Land space planning intelligent optimization method and system based on multi-objective evolutionary algorithm

Abstract

The invention discloses an intelligent optimization method and system for territorial space planning based on a multi-objective evolutionary algorithm, and relates to the technical field of territorial space planning, and the method comprises the steps: collecting multi-source basic data needed by territorial space planning, and carrying out the optimization of the territorial space planning based on ecological environment bearing capacity and construction land development suitability indexes; constructing a nonlinear mapping model to quantitatively evaluate the development risk of each grid unit, constructing a multi-objective optimization model covering economic, ecological and social benefits by taking the area or quantity of each land type as a decision variable, and calculating the development risk of each grid unit in combination with the initial land utilization state and developable spatial data. The FLUS model is adopted to carry out simulation expansion on the urban development boundary, and the planning scale and the land use growth trend are responded in real time by dynamically adjusting the conversion rule in the simulation process. According to the method, the data integration accuracy and the model response flexibility are remarkably improved, the scientificity and the intelligent level of planning decision making are enhanced, and powerful technical support is provided for regional sustainable development.

Description

Technical Field

[0001] The present invention relates to the technical field of territorial space planning, and specifically provides an intelligent optimization method and system for territorial space planning based on a multi-objective evolutionary algorithm. Background Art

[0002] In recent years, with the rapid development of remote sensing technology, geographic information system (GIS), and big data analysis, the field of territorial space planning is undergoing a profound technological innovation. Multi-objective evolutionary algorithms and cellular automata models have been widely used in urban planning and land use optimization, which use methods such as genetic algorithms and non-dominated sorting to achieve a trade-off between economic, ecological, and social multi-objectives. At the same time, as a spatial simulation tool, the FLUS model has made certain progress in predicting the expansion of urban development boundaries. The introduction of a dynamic parameter adjustment mechanism and a multi-agent collaborative decision-making system has made the planning model have higher adaptability and real-time response capabilities, providing a solid technical support for regional sustainable development.

[0003] However, there are still many deficiencies in the existing technologies for realizing the intelligent optimization of territorial space planning. First, due to the heterogeneity of multi-source spatial data in terms of acquisition means, resolution, and data format, even after unified coordinate transformation, format standardization, denoising, bias correction, and resampling processing, its spatial accuracy and consistency are still difficult to fully meet the requirements of high-resolution planning. Second, the traditional non-linear mapping model and static conversion rules based on ecological environment carrying capacity and construction land development suitability indicators fail to capture the dynamic changes and expansion trends of land use within the region in real time, resulting in a deviation between the simulated urban development boundary and the actual situation. In addition, the current multi-objective optimization models constructed with various land use areas or quantities as decision variables mainly rely on fixed parameter weights for the balance between multi-objectives, lacking a dynamic adaptive adjustment mechanism and being difficult to fully integrate the complex interactions between economic benefits, ecological protection, and social benefits. More critically, the existing methods have not established a multi-agent collaborative decision-making platform covering multiple parties such as the government, ecological protection departments, development entities, and the public, and cannot achieve effective interaction and consensus formation among various entities in the simulated scenarios, thus restricting the comprehensive optimization effect of the planning results. Therefore, there is an urgent need for an intelligent optimization method for territorial space planning that can dynamically adjust parameters, provide real-time feedback and correction, and integrate the interests of multiple parties to achieve the goals of high precision, dynamic adaptability, and multi-agent collaborative decision-making. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed.

[0005] Therefore, the technical problem to be solved by the present invention is that the existing national land space planning methods have problems such as low data integration accuracy, insufficient dynamic response ability, imperfect multi-agent collaborative decision-making, and how to achieve high-precision dynamic self-adaptation and multi-stakeholder collaborative optimization of national land space planning.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: An intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm, including collecting multi-source spatial data, performing unified coordinate transformation, format standardization, denoising and deviation correction, and resampling operations, and using a grid method to divide the research area into uniform spatial units to form a database integrating ecological environment and social and economic indicators; based on the ecological environment carrying capacity index and the construction land development suitability index, constructing a non-linear mapping model to quantify the development risk of each grid unit and output a risk assessment value, using the area or quantity of various land use types as decision variables, constructing a multi-objective optimization model that simultaneously considers economic benefits, ecological protection, and social benefits, and using an improved multi-objective evolutionary algorithm NSGA-II with a dynamic parameter adjustment mechanism to output a Pareto optimal solution set that meets the multi-objective equilibrium conditions, and screening the optimal solution according to the objective preference; combining the initial land use status and the spatial distribution of developability, using the FLUS model to simulate the expansion process of the urban development boundary, dynamically adjusting the conversion rules during the simulation process to adapt to the land use growth trend and planning scale, importing the evaluation and simulation results into a multi-agent collaborative decision-making system, forming an optimal collaborative decision result through the interest drive of each subject, establishing a feedback mechanism, and continuously adjusting the modeling parameters and rules through the comparative analysis of historical data and real-time monitoring data.

