Town space expansion simulation test analysis method based on historical data

Abstract

The invention discloses a historical data-based town spatial extension simulation test analysis method, which comprises the following steps of: obtaining historical town spatial extension data, and obtaining a town spatial extension conversion rule; a cellular automaton is used for obtaining a cellular transformation rule according to the city expansion transformation rule, a cellular automaton model is constructed, multiple subject policies are obtained through collection, and a multi-agent model is constructed through a multi-agent system; fusing the cellular automaton model and the multi-agent model to obtain a CA-MAS combined model, and establishing a town space expansion simulation model; carrying out superposition test on a town space expansion simulation result and a town space expansion actual condition, and continuously optimizing a town space expansion simulation model; the optimal scene and the optimal strategy of urban development are obtained through scene analysis, the cellular automaton model and the multi-agent model are fused, the influence of urban natural expansion and human policies on urban expansion is considered at the same time, and the accuracy of the urban dynamic expansion simulation model is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban space expansion simulation, and in particular to an urban space expansion simulation test and analysis method based on historical data. Background Art

[0002] In recent years, the utilization of land resources has attracted great attention from the society. Urbanization can be said to be the most critical form of land use and land cover change. Studying the simulation model of urban space evolution has important strategic significance for improving the quality of urban space utilization, promoting the coordination and unification of social benefits, economic benefits and ecological benefits, and achieving sustainable development.

[0003] At present, the Chinese invention patent application number is 201711484065.8, which discloses a method for constructing an urban CA model based on the maximum entropy principle. The present invention constructs a maximum entropy CA model and applies it to the simulation of urban land expansion, taking into account the problem of randomness, which helps to simulate urban development more accurately. However, it does not consider the impact of human subjects and different urban development policies on urban spatial expansion, nor does it verify and test the simulation results of urban expansion, and cannot guarantee the accuracy of the simulation results. Summary of the invention

[0004] The technical problem solved by the present invention is that the relevant technology does not consider the impact of human subjects and different urban development policies on urban spatial expansion, and does not verify and test the simulation results of urban expansion, and cannot guarantee the accuracy of the simulation results.

[0005] In order to solve the above technical problems, the present invention provides a method for analyzing the simulation test of urban expansion based on historical data, comprising the following steps:

[0006] Step S1: obtaining historical town space expansion data, performing data preprocessing on the historical town space expansion simulation data, and obtaining town space expansion transformation rules using a logistic regression analysis method;

[0007] Step S2: using cellular automata to obtain cellular transformation rules according to the urban space expansion transformation rules, constructing a cellular automata model according to the cellular transformation rules, collecting and obtaining the government’s main policies, residents’ main policies and developers’ main policies, and constructing a multi-agent model according to the government’s main policies, residents’ main policies and developers’ main policies using a multi-agent system;

[0008] Step S3: The cellular automaton model and the multi-agent model are integrated to obtain a CA-MAS combined model, and a town space expansion simulation model is established based on the CA-MAS combined model using a GIS geographic information system;

[0009] Step S4: superimpose the urban space expansion simulation results with the actual urban space expansion situation, compare point by point to obtain the fitting accuracy, and continuously optimize the urban space expansion simulation model until the fitting accuracy is greater than or equal to the expected threshold, so as to obtain the best urban space expansion simulation model;

[0010] Step S5: Introducing scenario analysis into the urban space expansion simulation model, obtaining the urban space expansion simulation models under different scenarios, and performing comparative analysis on the urban space expansion simulation models under different scenarios to obtain the best scenario and best strategy for urban development;

[0011] As a preferred solution of the method for simulating and testing the expansion of urban space based on historical data described in the present invention, the step S1 specifically includes:

[0012] Step S201, obtaining the historical town spatial extension data, the historical town spatial extension data including remote sensing image data, land use status data, DEM digital elevation model data and social economic data;

[0013] Step S202, preprocessing the remote sensing images, land use status data, DEM digital elevation model data and socio-economic data to obtain historical urban spatial expansion data after removing redundancy;

