Multi-objective evolutionary algorithm-based intelligent optimization method and system for national space planning

Abstract

The application discloses a kind of land space planning intelligent optimization method and system based on multi-objective evolutionary algorithm, it is related to land space planning technical field, including the multiple-source basic data needed for acquisition land space planning, based on ecological environment carrying capacity and construction land development suitability index, construct nonlinear mapping model to carry out quantitative evaluation to the development risk of each grid unit, simultaneously with each land type area or quantity as decision variable, construct multi-objective optimization model covering economic, ecological and social benefit, in combination with initial land use state and developable space data, FLUS model is used to simulate expansion to urban development boundary, in simulation process, by dynamic adjustment conversion rule, real-time response planning scale and land growth trend.The method disclosed in the application significantly improves the accuracy of data integration and the flexibility of model response, enhances the scientificity and intelligent level of planning decision, and provides strong technical support for regional sustainable development.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of land space planning, specifically to a land space planning intelligent optimization method and system based on a multi-objective evolutionary algorithm. BACKGROUND

[0002] In recent years, with the rapid development of remote sensing technology, geographic information systems (GIS) and big data analysis, the field of land space planning is undergoing a profound technological revolution. Multi-objective evolutionary algorithms and cellular automata models have been widely used in urban planning and land use optimization. They use genetic algorithms, non-dominated sorting and other methods to achieve a balance between economic, ecological and social multi-objectives. At the same time, the FLUS model as a spatial simulation tool has made some progress in predicting urban development boundary expansion. The introduction of dynamic parameter adjustment mechanisms and multi-agent collaborative decision-making systems makes the planning model more adaptive and responsive in real time, providing a solid technical support for regional sustainable development.

[0003] However, the existing technology still has many shortcomings in realizing intelligent optimization of land space planning. First, multi-source spatial data, due to the heterogeneity of collection means, resolution and data format, even after unified coordinate conversion, format standardization, denoising and correction, and resampling processing, its spatial accuracy and consistency still cannot 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 cannot capture the dynamic changes and expansion trends of land use in the region in real time, resulting in deviations between the simulated urban development boundary and the actual situation; in addition, the current multi-objective optimization model constructed with various land use areas or quantities as decision variables mainly relies on fixed parameter weights to balance multi-objectives, lacks dynamic adaptive adjustment mechanism, and is difficult to fully integrate the complex interactions between economic benefits, ecological protection and social benefits; more importantly, the existing methods have not established a multi-agent collaborative decision-making platform involving government, ecological protection departments, development subjects and the public, which cannot realize effective interaction and consensus formation among various subjects in the simulation scenario, thus restricting the comprehensive optimization effect of the planning results. Therefore, an intelligent optimization method for land space planning is needed, which can dynamically adjust parameters, real-time feedback and correction, and integrate the interests of multiple parties, to achieve high precision, dynamic adaptation and multi-agent collaborative decision-making. SUMMARY

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

[0005] Therefore, the technical problem solved by the present application is that the existing land space planning method has low data integration accuracy, insufficient dynamic response capability, imperfect multi-agent collaborative decision-making, and how to realize high-precision dynamic adaptation and multi-stakeholder collaborative optimization of land space planning.

[0006] To solve the above technical problems, the present application provides the following technical solutions: a land space planning intelligent optimization method based on a multi-objective evolutionary algorithm, including collecting multi-source spatial data, performing unified coordinate conversion, format standardization, denoising and rectification, and resampling operations, and dividing the research area into uniform spatial units using a gridding method to form a database integrating ecological environment and social economic indicators; based on ecological environment carrying capacity indicators and construction land development suitability indicators, a nonlinear mapping model is constructed to quantify the development risk of each grid unit and output risk assessment values; a multi-objective optimization model considering economic benefits, ecological protection and social benefits is constructed with the area or quantity of various land use types as decision variables; an improved multi-objective evolutionary algorithm NSGA-II with a dynamic parameter adjustment mechanism is used to output a Pareto optimal solution set that meets the multi-objective balance condition, and the optimal solution is selected according to the target preference; the initial land use state and developable spatial distribution are combined to simulate the urban development boundary expansion process using the FLUS model, and the conversion rules are dynamically adjusted to adapt to the local growth trend and planning scale during the simulation process; the evaluation and simulation results are imported into a multi-agent collaborative decision-making system to form an optimal collaborative decision-making result driven by the interests of each agent, and a feedback mechanism is established to continuously adjust the modeling parameters and rules through comparative analysis of historical data and real-time monitoring data.

