Land space planning method and system integrating ecological safety and urban development

Abstract

The invention provides a territorial space planning method and system fusing ecological safety and urban development, and the method comprises the steps: obtaining urban development evaluation factors and ecological evaluation factors to construct an urban development potential pattern network and an ecological safety pattern network, giving a development potential value and an ecological resistance value, and constructing an ecological-development conflict intensity network, the method comprises the steps of obtaining a resampling development potential value and a resampling ecological resistance value, obtaining an ecological-development conflict intensity index, generating a high-intensity conflict region spatial distribution map, defining a comprehensive conversion probability, constructing a town planning cellular definition model, setting a planning requirement group, and constructing a multi-objective optimization problem in combination with the comprehensive conversion probability. And solving a multi-objective optimization problem based on a swarm intelligent multi-objective optimization algorithm, obtaining a development ecological planning set and configuring an ecological development territorial space report, and realizing dynamic conflict identification and multi-objective optimization collaborative decision-making of ecological safety and urban development.

Description

Technical Field

[0001] This invention relates to the field of spatial planning technology, and more specifically, to a method and system for land spatial planning that integrates ecological security and urban development. Background Technology

[0002] With the establishment of the national spatial planning system, how to scientifically coordinate the relationship between ecological protection and urban development has become a core challenge. Current mainstream planning methods usually rely on qualitative judgment or static map overlay analysis. Specifically, at the level of ecological protection, spatial control is mainly achieved by delineating ecological protection red lines, while at the level of urban development, the layout of construction land is guided by the results of land suitability evaluation. This method is essentially a static process of evaluation-delineation-constraint, treating ecology and development as two independent layers that need to be easily avoided. It is difficult to dynamically simulate the complex spatial interaction and feedback relationship between the two during the planning process, which often leads to the final plan falling into a single-objective bias between protection and development.

[0003] On the one hand, existing technologies, when identifying conflicts between ecology and development, lack consideration of the spatial correlation and transmission effects of these conflicts. Current methods typically stop at generating two separate current status maps for ecological and development assessments, and then simply overlaying them to identify conflict areas. This isolated grid-like analysis cannot reveal the contiguous regional conflict hotspots caused by spatial proximity and functional association. Therefore, planning decisions struggle to achieve refined and differentiated spatial guidance based on conflict intensity gradients, often resorting to a one-size-fits-all, simplistic avoidance strategy.

[0004] On the other hand, when existing technologies integrate ecological constraints into development simulations, their rule systems are rigid and fixed. For example, in traditional cellular automata models, ecological constraints are often manifested as setting conversion restrictions. This rigid constraint mode cannot be dynamically and flexibly adjusted during the simulation process based on the overall regional protection and development needs. At the same time, existing methods lack effective mechanisms to simultaneously optimize multiple conflicting objectives, resulting in the generated schemes failing to systematically reveal the spectrum of development potential that may be achieved under different protection intensities, thus making it difficult to support true multi-objective optimization collaborative decision-making.

[0005] In summary, existing technologies, due to their static and isolated conflict identification methods and rigid, single-objective simulation constraints, cannot provide a complete technical system from conflict diagnosis and dynamic simulation to multi-scheme optimization. Therefore, there is an urgent need in this field for a method that can fundamentally overcome these limitations and achieve dynamic conflict identification between ecological security and urban development, as well as collaborative decision-making from multiple objectives. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention provides a land spatial planning method and system that integrates ecological security and urban development.

[0007] The first aspect of this invention provides a land spatial planning method that integrates ecological security and urban development, comprising: Obtain urban development evaluation factors and ecological evaluation factors, construct urban development potential pattern network and ecological security pattern network respectively, and assign development potential value and ecological resistance value; Based on the urban development potential pattern network and the ecological security pattern network, an ecological-development conflict intensity network is obtained, and resampled development potential values ​​and resampled ecological resistance values ​​are obtained. Based on the ecological-development conflict intensity network, an ecological-development conflict intensity index is obtained. A spatial distribution map of high-intensity conflict areas is generated through a fusion clustering strategy. Construct a cell definition model for urban planning, which includes comprehensive transformation probabilities; A set of planning requirements is defined, and a multi-objective optimization problem is constructed based on the planning requirements set and the comprehensive transformation probability. The multi-objective optimization problem is solved based on the swarm intelligence multi-objective optimization algorithm to obtain the development ecological planning set. Based on the spatial distribution map of high-intensity conflict areas, an ecological development land space report is configured for the development of ecological planning.

[0008] According to a preferred embodiment, urban development evaluation factors and ecological evaluation factors are obtained, and urban development potential pattern networks and ecological security pattern networks are constructed respectively, and development potential values ​​and ecological resistance values ​​are assigned, including: The ecological evaluation factors are specifically indicators that affect ecological security. The ecological evaluation factors are identified based on the minimum cumulative resistance model to obtain ecological source areas, ecological corridors, ecological nodes and ecological resistance values, and to construct an ecological security pattern network. Each grid cell in the ecological security pattern network is assigned an ecological resistance value. The urban development evaluation factors are specifically indicators that affect urban development. The suitability of the urban evaluation factors is assessed, the assessment results and development potential values ​​are obtained, and an urban development potential pattern network is constructed, wherein each grid cell of the urban development potential pattern network is assigned a development potential value.

[0009] According to a preferred embodiment, an ecological-development conflict intensity network is obtained based on an urban development potential pattern network and an ecological security pattern network, and resampled development potential values ​​and resampled ecological resistance values ​​are obtained. An ecological-development conflict intensity index is obtained based on the ecological-development conflict intensity network. A spatial distribution map of high-intensity conflict areas is generated through a fusion clustering strategy, including: A planning network standard is set, and each grid in the urban development potential pattern network and the ecological security pattern network is adaptively aligned according to the set planning network standard. Based on the aligned urban development potential pattern network and ecological security pattern network, data is resampled and normalized to obtain resampled ecological resistance value and resampled development potential value. The resampled ecological resistance value and the resampled development potential value are assigned to each grid cell in the aligned urban development potential pattern network and ecological security pattern network, and the aligned urban development potential pattern network and ecological security pattern network are superimposed to obtain the ecological-development conflict intensity network. The resampled ecological resistance value and the resampled development potential value are imported into the two-order conflict model to obtain the ecological-development conflict intensity index.

[0010] According to a preferred embodiment, the method further includes: Obtain the local conflict index for each network grid, which is the product of the resampled ecological resistance value and the resampled development potential value for each network grid; Set the conflict radius and select each network grid cell as a selected grid cell. The conflict radius is represented as the radius of a circle centered on the selected grid cell. The associated grid is obtained based on the conflict radius and the ecological-development conflict intensity index, and the spatially associated conflict index is obtained one by one according to the local conflict index.

[0011] According to a preferred embodiment, the method further includes: Candidate graticets are obtained based on the conflict radius, where the candidate graticet is defined as all network graticets whose conflict radius reaches the selected graticet and other graticets excluding the selected graticet. The mean of the local conflict index of the candidate raster is calculated as the local conflict intensity threshold. Select candidate rasters whose local conflict index is greater than or equal to the local conflict intensity threshold as associated rasters; The Euclidean distance is obtained based on the associated grid and the selected grid, and the attenuation base is obtained based on the Euclidean distance, wherein the attenuation base is set to the sum of 1 and the square of the Euclidean distance; The influence value is obtained one by one based on the local conflict index and attenuation base of the associated raster, and the spatial association conflict index is calculated based on the influence value.

[0012] Based on the aforementioned ecological-development conflict intensity network, spatial clustering analysis is performed on the ecological-development conflict intensity index to obtain high-conflict raster clusters. The high-conflict raster clusters are then filtered based on morphological filtering and a preset minimum patch area threshold to generate a spatial distribution map of the high-intensity conflict area.

[0013] According to a preferred embodiment, an urban planning cell definition model is constructed, wherein the urban planning cell definition model includes a comprehensive transformation probability, comprising: Obtain the land use status of each grid cell in the ecological-development conflict intensity network, wherein the land use status includes urban land and non-urban land; In the ecological-development conflict intensity network, each network grid is defined as a cell, and the land use status corresponding to each network grid is taken as the cell state and the cell neighborhood is defined using the Moore neighborhood algorithm. The neighborhood influence probability is obtained based on the cell neighborhood and cell state, the adaptation probability is obtained based on the resampled development potential value, and the conflict constraint probability is obtained based on the ecology-development conflict intensity index. The neighborhood influence probability, adaptation probability, and conflict constraint probability are combined with the undetermined conversion probability weight parameter to obtain the comprehensive conversion probability.