[0014] Step S203, using a logistic regression analysis method to perform attribution analysis on the historical urban spatial expansion data after redundancy removal, to obtain various influencing factors and their weights;

[0015] Step S204, obtaining a town space expansion conversion rule according to the weight of each influencing factor;

[0016] The influencing factors include natural factors, social factors and economic factors;

[0017] As a preferred solution of the method for simulating and testing the expansion of urban space based on historical data described in the present invention, step S2 specifically includes:

[0018] Step S201, setting the cell states in the cellular automaton to include non-urban land and urban land, obtaining cell transformation rules and cell transformation probabilities according to urban space expansion transformation rules, and establishing a cellular automaton model according to the cell transformation rules and cell transformation probabilities;

[0019] Step S202, after collecting and acquiring the government main policy, the resident main policy and the developer main policy, the government main policy includes the government main location probability P1, the resident main policy includes the resident main location probability P2, and the developer main policy includes the developer main location probability P3;

[0020] The government entity location probability P1 is expressed as follows:

[0021] P1=P f1 ×P f2

[0022] Among them, P f1 represents the probability that the relevant area is a prohibited construction area, the P f2 It represents the land importance index;

[0023] The expression formula of the main site selection probability P2 of residents is as follows:

[0024] P2=a×P 21 +b×P 22 +c×P 23 +d×P 24

[0025] Among them, P 21 represents traffic accessibility, P 22 Indicates the convenience of life, P 23 Indicates the beauty of the environment, P 24 represents the degree of educational resources, wherein a represents the weight coefficient of traffic accessibility, b represents the weight coefficient of living convenience, c represents the weight coefficient of environmental beauty, and d represents the weight coefficient of educational resources, and a+b+c+d=1;

[0026] The developer's main policy site selection probability P3 is expressed as follows:

[0027]

[0028] Among them, P3 represents the site selection probability of the developer, n represents the neighborhood window size, ∑ n×n N(urban i,j ) represents the number of construction land in the neighborhood window;

[0029] Step S203, obtaining the regional conversion probability of a certain area according to the government main policy, the resident main policy and the developer main policy, and establishing a multi-agent model according to the regional conversion probability;

[0030] As a preferred solution of the method for simulating and testing the expansion of urban space based on historical data described in the present invention, step S3 specifically includes:

[0031] Step S301, obtaining a final cell transition probability according to the cell transition probability and the region transition probability;

[0032] Step S302, gridding the town remote sensing image using grids and making one-to-one correspondence between grids and cells;

[0033] Step S303, using ArcGIS software to build a CA-MAS urban expansion simulation model according to the final cell transformation probability and cell transformation rules;

[0034] As a preferred solution of the method for simulating and testing the expansion of urban space based on historical data described in the present invention, step S4 specifically includes:

[0035] Step S401, obtaining actual images and actual data of town expansion;

[0036] Step S402, using a point-by-point comparison method, the CA-MAS urban expansion simulation model is compared with the actual image and actual data of urban expansion to obtain the fitting accuracy of each area in the CA-MAS urban expansion simulation model;

[0037] Step S403, obtaining the model fitting accuracy K according to the fitting accuracy of each region, and the expression of the model fitting accuracy K is as follows:

[0038]

[0039] Among them, P0 represents the proportion of correct simulation, P c represents the expected simulation proportion under random conditions, the P p represents the proportion of correct simulation under ideal conditions;

[0040] Step S404, if the fitting accuracy K of the CA-MAS urban expansion simulation model is greater than or equal to the expected threshold, the CA-MAS urban expansion simulation model is defined as the best simulation model;

[0041] If the fitting accuracy K of the CA-MAS urban expansion simulation is less than the expected threshold, the regional fitting accuracy is sorted, n regions with unsatisfactory fitting accuracy are screened out, and the regions with unsatisfactory fitting accuracy are analyzed and adjusted until the model fitting accuracy K reaches the expected threshold, and the adjusted CA-MAS urban expansion simulation model is defined as the best simulation model;