[0007] As a preferred embodiment of the intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to the present invention, wherein: the output of the risk assessment value includes constructing a risk index mapping method that fits the actual situation by considering the non-linear relationship between the ecological environment carrying capacity and the construction land development suitability.

[0008] As a preferred embodiment of the intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to the present invention, wherein: the multi-objective optimization model includes respectively modeling the economic objective, the ecological objective, and the social objective through characteristic coefficients, and introducing dynamic adjustment parameters to adapt to changes in the environment and population state during the evolution process.

[0009] As a preferred embodiment of the intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to the present invention, wherein: the FLUS model includes adopting a neighborhood effect and a time series adjustment strategy during the simulation process of the development boundary to realize the dynamic coupling of the suitability of spatial units and the surrounding development influencing factors.

[0010] As a preferred solution of the intelligent optimization method for territorial space planning based on the multi-objective evolutionary algorithm according to the present invention, wherein: the Pareto optimal solution set that meets the multi-objective equilibrium condition includes ensuring the high-precision fusion of multi-source heterogeneous data under a unified spatial reference system, and realizing the complete coverage and attribute matching of the data set in the geographical space.

[0011] As a preferred solution of the intelligent optimization method for territorial space planning based on the multi-objective evolutionary algorithm according to the present invention, wherein: the multi-agent collaborative decision-making system includes training its own behavior strategy using a machine learning algorithm according to the interest goal, and collaboratively outputting the optimal land use configuration plan that meets the expectations of multiple parties through information exchange and non-dominated sorting method on the platform.

[0012] As a preferred solution of the intelligent optimization method for territorial space planning based on the multi-objective evolutionary algorithm according to the present invention, wherein: the formation of the optimal collaborative decision result driven by the interests of each subject includes quantifying the planning deviation by comparing the planning simulation result with the actual observation data, and iteratively optimizing the model evolution rule through the dynamic parameter adjustment strategy.

[0013] Another object of the present invention is to provide an intelligent optimization system for territorial space planning based on the multi-objective evolutionary algorithm, which can construct a non-linear mapping model based on the ecological environment carrying capacity index and the construction land development suitability index, and solves the problem of low data integration accuracy existing in the existing territorial space planning methods.

[0014] As a preferred solution of the intelligent optimization system for territorial space planning based on the multi-objective evolutionary algorithm according to the present invention, wherein: it includes a data collection and preprocessing module, a multi-agent scenario optimization decision-making module, and a dynamic iteration and feedback tuning module. The data collection and preprocessing module is used to collect various types of data required for territorial space planning, and perform unified coordinate conversion, format standardization and grid processing on multi-source data. The multi-agent scenario optimization decision-making module is used to import the generated spatial element risk assessment data and boundary simulation results into the multi-agent collaborative decision-making system. The dynamic iteration and feedback tuning module is used to construct a closed-loop feedback mechanism, compare and analyze the planning output with historical data and real-time monitoring data, and dynamically adjust the parameters in the cellular automata / FLUS model and the multi-objective evolutionary algorithm.

[0015] A computer device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the intelligent optimization method for territorial space planning based on the multi-objective evolutionary algorithm.

[0016] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, it realizes the steps of an intelligent optimization method for territorial spatial planning based on a multi-objective evolutionary algorithm.