[0007] As a preferred scheme of the land space planning intelligent optimization method based on a multi-objective evolutionary algorithm, wherein: the output risk assessment value includes a risk index mapping method that considers the nonlinear relationship between ecological environment carrying capacity and construction land development suitability.

[0008] As a preferred scheme of the land space planning intelligent optimization method based on a multi-objective evolutionary algorithm, wherein: the multi-objective optimization model includes economic, ecological and social targets respectively modeled by characteristic coefficients, and dynamic adjustment parameters are introduced to adapt to the changes in the environment and population state during the evolutionary process.

[0009] As a preferred scheme of the land space planning intelligent optimization method based on a multi-objective evolutionary algorithm, wherein: the FLUS model includes a neighborhood effect and time sequence adjustment strategy during the development boundary simulation process to dynamically couple the spatial unit suitability and surrounding development influencing factors.

[0010] As a preferred scheme of the land space planning intelligent optimization method based on the multi-objective evolutionary algorithm, the output of the Pareto optimal solution set meeting the multi-objective balance condition includes ensuring high-precision fusion of multi-source heterogeneous data in a unified spatial reference system and realizing complete coverage and attribute matching of the data set in geographic space.

[0011] As a preferred scheme of the land space planning intelligent optimization method based on the multi-objective evolutionary algorithm, the multi-agent collaborative decision system includes training the behavior strategy according to the interest target by using the machine learning algorithm, and collaboratively outputting the optimal land use configuration scheme meeting the expectations of multiple parties through information exchange and non-dominant sorting method on the platform.

[0012] As a preferred scheme of the land space planning intelligent optimization method based on the multi-objective evolutionary algorithm, the optimal collaborative decision result formed by the interest driving 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 application is to provide a land space planning intelligent optimization system based on a multi-objective evolutionary algorithm, which can solve the problem of low data integration precision in existing land space planning methods by constructing a nonlinear mapping model based on ecological environment carrying capacity indicators and construction land development suitability indicators.

[0014] As a preferred scheme of the land space planning intelligent optimization system based on the multi-objective evolutionary algorithm, it includes a data acquisition and preprocessing module, a multi-agent scenario optimization decision module, and a dynamic iteration and feedback optimization module, the data acquisition and preprocessing module is used to collect various data required for land space planning, and to perform unified coordinate conversion, format standardization and gridding processing on multi-source data, the multi-agent scenario optimization decision module is used to import the generated spatial element risk assessment data and boundary simulation results into the multi-agent collaborative decision system, and the dynamic iteration and feedback optimization module is used to construct a closed-loop feedback mechanism, compare the planning output with historical data and real-time monitoring data, and dynamically adjust the parameters in the cellular automaton / 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 realize the steps of the land space planning intelligent optimization method based on the multi-objective evolutionary algorithm.

[0016] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm.