[0042] As a preferred solution of the method for simulating and testing the expansion of urban space based on historical data of the present invention, the step S5 specifically includes:

[0043] Step S501, obtaining current town extension data, and preprocessing the current town extension data;

[0044] Step S502, formulating different town expansion scenarios according to town expansion needs, and obtaining multiple town expansion strategies according to different town expansion scenarios;

[0045] Step S503, establishing multiple town space expansion simulation models for each town expansion strategy and the pre-processed town expansion data, and selecting the best scenario and the town space expansion simulation model under the best scenario according to the town expansion demand;

[0046] The urban expansion scenarios include natural development scenario, economic priority scenario and ecological priority scenario;

[0047] As a preferred solution of the method for simulating and testing the expansion of urban space based on historical data of the present invention, the steps S203 and S204 include:

[0048] Set up the logistic regression analysis function;

[0049] Use the logistic regression analysis function to obtain each influencing factor and its weight;

[0050] The influencing factors are standardized using the fuzzy membership function model;

[0051] Introducing random interference factors, the urban space expansion transformation rules are obtained according to the weights of various influencing factors and random interference factors;

[0052] As a preferred solution of the method for simulating and testing the expansion of urban space based on historical data of the present invention, the method of obtaining the cellular transformation rule and the cellular transformation probability according to the urban space expansion transformation rule comprises:

[0053] Use neighborhood operations to obtain neighborhood development probability;

[0054] The neighborhood factor is introduced into the impact factor, and the domain factor weight is obtained by using the logistic regression analysis method;

[0055] Obtain the cell transition rule and cell transition probability according to the influence factor and the influence factor weight after adding the neighborhood factor weight;

[0056] As a preferred solution of the method for simulating and testing the urban space expansion based on historical data described in the present invention, the CA-MAS urban expansion simulation model is compared with the actual image and actual data of urban expansion using a point-by-point comparison method, including regional area comparison and spatial distribution comparison;

[0057] The regional area comparison includes obtaining the regional area accuracy according to the simulated expansion area and the actual expansion area;

[0058] The spatial distribution comparison includes obtaining spatial comparison accuracy according to the simulated spatial position distribution and the actual spatial position distribution, and the spatial comparison accuracy is used to measure the consistency of the spatial position distribution;

[0059] An electronic device comprising a processor and a memory:

[0060] The memory stores a computer program that can be called by the processor; the processor executes the above-mentioned urban space expansion simulation test and analysis method based on historical data by calling the computer program stored in the memory.

[0061] The beneficial effects of the present invention are as follows: the present invention integrates the cellular automaton model and the multi-agent model to achieve complementary advantages of the two models. It not only follows the principle that human behavior is the fundamental driving force for promoting urban development, but also takes into account the self-organizing performance of urban space development, simulates the dynamic changes of towns more realistically, and improves the accuracy of the dynamic expansion simulation model of towns.

[0062] Verify and test the urban expansion simulation model through existing data, continuously optimize the urban expansion simulation model, and improve the accuracy of urban expansion model predictions.

[0063] By introducing multi-scenario analysis, the development scenario that best suits the current development status and future development strategies is screened out based on the simulation results of the urban expansion simulation model of each scenario, providing a reliable data basis for the macro-control of future urban expansion. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A basic flow chart of a method for simulating, testing and analyzing urban space expansion based on historical data is provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0066] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a method for analyzing a simulation test of urban expansion based on historical data, comprising:

[0067] Step S1: obtaining historical town space expansion data, performing data preprocessing on the historical town space expansion simulation data, and obtaining town space expansion transformation rules using a logistic regression analysis method;

[0068] Step S2: using cellular automata to obtain cellular transformation rules according to the urban space expansion transformation rules, constructing a cellular automata model according to the cellular transformation rules, collecting and obtaining the government’s main policies, residents’ main policies and developers’ main policies, and constructing a multi-agent model according to the government’s main policies, residents’ main policies and developers’ main policies using a multi-agent system;

