An ecological network construction method and device based on spatial correlation quantity, equipment and medium

Abstract

This invention discloses a method for constructing an ecological network based on spatial correlation, comprising: acquiring and preprocessing multi-source geographic information data of a target area; extracting urban green space patches based on the preprocessed data, and selecting candidate ecological nodes from the urban green space patches; calculating the spatial correlation between each candidate ecological node using a pre-constructed spatial correlation calculation model; identifying key nodes from the candidate ecological nodes based on the spatial correlation and extracting ecological corridors connecting the key nodes; calculating the ecological connectivity, land use cost, and planning compatibility of the target area, and generating an ecological network construction scheme; and outputting a spatial planning recommendation report for the target area based on the key nodes, the ecological corridors, and the ecological network construction scheme. This invention can significantly improve the stability and ecological service capacity of urban green space ecological networks, and enhance the rationality and feasibility of urban green space ecological network construction schemes.

Description

Technical Field

[0001] This invention relates to the field of ecological network construction technology, and in particular to an ecological network construction method, apparatus, equipment and medium based on spatial correlation quantities. Background Technology

[0002] With the accelerating pace of urbanization, urban green space systems, as crucial carriers for maintaining urban ecological security and the quality of the living environment, are of paramount importance in terms of structural integrity and functional connectivity. Currently, ecological network construction methods based on spatial correlation have gradually become a research hotspot. These methods aim to reveal potential ecological flow paths by quantifying the spatial interactions between green space patches, and thereby optimize the spatial organization of green space systems. Such methods typically integrate multi-source geospatial data, including remote sensing imagery, land use data, and topographic information, combined with landscape ecology principles and graph theory models, to assess the importance of green space nodes and the connectivity effectiveness of corridors.

[0003] However, existing technologies still have some problems in the construction of urban green space ecological networks: most methods rely on simple Euclidean distance or buffer analysis to characterize the spatial relationship between green spaces, failing to fully consider the resistance factors and directional characteristics in the actual ecological process, resulting in distorted correlation assessment results. At the same time, they lack comprehensive consideration of multi-scale ecological connectivity, making it difficult to balance the synergistic optimization of local connectivity and the overall regional network structure. Furthermore, the identification of key nodes and corridors is mostly based on a single indicator, without considering the functional differences of different green spaces, which affects the accuracy and implementation efficiency of planning schemes. Summary of the Invention

[0004] This invention provides a method for constructing an ecological network based on spatial correlation, which can significantly improve the stability and ecological service capacity of urban green space ecological networks, and enhance the rationality and feasibility of urban green space ecological network construction schemes.

[0005] In a first aspect, embodiments of the present invention provide a method for constructing an ecological network based on spatial correlation data, comprising: Acquire and preprocess multi-source geographic information data of the target area, including high-resolution remote sensing images, land use classification data, digital elevation models, and urban road network data; Urban green space patches are extracted based on the preprocessed data, and candidate ecological nodes are selected from the urban green space patches; The spatial correlation between each candidate ecological node is calculated using a pre-built spatial correlation calculation model. Based on the spatial correlation, key nodes are identified from the candidate ecological nodes, and ecological corridors connecting the key nodes are extracted. Calculate the ecological connectivity, land use cost, and planning compatibility of the target area to generate an ecological network construction scheme; Based on the key nodes, the ecological corridors, and the ecological network construction scheme, output a spatial planning recommendation report for the target area.

[0006] Furthermore, the step of extracting urban green space patches based on preprocessed data and screening candidate ecological nodes from these patches includes: Based on the preprocessed data, an object-oriented classification method was used to extract urban green space patches. The landscape pattern index of each green space patch was calculated using the moving window analysis method. Based on the landscape pattern index, candidate ecological nodes that meet the preset ecological function requirements are selected from the green patches.

