A method and system for intelligent optimization of urban land space with multiple coupled elements

Abstract

This invention discloses a multi-element coupled intelligent optimization method and system for urban land space, comprising: quantifying the functional zoning transfer probability of ecological protection zones, basic farmland, and urban development zones based on a Markov model; simulating the spatial distribution of functional zoning using a future land use simulation model; and constructing a first multi-objective optimization model by combining resistance surface analysis with a minimum cumulative resistance model; collecting urban POI data, selecting residential, commercial, and public service types as optimization objects, and using cluster analysis to divide the optimization objects and extract core points to construct a second multi-objective optimization model; and constructing a third multi-objective optimization model based on road network graph structure data, defining node and edge features, and using a graph neural network to train the graph structure of the road network and extract features to formulate multi-objective optimization decisions for the road network.

Description

Technical Field

[0001] This invention relates to the field of optimization methods, specifically to an intelligent optimization method and system for multi-element coupling of urban land space. Background Technology

[0002] As an important carrier of industrialization, urbanization and agricultural modernization, land resources are facing challenges due to rapid urbanization, urban expansion leading to reduced arable land and ecological fragmentation, and the problem of high stock land but low utilization rate is becoming increasingly apparent. Optimizing urban land space is an inevitable choice to address the complex problems of resource scarcity, ecological degradation and spatial conflicts in the process of urbanization.

[0003] In existing technologies, when optimizing land and space resources, land, ecology, and economy are evaluated independently, ignoring the coupling effect. This results in ecological corridors being cut off by roads, industrial layouts and job-housing balance being out of balance, failing to meet the development needs of urbanization. Summary of the Invention

[0004] The technical problem to be solved by this invention is that when optimizing land and space resources, elements such as land, ecology, and economy are evaluated independently, ignoring the coupling effect. This results in ecological corridors being cut off by roads, industrial layout and job-housing balance being out of balance, which cannot meet the development needs of urbanization. This invention provides a method and system for intelligent optimization of urban land space with multi-element coupling.

[0005] The present invention solves the above-mentioned technical problems through the following technical solutions, the present invention comprising:

[0006] Step 1: Based on the Markov model, quantify the functional zoning transfer probability of ecological protection zones, basic farmland, and urban development zones. Use the future land use simulation model to simulate the spatial distribution of functional zoning. Combine the resistance surface analysis of the minimum cumulative resistance model to construct the first multi-objective optimization model. Determine ecological resilience, urban spatial resilience, and the protection and intensive development of basic farmland as optimization objectives. Use geographic cellular automata and neural network algorithms to embed the optimization objective function and constraints, simulate the evolution trend of urban spatial pattern, analyze the dynamic change law, and optimize the spatial distribution of functional zoning.

[0007] Step 2: Collect urban POI data, select residential, commercial and public service types as optimization objects, use cluster analysis to divide the optimization objects and extract core points, construct a second multi-objective optimization model, quantify the spatial relationship and traffic accessibility between nodes, calculate and optimize the spatial intensification, network resilience and adaptability to future urban development areas of the core points, use the NSGA-II algorithm to solve the optimization scheme, analyze the spatial layout characteristics of the core points, and optimize the spatial distribution of core points of residential, commercial and public service types;

[0008] Step 3: Construct graph structure data based on the road network, define node and edge features, train the graph structure of the road network using a graph neural network and extract features, construct a third multi-objective optimization model, quantify the compactness and resilience of the road network, and embed the dynamically updated edge features of the third multi-objective optimization model into the message passing mechanism of the graph neural network to capture global topological characteristics, so as to formulate multi-objective optimization decisions for the road network, and return to Step 1 for iterative optimization.

[0009] The decision-making process includes at least one of the following: adding new, efficient connecting roads; expanding the capacity of highly integrated roads; and removing inefficient and redundant roads.

[0010] Optionally, the minimum cumulative resistance model includes:

[0011] C M =f∑D mn R m

[0012] Among them, C M It is a function of the minimum drag at any grid center within the range and its distance to all source locations; f is the negative correlation between the minimum cumulative drag and its distance to all source locations; D mn R represents the distance a species travels from its source region n through space m to a certain grid cell in space; m This represents the resistance of a species to traversing the landscape space;

[0013] The Markov model includes:

[0014] S (t+1) =P ab ·S (t)

[0015] Among them, S (t) ,S (t+1) P represents the state matrix of land space types in the study area at time t and time t+1. ab This represents the transition probability matrix from type a to type b;

[0016] The future land use simulation model simulates the spatial distribution of functional zones, including:

[0017] Using a neural network algorithm, the suitability probability of each land use type within the research scope is obtained from the base year land spatial pattern data and various driving factors including human and natural effects. The suitability probability is combined with neighborhood factors, adaptive inertia coefficient and conversion cost to obtain the overall conversion probability of each cell. The simulation results are obtained through a roulette competition mechanism.

[0018] The neural network algorithm includes:

[0019]

[0020] Where sp(p,i,t) is the suitability probability of space of type i under grid p at time t; w j,i The weights between the output and hidden layers are represented by sigmoid(), which is the activation function from the hidden layer to the output layer. j (p,t) represents the signal received by the j-th hidden layer grid p at time t.

[0021] Optionally, the ecological resilience includes the connectivity and compactness of the ecological reserve. The sprawl and cohesion of the ecological reserve are calculated to characterize the ecological connectivity and compactness, and the calculation method includes:

[0022]

[0023] Where CON is the sprawl index of the ecological reserve, representing its connectivity; m is the total number of functional zone types; g k The number of adjacent patches within an ecological protection zone or between an ecological protection zone and other types of functional zones;

[0024]

[0025] Among them, COH e is the cohesion index of the ecological reserve, representing the compactness of the ecological reserve; P is the total area of ​​the ecological reserve patches; p is the total boundary length of all patches in the ecological reserve; a is the total area of ​​all patches in the ecological reserve; A is the total area of ​​all functional zone patches.