[0069] Step S3: The cellular automaton model and the multi-agent model are integrated to obtain a CA-MAS combined model, and a town space expansion simulation model is established based on the CA-MAS combined model using a GIS geographic information system;

[0070] Step S4: superimpose the urban space expansion simulation results with the actual urban space expansion situation, compare point by point to obtain the fitting accuracy, and continuously optimize the urban space expansion simulation model until the fitting accuracy is greater than or equal to the expected threshold, so as to obtain the best urban space expansion simulation model;

[0071] Step S5: Introducing scenario analysis into the urban space expansion simulation model, obtaining the urban space expansion simulation models under different scenarios, and performing comparative analysis on the urban space expansion simulation models under different scenarios to obtain the best scenario and best strategy for urban development;

[0072] In this embodiment, by integrating the cellular automaton model and the multi-agent model, the advantages of the two models are complemented, the accuracy of the town dynamic expansion simulation model is improved, the town expansion simulation model is verified and tested through existing data, the town expansion simulation model is continuously optimized, and the accuracy of the urban expansion model prediction is improved. By introducing multi-scenario analysis, the development scenario that best meets the current development status and future development strategy is screened out according to the simulation results of the town expansion simulation model of each scenario, providing a reliable data basis for the macro-control of future town expansion;

[0073] The step S1 specifically includes:

[0074] Step S201, obtaining the historical town spatial extension data, the historical town spatial extension data including remote sensing image data, land use status data, DEM digital elevation model data and social economic data;

[0075] Step S202, preprocessing the remote sensing images, land use status data, DEM digital elevation model data and socio-economic data to obtain historical urban spatial expansion data after removing redundancy;

[0076] Step S203, using a logistic regression analysis method to perform attribution analysis on the historical urban spatial expansion data after redundancy removal, to obtain various influencing factors and their weights;

[0077] Step S204, obtaining a town space expansion conversion rule according to the weight of each influencing factor;

[0078] The influencing factors include natural factors, social factors and economic factors;

[0079] The preprocessing of remote sensing images comprises:

[0080] Radiometric calibration: converting the digital quantization value of an image into physical quantities such as radiation brightness value, reflectivity or surface temperature;

[0081] Atmospheric correction: Correct the influence of the atmosphere on remote sensing images, eliminate the influence of factors such as atmospheric scattering and absorption, and obtain reflectance data;

[0082] Orthorectification: Eliminate geometric distortion in remote sensing images and accurately map pixels to the earth's surface;

[0083] Geometric registration: geometrically transform the image so that it can correspond to the geographic coordinate system so that geospatial analysis can be performed;

[0084] Image fusion: Fuse remote sensing images of multiple bands to obtain more comprehensive and accurate information;

[0085] The logistic regression analysis method is a statistical method widely used in classification problems. It is a linear model used to solve binary or multi-classification problems. Logistic regression uses a logistic function to map the output of the linear model to a probability space, thereby predicting the probability of an event.

[0086] In this embodiment, the town space expansion rules are obtained by the logistic regression analysis method, which provides reliable town space transformation rules for obtaining cellular transformation rules and cellular transformation probabilities and establishing cellular automaton models;

[0087] The step S2 specifically includes:

[0088] Step S201, setting the cell states in the cellular automaton to include non-urban land and urban land, obtaining cell transformation rules and cell transformation probabilities according to urban space expansion transformation rules, and establishing a cellular automaton model according to the cell transformation rules and cell transformation probabilities;

[0089] Step S202, after collecting and acquiring the government main policy, the resident main policy and the developer main policy, the government main policy includes the government main location probability P1, the resident main policy includes the resident main location probability P2, and the developer main policy includes the developer main location probability P3;

[0090] The government entity location probability P1 is expressed as follows:

[0091] P1=P f1 ×P f2

[0092] Among them, P f1 represents the probability that the relevant area is a prohibited construction area, the P f2 It represents the land importance index;

[0093] The expression formula of the main site selection probability P2 of residents is as follows:

[0094] P2=a×P 21 +b×P 22 +c×P 23 +d×P 24

[0095] Among them, P 21 represents traffic accessibility, P 22 Indicates the convenience of life, P 23 Indicates the beauty of the environment, P 24 represents the degree of educational resources, wherein a represents the weight coefficient of traffic accessibility, b represents the weight coefficient of living convenience, c represents the weight coefficient of environmental beauty, and d represents the weight coefficient of educational resources, and a+b+c+d=1;

[0096] The developer's main policy site selection probability P3 is expressed as follows:

[0097]

[0098] Among them, P3 represents the site selection probability of the developer, n represents the neighborhood window size, ∑ n×n N(urban i,j ) represents the number of construction land in the neighborhood window;

[0099] Step S203, obtaining the regional conversion probability of a certain area according to the government main policy, the resident main policy and the developer main policy, and establishing a multi-agent model according to the regional conversion probability;

[0100] The expression of the area transition probability is as follows:

[0101] P MAS =μ×P1+ν×P2+λ×P3

[0102] Among them, P MAS represents the regional conversion probability in the multi-agent model, P1 represents the site selection probability of the government subject, P2 represents the site selection probability of the residents subject, P3 represents the site selection probability of the developer subject, μ represents the weight coefficient of the government subject, ν represents the weight coefficient of the residents subject, λ represents the weight coefficient of the developer subject, μ+ν+λ=1;

[0103] In this embodiment, the probability of urban area conversion is obtained according to the government's main policy, the residents' main policy and the developer's main policy, and a multi-agent model is established according to the probability of urban area conversion, which provides a model basis for establishing a CA-MAS urban space expansion simulation model;

[0104] The step S3 specifically includes:

[0105] Step S301, obtaining a final cell transition probability according to the cell transition probability and the region transition probability;

[0106] Step S302, gridding the town remote sensing image using grids and making one-to-one correspondence between grids and cells;

[0107] Step S303, using ArcGIS software to build a CA-MAS urban expansion simulation model according to the final cell transformation probability and cell transformation rules;

[0108] In this embodiment, by integrating the cellular automaton model and the multi-agent model, the advantages of the two models are complemented, which not only follows the principle that human behavior is the fundamental driving force for promoting urban development, but also takes into account the self-organizing performance of urban space development, simulates the dynamic changes of towns more realistically, and improves the accuracy of the dynamic expansion simulation model of towns;

[0109] The step S4 specifically includes:

[0110] Step S401, obtaining actual images and actual data of town expansion;

[0111] Step S402, using a point-by-point comparison method, the CA-MAS urban expansion simulation model is compared with the actual image and actual data of urban expansion to obtain the fitting accuracy of each area in the CA-MAS urban expansion simulation model;

[0112] Step S403, obtaining the model fitting accuracy K according to the fitting accuracy of each region, and the expression of the model fitting accuracy K is as follows:

[0113]

[0114] Among them, P0 represents the proportion of correct simulation, P c represents the expected simulation proportion under random conditions, the P p represents the proportion of correct simulation under ideal conditions;

[0115] Step S404, if the fitting accuracy K of the CA-MAS urban expansion simulation model is greater than or equal to the expected threshold, the CA-MAS urban expansion simulation model is defined as the best simulation model;

[0116] If the fitting accuracy K of the CA-MAS urban expansion simulation is less than the expected threshold, the regional fitting accuracy is sorted, n regions with unsatisfactory fitting accuracy are screened out, and the regions with unsatisfactory fitting accuracy are analyzed and adjusted until the model fitting accuracy K reaches the expected threshold, and the adjusted CA-MAS urban expansion simulation model is defined as the best simulation model;