[0017] Beneficial Effects of the Invention: The intelligent optimization method for national land spatial planning based on a multi-objective evolutionary algorithm, provided by the present invention, achieves an overall improvement in the intelligent optimization of national land spatial planning by integrating key steps such as multi-source spatial data acquisition, unified preprocessing, quantitative risk assessment, multi-objective optimization, and dynamic feedback tuning. First, high-resolution land use imagery, ecological and environmental indicators, and socioeconomic data are collected through satellite remote sensing, government statistics, and environmental monitoring. Through unified coordinate transformation, format standardization, denoising and correction, and resampling, a precise and unified basic database is constructed, providing solid data support for subsequent analysis. Second, based on ecological and environmental carrying capacity and construction land development suitability indicators, the development risk of each spatial unit is quantitatively assessed. GIS technology is used to divide the area into prohibited and developable areas. Simultaneously, ecological, agricultural, and urban construction suitability distribution data are extracted, revealing the complex interactive relationship between ecology and development. Third, a multi-objective optimization model is constructed by using the area of ​​different land types as decision variables. A dynamic adaptive parameter adjustment mechanism is introduced using an improved NSGA-II evolutionary algorithm to solve for a Pareto optimal solution set that balances economic, ecological, and social benefits, providing a scientific basis for planning schemes. Finally, combining the initial land use status and the spatial distribution of developability, an improved cellular automaton / FLUS model was used to simulate the expansion of urban development boundaries. Using a dynamic feedback tuning mechanism, model parameters were continuously adjusted to accommodate actual land use growth trends. Overall, this method significantly improved data integration accuracy and model response flexibility, enhancing the scientific and intelligent nature of planning decisions and providing strong technical support for regional sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 An overall flow chart of an intelligent optimization method for land space planning based on a multi-objective evolutionary algorithm provided in the first embodiment of the present invention.

[0020] Figure 2 An algorithm flow chart of an intelligent optimization method for land space planning based on a multi-objective evolutionary algorithm is provided for the first embodiment of the present invention.

[0021] Figure 3 A whole flow chart of a national space planning intelligent optimization system based on a multi-objective evolutionary algorithm is provided for a third embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the above objectives, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present application.

[0023] Embodiment 1, refer to Figure 1 - Figure 2 For an embodiment of the present application, a national space planning intelligent optimization method based on a multi-objective evolutionary algorithm is provided, comprising:

[0024] S1: Collect multi-source spatial data, perform unified coordinate conversion, format standardization, denoising and rectification, and resampling operation, and divide the research area into uniform spatial units by using the gridding method to form a database integrating ecological environment and social economic indicators.

[0025] Furthermore, a comprehensive collection of various types of basic data required for territorial spatial planning is conducted, including high-resolution land use images, water quality, vegetation coverage, and ecological sensitivity indicators reflecting regional ecological environment conditions, as well as population distribution, GDP, and other statistical data reflecting regional social and economic conditions. The data sources include satellite remote sensing, government statistical databases, environmental monitoring platforms, and third-party public data. Subsequently, a unified coordinate conversion method (e.g., converting to the national standard geodetic coordinate system using WGS84 or using Lambert projection technology) is adopted to ensure that all data sets are presented in the same spatial reference system. Next, the collected multi-source data is standardized using tool software (such as ArcGIS, QGIS, or Python GDAL library) to convert different formats (such as GeoTIFF, SHP, CSV, etc.) into a unified format. During this process, data denoising, rectification, and resampling are performed for preprocessing to improve data quality. Then, a gridding method is used to divide the entire study area into uniform grid cells, each of which integrates the attribute information of all collected data, facilitating subsequent quantitative analysis and risk assessment of spatial distribution. Finally, the data after coordinate conversion, format standardization, and gridding are 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 economic indicators. This provides reliable data support for subsequent use of improved cellular automata / FLUS models and multi-objective evolutionary algorithms for dynamic parameter adjustment and intelligent optimization of territorial spatial planning. The data value range and format are standardized data that objectively exist, can be collected, and can be input into calculations.

[0026] 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, output the risk assessment value, and construct a multi-objective optimization model considering economic benefits, ecological protection, and social benefits with the area or quantity of various land use types as decision variables. An improved multi-objective evolutionary algorithm NSGA-II with dynamic parameter adjustment mechanism is used to output the Pareto optimal solution set that satisfies the multi-objective balance condition, and the optimal solution is selected according to the target preference.