[0014] According to a preferred embodiment, the method further includes: The total number of cells in a cell's neighborhood and the number of cells in a town's neighborhood are counted. The total number of cells in a cell's neighborhood is the total number of cells in a cell's neighborhood, and the number of cells in a town's neighborhood is the number of cells in the total number of cells whose state is town land. The ratio of the number of cells in a town's neighborhood to the total number of cells is calculated and used as the neighborhood influence probability. Retrieve the resampling development potential value of the network raster corresponding to the cell, normalize the resampling development potential value and use it as the fitness probability; The ecological-development conflict intensity index of the network grid corresponding to the cell is retrieved, and the ecological-development conflict intensity index is input into a preset constraint function to obtain the conflict constraint probability. The preset constraint function ensures that the conflict constraint probability is negatively correlated with the ecological-development conflict intensity index.

[0015] According to a preferred embodiment, a planning requirement set is defined, a multi-objective optimization problem is constructed based on the planning requirement set and the comprehensive transformation probability, and the multi-objective optimization problem is solved based on a swarm intelligence multi-objective optimization algorithm to obtain a development ecological planning set, including: The planned area is set, which represents the total number of grid cells for newly added urban land during the planning period, and a high conflict conversion penalty coefficient is set based on the spatial distribution map of the high-intensity conflict area. Set development goals and ecological goals, wherein the development goals are to maximize the total efficiency of urban development at the end of the planning period, and the ecological goals are to minimize the total loss of ecosystem service value caused by urban expansion during the planning period; Constraints are obtained based on the planned area and the high-conflict conversion penalty coefficient. Development objective functions and ecological objective functions are obtained based on development goals and ecological goals, respectively. The undetermined conversion probability weight parameters in the comprehensive conversion probability are used as decision variables. The multi-objective optimization problem is constructed based on constraints, development objective function, ecological objective function, and decision variables.

[0016] According to a preferred embodiment, a planning requirement set is defined, a multi-objective optimization problem is constructed based on the planning requirement set and the comprehensive transformation probability, and the multi-objective optimization problem is solved based on a swarm intelligence multi-objective optimization algorithm to obtain a development ecological planning set, including: Based on the swarm intelligence multi-objective optimization algorithm, multiple sets of decision variables are obtained, and the decision variables drive the urban planning cellular definition model to carry out a complete urban expansion simulation. After the simulation, the development objective function value and ecological objective function value corresponding to the multiple sets of decision variables are obtained. Based on the results of urban expansion simulations, a development ecological planning set is defined, which represents a collection of multiple development ecological planning schemes that achieve different trade-offs between development goals and ecological goals.

[0017] According to a preferred embodiment, an ecological development land space report is configured for the development of an ecological planning set based on a spatial distribution map of high-intensity conflict areas.

[0018] A second aspect of the present invention also provides a land spatial planning system that integrates ecological security and urban development, comprising: The data acquisition and processing module is used to acquire urban development evaluation factors and ecological evaluation factors, construct urban development potential pattern network and ecological security pattern network respectively, and assign development potential value and ecological resistance value. The conflict identification and spatial analysis module is used to obtain the ecological-development conflict intensity network, obtain the resampled development potential value and resampled ecological resistance value based on the ecological-development conflict intensity network, and obtain the ecological-development conflict intensity index. It also generates a spatial distribution map of high-intensity conflict areas through a fusion clustering strategy. Urban planning cell definition model module, which is used to construct urban planning cell definition model; A multi-objective optimization module is used to construct and solve a multi-objective optimization problem based on a set of planning requirements and a comprehensive transformation probability, thereby obtaining a development ecological planning set. The report generation module is used to configure ecological development land space reports for the development ecological planning set based on the spatial distribution map of high-intensity conflict areas.

[0019] Based on the above, this application embodiment obtains urban development evaluation factors and ecological evaluation factors, constructs urban development potential pattern networks and ecological security pattern networks respectively, and assigns development potential values ​​and ecological resistance values. Then, based on the urban development potential pattern network and ecological security pattern network, it obtains an ecological-development conflict intensity network and obtains comparable resampled development potential values ​​and resampled ecological resistance values. On this basis, it introduces a two-order conflict model to calculate the ecological-development conflict intensity index, and generates a spatial distribution map of high-intensity conflict areas through a fusion clustering strategy. The above steps first ensure a scientific and reasonable quantitative basis in both the dimensions of ecological protection and urban development by constructing urban development potential pattern networks and ecological security pattern networks respectively. Then, it resamples based on the ecological-development conflict intensity network and introduces a two-order conflict model to calculate the ecological-development conflict intensity index, realizing dynamic and refined identification of the conflict relationship between ecological security and urban development, and significantly improving the accuracy and spatial representativeness of the conflict index calculation.

[0020] On the other hand, by defining the probability of neighborhood influence, the probability of adaptability, the probability of conflict constraints, and the probability of comprehensive transformation, and constructing a cellular definition model for urban planning based on these, a set of planning requirements including area and high conflict transformation penalty coefficients is set. A multi-objective optimization problem is constructed by combining the comprehensive transformation probability, and a swarm intelligence multi-objective optimization algorithm is used to solve it. Ultimately, a set of development-ecological planning schemes that achieve different trade-offs between development and ecological goals is obtained. Based on the spatial distribution map of high-intensity conflict areas, an ecological development land space report is configured for the development-ecological planning set. These steps first construct a cellular definition model for urban planning by introducing multi-source probability parameters, effectively simulating the inherent laws and external constraints of urban expansion. Then, a differentiated high-conflict transformation penalty mechanism is integrated into the constraint conditions, breaking through the limitations of traditional rigid constraints and achieving dynamic and flexible control of ecological protection efforts. Finally, a swarm intelligence multi-objective optimization algorithm is used to generate a Pareto optimal solution set, providing a set of scientific decision-making schemes for achieving multiple trade-offs in land space planning. Attached Figure Description

[0021] Figure 1 The flowchart of the land spatial planning method that integrates ecological security and urban development of the present invention is presented.

[0022] Figure 2 The architecture diagram of the urban planning cell definition model in the land spatial planning method that integrates ecological security and urban development of the present invention is presented.

[0023] Figure 3 A schematic diagram of the land spatial planning system that integrates ecological security and urban development according to the present invention is shown. Detailed Implementation

[0024] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0025] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0026] like Figure 1 , Figure 2 , Figure 3 As shown: The first aspect of this invention provides a land spatial planning method that integrates ecological security and urban development, comprising: Step S1: Obtain urban development evaluation factors and ecological evaluation factors, construct urban development potential pattern network and ecological security pattern network respectively, and assign development potential value and ecological resistance value.

[0027] In this embodiment, step S1 includes: Step S1-1: The ecological evaluation factor is specifically an indicator that affects ecological security. The ecological evaluation factor is identified based on the minimum cumulative resistance model to obtain ecological source areas, ecological corridors, ecological nodes and ecological resistance values, and to construct an ecological security pattern network. Each grid cell in the ecological security pattern network is assigned an ecological resistance value.

[0028] It should be noted that ecological evaluation factors are determined based on the multi-dimensional ecological protection goals in the national land spatial planning. By setting different ecological protection goals and selecting corresponding ecological evaluation factors, for example, assuming that the ecological protection goal is regional water safety, the selected ecological evaluation factors focus on hydrological processes. In this case, factors such as the protection level of water source, water conservation capacity, soil permeability and distance from river systems can be selected as ecological evaluation factors.

[0029] Understandably, ecological evaluation factors can be obtained through methods such as remote sensing data, environmental monitoring reports, geographic information systems (GIS), or assessments by geographic experts. For example, assuming that ecological evaluation factors include the protection level of water sources, vegetation coverage, importance of biomes, and distance from river systems, the distance from river systems can be calculated based on basic geographic information data; the protection level of water sources can be obtained based on the legal maps of protected areas designated by environmental protection departments; vegetation coverage can be obtained through methods such as calculating NDVI from remote sensing images; and the importance of biomes can be obtained based on the importance ratings of ecosystems such as wetlands and forests.