[0117] In this embodiment, the simulation results of urban space expansion are superimposed on the actual situation of urban space expansion, and the fitting accuracy is obtained by point-by-point comparison, so as to continuously optimize the simulation model of urban space expansion and improve the accuracy of the simulation model of urban space expansion;

[0118] The step S5 specifically includes:

[0119] Step S501, obtaining current town extension data, and preprocessing the current town extension data;

[0120] Step S502, formulating different town expansion scenarios according to town expansion needs, and obtaining multiple town expansion strategies according to different town expansion scenarios;

[0121] Step S503, establishing multiple town space expansion simulation models for each town expansion strategy and the pre-processed town expansion data, and selecting the best scenario and the town space expansion simulation model under the best scenario according to the town expansion demand;

[0122] The urban expansion scenarios include natural development scenario, economic priority scenario and ecological priority scenario;

[0123] In this embodiment, by introducing multi-scenario analysis, the development scenario that best matches the current development status and future development strategy is selected based on the simulation results of the urban expansion simulation model of each scenario, providing a reliable data basis for the macro-control of future urban expansion;

[0124] The steps S203 and S204 include:

[0125] Set up the logistic regression analysis function;

[0126] Use the logistic regression analysis function to obtain each influencing factor and its weight;

[0127] The influencing factors are standardized using the fuzzy membership function model;

[0128] Introducing random interference factors, the urban space expansion transformation rules are obtained according to the weights of various influencing factors and random interference factors;

[0129] The logistic regression analysis function expression is as follows:

[0130] Logistic(P)=β0+β1X1+β2X2+……+β n X n

[0131] The dependent variable Logistic(P) is the natural logarithm of the probability P when the transformation occurs, β0 is a constant term, and β n(n=1, 2...n) is the coefficient of each regression variable in the regression equation, X n (n=1,2……n) represents the factors affecting the expansion of construction land;

[0132] In this embodiment, the weight of each influencing factor is obtained by using a logistic regression analysis function, and a random interference factor is introduced, and the random interference factor is also added to the influencing factor of the town conversion probability, thereby improving the accuracy of the cellular automaton model;

[0133] The step of obtaining the cellular transformation rule and the cellular transformation probability according to the urban space expansion transformation rule includes:

[0134] Use neighborhood operations to obtain neighborhood development probability;

[0135] The neighborhood factor is introduced into the influencing factor, and the neighborhood factor weight is obtained by using the logistic regression analysis method;

[0136] Obtain the cell transition rule and cell transition probability according to the influence factor and the influence factor weight after adding the neighborhood factor weight;

[0137] In this embodiment, the neighborhood development probability is obtained according to the neighborhood operation, and the neighborhood factor is introduced into the influencing factor of town conversion, which provides more accurate neighborhood factor influence data for obtaining cell conversion rules and cell conversion probability;

[0138] The CA-MAS urban expansion simulation model is compared with the actual images and data of urban expansion using a point-by-point comparison method, including regional area comparison and spatial distribution comparison;

[0139] The regional area comparison includes obtaining the regional area accuracy according to the simulated expansion area and the actual expansion area;

[0140] The spatial distribution comparison includes obtaining spatial comparison accuracy according to the simulated spatial position distribution and the actual spatial position distribution, and the spatial comparison accuracy is used to measure the consistency of the spatial position distribution;

[0141] In this embodiment, the accuracy of the urban space expansion simulation model is obtained through a point-by-point comparison method, the accuracy of the urban space expansion simulation model is continuously optimized, and the accuracy of the urban space expansion simulation is improved.

[0142] The present invention integrates the cellular automaton model and the multi-agent model to achieve complementary advantages of the two models. It not only follows the principle that human behavior is the fundamental driving force for promoting urban development, but also takes into account the self-organizing performance of urban space development, simulates urban dynamic changes more realistically, and improves the accuracy of the urban dynamic expansion simulation model.

