, the proportion of the pixel in the neighborhood, the adaptive inertia coefficient, and the development probability of each type of land use. S7: Construct a roulette wheel through the overall probability; through the roulette wheel method, transform various land use types in the pixel area into the land use type that wins the competition; When the adjacent effect of a land use type is equal to 0, different types of random seeds are generated by calculating the overall probability; new land use types are generated through random seeds; S8: Based on the threshold decreasing rule, determine whether the conversion of the new land use type that wins the competition occurs; S9: Repeat steps S6 to S8 until the iteration reaches the target number of pixels, then stop the iteration and output the land use simulation map.

2. A patch generation land use simulation method as claimed in claim 1, characterized in that: Step S1 includes: S11: Acquire an initial land use classification image; perform format conversion or reclassification on the initial land use classification image to obtain initial land use data; the initial land use data includes: first-period land use data and second-period land use data; S12: extracting the changed part between the two periods of the initial land use data, that is, extracting the grids with changed states from the second period of land use data; S13: Extracting grids whose states have changed between the two periods, namely, changed grid data, based on the first period land use data and the second period land use data.

3. A patch generation land use simulation method as claimed in claim 1, characterized in that: Step S2 includes: Using uniform sampling strategy or proportional sampling strategy, random point sampling is performed on driving factor data and change grid data to obtain sampling data. The sample formula after sampling is expressed as: in Indicates The first sampling point is extracted Driver data; Indicates The data of the change grid data extracted from the sampling points; is transposed.

4. A patch generation land use simulation method as claimed in claim 1, characterized in that: Step S3 includes: The sampled data is normalized, and the normalization formula is as follows: in and Respectively represent The maximum and minimum values ​​of each driver; .

5. The patch generation land use simulation method according to claim 1, characterized in that: Step S3 also includes: The random forest classification algorithm is expressed as follows: in is a constant, either 0 or 1; is a vector consisting of a preset number of driving factors; is the indicator function of the decision tree set; is a vector The prediction type of the nth decision tree; is the total count of the decision tree.

6. A patch generation land use simulation method as claimed in claim 5, characterized in that: Step S6 includes: The overall probability synthesis formula is: in is a random value from 0 to 1; For land use type Thresholds for generating new land use patches, which are mined by users; is the neighborhood function; A scanning window is constructed through the neighborhood function, and the number of various pixels in the scanning window is counted to measure the spatial mutual influence of various land use types; Neighborhood functions is defined as follows: in Indicates the land use type at the last iteration within the n×n window The total number of grid cells occupied, is the weight between different land use types; Adaptive function The adaptive method is defined as follows: in and It is Second and Land use type at iteration The difference between current quantities and future demand.

7. A patch generation land use simulation method as claimed in claim 1, characterized in that: Step S7 includes: The threshold decreasing rule, the formula is as follows: in, The decreasing threshold The attenuation coefficient, Random values ​​that follow a normal distribution; is the decreasing threshold; is the number of attenuation times; is the decreasing step length; Defines whether land use type k is allowed to be converted to type The transformation matrix of represents the random forest probability, i.e., pixel Developed into type probability.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed by a computer, the method according to any one of claims 1 to 7 is executed.

Images