[0030] Specifically, the first step is to obtain the planning area and ecological planning scale in the national land spatial planning, set a unified ecological evaluation spatial resolution, and discretize the planning area into network units. This provides basic spatial units for the analysis, calculation, and assignment of ecological evaluation factors. The ecological evaluation spatial resolution is determined based on the ecological planning scale, which may include key indicators such as the minimum ecological action unit and the boundary accuracy of the action unit. It is necessary to consider key indicators such as the minimum ecological action unit and the boundary accuracy of the protection target during the planning period. For example, when protecting the water source security of the area, the resolution of the network grid needs to be able to distinguish the spatial details of important streams, small wetlands, and water conservation forests. Too coarse a resolution, such as 1 km × 1 km, will not be able to accurately identify narrow ecological corridors or small ecological nodes, leading to deviations in the ecological security pattern. Therefore, the ecological security pattern network usually needs to set a high spatial resolution, such as 100 m × 100 m, to ensure that details with important ecological functions can be captured.

[0031] Furthermore, ecological evaluation factors are input into the Minimum Cumulative Resistance (MCR) model. The MCR identifies core ecological functional areas, i.e., ecological source areas, and calculates the cumulative resistance that needs to be overcome for the ecological source areas to spread to any point in the planning area. Through this calculation process, ecological corridors, i.e., the path with the least resistance connecting different source areas, and ecological nodes, i.e., key intersections on the ecological corridors, can be identified. Ecological corridors and ecological nodes together constitute important ecological functional areas. At the same time, ecological resistance values ​​are obtained based on the MCR and assigned to each network grid.

[0032] Furthermore, the ecological resistance value quantifies the ecological cost of converting the grid into urban land. When obtaining the ecological resistance value in MCR, it is based on the ecological protection priority of the area. The higher the ecological protection priority of the area, the higher the ecological resistance value obtained. For example, for spatial areas with ecological source areas and important ecological function zones, the ecological cost of urban construction is relatively high, so the ecological protection priority is high, and a high ecological resistance value is obtained and assigned to the corresponding network grid. Conversely, the lower the ecological protection priority of the area, the lower the ecological resistance value obtained. For example, for spatial areas without ecological source areas and important ecological function zones, the ecological cost of urban construction is relatively low, so the ecological protection priority is low, and a low ecological resistance value is obtained and assigned to the corresponding network grid.

[0033] In some possible embodiments, the MCR can select the following standards to obtain the ecological resistance value: for network grids covering important core functional areas, an ecological resistance value of 8-9 is obtained based on the coverage rate; for network grids covering important ecological functional areas, an ecological resistance value of 5-7 is obtained based on the coverage rate; and for network grids not covering core functional areas and important ecological functional areas, an ecological resistance value of 1-4 is obtained based on the specific situation of ecological function degradation. In actual use, users can adapt and change the standards or the parameters in the above standards. Here, the standard for obtaining the ecological resistance value is only explained by example.

[0034] For example, suppose we are developing a land-use planning scheme for City XX. Based on the city's ecological protection goals, we select ecological evaluation factors. If we select factors such as nature reserves, XX wetlands, and important biodiversity conservation areas, and the spatial resolution is set at 100m x 100m based on the ecological planning scale, then, based on MCR (Mean Correlation Rate), we identify the western nature reserve as an ecological source area. We assign an ecological resistance value of 9 to network grids that fully cover the western nature reserve. For network grids that do not fully cover the western nature reserve, we assign ecological resistance values ​​of 8-8.9 based on the calculated coverage. Along... Coastal mangrove wetlands and rivers serve as ecological corridors. Network grids that fully cover coastal mangrove wetlands and rivers are assigned an ecological resistance value of 7. For network grids that do not fully cover coastal mangrove wetlands and rivers, an ecological resistance value of 5-6.9 is assigned based on the calculated coverage rate. The tributary diversion points of the Huamu River are ecological nodes. Network grids that fully cover the tributary diversion points of the Huamu River are assigned an ecological resistance value of 7. For network grids that do not fully cover the tributary diversion points of the Huamu River, an ecological resistance value of 5-6.9 is assigned based on the calculated coverage rate. Other network grids are assigned an ecological resistance value of 1-4.

[0035] Furthermore, based on the above MCR identification results, each network grid is assigned a value according to the ecological resistance value assignment standard, and all network grids and their ecological resistance values ​​together constitute an ecological security pattern network.

[0036] Step S1-2: The urban development evaluation factor is specifically an indicator that affects urban development. The suitability of the urban evaluation factor is assessed, the assessment results and development potential values ​​are obtained, and an urban development potential pattern network is constructed, wherein each grid cell of the urban development potential pattern network is assigned a development potential value.

[0037] It should be noted that the urban development evaluation factors are determined based on the multi-dimensional socio-economic development goals in the territorial spatial planning. By setting different socio-economic development goals and selecting corresponding urban development evaluation factors, for example, assuming that the socio-economic development goal is to optimize industrial layout and transportation efficiency, focusing on location and transportation conditions, factors such as distance from transportation hubs, road network density, existing industrial agglomeration, and suitability of terrain slope can be selected as urban development evaluation factors.

[0038] Understandably, urban development evaluation factors can be obtained through socio-economic statistics, urban planning maps, geographic information systems (GIS), and infrastructure planning maps. For example, road network data comes from official road network data from the transportation department, population density data comes from the latest population census bulletin, land use status is obtained through remote sensing image interpretation, and the location of major planned infrastructure is obtained based on approved special planning maps.

[0039] Specifically, the first step is to obtain the planning space and urban planning scale from the national land spatial planning, set a unified urban development spatial resolution, and discretize the planning area into network units. This provides basic spatial units for the analysis, calculation, and assignment of urban development evaluation factors. The urban development spatial resolution is determined by the urban planning scale, which may include key indicators such as basic planning management units, infrastructure distribution distances, and the degree of economic activity agglomeration. It is necessary to consider these key indicators in the planning area and avoid excessively high resolutions. For example, while a resolution of 10 meters × 10 meters can depict the differences between plots in detail, it will drastically increase the amount of data and computational complexity, and it is not compatible with the area of ​​basic planning management units such as urban blocks and communities. On the other hand, a resolution of 1 kilometer × 1 kilometer cannot reflect the differences in development potential within the city, which includes infrastructure distribution distances and the degree of economic activity agglomeration. For example, it cannot reflect the differences in distance between each block and its nearest subway station. Therefore, the development potential pattern network usually adopts a medium resolution, such as 500 meters × 500 meters, to balance analytical accuracy and computational efficiency.

[0040] Furthermore, a suitability assessment is conducted on the urban development evaluation factors. The suitability assessment can be carried out using methods such as weighted superposition or machine learning classification. This assessment process quantifies the contribution of each urban development evaluation factor to urban development and obtains the suitability of each network grid for urban development, i.e., the development potential value, through the suitability assessment method. The development potential value is then assigned to each network grid.

[0041] Understandably, the development potential value quantifies the expected development benefits of urban construction within a network grid. A higher development potential value indicates a higher priority for urban development suitability in that area. For spatial areas with convenient transportation, concentrated population and economic factors, flat terrain, and compliance with planning guidelines, urban construction yields high development benefits, resulting in a high development potential value, which is then assigned to the corresponding network grid. Conversely, for areas with inconvenient transportation, sparse population, complex terrain, or planning restrictions, urban construction yields low development benefits, resulting in a low development potential value, which is then assigned to the corresponding network grid.

[0042] In some possible embodiments, the MCR can select the following standards to obtain the ecological resistance value: for network grids covering important core functional areas, an ecological resistance value of 8-9 is obtained based on the coverage rate; for network grids covering important ecological functional areas, an ecological resistance value of 5-7 is obtained based on the coverage rate; and for network grids not covering core functional areas and important ecological functional areas, an ecological resistance value of 1-4 is obtained based on the specific situation of ecological function degradation. In actual use, users can adapt and change the standards or the parameters in the above standards. Here, the standard for obtaining the ecological resistance value is only explained by example.

[0043] In some possible embodiments, the following criteria can be used to obtain the development potential value: the development benefits are quantified into specific values ​​using a multi-factor weighted superposition method, and the network grid is divided into four categories based on the specific values ​​of the development benefits: extremely high development benefits, good development benefits, average development benefits, and poor development benefits. For network grids with extremely high development benefits, a development potential value of 0.8-1.0 is obtained based on the specific values ​​of the development conditions; for network grids with good development benefits, a development potential value of 0.5-0.7 is obtained based on the specific values ​​of the development conditions; and for network grids with average or poor development benefits, a development potential value of 0.1-0.4 is obtained based on the specific values ​​of the development conditions.