[0027] Furthermore, the ecological environment carrying capacity and construction land development suitability indexes are extracted from the database of ecological environment and social economic indicators to assess the risk of various spatial elements in the study area. GIS technology is used to divide the region into prohibited development areas and developable areas, and extract ecological, agricultural, and urban construction suitability spatial distribution data, represented as:

[0028] ;

[0029] wherein, is the risk assessment value after improved by nonlinear mapping (logistic function), whose output range is between 0 and 1, and the value closer to 1 indicates higher risk; is the sensitivity parameter of suitability index in exponential transformation; is the sensitivity parameter of ecological index in exponential transformation; is the parameter to adjust the influence degree of the difference between suitability index and ecological index; is the threshold parameter for correcting overall bias.

[0030] The area or grid number of different land types (such as urban construction land, farmland, ecological land, etc.) is taken as the decision variable, and 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, with the introduction of dynamic adaptive parameter adjustment) is used for solution, to obtain a set of Pareto optimal solutions, and the optimal number combination scheme is selected according to the target preference.

[0031] In order to more fully reflect the dynamic adaptive parameter adjustment mechanism in NSGA-II, time (or algebra) related parameters are introduced Then, exponential transformation is adopted for each objective function, and a comprehensive normalized fraction is constructed, which is expressed as:

[0032] ;

[0033] ;

[0034] ;

[0035] At the same time, the comprehensive objective function is constructed and expressed as:

[0036] ;

[0037] wherein, parameter is a dynamic adaptive parameter, which is dynamically adjusted with the evolution algebra of NSGA-II (for example, it can be set as a function of the ratio of the current algebra to the preset maximum algebra), so that the model can automatically adjust the convergence rate according to the population diversity change in the iteration process; the value of the comprehensive objective function is in the range of , and the value closer to 1 indicates that the economic, ecological and social indicators achieve better balance, thereby providing a more scientific optimal land use number combination scheme for decision makers, is the area or grid number of urban construction land, is the area or grid number of farmland, 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 ecological risk impact parameter of cultivated land, is the ecological risk impact parameter of urban construction land, is the ecological service parameter of ecological land, is the social benefit sensitivity coefficient of urban construction land, is the social benefit sensitivity coefficient of cultivated land, is the social benefit sensitivity coefficient of ecological land, is the total area or total grid number of the study area, is a dynamic adaptive parameter, which is a regulating factor reflecting the change of environment and population diversity in the evolution process of NSGA-II, and its value is usually a positive real number and is updated with iteration, 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, respectively, and the exponential transformation and adaptive adjustment are introduced, is the comprehensive normalized multi-objective function, and its value range is The higher the value is, the better the balance between the objectives is

[0038] S3: Based on the initial land use status and the developability spatial distribution, the FLUS model is used to simulate the expansion process of the urban development boundary. In the simulation process, the conversion rules are dynamically adjusted to adapt to the land use growth trend and the planning scale. The evaluation and simulation results are imported into the multi-agent collaborative decision-making system, and the optimal collaborative decision-making results are formed by the driving of the interests of each agent. A feedback mechanism is established, and the modeling parameters and rules are continuously adjusted through the comparative analysis of historical data and real-time monitoring data.

[0039] Further, based on the developability spatial distribution data as the base map, combined with the initial land use status, the improved cellular automaton / FLUS model is used to simulate the expansion of the urban development boundary.

[0040] In the simulation process, the comprehensive objective function determines the optimal land type combination to drive the preliminary planning layout simulation. A dynamic parameter adjustment mechanism is introduced, 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, and the preliminary planning layout is represented as:

[0041] ;

[0042] wherein, is a variable representing the index of a spatial unit, is the time step or iteration number in the simulation process, is the spatial suitability function of the unit extracted from GIS data, whose value ranges from 0 to 1, and the larger the value, the higher the possibility of the unit being suitable for development, is a fixed coefficient reflecting the sensitivity of the conversion process, which is a positive real number, is the aggregation function of the neighborhood effect around the unit , whose value reflects the influence degree of development activities in the neighborhood, is a fixed conversion threshold parameter, whose value is a positive real number, is the proportional amplification coefficient in the dynamic adjustment term, is a function representing the change of the planning scale over time, is a function representing the change of the land use growth trend over time, and the outputs of the two functions are both non-negative real numbers, is a positive real coefficient reflecting the time decay effect; the original formula and the improved formula are both normalized by the standard logistic function, and the output value range of both is , where a value close to 1 indicates that the unit has a higher conversion probability (or expansion tendency), and a value close to 0 indicates a lower conversion probability.