[0007] Furthermore, the step of using a pre-built spatial correlation calculation model to calculate the spatial correlation between each of the candidate ecological nodes includes: Based on land use type and slope data of the target area, an ecological resistance surface is constructed; The minimum cumulative resistance model is used to calculate the minimum cumulative resistance path from each candidate ecological node to all other candidate ecological nodes, as well as the minimum cumulative resistance value of the corresponding path. Based on the minimum cumulative resistance value and the pre-constructed spatial correlation calculation equation, the spatial correlation between any two candidate ecological nodes is calculated.

[0008] Furthermore, the construction of the ecological resistance surface based on land use type and slope data of the target area includes: Obtain land use type, slope data, and corresponding land use resistance coefficient and slope resistance coefficient for the target area; wherein, each land use type corresponds to a land use resistance coefficient, and each slope range corresponds to a slope resistance coefficient. Based on the land use resistance coefficient, the slope resistance coefficient, and the pre-set land use resistance weight and slope resistance weight, the ecological resistance surface of the target area is generated by weighted summation.

[0009] Furthermore, the step of identifying key nodes from the candidate ecological nodes based on the spatial correlation quantity includes: An ecological network graph is constructed using the candidate ecological nodes as network nodes and the spatial correlation between each candidate ecological node as the network edge weight. Calculate the betweenness centrality of each network node in the ecological network graph, and select a preset number of network nodes as the first key nodes based on the betweenness centrality; wherein, the betweenness centrality is the proportion of network nodes that appear on the shortest path between all pairs of nodes. The ecological network graph is iteratively analyzed using a node deletion method. The network connectivity after node deletion is calculated, and nodes whose network connectivity decreases by more than a preset first decrease threshold after deletion are marked as second key nodes. The set of key nodes is obtained by taking the union of the first key node and the second key node.

[0010] Furthermore, the extraction of the ecological corridors connecting the key nodes includes: The connection threshold is determined based on the spatial correlation quantity; the connection threshold is a critical value used to distinguish between effective and ineffective connections between ecological nodes. Based on the connection threshold, the key nodes are used as the starting and ending points of the path. The minimum path algorithm is used to search for and extract the path with the minimum cumulative resistance value on the ecological resistance surface, which is used as the ecological corridor connecting the corresponding key nodes.

[0011] Furthermore, the calculation of ecological connectivity, land use costs, and planning compatibility of the target area generates an ecological network construction scheme, including: Calculate the ecological connectivity, land use cost, and planning compatibility of the area to be planned; Construct an objective function that aims to maximize the weighted sum of the ecological connectivity, the land use cost, and the planning compatibility; The objective function is solved using a multi-objective genetic algorithm to generate an ecological network construction scheme.

[0012] Secondly, embodiments of the present invention provide an ecological network construction device based on spatial correlation data, comprising: The data acquisition module is used to acquire and preprocess multi-source geographic information data of the target area, including high-resolution remote sensing images, land use classification data, digital elevation models, and urban road network data. An ecological node extraction module is used to extract urban green space patches based on preprocessed data and to select candidate ecological nodes from the urban green space patches. The spatial correlation calculation module is used to calculate the spatial correlation between each of the candidate ecological nodes using a pre-built spatial correlation calculation model. An ecological corridor extraction module is used to identify key nodes from the candidate ecological nodes based on the spatial correlation quantity, and extract the ecological corridors connecting the key nodes. The scheme generation module is used to calculate the ecological connectivity, land use cost and planning compatibility of the target area, and generate ecological network construction schemes. The output module is used to output a spatial planning suggestion report for the target area based on the key nodes, the ecological corridors, and the ecological network construction scheme.

[0013] Thirdly, embodiments of the present invention provide an electronic device, comprising: Memory, used to store computer programs; A processor for executing the computer program; Wherein, when the processor executes the computer program, it implements the ecological network construction method based on spatial correlation quantity as described in any of the first aspects above.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed, implements the ecological network construction method based on spatial correlation quantities as described in any of the first aspects above.