[0044] For example, suppose we are developing a land use planning scheme for City XX. Based on the city's economic development goals and spatial planning scale, the selected urban development factors include distance from highway exits, distance from the city's commercial center, current land use, and terrain slope. The spatial resolution is set to 100 meters × 100 meters, consistent with the ecological network. Based on suitability evaluation, the network grids around the city center commercial area and major transportation hubs are assigned a development potential value of 0.9-1.0 due to their excellent location and transportation conditions. The grids in the suburbs of the city, with flat terrain and a certain level of development, are assigned a development potential value of 0.6-0.8. The grids inside the western ecological protection zone with steep slopes are assigned a development potential value of 0.1-0.3.

[0045] Furthermore, based on the above suitability evaluation results, each network grid is assigned a value according to the development potential value assignment standard, and all network grids and their development potential values ​​together constitute the urban development potential pattern network.

[0046] Step S2: Based on the urban development potential pattern network and the ecological security pattern network, obtain the ecological-development conflict intensity network and obtain the resampled development potential value and resampled ecological resistance value. Based on the ecological-development conflict intensity network, obtain the ecological-development conflict intensity index. Generate a spatial distribution map of high-intensity conflict areas through a fusion clustering strategy.

[0047] In this embodiment, step S2 includes: Step S21: Set planning network standards. Each grid in the urban development potential pattern network and the ecological security pattern network is adaptively aligned according to the set planning network standards. Based on the aligned urban development potential pattern network and ecological security pattern network, data is resampled and normalized to obtain resampled ecological resistance values ​​and resampled development potential values.

[0048] Understandably, in the preceding steps, ecological resistance and development potential values ​​were obtained based on the inherent scale patterns of different evaluation systems to ensure the scientific validity of the source data. For example, assuming the ecological protection goal is regional water safety, the spatial resolution of the ecological evaluation can be set to 100m × 100m to distinguish the spatial details of streams, small wetlands, and water conservation forests. If a stream that is important to the downstream ecological environment is only 100-200m wide, and the urban development spatial resolution set for urban construction and management, such as 500m × 500m, is directly used as the spatial resolution of the ecological evaluation, the spatial details and connectivity of such ecological evaluation factors will be blurred or even ignored, leading to deviations in the ecological security pattern network. Therefore, only by running the minimum cumulative resistance model under the premise of appropriate ecological evaluation spatial resolution can ecological resistance values ​​that are both professional and accurate be obtained. In this step, we created comparison conditions for ecological resistance and development potential values ​​by setting planning network standards, ensuring that a unified coordinate system, resolution, and data resampling are carried out while maintaining the professionalism and accuracy of the original data to the greatest extent.

[0049] Specifically, planning network standards can include key indicators in terms of data scale such as planning coordinate system and planning spatial resolution. First, the data of the urban development potential pattern network and the ecological security pattern network are unified under the planning coordinate system to ensure that the edges of the map patches representing the planning area in the two networks are completely aligned. The planning coordinate system can use a coordinate system commonly used in planning and design, such as the CGCS2000 National Geodetic Coordinate System, to ensure consistent spatial location benchmarks and eliminate distortion errors caused by map projection. Then, the network grids of the two networks are redefined based on the planning spatial resolution. The planning spatial resolution is determined based on the planning spatial scale in the national land spatial planning. The planning spatial scale can include the planning area and planning content. For example, when we need to carry out small community planning in XX City, the planning spatial resolution can be based on the area of ​​the small community in XX City, and a higher planning spatial resolution, such as 100 meters × 100 meters, can be set. The process of adaptively aligning the two networks based on the planning network standards eliminates the differences between the two networks in terms of data scale such as coordinate system and resolution.

[0050] Furthermore, by adapting and aligning the urban development potential pattern network and the ecological security pattern network, the location and quantity requirements for data resampling are determined. For example, for the small community planning of XX City, the location of the resampled data is first aligned with its planning coordinate system, namely the CGCS2000 National Geodetic Coordinate System. The number of network grids defined based on the planning spatial resolution of 100m × 100m is used as the quantity requirement for data resampling. The ecological resistance value and development potential value are normalized. For example, the ecological resistance value range of the original ecological security pattern network of XX City is 0-10. A unified value range standard of 0-1 is set. The ecological resistance value range can be mapped to 0-1 through linear normalization. Then, according to the location and quantity requirements of data resampling, resampled ecological resistance values ​​and resampled development potential values ​​are obtained through resampling methods such as bilinear interpolation. For example, using bilinear interpolation as an example, in the small community planning of XX City, the urban development spatial resolution is 500m × 500m. Assuming a 500m × 500m network grid... Its development potential value The value is 0.8, which is achieved when aligning and resampling according to the planned network standard. It is subdivided into 25 grids of 100 meters by 5 grids each, and one of these grids is used as a reference. For example, The center point falls on Internally, it can be based on The center point is at The internal relative positions are weighted averaged to obtain Resampling development potential value ,like The center point is very close If the center is , then its interpolation result is... Very close 0.8, It could be 0.79, or vice versa. The center point is located at The edge of the interpolation will be affected by the edge of the intersection. The influence of adjacent 500m x 500m grid cells creates a smooth transition. It might be 0.72. Through the interpolation process, the originally single... 0.8 is transformed into a set of resampled development potential values ​​corresponding to the planning spatial resolution. This set of resampled development potential values ​​exhibits a smooth gradient change in space, which is more refined than a single development potential value.

[0051] Understandably, by resampling the data of the adaptively aligned urban development potential pattern network and ecological security pattern network using bilinear interpolation and other resampling methods, it can be ensured that each network grid has a corresponding resampled ecological resistance value and a resampled development potential value, and that the two values ​​are comparable.

[0052] Step S22: Assign the resampled ecological resistance value and the resampled development potential value to each grid cell in the aligned urban development potential pattern network and ecological security pattern network, and overlay the aligned urban development potential pattern network and ecological security pattern network to obtain the ecological-development conflict intensity network.

[0053] Understandably, the resulting ecological-development conflict intensity network, formed by overlaying, records the potential conflict level between ecology and development in network grids. A combination of high-resampled development potential values ​​and high-resampled ecological resistance values ​​represents a high-conflict combination, while a combination of low-resampled development potential values ​​and high-resampled ecological resistance values, or vice versa, represents a low-conflict combination. For example, in network grids... Because it is suitable for developing values ​​with high resampling potential. 0.79, and due to its location within a mangrove reserve, it has a high ecological resistance value for resampling. If the value is 0.9, then the network grid conflict is strong, and the ecological-development conflict intensity network is stored in the form of a grid matrix.

[0054] Step S23: Import the resampled ecological resistance value and the resampled development potential value into the two-order conflict model to obtain the ecological-development conflict intensity index.

[0055] Specifically, step S23 also includes the following steps: Step S23-1: Obtain the local conflict index for each network grid, wherein the local conflict index is the product of the resampled ecological resistance value and the resampled development potential value of each network grid.

[0056] Understandably, the local conflict index quantifies the inherent conflict level of the network grid, and the larger the product, the more acute the contradiction between ecological protection and urban development.

[0057] Specifically, the local conflict index is calculated based on resampled development potential values ​​and resampled ecological resistance values, expressed by the following formula: ,in Represents a network grid Local conflict index Represents a network grid The potential value of resampling development, Represents a network grid Resampling ecological resistance values, for example, a network grid in XX city. Corresponding resampling ecological resistance value The value is 0.8, representing the resampling development potential value. If the value is 0.79, then the local conflict index is... It is 0.632.

[0058] Step S23-2: Set the conflict radius and select each network grid cell as a selected grid cell. The conflict radius is represented as the radius of a circle centered on the selected grid cell.

[0059] Understandably, the conflict radius defines the spatial range of the conflict level of a network grid. The size of the conflict radius is determined by the planning spatial scale. For example, for the detailed community spatial planning of XX city, we can set the conflict radius to the radiation range of a medium-sized community, which can be 500 meters.

[0060] Step S23-3: Obtain the associated grid based on the conflict radius and the ecological-development conflict intensity index, and obtain the spatial associated conflict index one by one according to the local conflict index.