[0043] After completing the data preprocessing, the previously obtained spatial element risk assessment data and the preliminary boundary simulation results are imported into the multi-agent system to build a multi-party game collaboration platform. In this platform, each participating agent forms individual decision-making behavior expressions based on its own interests and goals (such as economic benefits, ecological benefits, and social benefits) through machine learning technology-based decision-making rules, such as those trained using restricted Boltzmann machines, and then carries out interactive negotiation and information exchange among multiple agents on the platform. The platform introduces mechanisms such as non-dominated sorting and crowding degree evaluation to ensure that the opinions of each agent can be balanced in the multi-objective optimization process, and to achieve dynamic matching of regional development potential and ecological carrying capacity in the preliminary planning layout, thereby outputting a set of Pareto optimal solutions for decision-makers to select the optimal combination of land types according to their target preferences.

[0044] In order to make the planning scheme more in line with the actual demand 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 deviation between the current planning and the preset target is quantified by using error feedback and trend analysis method; based on the feedback result, a dynamic adaptive parameter adjustment strategy (for example, the ratio of the current iteration number to the preset maximum iteration number is used as the adjustment factor) is adopted to update the conversion rules, neighborhood effect parameters in the cellular automaton or FLUS model, and the population diversity control parameters in the multi-objective evolutionary algorithm in real time; after multiple rounds of iteration, updating and correction, until the planning results reach the preset standards in economic, ecological and social benefits and other indicators, ensuring that the entire land space planning process has high adaptability and continuous optimization capability, and providing scientific and practical reference for the final decision.

[0045] In one embodiment of the present application, an intelligent optimization method for land space planning based on a multi-objective evolutionary algorithm is provided. In order to verify the beneficial effects of the present application, scientific demonstration is carried out through economic benefit calculation and simulation experiment.

[0046] Firstly, a certain city region was selected as the experimental region of national spatial planning. Satellite remote sensing technology, government statistical database, environmental monitoring platform and third-party public data were used to collect high-resolution land use images, regional water quality monitoring data, vegetation coverage, ecological sensitivity index, population distribution and regional GDP, and other basic data. The collected data was converted to the national standard geodetic coordinate system using the WGS84 coordinate system, and the spatial data was aligned using the Lambert projection method. At the same time, different data formats (such as GeoTIFF, SHP, CSV) were converted to a unified format using ArcGIS and QGIS software, and data denoising, rectification and resampling were performed using the GDAL library to ensure data quality and consistency. Then, the processed data was divided into uniform spatial units using the gridding method, each unit integrated image, ecological and economic indicators, and a unified basic database was constructed, with data stored in a standardized format, with objective existence, collectable and computable value range and precision. Subsequently, based on the ecological environment carrying capacity index and the construction land development suitability index, the development risk of each grid unit was quantitatively evaluated using a nonlinear mapping model, and the forbidden development and developable areas were divided using GIS technology, and the ecological, agricultural and urban construction suitability spatial distribution data were extracted. On this basis, the area of different land types was taken as the decision variable to construct a multi-objective optimization model covering economic, ecological and social benefits, and the improved NSGA-II algorithm (introducing a dynamic adaptive parameter adjustment mechanism) was used to obtain the Pareto optimal solution set. Finally, combined with the initial land use state and developable spatial data, an improved cellular automaton / FLUS model was used to simulate the urban development boundary expansion process, and through the dynamic parameter adjustment mechanism, the conversion rules were adjusted in real time according to the planning scale and land use growth trend, forming the preliminary planning layout. The whole process forms a complete closed loop from data collection, preprocessing, risk assessment, regional division, multi-objective optimization, to dynamic simulation expansion and feedback adjustment, providing reliable data support and decision basis for intelligent optimization of national spatial planning.