[0026] Optionally, the urban development zone is a source landscape type, and the ecological protection zone and basic farmland are sink landscape types. The urban spatial resilience is measured by calculating the source-sink landscape pattern index. The calculation process includes:

[0027]

[0028] Where: D is the average distance index of the source landscape patch; d ij The distance between grid i in the source landscape patch and grid j in the sink landscape patch is represented; m and n represent the number of grids in the source landscape patch and the number of grids in the sink landscape patch, respectively.

[0029] Optionally, the intensive development is characterized by calculating the cohesion of basic farmland and urban development zones, and the calculation method includes:

[0030]

[0031] Among them, COH c and COH u, respectively, are the cohesion indices of basic farmland and urban development zones, representing the degree of agglomeration of the two. P is the total area of ​​the corresponding functional zone patch, p is the total boundary length of all patches in the corresponding functional zone, a is the total area of ​​all patches in the corresponding functional zone, and A is the total area of ​​all functional zone patches.

[0032] Optionally, the constraints include:

[0033]

[0034] Among them, A e A c A u These refer to the optimized areas of ecological protection zones, basic farmland, and urban development areas, respectively. A e,min A c,min A u,max The red line control limits for ecological protection zones, basic farmland, and urban development zones are respectively defined in the national land space planning.

[0035] Optionally, the calculation and optimization of the spatial compactness, network resilience, and adaptability to future urban development areas of the core points includes:

[0036]

[0037] in, d represents the average shortest geometric distance between all core points, used to measure spatial compactness; N is the total number of core points; d ij It is the shortest geometric distance between the i-th and j-th core points.

[0038] Optionally, the step of using the NSGA-II algorithm to solve the optimization scheme includes:

[0039]

[0040] Population = {Position} p Position c Position s}

[0041] Among them, Position p Position c Postition s The spatial location matrix represents the core residential area, the core commercial area, and the core public service area, respectively. n,m For a specific spatial unit, if the unit has a core point, it is set to 1; otherwise, it is set to 0. n and m respectively determine the spatial range within which a core point can be placed.

[0042] Optionally, the quantification of the road network's intensification and resilience includes:

[0043]

[0044] Among them, S compact (e ij ) is edge e ij The intensity score is used to represent the intensity level of the edge; For edge e ij The average kernel density of the core points traversing the region represents the edge e. ij The demand for transportation at the core of the space; R(e) ij ) represents edge e ij The geometric length of the edge is used to represent the resource consumption of that edge;

[0045] The road network resilience is primarily characterized by maximizing the connectivity and adaptability of the road network during emergencies. It is measured by the network's connectivity and alternative paths for key nodes, and a resilience score S is defined for each edge. resilience (e ij )for:

[0046]

[0047] Among them, C b (e ij ) represents edge e ij The betweenness centrality of an edge measures its importance in the global shortest path, reflecting the flow it carries in the network. For each pair of nodes (V... i V j ) edge e ij Betweenness centrality is defined as:

[0048]

[0049] Where V is the set of all nodes; σ ij For passing through node V i To node V j The number of all shortest paths; σ ij (e ij ) are the paths that pass through edge e ij Quantity;

[0050] P backup (e ij ) represents edge e ij The number of alternative paths reflects the alternative capability when an edge fails; specifically, if edge e ij The ability to maintain connectivity between nodes through alternative paths after a failure is defined as P. backup (e ij )for:

[0051]

[0052] Among them, P ij For passing through node V i To node V j The set of all shortest paths; O() is an indicator function, if path P ij Includes edge e ij If it is not, assign it the value 0; otherwise, assign it the value 1.

[0053] On the other hand, this application also provides an intelligent optimization system for multi-element coupling of urban land space, including:

[0054] The Urban Territorial Spatial Surface Element Optimization Module is used to quantify the functional zoning transfer probability of ecological protection zones, basic farmland, and urban development zones based on Markov models. It uses a future land use simulation model to simulate the spatial distribution of functional zones, and combines the resistance surface analysis of the minimum cumulative resistance model to construct the first multi-objective optimization model. It determines ecological resilience, urban spatial resilience, and the protection and intensive development of basic farmland as optimization objectives. It adopts geographic cellular automata and neural network algorithms, embedding optimization objective functions and constraints to simulate the evolution trend of urban spatial patterns, analyze dynamic change patterns, and optimize the spatial distribution of functional zones.

[0055] The Urban Spatial Point Element Optimization Module is used to collect urban POI data, select residential, commercial and public service types as optimization objects, use cluster analysis to divide optimization objects and extract core points, construct a second multi-objective optimization model, quantify the spatial relationship and traffic accessibility between nodes, calculate and optimize the spatial intensification, network resilience and adaptability to future urban development areas of core points, use the NSGA-II algorithm to solve the optimization scheme, analyze the spatial layout characteristics of core points, and optimize the spatial distribution of core points of residential, commercial and public service types.

[0056] The Urban Territorial Spatial Line Element Optimization Module is used to construct graph structure data based on the road network, define node and edge features, train the graph structure of the road network using a graph neural network and extract features, construct a third multi-objective optimization model, quantify the compactness and resilience of the road network, and embed the dynamically updated edge features of the third multi-objective optimization model into the message passing mechanism of the graph neural network to capture global topological characteristics, so as to formulate multi-objective optimization decisions for the road network, and return to step one for iterative optimization.

[0057] The decision-making process includes at least one of the following: adding new, efficient connecting roads; expanding the capacity of highly integrated roads; and removing inefficient and redundant roads.