[0143] Verify and test the urban expansion simulation model through existing data, continuously optimize the urban expansion simulation model, and improve the accuracy of urban expansion model prediction;

[0144] By introducing multi-scenario analysis, the development scenario that best suits the current development status and future development strategies is screened out based on the simulation results of the urban expansion simulation model of each scenario, providing a reliable data basis for the macro-control of future urban expansion.

[0145] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A simulation test and analysis method for urban space expansion based on historical data, characterized in that: include: Step S1: obtaining historical town space expansion data, performing data preprocessing on the historical town space expansion simulation data, and obtaining town space expansion transformation rules using a logistic regression analysis method; Step S2: using cellular automata to obtain cellular transformation rules according to the urban space expansion transformation rules, constructing a cellular automata model according to the cellular transformation rules, collecting and obtaining the government’s main policies, residents’ main policies and developers’ main policies, and constructing a multi-agent model according to the government’s main policies, residents’ main policies and developers’ main policies using a multi-agent system; Step S3: The cellular automaton model and the multi-agent model are integrated to obtain a CA-MAS combined model, and a town space expansion simulation model is established based on the CA-MAS combined model using a GIS geographic information system; Step S4: superimpose the urban space expansion simulation results with the actual urban space expansion situation, compare point by point to obtain the fitting accuracy, and continuously optimize the urban space expansion simulation model until the fitting accuracy is greater than or equal to the expected threshold, so as to obtain the best urban space expansion simulation model; Step S5: Introduce scenario analysis into the urban space expansion simulation model, obtain the urban space expansion simulation models under different scenarios, conduct comparative analysis on the urban space expansion simulation models under different scenarios, and obtain the best scenario and best strategy for urban development.

2. The method for simulating, testing and analyzing urban space expansion based on historical data according to claim 1, characterized in that: The step S1 specifically includes: Step S201, obtaining the historical town spatial extension data, the historical town spatial extension data including remote sensing image data, land use status data, DEM digital elevation model data and social economic data; Step S202, preprocessing the remote sensing images, land use status data, DEM digital elevation model data and socio-economic data to obtain historical urban spatial expansion data after removing redundancy; Step S203, using a logistic regression analysis method to perform attribution analysis on the historical urban spatial expansion data after redundancy removal, to obtain various influencing factors and their weights; Step S204, obtaining a town space expansion conversion rule according to the weight of each influencing factor; The influencing factors include natural factors, social factors and economic factors.

3. The method for simulating, testing and analyzing urban space expansion based on historical data according to claim 1, characterized in that: The step S2 specifically includes: Step S201, setting the cell states in the cellular automaton to include non-urban land and urban land, obtaining cell transformation rules and cell transformation probabilities according to urban space expansion transformation rules, and establishing a cellular automaton model according to the cell transformation rules and cell transformation probabilities; Step S202, after collecting and acquiring the government main policy, the resident main policy and the developer main policy, the government main policy includes the government main location probability P1, the resident main policy includes the resident main location probability P2, and the developer main policy includes the developer main location probability P3; The government entity location probability P1 is expressed as follows: P1=P f1 ×P f2 Among them, P f1 represents the probability that the relevant area is a prohibited construction area, the P f2 It represents the land importance index; The expression formula of the resident main site selection probability P2 is as follows: P2=a×P 21 +b×P 22 +c×P 23 +d×P 24 Among them, P 21 represents traffic accessibility, P 22 Indicates the convenience of life, P 23 Indicates the beauty of the environment, P 24 represents the degree of educational resources, wherein a represents the weight coefficient of traffic accessibility, b represents the weight coefficient of living convenience, c represents the weight coefficient of environmental beauty, and d represents the weight coefficient of educational resources, and a+b+c+d=1; The developer's main policy site selection probability P3 is expressed as follows: Among them, P3 represents the site selection probability of the developer, n represents the neighborhood window size, ∑ n×n N(urban i,j ) represents the number of construction land in the neighborhood window; Step S203, obtaining the regional conversion probability of a certain area according to the government's main policies, residents' main policies and developers' main policies, and establishing a multi-agent model according to the regional conversion probability.