[0017] Advantages of the present invention: The intelligent optimization method for territorial spatial planning based on a multi-objective evolutionary algorithm provided by the present invention realizes the overall improvement of intelligent optimization of territorial spatial planning by integrating key steps such as multi-source spatial data collection, unified preprocessing, risk quantitative assessment, multi-objective optimization, and dynamic feedback tuning. First, high-resolution land use images, ecological environment indicators, and socioeconomic data are collected through channels such as satellite remote sensing, government statistics, and environmental monitoring, and an accurate and unified basic database is constructed through unified coordinate transformation, format standardization, denoising and bias correction, and resampling processing, providing strong data support for subsequent analysis. Second, based on ecological environment carrying capacity and construction land development suitability indicators, the development risks of each spatial unit are quantitatively evaluated, and the region is divided into prohibited development and developable areas using GIS technology. At the same time, ecological, agricultural, and urban construction suitability distribution data are extracted to reveal the complex interaction relationship between ecology and development. Third, a multi-objective optimization model is constructed by taking the areas of different land types as decision variables, and an improved NSGA-II evolutionary algorithm is used to introduce a dynamic adaptive parameter adjustment mechanism to solve the Pareto optimal solution set that satisfies the balance of economic, ecological, and social benefits, providing a scientific basis for the planning scheme. Finally, combined with the initial land use state and the spatial distribution of developability, an improved cellular automaton / FLUS model is used to simulate the expansion of the urban development boundary, and under the action of the dynamic feedback tuning mechanism, the model parameters are continuously adjusted to adapt to the actual land use growth trend. Overall, the present invention significantly improves the accuracy of data integration and the flexibility of model response, enhances the scientificity and intelligence level of planning decisions, and provides strong technical support for regional sustainable development. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0019] Figure 1 It is the overall flowchart of an intelligent optimization method for territorial spatial planning based on a multi-objective evolutionary algorithm provided by the first embodiment of the present invention.

[0020] Figure 2 It is the algorithm flowchart step diagram of an intelligent optimization method for territorial spatial planning based on a multi-objective evolutionary algorithm provided by the first embodiment of the present invention.

[0021] Figure 3 It is the overall flowchart of an intelligent optimization system for territorial space planning based on a multi-objective evolutionary algorithm provided for the third embodiment of the present invention. Specific implementation manners

[0022] To make the above objects, features, and advantages of the present invention more obvious and understandable, the specific implementation manners of the present invention will be described in detail below with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Embodiment 1, refer to Figure 1 - Figure 2 This is an embodiment of the present invention, which provides an intelligent optimization method for territorial space planning based on a multi-objective evolutionary algorithm, including: S1: Collect multi-source spatial data, perform unified coordinate transformation, format standardization, noise removal, deviation correction, and resampling operations, and use the grid method to divide the research area into uniform spatial units to form a database integrating ecological environment and socioeconomic indicators.

[0024] Furthermore, comprehensive collection of various types of basic data required for territorial spatial planning is carried out. These data include high-resolution land use images, water quality, vegetation coverage rate, and ecological sensitivity indicators reflecting the regional ecological environment status, as well as statistical data such as population distribution and GDP reflecting the regional social and economic status. The data sources cover satellite remote sensing, government statistical databases, environmental monitoring platforms, and third-party public data. Subsequently, by adopting a unified coordinate transformation method (such as using the WGS84 coordinate system to transform to the national standard geodetic coordinate system or using technologies such as Lambert projection), it is ensured that all data sets are presented under the same spatial reference system. Next, the multi-source data collected is subjected to format standardization processing using tool software (such as ArcGIS, QGIS, or the GDAL library in Python), converting data in different formats (such as GeoTIFF, SHP, CSV, etc.) into a unified format, and performing preprocessing operations such as data denoising, rectification, and resampling during this process to improve data quality. Then, the entire study area is divided into uniform grid cells using the grid method, and each grid cell integrates the attribute information of all the collected data for subsequent quantitative analysis of spatial distribution and risk assessment. Finally, the data after coordinate transformation, format standardization, and grid processing is stored in the basic database according to a unified data structure, ensuring that the database not only contains accurate spatial geometric information but also integrates various ecological environment and social and economic indicators, providing reliable data support for subsequent dynamic parameter adjustment and intelligent optimization of territorial spatial planning using the improved cellular automata / FLUS model and multi-objective evolutionary algorithm. Its data value range and format are standardized data that objectively exist, can be collected, and can be substituted for calculation.