[0058] Compared with the prior art, the present invention has the following advantages: it integrates the optimization modules of urban land space point, line and surface elements, optimizes step by step in the order of "surface-point-line", and performs iterative analysis through the transmission of optimization results, and finally realizes the intelligent optimization of urban land space multi-element coupling with intensive resilience. Attached Figure Description

[0059] Figure 1 This is an overall flowchart of the present invention;

[0060] Figure 2 This is the NSGA-II algorithm execution logic of the present invention;

[0061] Figure 3 This is a system structure diagram of the present invention. Detailed Implementation

[0062] The embodiments of the present invention are described in detail below. These embodiments are implemented based on the technical solution of the present invention, and provide detailed implementation methods and specific operation processes. However, the scope of protection of the present invention is not limited to the following embodiments.

[0063] like Figure 1-3 As shown, this embodiment provides a technical solution: a multi-element coupled intelligent optimization method for urban land space, comprising:

[0064] Step 1: Based on the Markov model, quantify the functional zoning transfer probability of ecological protection zones, basic farmland, and urban development zones. Use the Future Land Use Simulation (FLUS) model to simulate the spatial distribution of functional zoning. Combined with the resistance surface analysis of the Minimum Cumulative Resistance (MCR) model, construct the first multi-objective optimization model. Determine ecological resilience, urban spatial resilience, and the protection and intensive development of basic farmland as optimization objectives. Employ Geographic Cellular Automata (Geo-CA) and Artificial Neural Network (ANN) algorithms, embedding optimization objective functions and constraints, to simulate the evolution trend of urban spatial patterns, analyze dynamic change patterns, and optimize the spatial distribution of functional zoning.

[0065] For example, the surface feature optimization module is built on the MCR-Markov-FLUS framework. The MCR-Markov-FLUS framework is an important tool in urban spatial functional zoning optimization and simulation research. The MCR model optimizes functional zoning configuration through resistance surface analysis, minimizing the cumulative resistance to system disturbances. The Markov model quantifies and predicts the transition probability between functional zoning based on time-series data. The FLUS model utilizes neural network algorithms and geographic cellular automata to generate the spatial distribution of functional zoning, emphasizing spatial heterogeneity and complexity. The analytical framework formed by these three components can be applied to simulate the changing trends of functional zoning and achieve spatial optimization configuration. The basic architecture of this framework is as follows:

[0066] (1) MCR model

[0067] The essence of the MCR model lies in minimizing the resistance required to reach the destination from the source area, reflecting accessibility. Viewing the evolution of functional zoning as the result of the diffusion of ecological and construction sources to the surrounding areas, minimum cumulative resistance surfaces for ecological and construction sources are constructed separately to represent the spatial span characteristics of functional zoning. The calculation formula is as follows:

[0068] C M =f∑D mn R m

[0069] Among them, C M It is a function of the minimum drag at any grid center within the range and its distance to all source locations; f is the negative correlation between the minimum cumulative drag and its distance to all source locations; D mn R represents the distance a species travels from its source region n through space m to a certain grid cell in space; m This represents the resistance a species experiences when traversing the landscape space.

[0070] (2) Markov model

[0071] The Markov model simulates changes in national land space by setting the state of a certain spatial type at time t+1 to depend only on time t. Its expression is as follows:

[0072] S (t+1) =P ab ·S (t)

[0073] Among them, S (t) ,S (t+1) P represents the state matrix of land space types in the study area at time t and time t+1. ab This represents the transition probability matrix from type a to type b.

[0074] (3) Flus model

[0075] The suitability probability of each land use type within the study area is obtained from the base year land spatial pattern data and various driving factors including human and natural effects using neural network algorithms (ANN). Then, the suitability probability is combined with neighborhood factors, adaptive inertia coefficients and conversion costs to obtain the overall conversion probability of each cell. Finally, the simulation results are obtained through a roulette wheel competition mechanism.

[0076] An ANN consists of an input layer, hidden layers, and an output layer. By normalizing the basic data of the driving factors and using uniform sampling to sample the land spatial data and driving factors, the suitability probability for different spaces is calculated using the ANN. The specific calculation formula is as follows:

[0077]

[0078] Where sp(p,i,t) is the suitability probability of space of type i under grid p at time t; w j,i The weights between the output and hidden layers are represented by sigmoid(), which is the activation function from the hidden layer to the output layer. j (p,t) represents the signal received by the j-th hidden layer grid p at time t. The sum of the suitability probabilities for each spatial type obtained by the ANN is always 1. That is:

[0079]

[0080] Neighborhood development density is chosen to measure the neighborhood effect, and the calculation formula is as follows:

[0081]

[0082] in, w represents the total number of grid cells representing the i-th land type in an N×N Moore neighborhood window after the previous iteration. i This represents the neighborhood effect weight for various spatial types. The neighborhood factor parameter ranges from [0,1], with a closer value to 1 indicating a stronger expansion capability for that functional partition type.

[0083] First multi-objective optimization model:

[0084] In urban spatial optimization, the objective function and constraints are core elements for achieving scientific planning. The objective function clarifies the direction of optimization, provides a quantitative basis for optimization, and ensures that the results are consistent with the planning objectives. Constraints limit the feasible range of the optimization scheme and prevent it from violating actual needs or policy regulations. In this case, the objective function for optimizing the urban land spatial pattern elements is set as follows:

[0085] (1) Ecological resilience

[0086] The connectivity and compactness of ecological reserves are important indicators for measuring ecological resilience. Better connectivity indicates a higher degree of connection between different patches within the ecological reserve, reducing the island effect and enhancing the stability and resilience of the ecosystem. Better compactness indicates a closer and more concentrated distribution of ecological patches, helping to reduce external disturbances that could damage the core ecological area. Based on the concept of the landscape pattern index, the connectivity and compactness of ecological reserves are measured by calculating their sprawl and cohesion, and these measurements are used as standards for measuring ecological resilience. The specific calculation formulas are as follows:

[0087]

[0088] Where CON is the sprawl index of the ecological reserve, representing its connectivity; m is the total number of functional zone types; g k This refers to the number of adjacent patches within an ecological protection zone or between an ecological protection zone and other types of functional zones.