4. The method for simulating, testing and analyzing urban space expansion based on historical data according to claim 1, characterized in that: The step S3 specifically includes: Step S301, obtaining a final cell transition probability according to the cell transition probability and the region transition probability; Step S302, gridding the town remote sensing image using grids and making one-to-one correspondence between grids and cells; Step S303: Using ArcGIS software to build a CA-MAS urban expansion simulation model according to the final cell transformation probability and cell transformation rules.

5. The method for simulating, testing and analyzing urban space expansion based on historical data according to claim 1, characterized in that: The step S4 specifically includes: Step S401, obtaining actual images and actual data of town expansion; Step S402, using a point-by-point comparison method, the CA-MAS urban expansion simulation model is compared with the actual image and actual data of urban expansion to obtain the fitting accuracy of each area in the CA-MAS urban expansion simulation model; Step S403, obtaining the model fitting accuracy K according to the fitting accuracy of each region, and the expression of the model fitting accuracy K is as follows: Among them, P0 represents the proportion of correct simulation, P c represents the expected simulation proportion under random conditions, the P p represents the proportion of correct simulation under ideal conditions; Step S404, if the fitting accuracy K of the CA-MAS urban expansion simulation model is greater than or equal to the expected threshold, the CA-MAS urban expansion simulation model is defined as the best simulation model; If the fitting accuracy K of the CA-MAS urban expansion simulation is less than the expected threshold, the regional fitting accuracy is sorted, n areas with unsatisfactory fitting accuracy are screened out, and the areas with unsatisfactory fitting accuracy are analyzed and adjusted until the model fitting accuracy K reaches the expected threshold. The adjusted CA-MAS urban expansion simulation model is defined as the optimal simulation model.

6. The method for simulating, testing and analyzing urban space expansion based on historical data according to claim 1, characterized in that: The step S5 specifically includes: Step S501, obtaining current town extension data, and preprocessing the current town extension data; Step S502, formulating different town expansion scenarios according to town expansion needs, and obtaining multiple town expansion strategies according to different town expansion scenarios; Step S503, establishing multiple town space expansion simulation models for each town expansion strategy and the pre-processed town expansion data, and selecting the best scenario and the town space expansion simulation model under the best scenario according to the town expansion demand; The urban expansion scenarios include natural development scenarios, economic priority scenarios and ecological priority scenarios.

7. The method for simulating, testing and analyzing urban space expansion based on historical data according to claim 2, characterized in that: The steps S203 and S204 include: Set up the logistic regression analysis function; Use the logistic regression analysis function to obtain each influencing factor and its weight; The influencing factors are standardized using the fuzzy membership function model; Random interference factors are introduced, and the urban space expansion transformation rules are obtained according to the weights of various influencing factors and random interference factors.

8. The method for simulating, testing and analyzing urban space expansion based on historical data according to claim 1, characterized in that: The step of obtaining the cellular transformation rule and the cellular transformation probability according to the urban space expansion transformation rule includes: Use neighborhood operations to obtain neighborhood development probability; The neighborhood factor is introduced into the influencing factor, and the neighborhood factor weight is obtained by using the logistic regression analysis method; The cell transition rule and cell transition probability are obtained according to the influence factor and the influence factor weight after adding the neighborhood factor weight.

9. The method for simulating, testing and analyzing urban space expansion based on historical data according to claim 1, characterized in that: The CA-MAS urban expansion simulation model is compared with the actual images and data of urban expansion using a point-by-point comparison method, including regional area comparison and spatial distribution comparison; The regional area comparison includes obtaining the regional area accuracy according to the simulated expansion area and the actual expansion area; The spatial distribution comparison includes obtaining spatial comparison accuracy according to the simulated spatial position distribution and the actual spatial position distribution, and the spatial comparison accuracy is used to measure the consistency of the spatial position distribution.

10. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the urban space expansion simulation test and analysis method based on historical data as described in claims 1 to 9 by calling the computer program stored in the memory.

Images