[0025] S2: Based on the ecological environment carrying capacity index and the construction land development suitability index, a non-linear mapping model is constructed to quantify the development risk of each grid cell and output the risk assessment value. Taking the area or quantity of various land use types as decision variables, a multi-objective optimization model considering economic benefits, ecological protection, and social benefits is constructed. The improved multi-objective evolutionary algorithm NSGA-II with a dynamic parameter adjustment mechanism is adopted to output the Pareto optimal solution set that meets the multi-objective equilibrium condition, and the optimal solution is screened according to the objective preference.

[0026] Furthermore, the ecological environment carrying capacity and construction land development suitability indicators are extracted from the database of ecological environment and social and economic indicators to conduct a risk assessment of each spatial element in the study area. The GIS technology is used to divide the region into prohibited development areas and developable areas, and at the same time, the spatial distribution data of ecological, agricultural, and urban construction suitability is extracted, expressed as: ; Among them, is the risk assessment value obtained through normalization by non-linear mapping (logistic function) after improvement, and its output range is between 0 and 1. The closer the value is to 1, the higher the risk; is the sensitivity parameter of the suitability index in the exponential transformation; is the sensitivity parameter of the ecological index in the exponential transformation; is the parameter for adjusting the influence degree of the difference between suitability and ecological index; is the threshold parameter for correcting the overall deviation.

[0027] Taking the area or grid number of different land types (such as urban construction land, cultivated land, ecological land, etc.) as decision variables, an optimization problem covering multiple objective functions such as economic, ecological, and social benefits is constructed. The optimization process of the comprehensive objective function is guided by the risk assessment value, and an improved multi-objective evolutionary algorithm (such as NSGA-II, and introducing dynamic adaptive parameter adjustment) is used to solve it, obtaining a set of Pareto optimal solutions, and the optimal quantity combination scheme is selected according to the objective preference.

[0028] To more fully reflect the dynamic adaptive parameter adjustment mechanism in NSGA-II, a time (or generation)-related parameter is introduced. After that, an exponential transformation is performed on each objective function and a comprehensive normalization fraction is constructed, which is expressed as: ; ; ; At the same time, a comprehensive objective function is constructed and expressed as: ; Among them, the parameter is a dynamic adaptive parameter, which is dynamically adjusted with the evolutionary generation of NSGA-II (for example, it can be set as a function of the ratio of the current generation to the preset maximum generation), so that the model can automatically adjust the convergence rate according to the change of population diversity in the iterative process; the value range of the comprehensive objective function is . The closer the value is to 1, it indicates that a better balance is achieved among the three economic, ecological and social indicators, thus providing a more scientific optimal land use quantity combination scheme for decision-makers. is the area or grid number of urban construction land, is the area or grid number of cultivated land, is the area or grid number of ecological land, is the economic benefit coefficient of urban construction land, is the economic benefit coefficient of cultivated land, is the economic benefit coefficient of ecological land, is the cultivated land ecological risk impact parameter, is the ecological risk impact parameter for urban construction land, is the ecological service parameter for ecological land, is the social benefit sensitivity coefficient for urban construction land, is the social benefit sensitivity coefficient for cultivated land, is the social benefit sensitivity coefficient for ecological land, is the total area or total number of grids of the study area, is a dynamic adaptive parameter, a regulatory factor reflecting the changes in the environment and population diversity during the NSGA-II evolution process, and its value is usually a positive real number and is updated with iterations, is the original economic objective function value, is the original ecological objective function value, is the original social objective function value, 、 and are the economic, ecological, and social objective function values after improvement by introducing exponential transformation and adaptive adjustment respectively, is the comprehensive normalized multi-objective function, and its value range is , and the higher the value, the better the balance among the objectives S3: Combining the initial land use status and the spatial distribution of developability, use the FLUS model to simulate the expansion process of the urban development boundary. During the simulation process, dynamically adjust the conversion rules to adapt to the land use growth trend and planning scale. Import the evaluation and simulation results into the multi-agent collaborative decision-making system, and form the optimal collaborative decision-making result through the interest drive of each subject. Establish a feedback mechanism, and continuously adjust the modeling parameters and rules through the comparative analysis of historical data and real-time monitoring data.

[0029] Furthermore, using the spatial distribution data of developability as the base map and combining the initial land use status, use the improved cellular automata / FLUS model to simulate the expansion of the urban development boundary.