[0089]

[0090] Among them, COH e is the cohesion index of the ecological reserve, representing the compactness of the ecological reserve; P is the total area of ​​the ecological reserve patches; p is the total boundary length of all patches in the ecological reserve; a is the total area of ​​all patches in the ecological reserve; A is the total area of ​​all functional zone patches.

[0091] (2) Urban spatial resilience

[0092] Urban spatial resilience focuses on the morphology of urban construction itself and its impact on the ecological pattern, as well as the interaction between internal structure and the external environment. The integration of urban development space and ecological protection space creates a landscape pattern conducive to mitigating adverse impacts, while the decentralized layout of urban development space helps improve the self-organization and independence of local areas, increasing urban resilience. The source-sink landscape theory measures the morphological resilience characteristics of cities from a landscape ecology perspective. This theory posits that heterogeneous landscapes can be divided into two types: source and sink landscapes. Source landscapes are those that promote process development, while sink landscapes are those that inhibit or delay process development. The negative effects of source landscapes can be absorbed and mitigated by sink landscapes. In this study, urban development space is defined as the source landscape, and ecological protection areas and basic farmland as the sink landscape. The source-sink landscape pattern index is used to measure urban spatial resilience. The specific calculation formula is as follows:

[0093]

[0094] Where: D is the average distance index of the source landscape patch; d ijdenoted by D, the distance between grid i in the source landscape patch and grid j in the sink landscape patch is represented; m and n represent the number of grids in the source landscape patch and the number of grids in the sink landscape patch, respectively. The smaller the D value, the stronger the coupling between the source and sink landscapes, and the stronger the urban spatial resilience; conversely, the larger the D value, the more severe the spatial isolation between the source and sink landscapes, and the more difficult it is for the negative effects of the source landscape to be offset by the sink landscape, thus resulting in poor urban spatial resilience.

[0095] (3) Intensive development of basic farmland and urban space

[0096] The intensive development of basic farmland and urban space requires ensuring that basic farmland and urban development space are as concentrated and compact as possible to minimize spatial fragmentation. This involves improving regional efficiency and sustainability through large-scale development and shared infrastructure. Urban development should focus on the efficient use of space, achieving a compact urban development model and reducing the encroachment of scattered urban sprawl on surrounding farmland, which would lead to the fragmentation of previously large-scale farmland. This study uses the concept of a landscape pattern index to calculate the compactness of basic farmland and urban development areas, serving as a measure of intensive development. The specific calculation method is as follows:

[0097]

[0098] Among them, COH c and COH u , respectively, represent the cohesion index of basic farmland and urban development area, characterizing the degree of agglomeration of the two; P is the total area of ​​the corresponding functional zone patch; p is the total boundary length of all patches in the corresponding functional zone; a is the total area of ​​all patches in the corresponding functional zone; A is the total area of ​​all functional zone patches.

[0099] The constraints primarily stem from the "three zones and three lines" red line control restrictions outlined in the national land spatial planning documents. The "three zones and three lines" include the ecological protection red line, the permanent basic farmland protection red line, and the urban development boundary red line. The ecological protection red line refers to the area that must be strictly protected to ensure national ecological security and maintain ecological functions; the permanent basic farmland protection red line is the foundation for ensuring national food security, specifying the minimum protected area for basic farmland; and the urban development boundary red line refers to the development boundary in urban planning, specifying the maximum area for urban development. Specifically, the constraints can be expressed as follows:

[0100]

[0101] Among them, A e A c A u These refer to the optimized areas of ecological protection zones, basic farmland, and urban development areas, respectively; A e,min A c,min A u,maxThe red line control limits for ecological protection zones, basic farmland, and urban development areas are respectively defined in the national land space planning.

[0102] Step 2: Collect city POI data, select residential, commercial and public service types as optimization objects, use cluster analysis to divide the optimization objects and extract core points, construct a second multi-objective optimization model, quantify the spatial relationship and traffic accessibility between nodes, calculate and optimize the spatial intensification, network resilience and adaptability to future urban development areas of the core points, use the NSGA-II algorithm to solve the optimization scheme, analyze the spatial layout characteristics of the core points, and optimize the spatial distribution of core points of residential, commercial and public service types.

[0103] Understandably, in order to better optimize land and space resources, multiple sources of data can be collected when collecting receipts, such as... Figure 2 As shown, examples include: meteorological data, topographic data, land use data, soil data, administrative boundary data, POI data, and road network data. Among them, POI data (Points of Interest) is an important data type in Geographic Information Systems (GIS), representing the location of discrete points in the real world that have specific functions or meanings. It usually contains attribute information such as name, category, coordinates, and address.

[0104] Considering future changes in urban development space, optimizing the layout of existing core points and selecting new core points become particularly important. This paper optimizes the layout of existing urban core points based on complex network theory, while rationally allocating new core points according to future changes in urban development space. The optimization aims to improve spatial efficiency, enhance network resilience, and ensure that new core points can be effectively integrated into future urban development plans.

[0105] In the second multi-objective optimization model, nodes are the core points identified, and edges represent the connections between nodes. The weights of the edges are determined by the spatial distance and accessibility between these nodes. The specific weights of the edges are expressed as follows:

[0106]

[0107] Among them, w i,j d represents the weight of the edge between node i and node j, reflecting the connection strength between the nodes; i,j k is the geometric spatial distance between node i and node j. i,j This represents the number of roads that directly connect node i and node j.

[0108] The objective function for optimizing the spatial layout of urban core points mainly includes three aspects: spatial intensification, network resilience, and adaptability to future urban development. Spatial intensification requires that the layout of urban functional points be as compact as possible to reduce space waste. In core point layout optimization, the intensification objective is expressed as minimizing the average geometric distance between core points, achieving efficient sharing of resources and services, and improving space utilization efficiency and resource allocation efficiency. The objective function for intensification optimization is expressed as:

[0109]

[0110] in, d represents the average shortest geometric distance between all core points, used to measure spatial compactness; N is the total number of core points; d ij It is the shortest geometric distance between the i-th and j-th core points.