[0061] Furthermore, step S23-3 also includes the following steps: Step S23-3-1: Obtain candidate grids based on the conflict radius. The candidate grids are all network grids touched by the conflict radius excluding the selected grid, with the selected grid as the center.

[0062] Understandably, candidate graticles define all network graticles whose inherent conflict levels will affect the selected graticle's ecological-development conflict intensity index.

[0063] In some possible embodiments, it is assumed that in the community spatial planning of XX city, for a selected grid, its 500-meter conflict radius covers a total of 20 other grids. These 20 grids are the candidate grids of the selected grid, and their local conflict index will have a certain impact on the ecological-development conflict intensity index of the selected grid.

[0064] Step S23-3-2: Calculate the mean of the local conflict index of the candidate grid as the local conflict intensity threshold.

[0065] Understandably, the process of calculating the mean of the ecological-development conflict intensity index of candidate rasters represents an adaptive and relativistic method for identifying local conflict intensity benchmarks. This method can truly reflect the relative conflict levels of different regions and avoid the problem of local-to-overall inconsistency caused by fixed thresholds. For example, if a fixed conflict intensity threshold of 0.7 is set for the planning area, then in areas where the conflict intensity is generally low, some candidate rasters that should be valued within the conflict radius may be ignored because they do not reach the excessively high fixed conflict intensity threshold of 0.7.

[0066] Step S23-3-3: Select candidate rasters whose local conflict index is greater than or equal to the local conflict intensity threshold as associated rasters.

[0067] In some possible embodiments, it is assumed that in the community spatial planning of XX city, for a selected grid of 20 candidate grids, the local conflict intensity threshold is 0.4, and 8 candidate grids have a local conflict index greater than or equal to 0.4. These 8 candidate grids are the associated grids.

[0068] Step S23-3-4: Obtain the Euclidean distance based on the associated grid and the selected grid, and obtain the attenuation base number based on the Euclidean distance, wherein the attenuation base number is set to the sum of 1 and the square of the Euclidean distance.

[0069] It should be noted that Euclidean distance is a spatial metric that conforms to the first law of geography. This step uses Euclidean distance as the metric for spatial attenuation, which ensures that the attenuation base reasonably characterizes the influence of the local conflict index of the associated rasters on the selected rasters. The Euclidean distance between the associated rasters and the selected rasters is calculated based on the geometric center point of the network rasters.

[0070] Step S23-3-5: Obtain the influence value one by one according to the local conflict index and attenuation base of the associated grid, and calculate the spatial association conflict index based on the influence value.

[0071] Specifically, for each associated raster, its local conflict index is divided by its corresponding attenuation base to obtain the influence value of the associated raster on the selected raster. Then, the influence values ​​of all associated rasteres are summed to obtain the spatial conflict index of the selected raster. ,in Indicates the selection of a grid. Spatial association conflict index, Indicates the selection of a grid. Associated Grid The Euclidean distance between them Indicates the conflict radius. Represents associated raster Local conflict index Represents associated raster The attenuation base.

[0072] It should be noted that the impact value Characterizes the associated raster The effect varies with the selected raster. The first law of geography, which states that the Euclidean distance between two points decreases as the distance increases, is applied to the spatial correlation conflict index formula. The technical principle of this formula lies in simulating the field strength attenuation and multi-source superposition effect of spatial correlation conflicts. Through this simulation, regional conflict zones with high potential conflict risks and contiguous distribution can be identified more accurately. For example, a network grid with a low local conflict index can be identified as having a high ecological-development conflict intensity index if it is surrounded by multiple correlated grids with high local conflict indices. This provides a forward-looking spatial location insight method for conflict control in national land spatial planning.

[0073] Step S24: Based on the ecological-development conflict intensity network, perform spatial clustering analysis on the ecological-development conflict intensity index to obtain high-conflict raster clusters. Based on morphological filtering and a preset minimum patch area threshold, filter the high-conflict raster clusters to generate the spatial distribution map of the high-intensity conflict area.

[0074] Specifically, spatial clustering analysis of the eco-development conflict intensity index can be performed. Density clustering algorithms can be used to identify spatially dense data clusters. Based on these clusters, corresponding network grids can be identified as high-conflict grid groups. Morphological filtering, such as opening operations, can then be applied to smooth the boundaries of the identified high-conflict grid groups to eliminate jagged edges and make them more consistent with the morphology of actual geographic units. At the same time, high-conflict grid groups can be screened based on a preset minimum patch area threshold to remove scattered patches that are too small or lack practical significance. For example, the minimum patch area threshold can be calculated based on the minimum ecological function unit to ensure that the selected and retained conflict patches have basic ecological regulation functions.

[0075] In some possible implementations, assuming a land space planning scheme is being developed for XX City, the smallest ecological function unit in XX City has been identified as the A River ecological corridor, with a minimum width of 300 meters. Therefore, the minimum patch area threshold can be set to the area matching the minimum width of this ecological corridor, i.e., 300 meters × 300 meters, or 9 hectares. This means that any conflict patch with an area less than 9 hectares is considered to lack basic ecological regulation function.

[0076] Understandably, the minimum area threshold for a map patch is determined based on the planning spatial scale in the national land spatial planning. For example, for the detailed community spatial planning of XX city, we can set the minimum area threshold for a map patch to the size of a medium-sized community, which could be 15 hectares.

[0077] In summary, step S2 integrates the ecological assessment network and the urban development assessment network, spatializing and visualizing the contradiction between ecological protection and urban development, and providing decision-making references for territorial spatial planning schemes.

[0078] Step S3: Construct a town planning cell definition model, which includes a comprehensive transformation probability.

[0079] Understandably, the urban planning cell definition model simulates the overall process of urban expansion, dynamically integrating ecological security pattern constraint data such as the ecological-development conflict intensity index and resampled development potential value into the urban planning cell definition model. This transforms macro-level ecological security pattern constraints into micro-level land use conversion rules. This cell model, which dynamically incorporates ecological security pattern constraint data, differs from the static constraint cell model set by socio-economic development goals. It transforms cell conversion from blind growth to guided growth that can automatically identify and avoid conversion of high-conflict grids.

[0080] In this embodiment, step S3 includes: Step S31: Obtain the current land use status of each grid cell in the ecological-development conflict intensity network, wherein the current land use status includes urban land and non-urban land.

[0081] Understandably, land use status data for each network grid can be obtained through remote sensing data interpretation, and the land use status can be simplified into two categories based on land use type: urban land and non-urban land. For example, based on the land use data of XX City in 2020, land use data can be obtained through supervised classification results of remote sensing images. The supervised classification standard can be that within a 100m × 100m network grid, if more than 20% of the area is identified as industrial land or residential land, the network grid is marked as urban land; otherwise, it is marked as non-urban land.

[0082] Step S32: Define each network grid in the ecological-development conflict intensity network as a cell, and define the current land use status corresponding to each network grid as the cell state and use the Moore neighborhood algorithm to define the cell neighborhood.

[0083] Understandably, the current land use status is used as the initial state of the cells, and Moore's neighborhood is used to define the local spatial environment. Through these processes, the geographic space is mapped into the computational model. For example, taking XX city as an example, each 100m × 100m grid in its ecological-development conflict intensity network is defined as a cell. The initial state of this cell is directly defined by the land use status of its corresponding grid cell as urban or non-urban land. The neighborhood of the cell is defined using Moore's neighborhood, that is, the 3×3 grid cell centered on the selected cell is its cell neighborhood. There are a total of the selected cell and 8 neighboring cells in the neighborhood. During the simulation, whether a cell whose current state is non-urban land will be converted to urban land will be affected by the number of its 8 neighboring cells that are already in the urban land state.

[0084] Step S33: Obtain the neighborhood influence probability based on the cell neighborhood and cell state, obtain the adaptation probability based on the resampled development potential value, obtain the conflict constraint probability based on the ecology-development conflict intensity index, and combine the neighborhood influence probability, adaptation probability and conflict constraint probability with the undetermined conversion probability weight parameter to obtain the comprehensive conversion probability.

[0085] Specifically, the overall conversion probability Represented as ; in, The probability of influence from the neighborhood. For the fitness probability, Conflict constraint probability, The transition probability weight parameters are to be determined.