[0030] During the simulation process, after the comprehensive objective function determines the optimal land type combination, it drives the simulation of the preliminary planning layout. Introduce a dynamic parameter adjustment mechanism, so that the model can adjust the conversion rules in real time according to the planning scale, land use growth trend, etc. during the simulation process. The obtained preliminary planning layout is expressed as: ; where is a variable representing the spatial unit index, is the time step or iteration number during the simulation process, is the unit extracted based on GIS data 's spatial suitability function, and its numerical range is between 0 and 1. The larger the value, the higher the possibility that the unit is suitable for development, is a fixed coefficient reflecting the sensitivity of the conversion process and is a positive real number. is the cell aggregation function of the surrounding neighborhood effect, and its value reflects the degree of influence of development activities within the neighborhood. is a fixed conversion threshold parameter, and its value is a positive real number. is the proportional amplification coefficient in the dynamic adjustment term. is a function representing the change of the planned scale over time. is a function representing the change of the land use growth trend over time. The outputs of these two functions are both non - negative real numbers. is a positive real number coefficient reflecting the time decay effect; the above original formula and the improved formula are both normalized by the standard logistic function, and their output value ranges are both , where a value close to 1 indicates that the cell has a high conversion probability (or expansion tendency), and a value close to 0 indicates a low conversion probability.

[0031] After completing the data pre - processing, the previously obtained spatial element risk assessment data and the preliminary boundary simulation results are used as inputs and imported into the multi - agent system to construct a game - collaborative platform with multiple parties participating. In this platform, each participating subject forms an individual decision - making behavior expression based on its own interests and goals (such as economic benefits, ecological benefits, and social benefits) through machine - learning techniques - for example, specific decision rules trained using restricted Boltzmann machines - and then conducts interactive negotiation and information exchange among multiple agents on the platform. Mechanisms such as non - dominated sorting and crowding degree evaluation are introduced inside the platform to ensure that the opinions of each subject can be balanced during the multi - objective optimization process, realizing the dynamic matching of the development potential and ecological carrying capacity of each region in the preliminary planning layout, so as to output a set of Pareto optimal solutions for decision - makers to select the optimal combination of land type quantities according to their target preferences.

[0032] In order to make the planning scheme more in line with the actual needs and real - time changes, a closed - loop feedback mechanism is established to compare and analyze the planning output with historical data and real - time monitoring data, and the error feedback and trend analysis methods are used to quantify the deviation between the current plan and the preset target. Based on this feedback result, a dynamic adaptive parameter adjustment strategy (for example, using the ratio of the current iteration generation to the preset maximum generation as the adjustment factor) is adopted to update the conversion rules, neighborhood effect parameters in the cellular automaton or FLUS model, and population diversity control parameters in the multi - objective evolutionary algorithm in real - time. After multiple rounds of iterative update and correction, until the planning results meet the preset standards in terms of various indicators such as economic, ecological, and social benefits, ensuring that the entire national territorial space planning process has high adaptability and continuous optimization ability, providing a scientific and practical reference basis for the final decision - making.

[0033] Example 2, an embodiment of the present invention, provides an intelligent optimization method for territorial space planning based on a multi-objective evolutionary algorithm. To verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0034] First, a certain city area is selected as the experimental area for territorial space planning. Using satellite remote sensing technology, government statistical databases, environmental monitoring platforms, and third-party public data, a variety of basic data such as high-resolution land use images, water quality monitoring data within the region, vegetation coverage rate, ecological sensitivity index, population distribution, and regional GDP are comprehensively collected. For the collected various data, the WGS84 coordinate system is used to convert it to the national standard geodetic coordinate system, and the Lambert projection method is used to align the spatial data; at the same time, through ArcGIS and QGIS software, the unified format conversion of different data formats (such as GeoTIFF, SHP, CSV) is carried out, and the GDAL library is used to perform data denoising, rectification, and resampling processing, so as to ensure data quality and consistency. Then, the processed data is divided into uniform spatial units by the grid method. Each unit integrates images, ecological and economic indicators, and a unified basic database is constructed. The data is stored in a standardized format, and its numerical range and accuracy are objectively existing, collectable, and computable. Subsequently, based on the ecological environment carrying capacity index and the construction land development suitability index, a non-linear mapping model is used to quantitatively evaluate the development risks of each grid unit, and the prohibited development and developable areas are divided through GIS technology. At the same time, the spatial distribution data of ecological, agricultural, and urban construction suitability is extracted. On this basis, the area of different land types is used as a decision variable to construct a multi-objective optimization model covering economic, ecological, and social benefits, and an improved NSGA-II algorithm (introducing a dynamic adaptive parameter adjustment mechanism) is used to solve the Pareto optimal solution set. Finally, combined with the initial land use status and the developable spatial data, an improved cellular automata / FLUS model is used to simulate the process of urban development boundary expansion. During the simulation process, through the dynamic parameter adjustment mechanism, the conversion rules are adjusted in real time according to the planning scale and land use growth trend to form a preliminary planning layout. The whole process forms a complete closed loop from data collection, preprocessing, to risk assessment, regional division, multi-objective optimization, and then to dynamic simulation expansion and feedback adjustment, providing reliable data support and decision-making basis for the intelligent optimization of territorial space planning.