[0111] Urban network resilience refers to the ability of an urban system to quickly recover and maintain its basic functions when subjected to disturbances or shocks (such as traffic accidents or natural disasters). From the perspective of complex networks, network resilience is typically enhanced by increasing redundant connections between nodes. The objective function of resilience optimization is to maximize redundant paths and network connectivity between urban functional points, ensuring that the system can recover through other paths even if some nodes fail. Therefore, resilience is measured by the network's betweenness centrality. The specific calculation method is as follows:

[0112]

[0113] Among them, C b For the overall resilience of the network; σ ij Let σ be the number of shortest paths from node i to node j. ij (k) represents the number of shortest paths through node k.

[0114] The optimization of urban land space elements delineates new urban development zones. Core points need to be rationally distributed to adapt to the needs of these new urban development zones. The adaptability objective function is measured by the coverage of the core points within the new urban development zones. The objective function is as follows:

[0115]

[0116] Among them, C s Core point coverage is used to characterize adaptability; A p The service area covering the urban development area of ​​the core points is obtained by overlaying analysis of the 15-minute driving reach area of ​​each core point based on the road network; A u This refers to the total area of ​​the urban development zone.

[0117] In summary, the objective function for optimizing the spatial layout of urban core points can be expressed as:

[0118]

[0119] Where F is the set of objective functions for optimizing the spatial layout of the city's core points; the other parameters are consistent with the description above.

[0120] The constraints for optimizing the spatial layout of urban core points define the distribution logic of these core points, mainly including constraints on urban development space, urban core area, and the number of core points. Among these, the urban development space constraint requires that resident core points can only be distributed within the urban development space, expressed as:

[0121]

[0122] Where, x i The core concept is {Urban}, which represents a collection of urban development spaces.

[0123] Furthermore, the existing layout of the city center and sub-centers should not undergo drastic changes during the optimization process; the optimization process should ensure that the distribution pattern of these core areas remains stable. Therefore, the following constraints are set:

[0124] |d ij -d ij,0 |≤∈

[0125] Where, d ij For the optimized core point x i and x j The geometric distance between them; d ij,0 For the optimized core point x i and x j The geometric distance between them; ∈ represents the tolerance, used to control the consistency between the optimization results and the existing urban structural pattern.

[0126] At the same time, the number of core points should conform to the city's development status and future plans. Therefore, the following constraints are set:

[0127] N∈[N plan ]

[0128] Where N is the number of core points; [N plan This refers to the range of planned locations for commercial hubs (or public service hubs) determined based on urban development and planning documents.

[0129] The NSGA-II algorithm from the genetic algorithm family is used to solve the optimization scheme, resulting in the optimized spatial layout. The NSGA-II algorithm is a multi-objective optimization algorithm based on the principles of heredity, variation, and evolution in biology. The NSGA-II algorithm combines non-dominated sorting and crowding operators through an elite strategy of population evolution. Furthermore, the algorithm employs a fast non-dominated sorting method based on Pareto dominance and optimality concepts to differentiate the solution. The spatial locations of residential core points, commercial core points, and public service core points are each represented by a matrix. Each combination of the spatial location matrices of the three types of core points is considered an individual, and the set of individuals constitutes the population. The details are shown below:

[0130]

[0131] Population = {Positon} p Position c Position s}

[0132] Among them, Position p Position c Position s A spatial location matrix representing the core residential areas, commercial areas, and public service areas; x n,m For a specific spatial unit, if the unit has a core point, it is set to 1; otherwise, it is set to 0. n and m respectively determine the spatial range within which a core point can be placed.

[0133] (1) Basic operating logic of NSGA-II algorithm

[0134] like Figure 2 As shown, the NSGA-II algorithm, based on the constraints set above, determines the permissible composition of each individual in the population, including its parents and all subsequent offspring. These constraints constitute the external environment that determines the survival of the population. In this case, individuals unable to adapt to the external environment face "natural selection" and cannot enter the next iteration. The objective function in the optimization model reflects the degree of adaptation of an individual to the external environment and determines the individual's hierarchical position in the group. Individuals with stronger adaptability have a survival advantage, and their adaptive "genes" can be passed on to their offspring. To prevent homogenization within the population, the algorithm is configured to calculate the values ​​of the next generation through multi-point crossover and Gaussian mutation. This process ensures that offspring can efficiently inherit "advantageous genes" from their parents while introducing a certain amount of "genetic mutation," ensuring individual diversity and avoiding convergence of optimization results. In this example, the population size is set to 100, the mutation range is set to [0,1], the mutation probability is set to 10%, and the number of iterations is set to 1000.

[0135] (2) Fast Non-Dominated Sort and Crowding Operator

[0136] The fast nondominated sorting in the NSGA-II algorithm constitutes a population hierarchical structure based on the level of individual nondominated solutions. This hierarchical structure effectively guides the search towards the Pareto optimal solution set. Fast nondominated sorting represents a cyclical process that adapts to value hierarchy. The analysis logic is as follows: Find the overall nondominated solution set, called the first nondominated layer F1. Remove all individuals in F1 from the population. Then continue searching for the remaining nondominated solution set, called the second nondominated layer F2, and continue removing individuals from F2 from the remaining population. Continue this analysis logic until the entire population is hierarchically structured, obtaining all F1 values. rank Individuals within the same stratum share the same non-dominated ranking. Fast non-dominated ranking ranks all individuals within the population, but it does not establish rankings among individuals at the same stratum of the non-dominated ranking. If, after including individuals maladapted to the environment, the selection of the next generation of parents exceeds predetermined constraints, it is necessary to determine which individuals are eligible to become the next generation of parents. Therefore, a crowding operator is used to rank individuals within the same non-dominated stratum of the non-dominated ranking to achieve parental selection.