[0086] It should be noted that by weighting and synthesizing the three key indicators that reflect the inherent laws and external constraints of urban expansion—neighborhood influence probability, adaptive probability, and conflict constraint probability—into a comprehensive probability, the drawbacks of fixed rules and subjective weights in traditional cellular automata models are avoided. This multi-source fusion process characterizes the fact that urban expansion is the result of the combined action of multiple driving forces, and the relative importance of each driving force should change dynamically with the planning objectives.

[0087] Specifically, step S33 also includes the following steps: Step S33-1: Calculate the total number of cells in the cell's neighborhood and the number of cells in the town's neighborhood. The total number of cells is the total number of cells in the cell's neighborhood, and the number of cells in the town's neighborhood is the number of cells in the total number of cells whose state is town land. Calculate the ratio of the number of cells in the town's neighborhood to the total number of cells and use it as the neighborhood influence probability.

[0088] Understandably, by calculating the proportion of urban neighborhood cells in the total number of cells in a single cell, the agglomeration effect in urban development can be simulated, which characterizes the inherent inertia of urban planning. For example, an open space surrounded by built-up areas is far more likely to be developed than an open space isolated in the wilderness.

[0089] Step S33-2: Retrieve the resampling development potential value of the network grid corresponding to the cell, normalize the resampling development potential value and use it as the fitness probability.

[0090] Understandably, the development potential value of the network grid corresponding to a single cell is normalized and directly used as the adaptive probability. This process characterizes the attractiveness of the land parcel's own attributes to urban planning. The land parcel's own attributes may include indicators that are conducive to achieving socio-economic development goals, such as topography and transportation conditions. For example, a flat piece of land that is close to a highway has a high development potential value and a correspondingly high adaptive probability. Calculating the adaptive probability ensures that the simulation process of urban expansion conforms to the laws of land adaptability.

[0091] Step S33-3: Retrieve the ecological-development conflict intensity index of the network grid corresponding to the cell, and input the ecological-development conflict intensity index into the preset constraint function to obtain the conflict constraint probability. The preset constraint function ensures that the conflict constraint probability is negatively correlated with the ecological-development conflict intensity index.

[0092] Specifically, a linear decay function or similar function can be used as a preset constraint function to transform the ecological-development conflict intensity index into a constraint factor with a value range of 0-1 that can be directly used in probability calculation, namely the conflict constraint probability.

[0093] It needs to be explained that the negative correlation between the conflict constraint probability and the ecological-development conflict intensity index represents a dynamic spatial control rule based on two dimensions of ecological protection goals and socio-economic development goals in the simulation process of urban expansion. For example, for conflict hotspots with high ecological importance and high development value, i.e. cells with high conflict indices, the system will calculate and output a low conflict constraint probability through a preset constraint function, thereby reducing the possibility of the cell being converted.

[0094] Step S4: Set up a planning requirement group, construct a multi-objective optimization problem based on the planning requirement group and the comprehensive transformation probability, solve the multi-objective optimization problem based on the swarm intelligence multi-objective optimization algorithm, and obtain the development ecological planning set.

[0095] It should be noted that the planning requirements set is the core set of input parameters for constructing a multi-objective optimization problem. The planning requirements set defines the core objectives and constraints for the planning period. The core objectives include the development objective function and the ecological objective function, and the constraints are as follows.

[0096] Specifically, step S4 also includes the following steps: Step S41: Set the planned area, which represents the total number of grid cells for newly added urban land during the planning period, and set a high conflict conversion penalty coefficient based on the spatial distribution map of the high-intensity conflict area.

[0097] Specifically, the spatial distribution map of high-intensity conflict areas is overlaid and aligned with the network grid of the urban planning cell definition model, and a high-conflict cell judgment is made. The high-conflict cell judgment is specifically as follows: if the network grid corresponding to the selected cell is located within the range defined by the spatial distribution map of high-intensity conflict areas, the selected cell is marked as a high-conflict cell; otherwise, it is marked as an ordinary cell. Differentiated penalty rules are defined based on the high-conflict cell judgment.

[0098] Specifically, the penalty rule is as follows: if the selected cell is a normal cell, the loss of ecosystem service value resulting from the transformation of the selected cell is the resampled ecosystem resistance value corresponding to the selected cell; if the selected cell is a high-conflict cell, the loss of ecosystem service value resulting from the transformation of the selected cell is the resampled ecosystem resistance value corresponding to the selected cell multiplied by the high-conflict transformation penalty coefficient. The high-conflict transformation penalty coefficient must be significantly greater than 1 to ensure that the loss of ecosystem service value from cell transformation in high-conflict regions has a decisive impact on the ecological objective function of the swarm intelligence multi-objective optimization algorithm, thereby effectively guiding the search direction. The high-conflict transformation penalty coefficient is usually taken in the range of 1.5-3.0. Loss of ecosystem service value resulting from conversion to urban land The calculation formula is , For cells The corresponding resampling ecological resistance value, The set of cells identified as high-conflict cells. The penalty coefficient for high conflict conversion.

[0099] It should be noted that the specific value of the high conflict conversion penalty coefficient can be set based on the urgency and strictness of ecological protection in the land spatial planning. For example, in arid areas, based on the importance attached to water source ecology, the high conflict conversion penalty coefficient can be set to 2.5 to reflect strict ecological pattern constraints, while in areas with better ecological background, the high conflict conversion penalty coefficient can be set to 1.5 to achieve a more moderate regulation.

[0100] Understandably, by imposing a multiplier penalty on the transformation of high-conflict areas at the objective function level, the loss of ecological service value due to urban development in high-conflict areas is increased. This guides the swarm intelligence multi-objective optimization algorithm to actively avoid cell transformation in high-intensity conflict areas during the solution process, thereby achieving rigid constraints on the ecological security pattern through this guidance process.

[0101] Step S42: Set development goals and ecological goals, wherein the development goals are to maximize the total efficiency of urban development at the end of the planning period, and the ecological goals are to minimize the total loss of ecosystem service value caused by urban expansion during the planning period.

[0102] Specifically, the total efficiency of urban development is the sum of the resampled development potential values ​​of the network grids corresponding to all transformed cells at the end of the planning period, and the total loss of ecosystem service value is the sum of the ecosystem service value losses corresponding to all transformed cells at the end of the planning period. It can be understood that the development potential value represents the objective suitability of the area corresponding to the network grid to be transformed from non-urban land to urban land, while the loss of ecosystem service value represents the loss to the ecological environment caused by the transformation of the area corresponding to the network grid from non-urban land to urban land.

[0103] Step S43: Obtain constraints based on the planned area and the high conflict conversion penalty coefficient; obtain development objective function and ecological objective function based on development goal and ecological goal respectively; and use the undetermined conversion probability weight parameter in the comprehensive conversion probability as decision variable.

[0104] Specifically, the planned area is used as a hard constraint, meaning that during the cellular automata simulation, the total number of network grids corresponding to urban land use at the end of the planning period must not exceed the preset planned area. Simultaneously, a high-conflict conversion penalty coefficient is used as a penalty term constraint. Through the penalty rules defined in step S41, the suppression of high-conflict area conversion behavior is reflected in the calculation of the ecological objective function. Here, the development objective function is assumed to be... The ecological objective function is assumed to be: This will be used as an explanation.

[0105] It should be noted that the development objective function aims to maximize the overall efficiency of urban development at the end of the planning period. To develop the objective function value, This is the set of cells representing all land converted from non-urban to urban use during the planning period. For cells The resampled development potential value of the corresponding network grid is the sum of the development potential values ​​of all newly added urban land cells. The higher the value, the greater the development efficiency of the planning scheme. The ecological objective function aims to minimize the total loss of ecosystem service value caused by urban expansion during the planning period. The value of the ecological objective function. For cells The loss of ecosystem service value resulting from conversion to urban land use.

[0106] Step S44: Construct the multi-objective optimization problem based on constraints, development objective function, ecological objective function, and decision variables.

[0107] Understandably, the core requirement of multi-objective optimization problems is to find the optimal transition probability weight parameters. These parameters need to simultaneously satisfy two objectives: maximizing the overall efficiency of urban development and minimizing the total loss of ecosystem service value. However, these two objectives are conflicting, and it is impossible to achieve the optimal values ​​of both objectives through a single solution. Therefore, the solution to a multi-objective optimization problem is not a unique optimal solution, but rather a set of N optimal trade-off solutions that achieve different balance points between the two objectives, i.e., the Pareto optimal solution set. The process of solving multi-objective optimization problems needs to comply with hard constraints and penalty terms.