[0047] Table 1 Experimental data table

[0048]

[0049] The experimental data tables show that after standardization during the data collection and preprocessing phases, the data from each experimental object achieved high accuracy and consistency. For example, the land use image quality scores were all above 85, indicating high resolution and clarity. The ecological carrying capacity and development suitability indices were both between 0.65 and 0.85, reflecting the overall stability and development potential of the ecosystem within the region. Furthermore, a comparison of the data from each experimental object reveals a contrast between Areas C and E in terms of ecological carrying capacity and development suitability. Area C has a higher carrying capacity and excellent development suitability, while Area E has a relatively lower one. This provides clear improvement directions for subsequent multi-objective optimization. When constructing the multi-objective optimization model, a dynamic adaptive parameter adjustment mechanism was introduced, enabling the optimization algorithm to adjust the weights of each objective in real time, comprehensively considering economic, ecological, and social benefits, thereby ensuring that the output Pareto optimal solution achieves the best balance among the objectives. At the same time, when the improved cellular automaton / FLUS model is used to simulate the expansion of urban development boundaries, the dynamic adjustment of the conversion rules enables the simulation process to flexibly respond to land use growth trends and changes in planning scale, ensuring that the final planning layout is more in line with actual needs. Overall, the tabular data not only proves the objective accuracy of various basic data after pre-processing, but also demonstrates the significant advantages of the present invention in risk assessment, multi-objective optimization and dynamic feedback tuning through comparative analysis between data. Compared with traditional static planning methods, this technical solution based on fine data integration and real-time dynamic adjustment can not only more accurately reflect the current status of land use in the region, but also continuously optimize planning schemes in a dynamic environment, improve the scientificity and practicality of national land space planning, and provide more reliable technical support for regional sustainable development.

[0050] Example 3, reference Figure 3 , is an embodiment of the present invention, which provides a national land space planning intelligent optimization system based on a multi-objective evolutionary algorithm, including a data acquisition and preprocessing module, a multi-agent scenario optimization decision module, and a dynamic iteration and feedback tuning module.

[0051] The data acquisition and preprocessing module is used to collect various types of data required for national land space planning, and to 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 build 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 automation / FLUS model and multi-objective evolutionary algorithm.

[0052] If the functions are implemented in software, the functions can be stored in or implemented as one or more instructions or code on a computer-readable medium. Computer-readable media include both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage medium can be any available medium that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, or twisted pair, then the coaxial cable, fiber optic cable, or twisted pair are included in the definition of medium. Disk and disc, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), and Blu-Ray® disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0053] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0054] In other words, like a human driver of a vehicle, the autonomous vehicle 100 can be programmed to follow traffic laws and rules of the road, and to make decisions based on its programming and the information it receives from its sensors and other sources. The autonomous vehicle 100 can also be programmed to make decisions based on its programming and the information it receives from its sensors and other sources, even if those decisions are not in accordance with traffic laws and rules of the road. For example, the autonomous vehicle 100 can be programmed to avoid a collision with another vehicle, even if doing so would violate a traffic law or rule of the road.

[0055] It should be understood that portions of the present application can be implemented with hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, implementation can be with any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions upon an application of data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be understood that the foregoing embodiments are merely illustrative of the present application and are not to be used to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, it will be apparent to those skilled in the art that various changes and modifications can be contributed to the present application without departing from the spirit and scope of the present application, and such changes and modifications should be encompassed within the scope of the appended claims.

[0056] It should be understood that the foregoing embodiments are merely illustrative of the present application and are not to be used to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, it will be apparent to those skilled in the art that various changes and modifications can be contributed to the present application without departing from the spirit and scope of the present application, and such changes and modifications should be encompassed within the scope of the appended claims.