[0137] The crowding operator refers to the average functional distance C between two individuals within the same non-dominated layer, calculated based on the objective function value. i The average functional distance is represented by the perimeter of a rectangle, with each individual and its nearest neighbor forming vertices. Points on the rectangle's boundary are set to infinite crowding. For all other intermediate individuals, the crowding is the sum of the normalized absolute differences of all objective function values ​​between two adjacent individuals.

[0138] (3) Natural selection process

[0139] Non-dominated hierarchy F based on non-dominated sorting rank and the crowding operator C i Construct the natural selection sequence [F] rank C i Based on this sequence, all individuals are ranked. The natural selection process prioritizes the non-dominated level, and then considers the crowding operator ranking within the same non-dominated level. The next generation of parents is selected for each iteration based on the natural selection process and the set population size.

[0140] Step 3: Construct graph structure data based on the road network, define node and edge features, train the graph structure of the road network using a graph neural network and extract features, construct a third multi-objective optimization model, quantify the compactness and resilience of the road network, and embed the dynamically updated edge features of the third multi-objective optimization model into the message passing mechanism of the graph neural network to capture global topological characteristics, so as to formulate multi-objective optimization decisions for the road network, and return to Step 1 for iterative optimization.

[0141] The decision-making process includes at least one of the following: adding new, efficient connecting roads; expanding the capacity of highly integrated roads; and removing inefficient and redundant roads.

[0142] Representing road networks as graph data G=(V,E) is a cutting-edge modeling method in related fields, where V represents the set of nodes and E represents the set of edges. Nodes v∈V represent road intersections, and edges e represent... ij ∈E represents a road segment connecting two nodes. Each node and edge is assigned specific features to reflect its geographical or traffic attributes.

[0143] (1) Node construction and node feature setting

[0144] Each intersection of the road network vector data is obtained through topology analysis and designated as a node. Each node v i The eigenvectors of ∈V are represented as X i ∈R d , where d is the feature dimension. In , node v i The location feature is defined as:

[0145] X i =[x i ,y i ,r i ,q i ]

[0146] Among them, X i For node v i eigenvectors; x i For node v i longitude; y i For node v i latitude; r i Represents node v i Whether it is located in an urban development area; if it is, assign 1; otherwise, assign 0. i Represents node v i Due to the influence of various surrounding core points, nodes with a high degree of impact have a higher demand for traffic carrying capacity. The core point density value of the node location is used for measurement (the calculation method is the same as Equation 11).

[0147] (2) Edge construction and edge feature setting

[0148] The edge set E represents the topology of road segments. Each road segment between intersections is extracted from the road network as a connection between nodes. Each edge e ij ∈E represents node v i and v j The connection relationship, characterized by e ij ∈Rk It reflects the physical or attribute information of the road segment. The feature vector of each edge can be represented as:

[0149]

[0150] Among them, l ij For edge e ij Length; r ij Characterizing edge e ij Whether it passes through an urban development area; if it does, assign 1, otherwise assign 0. Representing edge e ij Due to the influence of various surrounding key points, the edges that are more affected have a higher demand for traffic carrying capacity, and edge e- ij The average core density of the core points traversing the region is used as a measure.

[0151] (3) Construction of adjacency matrix

[0152] Adjacency matrix A∈R n×n This is used to describe the topology of a road network diagram, where n is the number of nodes. If node v i and v j If there is an edge between A and B, then A ij =1, otherwise A ij =0.

[0153] 2. Construction of the Third Multi-Objective Optimization Model

[0154] (1) Objective function

[0155] The intensive objective in the objective function primarily represents maximizing the service efficiency of the road network to traffic demand while minimizing the waste of redundant resources. In a graph structure, the intensive objective is measured by the coverage of traffic demand by the spatial layout of edges to core points. For each edge e... ij Its intensiveness score S compact (e ij This represents the ratio of the traffic demand at the core point of the space through which the edge passes to the length of the edge:

[0156]

[0157] Among them, S compact (e ij ) is edge e ij The intensity score is used to represent the intensity level of the edge; For edge e ij The average kernel density of the core points traversing the region represents the edge e. ij The demand for transportation at the core of the space; R(e) ij ) represents edge e ijThe geometric length of the edge is used to represent the resource consumption of that edge.

[0158] The resilience objective in the objective function primarily represents maximizing the connectivity and adaptability of the road network during emergencies, measured by network connectivity and alternative paths for key nodes. A resilience score S is defined for each edge. resilience (e ij )for:

[0159]

[0160] Among them, C b (e ij ) represents edge e ij The betweenness centrality of an edge measures its importance in the global shortest path, reflecting the flow it carries in the network. For each pair of nodes (V... i V j ) edge e ij Betweenness centrality is defined as:

[0161]

[0162] Where V is the set of all nodes; σ ij For passing through node V i To node V j The number of all shortest paths; σ ij (e ij ) are the paths that pass through edge e ij The quantity.

[0163] P backup (e ij ) represents edge e ij The number of alternative paths reflects the alternative capability when an edge fails. Specifically, if edge e ij The ability to maintain connectivity between nodes through alternative paths after a failure. Define P. backup (e ij )for:

[0164]

[0165] Among them, P ij For passing through node V i To node V j The set of all shortest paths; O() is an indicator function, if path P ij Includes edge e ij If it is not, assign it the value 0; otherwise, assign it the value 1.

[0166] (2) Constraints

[0167] The main constraints in the optimization model are connectivity constraints, which mean that the network must maintain connectivity after optimization, i.e., the spectral radius of the adjacency matrix A′ must be greater than zero.

[0168] λ min (A′)>0

[0169] Where A′ is the optimized graph structure adjacency matrix; λ min Let A be the smallest non-zero eigenvalue of A′.

[0170] In this embodiment, an optimization module for urban land space point, line and surface elements is integrated. The optimization is carried out step by step in the order of "surface-point-line". The optimization results are transmitted for iterative analysis, and finally the intelligent optimization of urban land space multi-element coupling with intensive resilience is achieved.