[0108] Step S45: Obtain multiple sets of decision variables based on the swarm intelligence multi-objective optimization algorithm, and use the decision variables to drive the urban planning cell definition model to perform a complete urban expansion simulation. After the simulation, obtain the development objective function value and ecological objective function value corresponding to the multiple sets of decision variables.

[0109] Specifically, a suitable swarm intelligence multi-objective optimization algorithm, such as the non-dominated sorting genetic algorithm NSGA-II, is selected to initialize the algorithm parameters, including setting the population size and the maximum number of iterations. Each individual in the population represents a set of possible transition probability weight parameters.

[0110] Furthermore, the swarm intelligence multi-objective optimization algorithm enters an iterative loop, generating a set of transition probability weight parameters in each iteration. This combination is then substituted into the urban planning cell definition model, driving the model to perform a complete dynamic simulation of urban expansion from the planning base period to the end of the planning period. After the simulation, the development objective function value and the ecological objective function value are calculated based on the generated urban spatial layout results. Based on each set of transition probability weight parameters and the corresponding development objective function value and ecological objective function value, the swarm intelligence multi-objective optimization algorithm uses its specific evolutionary mechanisms, such as selection, crossover, and mutation, to generate a new population. This process is repeated until the preset number of iterations or convergence conditions are reached.

[0111] Furthermore, a Pareto optimal solution set consisting of non-dominated solutions is output through a swarm intelligence multi-objective optimization algorithm. Each solution in the Pareto optimal solution set corresponds to a set of transformation probability weight parameters, as well as a set of development objective function values ​​and ecological objective function values ​​obtained by simulation calculation through the urban planning cell definition model under these transformation probability weight parameters.

[0112] Step S46: Define a development ecological planning set based on the results of the urban expansion simulation.

[0113] It should be noted that the result of the town expansion simulation is the Pareto optimal solution set obtained in step S45.

[0114] Specifically, in the urban planning cell definition model, the urban spatial layout simulation map corresponding to each solution in the Pareto optimal solution set is retrieved. The urban spatial layout simulation map contains the network grid data of a complete urban expansion of the urban planning cell definition model, reflecting the network grid corresponding to all the transformed cells.

[0115] The development ecological planning set refers to a collection of multiple development ecological planning schemes that achieve different trade-offs between development goals and ecological goals. Each development ecological planning scheme includes a set of conversion probability weight parameters, a corresponding urban spatial layout simulation map, development goal function values, and ecological goal function values.

[0116] Step S5: Configure an ecological development land space report for the development ecological planning set based on the spatial distribution map of high-intensity conflict areas.

[0117] Specifically, each urban spatial layout simulation map is spatially overlaid with a high-intensity conflict area spatial distribution map for analysis. This assesses the specific occupation of ecological space by urban expansion under different development ecological planning schemes, and generates an ecological impact assessment report for each development ecological planning scheme accordingly.

[0118] Specifically, in a Geographic Information System (GIS), a network raster overlay analysis can be performed on the urban spatial layout simulation map corresponding to each development ecological planning scheme and the distribution map of high-intensity conflict areas. That is, for each overlay result, key quantitative indicators are calculated, such as the area and proportion of conflict zones and the impact of key ecological units. Based on the key quantitative indicators, an ecological impact assessment description is generated for each development ecological planning scheme. The ecological impact assessment description may include an overall impact summary, a list of key data, and management recommendations.

[0119] In some possible implementations, assuming a land use planning scheme is being developed for City XX, a development ecological planning scheme is generated. Network grid overlay analysis of this scheme reveals that 180 hectares of newly added urban land are located within a high-intensity conflict zone, accounting for 8% of the total area of ​​all high-intensity conflict zones. This includes encroaching on approximately 5 kilometers of a river's ecological corridor and occupying two important biological migration and resting ecological nodes. The resulting ecological impact assessment indicates that this scheme has a significant impact on the ecological security pattern. Although it meets the goal of high development efficiency, it results in a large-scale disruption of the core ecological corridor, potentially affecting the biodiversity of the watershed. It is recommended that subsequent planning strictly avoid the remaining ecological corridor and that compensation facilities such as ecological bridges be planned and constructed near the occupied areas.

[0120] A second aspect of this invention provides a land spatial planning system that integrates ecological security and urban development, comprising: The data acquisition and processing module is used to acquire urban development evaluation factors and ecological evaluation factors, construct urban development potential pattern network and ecological security pattern network respectively, and assign development potential value and ecological resistance value. The conflict identification and spatial analysis module is used to obtain the ecological-development conflict intensity network, obtain the resampled development potential value and resampled ecological resistance value based on the ecological-development conflict intensity network, and obtain the ecological-development conflict intensity index. It also generates a spatial distribution map of high-intensity conflict areas through a fusion clustering strategy. Urban planning cell definition model module, which is used to construct urban planning cell definition model; A multi-objective optimization module is used to construct and solve a multi-objective optimization problem based on a set of planning requirements and a comprehensive transformation probability, thereby obtaining a development ecological planning set. The report generation module is used to configure ecological development land space reports for the development ecological planning set based on the spatial distribution map of high-intensity conflict areas.

[0121] The specific usage and function of this invention are described below: This application embodiment obtains urban development evaluation factors and ecological evaluation factors, constructs urban development potential pattern networks and ecological security pattern networks respectively, and assigns development potential values ​​and ecological resistance values. Then, based on the urban development potential pattern network and ecological security pattern network, it obtains an ecological-development conflict intensity network and obtains comparable resampled development potential values ​​and resampled ecological resistance values. On this basis, it introduces a two-order conflict model to calculate the ecological-development conflict intensity index, and generates a spatial distribution map of high-intensity conflict areas through a fusion clustering strategy. The above steps first ensure a scientific and reasonable quantitative basis in both the dimensions of ecological protection and urban development by constructing urban development potential pattern networks and ecological security pattern networks respectively. Then, it resamples based on the ecological-development conflict intensity network and introduces a two-order conflict model to calculate the ecological-development conflict intensity index, realizing dynamic and refined identification of the conflict relationship between ecological security and urban development, and significantly improving the accuracy and spatial representativeness of the conflict index calculation.

[0122] On the other hand, by defining the probability of neighborhood influence, the probability of adaptability, the probability of conflict constraints, and the probability of comprehensive transformation, and constructing a cellular definition model for urban planning based on these, a set of planning requirements including area and high conflict transformation penalty coefficients is set. A multi-objective optimization problem is constructed by combining the comprehensive transformation probability, and a swarm intelligence multi-objective optimization algorithm is used to solve it. Ultimately, a set of development-ecological planning schemes that achieve different trade-offs between development and ecological goals is obtained. Based on the spatial distribution map of high-intensity conflict areas, an ecological development land space report is configured for the development-ecological planning set. These steps first construct a cellular definition model for urban planning by introducing multi-source probability parameters, effectively simulating the inherent laws and external constraints of urban expansion. Then, a differentiated high-conflict transformation penalty mechanism is integrated into the constraint conditions, breaking through the limitations of traditional rigid constraints and achieving dynamic and flexible control of ecological protection efforts. Finally, a swarm intelligence multi-objective optimization algorithm is used to generate a Pareto optimal solution set, providing a set of scientific decision-making schemes for achieving multiple trade-offs in land space planning.

[0123] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A land-use planning method that integrates ecological security and urban development, characterized in that: The method includes: Obtain urban development evaluation factors and ecological evaluation factors, construct urban development potential pattern network and ecological security pattern network respectively, and assign development potential value and ecological resistance value; Based on the urban development potential pattern network and the ecological security pattern network, an ecological-development conflict intensity network is obtained, and resampled development potential values ​​and resampled ecological resistance values ​​are obtained. Based on the ecological-development conflict intensity network, an ecological-development conflict intensity index is obtained. A spatial distribution map of high-intensity conflict areas is generated through a fusion clustering strategy. Construct a cell definition model for urban planning, which includes comprehensive transformation probabilities; A set of planning requirements is defined, and a multi-objective optimization problem is constructed based on the planning requirements set and the comprehensive transformation probability. The multi-objective optimization problem is solved based on the swarm intelligence multi-objective optimization algorithm to obtain the development ecological planning set. Based on the spatial distribution map of high-intensity conflict areas, an ecological development land space report is configured for the development of ecological planning.