Claims

1. An intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm, characterized in that: include: Collect multi-source spatial data, perform unified coordinate conversion, format standardization, denoising and correction, and resampling operations, and use a gridding method to divide the study area into uniform spatial units to form a database integrating ecological environment and socio-economic indicators; Based on a database of ecological and social economic indicators, ecological and environmental carrying capacity indicators and construction land development suitability indicators are collected. A nonlinear mapping model is constructed to quantify the development risk of each grid unit and output a risk assessment value. The area or quantity of each land use type is used as a decision variable. The risk assessment value guides the construction of a multi-objective optimization model that simultaneously considers economic benefits, ecological protection, and social benefits. An improved multi-objective evolutionary algorithm NSGA-II, which introduces a dynamic parameter adjustment mechanism, is used to output a Pareto optimal solution set that meets multi-objective equilibrium conditions, and the optimal solution is screened based on objective preferences. The multi-objective optimization model includes economic goals, ecological goals and social goals, which are modeled by characteristic coefficients respectively, and introduces dynamic adjustment parameters to adapt to changes in the environment and population status during the evolution process; The improved multi-objective evolutionary algorithm NSGA-II includes the introduction of time-related parameters , apply exponential transformation to each objective function and construct a comprehensive normalized fraction; The optimal land type combination is determined through the Pareto optimal solution set. Combined with the initial land use status and the spatial distribution of developability, the FLUS model is used to simulate the expansion process of urban development boundaries. During the simulation process, the conversion rules are dynamically adjusted to adapt to the land use growth trend and planning scale. The evaluation and simulation results are imported into the multi-agent collaborative decision-making system. The optimal collaborative decision-making result is formed through the interests of various subjects. A feedback mechanism is established. Through comparative analysis of historical data and real-time monitoring data, the modeling parameters and rules are continuously adjusted.

2. The intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to claim 1 is characterized by: The output risk assessment value includes constructing a risk indicator mapping method that fits the actual situation by considering the nonlinear relationship between the ecological environment carrying capacity and the suitability of construction land development.

3. The intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to claim 2 is characterized by: The FLUS model includes the use of neighborhood effects and temporal adjustment strategies in the development boundary simulation process to achieve dynamic coupling of spatial unit suitability and surrounding development influencing factors.

4. The intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to claim 3 is characterized by: The output of the Pareto optimal solution set that satisfies multi-objective equilibrium conditions includes ensuring high-precision fusion of multi-source heterogeneous data in a unified spatial reference system and achieving complete coverage and attribute matching of the data set in geographic space.

5. The intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to claim 4 is characterized in that: The multi-agent collaborative decision-making system includes using a machine learning algorithm to train its own behavior strategy according to interest goals, and through information exchange and non-dominated sorting methods on the platform, collaboratively outputting the optimal land use configuration plan that meets the expectations of multiple parties.

6. The intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to claim 5 is characterized by: The formation of the optimal collaborative decision-making result driven by the interests of each subject includes quantifying planning deviations by comparing planning simulation results with actual observation data, and iteratively optimizing model evolution rules through dynamic parameter adjustment strategies.

7. A system using the intelligent optimization method for national land space planning based on a multi-objective evolutionary algorithm according to any one of claims 1 to 6, characterized in that: It includes data collection and preprocessing module, multi-agent scenario optimization decision module, dynamic iteration and feedback tuning module; The data acquisition and preprocessing module is used to collect various types of data required for national land space planning, and perform unified coordinate conversion, format standardization and grid processing on multi-source data; The multi-agent scenario optimization decision module is used to import the generated spatial element risk assessment data and boundary simulation results into the multi-agent collaborative decision system; The dynamic iteration and feedback tuning module is used to build 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 automation / FLUS model and the multi-objective evolutionary algorithm.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, it implements the steps of the intelligent optimization method for land space planning based on a multi-objective evolutionary algorithm as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent optimization method for land space planning based on a multi-objective evolutionary algorithm described in any one of claims 1 to 6 are implemented.

Images