[0171] In another embodiment of this application, such as Figure 3 As shown, a multi-element coupled intelligent optimization system for urban land space is provided, including:

[0172] The Urban Territorial Spatial Surface Element Optimization Module is used to quantify the functional zoning transfer probability of ecological protection zones, basic farmland, and urban development zones based on Markov models. It uses a future land use simulation model to simulate the spatial distribution of functional zones, and combines the resistance surface analysis of the minimum cumulative resistance model to construct the first multi-objective optimization model. It determines ecological resilience, urban spatial resilience, and the protection and intensive development of basic farmland as optimization objectives. It adopts geographic cellular automata and neural network algorithms, embedding optimization objective functions and constraints to simulate the evolution trend of urban spatial patterns, analyze dynamic change patterns, and optimize the spatial distribution of functional zones.

[0173] The Urban Spatial Point Element Optimization Module is used to collect urban POI data, select residential, commercial and public service types as optimization objects, use cluster analysis to divide optimization objects and extract core points, construct a second multi-objective optimization model, quantify the spatial relationship and traffic accessibility between nodes, calculate and optimize the spatial intensification, network resilience and adaptability to future urban development areas of core points, use the NSGA-II algorithm to solve the optimization scheme, analyze the spatial layout characteristics of core points, and optimize the spatial distribution of core points of residential, commercial and public service types.

[0174] The Urban Territorial Spatial Line Element Optimization Module is used to construct graph structure data based on the road network, define node and edge features, train the graph structure of the road network using a graph neural network and extract features, construct a third multi-objective optimization model, quantify the compactness and resilience of the road network, and embed the dynamically updated edge features of the third multi-objective optimization model into the message passing mechanism of the graph neural network to capture global topological characteristics, so as to formulate multi-objective optimization decisions for the road network, and return to step one for iterative optimization.

[0175] The decision-making process includes at least one of the following: adding new, efficient connecting roads; expanding the capacity of highly integrated roads; and removing inefficient and redundant roads.

[0176] In this embodiment, an optimization module for urban land space point, line and surface elements is integrated. The optimization is carried out step by step in the order of "surface-point-line". The optimization results are transmitted for iterative analysis, and finally the intelligent optimization of urban land space multi-element coupling with intensive resilience is achieved.

[0177] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0178] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0179] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A multi-element coupled intelligent optimization method for urban land space, characterized in that, include: Step 1: Based on the Markov model, quantify the functional zoning transfer probability of ecological protection zones, basic farmland, and urban development zones. Use the future land use simulation model to simulate the spatial distribution of functional zoning. Combine the resistance surface analysis of the minimum cumulative resistance model to construct the first multi-objective optimization model. Determine ecological resilience, urban spatial resilience, and the protection and intensive development of basic farmland as optimization objectives. Use geographic cellular automata and neural network algorithms to embed the optimization objective function and constraints, simulate the evolution trend of urban spatial pattern, analyze the dynamic change law, and optimize the spatial distribution of functional zoning. Step 2: Collect urban POI data, select residential, commercial and public service types as optimization objects, use cluster analysis to divide the optimization objects and extract core points, construct a second multi-objective optimization model, quantify the spatial relationship and traffic accessibility between nodes, calculate and optimize the spatial intensification, network resilience and adaptability to future urban development areas of the core points, use the NSGA-II algorithm to solve the optimization scheme, analyze the spatial layout characteristics of the core points, and optimize the spatial distribution of core points of residential, commercial and public service types; Step 3: Construct graph structure data based on the road network, define node and edge features, train the graph structure of the road network using a graph neural network and extract features, construct a third multi-objective optimization model, quantify the compactness and resilience of the road network, and embed the dynamically updated edge features of the third multi-objective optimization model into the message passing mechanism of the graph neural network to capture global topological characteristics, so as to formulate multi-objective optimization decisions for the road network, and return to Step 1 for iterative optimization. The decision-making process includes at least one of the following: adding new, efficient connecting roads; expanding the capacity of highly integrated roads; and removing inefficient and redundant roads.

2. The intelligent optimization method for multi-element coupling of urban land space according to claim 1, characterized in that: The minimum cumulative resistance model includes: C M =f∑D mn R m Among them, C M It is a function of the minimum drag at any grid center within the range and its distance to all source locations; f is the negative correlation between the minimum cumulative drag and its distance to all source locations; D mn R represents the distance a species travels from its source region n through space m to a certain grid cell in space; m This represents the resistance of a species to traversing the landscape space; The Markov model includes: S (t+1) =P ab ·S (t) Among them, S (t) ,S (t+1) P represents the state matrix of land space types in the study area at time t and time t+1. ab This represents the transition probability matrix from type a to type b; The future land use simulation model simulates the spatial distribution of functional zones, including: Using a neural network algorithm, the suitability probability of each land use type within the research scope is obtained from the base year land spatial pattern data and various driving factors including human and natural effects. The suitability probability is combined with neighborhood factors, adaptive inertia coefficient and conversion cost to obtain the overall conversion probability of each cell. The simulation results are obtained through a roulette competition mechanism. The neural network algorithm includes: Where sp(p,i,t) is the suitability probability of space of type i under grid p at time t; w j,i The weights between the output and hidden layers are represented by sigmoid(), which is the activation function from the hidden layer to the output layer. j (p,t) represents the signal received by the j-th hidden layer grid p at time t.

3. The intelligent optimization method for multi-element coupling of urban land space according to claim 1, characterized in that: The ecological resilience includes the connectivity and compactness of the ecological reserve. The sprawl and cohesion of the ecological reserve are calculated to characterize ecological connectivity and compactness. The calculation methods include: Where CON is the sprawl index of the ecological reserve, representing its connectivity; m is the total number of functional zone types; g k The number of adjacent patches within an ecological protection zone or between an ecological protection zone and other types of functional zones; Among them, COH e is the cohesion index of the ecological reserve, representing the compactness of the ecological reserve; P is the total area of ​​the ecological reserve patches; p is the total boundary length of all patches in the ecological reserve; a is the total area of ​​all patches in the ecological reserve; A is the total area of ​​all functional zone patches.