[0035] Table 1 Experimental data table

[0036] As can be seen from the experimental data table, after the selected area was standardized during the data collection and preprocessing stage, the data of each test object reached a high level of accuracy and consistency. For example, the quality scores of the land use images were all above 85 points, indicating that the collected image data had high resolution and clarity; the ecological environment carrying capacity and development suitability indexes were all distributed between 0.65 and 0.85, which better reflected the comprehensive situation of the stability of the ecosystem and development potential within the region. Further, by comparing the data of each test object, there was a certain contrast between Region C and Region E in terms of ecological environment carrying capacity and development suitability. Region C had a higher carrying capacity and excellent development suitability, while Region E was relatively lower, which provided a clear improvement direction for subsequent multi-objective optimization. When constructing the multi-objective optimization model, by introducing a dynamic adaptive parameter adjustment mechanism, the optimization algorithm could adjust the weights of each objective in real time, comprehensively considering economic, ecological, and social benefits, so as to ensure that the output Pareto optimal solution achieved the best balance among each objective. At the same time, when using the improved cellular automata / FLUS model to simulate the expansion of the urban development boundary, the dynamic adjustment of the conversion rules enabled the simulation process to flexibly respond to the land use growth trend and the change of the planned scale, ensuring that the final planned layout was more in line with the actual needs. Overall, the table data not only proved the objective accuracy of the basic data after preprocessing, but also demonstrated the significant advantages of the present invention in risk assessment, multi-objective optimization, and dynamic feedback optimization through the comparative analysis of the data. This technical solution based on fine data integration and real-time dynamic adjustment, compared with the traditional static planning method, can not only more accurately reflect the current situation of land use within the region, but also continuously optimize the planning scheme in a dynamic environment, improve the scientificity and practicality of the territorial space planning, and provide more reliable technical support for the sustainable development of the region.

[0037] Example 3, referring to Figure 3 , which is an embodiment of the present invention, provides an intelligent optimization system for territorial space planning based on a multi-objective evolutionary algorithm, including a data collection and preprocessing module, a multi-agent scenario optimization and decision-making module, and a dynamic iteration and feedback optimization module.

[0038] Among them, the data collection and preprocessing module is used to collect various types of data required for territorial space planning, and perform unified coordinate transformation, format standardization, and grid processing on multi-source data. The multi-agent scenario optimization and decision-making module is used to import the generated spatial element risk assessment data and boundary simulation results into the multi-agent collaborative decision-making system. The dynamic iteration and feedback optimization module is used to construct a closed-loop feedback mechanism, compare and analyze the planning output with historical data and real-time monitoring data, and dynamically adjust the parameters in the cellular automata / FLUS model and the multi-objective evolutionary algorithm.

[0039] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., all kinds of media that can store program codes.