2. The land spatial planning method integrating ecological security and urban development according to claim 1, characterized in that, Based on the urban development potential pattern network and the ecological security pattern network, an ecological-development conflict intensity network is obtained, along with resampled development potential values ​​and resampled ecological resistance values. An ecological-development conflict intensity index is then derived from this network. Finally, a spatial distribution map of high-intensity conflict areas is generated using a fusion clustering strategy, including: A planning network standard is set, and each grid in the urban development potential pattern network and the ecological security pattern network is adaptively aligned according to the set planning network standard. Based on the aligned urban development potential pattern network and ecological security pattern network, data is resampled to obtain resampled ecological resistance value and resampled development potential value. The resampled ecological resistance value and the resampled development potential value are assigned to each grid cell in the aligned urban development potential pattern network and ecological security pattern network, and the aligned urban development potential pattern network and ecological security pattern network are superimposed to obtain the ecological-development conflict intensity network. The resampled ecological resistance value and the resampled development potential value are imported into the two-order conflict model to obtain the ecological-development conflict intensity index. Based on the aforementioned ecological-development conflict intensity network, spatial clustering analysis is performed on the ecological-development conflict intensity index to obtain high-conflict raster clusters. The high-conflict raster clusters are then filtered based on morphological filtering and a preset minimum patch area threshold to generate a spatial distribution map of the high-intensity conflict area.

3. The land spatial planning method integrating ecological security and urban development according to claim 1, characterized in that, The resampled ecological resistance values ​​and resampled development potential values ​​are imported into a two-order conflict model to obtain an ecological-development conflict intensity index, including: Obtain the local conflict index for each network grid, which is the product of the resampled ecological resistance value and the resampled development potential value for each network grid; Set the conflict radius and select each network grid cell as a selected grid cell. The conflict radius is represented as the radius of a circle centered on the selected grid cell. The associated grid is obtained based on the conflict radius and the ecological-development conflict intensity index, and the spatially associated conflict index is obtained one by one according to the local conflict index.

4. The land spatial planning method integrating ecological security and urban development according to claim 1, characterized in that, The associated grid is obtained based on the conflict radius and the ecology-development conflict intensity index, and the spatially associated conflict index is obtained one by one according to the local conflict index, including: Candidate graticets are obtained based on the conflict radius, where the candidate graticet is defined as all network graticets whose conflict radius reaches the selected graticet and other graticets excluding the selected graticet. The mean of the local conflict index of the candidate raster is calculated as the local conflict intensity threshold. Select candidate rasters whose local conflict index is greater than or equal to the local conflict intensity threshold as associated rasters; The Euclidean distance is obtained based on the associated grid and the selected grid, and the attenuation base is obtained based on the Euclidean distance, wherein the attenuation base is set to the sum of 1 and the square of the Euclidean distance; The influence value is obtained one by one based on the local conflict index and attenuation base of the associated raster, and the spatial association conflict index is calculated based on the influence value.

5. The land spatial planning method integrating ecological security and urban development according to claim 1, characterized in that, A cell definition model for urban planning is constructed, which includes comprehensive transformation probabilities, including: Obtain the land use status of each grid cell in the ecological-development conflict intensity network, wherein the land use status includes urban land and non-urban land; In the ecological-development conflict intensity network, each network grid is defined as a cell, and the land use status corresponding to each network grid is taken as the cell state and the cell neighborhood is defined using the Moore neighborhood algorithm. The neighborhood influence probability is obtained based on the cell neighborhood and cell state, the adaptation probability is obtained based on the resampled development potential value, and the conflict constraint probability is obtained based on the ecology-development conflict intensity index. The neighborhood influence probability, adaptation probability, and conflict constraint probability are combined with the undetermined conversion probability weight parameter to obtain the comprehensive conversion probability.

6. The land spatial planning method integrating ecological security and urban development according to claim 1, characterized in that, The probability of neighborhood influence is obtained based on cell neighborhood and cell state; the probability of adaptation is obtained based on resampled development potential value; and the probability of conflict constraint is obtained based on ecology-development conflict intensity index, including: The total number of cells in a cell's neighborhood and the number of cells in a town's neighborhood are counted. The total number of cells in a cell's neighborhood is the total number of cells in a cell's neighborhood, and the number of cells in a town's neighborhood is the number of cells in the total number of cells whose state is town land. The ratio of the number of cells in a town's neighborhood to the total number of cells is calculated and used as the neighborhood influence probability. Retrieve the resampling development potential value of the network raster corresponding to the cell, normalize the resampling development potential value and use it as the fitness probability; The ecological-development conflict intensity index of the network grid corresponding to the cell is retrieved, and the ecological-development conflict intensity index is input into a preset constraint function to obtain the conflict constraint probability. The preset constraint function ensures that the conflict constraint probability is negatively correlated with the ecological-development conflict intensity index.

7. The land spatial planning method integrating ecological security and urban development according to claim 1, characterized in that, Define a set of planning requirements, and construct a multi-objective optimization problem based on the set of planning requirements and the comprehensive transformation probability, including: The planned area is set, which represents the total number of grid cells for newly added urban land during the planning period, and a high conflict conversion penalty coefficient is set based on the spatial distribution map of the high-intensity conflict area. Set development goals and ecological goals, wherein the development goals are to maximize the total efficiency of urban development at the end of the planning period, and the ecological goals are to minimize the total loss of ecosystem service value caused by urban expansion during the planning period; Constraints are obtained based on the planned area and the high-conflict conversion penalty coefficient. Development objective functions and ecological objective functions are obtained based on development goals and ecological goals, respectively. The undetermined conversion probability weight parameters in the comprehensive conversion probability are used as decision variables. The multi-objective optimization problem is constructed based on constraints, development objective function, ecological objective function, and decision variables.

8. The land spatial planning method integrating ecological security and urban development according to claim 1, characterized in that, A swarm intelligence multi-objective optimization algorithm is used to solve multi-objective optimization problems and obtain a set of development ecological plans, including: Based on the swarm intelligence multi-objective optimization algorithm, multiple sets of decision variables are obtained, and the decision variables drive the urban planning cellular definition model to carry out a complete urban expansion simulation. After the simulation, the development objective function value and ecological objective function value corresponding to the multiple sets of decision variables are obtained. Based on the results of urban expansion simulations, a development ecological planning set is defined, which represents a collection of multiple development ecological planning schemes that achieve different trade-offs between development goals and ecological goals.

9. The land spatial planning method integrating ecological security and urban development according to claim 1, characterized in that, Urban development evaluation factors and ecological evaluation factors are obtained, and urban development potential pattern networks and ecological security pattern networks are constructed respectively, and development potential values ​​and ecological resistance values ​​are assigned, including: The ecological evaluation factors are specifically indicators that affect ecological security. The ecological evaluation factors are identified based on the minimum cumulative resistance model to obtain ecological source areas, ecological corridors, ecological nodes and ecological resistance values, and to construct an ecological security pattern network. Each grid cell in the ecological security pattern network is assigned an ecological resistance value. The urban development evaluation factors are specifically indicators that affect urban development. The suitability of the urban evaluation factors is assessed, the assessment results and development potential values ​​are obtained, and an urban development potential pattern network is constructed, wherein each grid cell of the urban development potential pattern network is assigned a development potential value.

10. A land spatial planning system integrating ecological security and urban development, using the method described in claims 1 to 9, characterized in that, include: The data acquisition and processing module is used to acquire urban development evaluation factors and ecological evaluation factors, construct urban development potential pattern network and ecological security pattern network respectively, and assign development potential value and ecological resistance value. The conflict identification and spatial analysis module is used to obtain the ecological-development conflict intensity network, obtain the resampled development potential value and resampled ecological resistance value based on the ecological-development conflict intensity network, and obtain the ecological-development conflict intensity index. It also generates a spatial distribution map of high-intensity conflict areas through a fusion clustering strategy. Urban planning cell definition model module, which is used to construct urban planning cell definition model; A multi-objective optimization module is used to construct and solve a multi-objective optimization problem based on a set of planning requirements and a comprehensive transformation probability, thereby obtaining a development ecological planning set. The report generation module is used to configure ecological development land space reports for the development ecological planning set based on the spatial distribution map of high-intensity conflict areas.

Images