4. The intelligent optimization method for multi-element coupling of urban land space according to claim 1, characterized in that: The urban development zone is a source landscape type, and the ecological protection zone and basic farmland are sink landscape types. The source-sink landscape pattern index is used to measure urban spatial resilience. The calculation process includes: Where: D is the average distance index of the source landscape patch; d ij The distance between grid i in the source landscape patch and grid j in the sink landscape patch is represented; m and n represent the number of grids in the source landscape patch and the number of grids in the sink landscape patch, respectively.

5. The intelligent optimization method for multi-element coupling of urban land space according to claim 1, characterized in that: The intensive development mentioned above is characterized by calculating the cohesion of basic farmland and urban development zones. The calculation method includes: Among them, COH c and COH u , respectively, are the cohesion indices of basic farmland and urban development zones, representing the degree of agglomeration of the two. P is the total area of ​​the corresponding functional zone patch, p is the total boundary length of all patches in the corresponding functional zone, a is the total area of ​​all patches in the corresponding functional zone, and A is the total area of ​​all functional zone patches.

6. The intelligent optimization method for multi-element coupling of urban land space according to claim 1, characterized in that: The constraints include: Among them, A e A c A u These refer to the optimized areas of ecological protection zones, basic farmland, and urban development areas, respectively. A e,min A c,min A u,max The red line control limits for ecological protection zones, basic farmland, and urban development zones are respectively defined in the national land space planning.

7. The intelligent optimization method for multi-element coupling of urban land space according to claim 1, characterized in that: The calculation and optimization of the spatial compactness, network resilience, and adaptability to future urban development areas of the core points include: in, d represents the average shortest geometric distance between all core points, used to measure spatial compactness; N is the total number of core points; d ij It is the shortest geometric distance between the i-th and j-th core points.

8. The intelligent optimization method for multi-element coupling of urban land space according to claim 1, characterized in that: The method of solving the optimization scheme using the NSGA-II algorithm includes: Population={Position p ,Position c ,Position s } Among them, Position p Position c Position s The spatial location matrix represents the core residential area, the core commercial area, and the core public service area, respectively. n,m For a specific spatial unit, if the unit has a core point, it is set to 1; otherwise, it is set to 0. n and m respectively determine the spatial range within which a core point can be placed.

9. The intelligent optimization method for multi-element coupling of urban land space according to claim 1, characterized in that, The quantification of the road network's intensification and resilience includes: Among them, S compact (e ij ) is edge e ij The intensity score is used to represent the intensity level of the edge; For edge e ij The average kernel density of the core points traversing the region represents the edge e. ij The demand for transportation at the core of the space; R(e) ij ) represents edge e ij The geometric length of the edge is used to represent the resource consumption of that edge; The road network resilience is primarily characterized by maximizing the connectivity and adaptability of the road network during emergencies. It is measured by the network's connectivity and alternative paths for key nodes, and a resilience score S is defined for each edge. resilience (e ij )for: Among them, C b (e ij ) represents edge e ij The betweenness centrality of an edge measures its importance in the global shortest path, reflecting the flow it carries in the network. For each pair of nodes (V... i V j ) edge e ij Betweenness centrality is defined as: Where V is the set of all nodes; σ ij For passing through node V i To node V j The number of all shortest paths; σ ij (e ij ) are the paths that pass through edge e ij Quantity; P backup (e ij ) represents edge e ij The number of alternative paths reflects the alternative capability when an edge fails; specifically, if edge e ij The ability to maintain connectivity between nodes through alternative paths after a failure is defined as P. backup (e ij )for: Among them, P ij For passing through node V i To node V j The set of all shortest paths; O() is an indicator function, if path P ij Includes edge e ij If it is not, assign it the value 0; otherwise, assign it the value 1.

10. A multi-element coupled intelligent optimization system for urban land space, characterized in that, include: The Urban Territorial Spatial Surface Element Optimization Module is used to quantify the functional zoning transfer probability of ecological protection zones, basic farmland, and urban development zones based on Markov models. It uses a future land use simulation model to simulate the spatial distribution of functional zones, and combines the resistance surface analysis of the minimum cumulative resistance model to construct the first multi-objective optimization model. It determines ecological resilience, urban spatial resilience, and the protection and intensive development of basic farmland as optimization objectives. It adopts geographic cellular automata and neural network algorithms, embedding optimization objective functions and constraints to simulate the evolution trend of urban spatial patterns, analyze dynamic change patterns, and optimize the spatial distribution of functional zones. The Urban Spatial Point Element Optimization Module is used to collect urban POI data, select residential, commercial and public service types as optimization objects, use cluster analysis to divide optimization objects and extract core points, construct a second multi-objective optimization model, quantify the spatial relationship and traffic accessibility between nodes, calculate and optimize the spatial intensification, network resilience and adaptability to future urban development areas of core points, use the NSGA-II algorithm to solve the optimization scheme, analyze the spatial layout characteristics of core points, and optimize the spatial distribution of core points of residential, commercial and public service types. The Urban Territorial Spatial Line Element Optimization Module is used to construct graph structure data based on the road network, define node and edge features, train the graph structure of the road network using a graph neural network and extract features, construct a third multi-objective optimization model, quantify the compactness and resilience of the road network, and embed the dynamically updated edge features of the third multi-objective optimization model into the message passing mechanism of the graph neural network to capture global topological characteristics, so as to formulate multi-objective optimization decisions for the road network, and return to step one for iterative optimization. The decision-making process includes at least one of the following: adding new, efficient connecting roads; expanding the capacity of highly integrated roads; and removing inefficient and redundant roads.

Images