[0040] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0041] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memories), fiber optic devices, and portable compact disc read-only memories (CDROM). Additionally, a computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0042] It should be understood that each part of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following technologies well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0043] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. An intelligent optimization method for territorial space planning based on a multi-objective evolutionary algorithm, characterized in that, Including: Collect multi-source spatial data, perform unified coordinate transformation, format standardization, denoising, rectification and resampling operations, and use the grid method to divide the research area into uniform spatial units to form a database integrating ecological environment and socioeconomic indicators; Based on the database of ecological environment and socioeconomic indicators, collect ecological environment carrying capacity indicators and construction land development suitability indicators, construct a non-linear mapping model, quantify the development risk of each grid unit, output risk assessment values, use the area or quantity of various land use types as decision variables, and guide the construction of a multi-objective optimization model considering economic benefits, ecological protection and social benefits through risk assessment values. Use the improved multi-objective evolutionary algorithm NSGA-II with a dynamic parameter adjustment mechanism to output the Pareto optimal solution set that meets the multi-objective equilibrium conditions, and screen the optimal solution according to the objective preference; Determine the optimal land type combination through the Pareto optimal solution set, combine the initial land use status and the spatial distribution of developability, use the FLUS model to simulate the expansion process of the urban development boundary, dynamically adjust the conversion rules during the simulation process to adapt to the land use growth trend and planning scale, import the evaluation and simulation results into the multi-agent collaborative decision-making system, form the optimal collaborative decision-making result through the interest drive of each subject, establish a feedback mechanism, and continuously adjust the modeling parameters and rules through the comparative analysis of historical data and real-time monitoring data.

2. The intelligent optimization method for territorial spatial planning based on multi-objective evolutionary algorithm according to claim 1, characterized in that: The output risk assessment value includes constructing a risk index mapping method that fits the actual situation by considering the non-linear relationship between the ecological environment carrying capacity and the construction land development suitability.

3. The intelligent optimization method for territorial spatial planning based on multi-objective evolutionary algorithm according to claim 2, characterized in that: The multi-objective optimization model includes modeling the economic objective, ecological objective and social objective through characteristic coefficients respectively, and introducing dynamic adjustment parameters to adapt to the changes of the environment and population state during the evolution process.

4. The intelligent optimization method for territorial spatial planning based on multi-objective evolutionary algorithm according to claim 3, characterized in that: The FLUS model includes adopting the neighborhood effect and time series adjustment strategy during the development boundary simulation process to realize the dynamic coupling of the suitability of spatial units and the surrounding development influencing factors.

5. The intelligent optimization method for territorial spatial planning based on multi-objective evolutionary algorithm according to claim 4, characterized in that: The output of the Pareto optimal solution set that meets the multi-objective equilibrium conditions includes ensuring the high-precision fusion of multi-source heterogeneous data under a unified spatial reference system, and realizing the complete coverage and attribute matching of the data set in the geographical space.

6. The intelligent optimization method for territorial spatial planning based on the multi-objective evolutionary algorithm according to claim 5, characterized in that: The multi-agent collaborative decision-making system includes training its own behavior strategy using machine learning algorithms according to the interest objective, and collaboratively outputting the optimal land use allocation plan that meets the expectations of multiple parties through information exchange and non-dominated sorting methods on the platform.

7. The intelligent optimization method for territorial spatial planning based on the multi-objective evolutionary algorithm according to claim 6, characterized in that: The formation of the optimal collaborative decision-making result through the interest drive of each subject includes quantifying the planning deviation by comparing the planning simulation result with the actual observation data, and iteratively optimizing the model evolution rule through the dynamic parameter adjustment strategy.

8. A system adopting the intelligent optimization method for territorial spatial planning based on the multi-objective evolutionary algorithm as described in any one of claims 1 to 7, characterized in that: Including a data collection and preprocessing module, a multi-agent scenario optimization decision-making module, and a dynamic iteration and feedback tuning module; The data collection and preprocessing module is used to collect various data required for the national land space planning, and perform unified coordinate transformation, format standardization and grid processing on the multi-source data; The multi-agent scenario optimization and decision-making module is used to import the generated spatial element risk assessment data and boundary simulation results into the multi-agent collaborative decision-making system; The dynamic iteration and feedback tuning module is used to construct a closed-loop feedback mechanism, compare and analyze the planning output with historical data and real-time monitoring data, and dynamically adjust the parameters in the cellular automata / FLUS model and the multi-objective evolutionary algorithm.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent optimization method for territorial space planning based on the multi-objective evolutionary algorithm described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent optimization method for territorial space planning based on the multi-objective evolutionary algorithm described in any one of claims 1 to 7.

Images