[0015] Compared with existing technologies, the ecological network construction method based on spatial correlation provided by this invention has the following advantages: It acquires and preprocesses multi-source geographic information data of the target area, including high-resolution remote sensing images, land use classification data, digital elevation models, and urban road network data; extracts urban green space patches based on the preprocessed data, and selects candidate ecological nodes from these patches; calculates the spatial correlation between each candidate ecological node using a pre-constructed spatial correlation calculation model; identifies key nodes from the candidate ecological nodes based on the spatial correlation, and extracts ecological corridors connecting these key nodes; calculates the ecological connectivity, land use cost, and planning compatibility of the target area, and generates an ecological network construction scheme; and outputs a spatial planning recommendation report for the target area based on the key nodes, ecological corridors, and the ecological network construction scheme. This invention can significantly improve the stability and ecological service capacity of urban green space ecological networks, and enhance the rationality and feasibility of urban green space ecological network construction schemes. Attached Figure Description

[0016] To more clearly illustrate the technical features of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1This is a flowchart illustrating a method for constructing an ecological network based on spatial correlation data, provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of an ecological network construction device based on spatial correlation quantity provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0021] In a first aspect, embodiments of the present invention provide a method for constructing an ecological network based on spatial correlation quantities, see [link to previous document]. Figure 1 This is a flowchart illustrating an embodiment of an ecological network construction method based on spatial correlation quantities provided by the present invention.

[0022] like Figure 1 As shown, the method includes the following steps: S1: Acquire and preprocess multi-source geographic information data of the target area, including high-resolution remote sensing images, land use classification data, digital elevation models, and urban road network data; S2: Extract urban green space patches based on the preprocessed data, and select candidate ecological nodes from the urban green space patches; S3: Using a pre-built spatial correlation calculation model, calculate the spatial correlation between each of the candidate ecological nodes; S4: Identify key nodes from the candidate ecological nodes based on the spatial correlation quantity, and extract the ecological corridors connecting the key nodes; S5: Calculate the ecological connectivity, land use cost and planning compatibility of the target area, and generate an ecological network construction scheme; S6: Based on the key nodes, the ecological corridors, and the ecological network construction scheme, output a spatial planning suggestion report for the target area.

[0023] In practice, multi-source geographic information data of the target area are collected, including but not limited to high-resolution remote sensing images, land use classification data, digital elevation models, and urban road network data. Then, the collected multi-source data are preprocessed, and geometric correction, radiometric calibration, spatial registration and unified spatial resolution are performed on the high-resolution remote sensing images and digital elevation model data. All data are then unified to the same geographic coordinate system to finally obtain a standardized multi-source geographic information dataset.

[0024] Based on preprocessed multi-source geographic information data, urban green space patches within the target area are accurately extracted. On this basis, combined with preset ecological function screening criteria, candidate ecological nodes with potential ecological support value are further screened from the extracted urban green space patches. A pre-built spatial correlation calculation model is called to calculate the spatial correlation between each candidate ecological node, thereby quantifying the degree of ecological correlation between different candidate ecological nodes.

[0025] Based on the calculated spatial correlation data, key nodes that play a crucial supporting role in the stability and connectivity of the ecological network are identified from the candidate ecological nodes. At the same time, with the key nodes as the core, ecological corridors that can achieve effective connections between key nodes are extracted to construct the core framework of the ecological network.

[0026] Finally, the three core indicators of ecological connectivity level, land use economic cost, and planning compatibility score of the target area are comprehensively calculated. This results in an ecological network construction scheme that balances ecological benefits, economic rationality, and planning compliance. The scheme integrates key nodes, ecological corridors, and the ecological network construction, outputting a spatial planning recommendation report for the target area. The final output includes both vector and raster data. The vector data uses ESRI Shapefile format and includes ecological node distribution layers, ecological corridor network layers, and optimized green space layout recommendation layers. Each layer includes a complete attribute table recording attributes such as area, length, correlation strength, and construction priority. The raster data uses GeoTIFF format with a spatial resolution of 2 meters and includes thematic maps of ecological resistance surfaces, spatial correlation distribution, and multi-objective optimization results. All spatial data includes metadata conforming to ISO 19115 standards, describing detailed information such as data source, processing method, coordinate system, and accuracy assessment.

[0027] Understandably, the spatial planning recommendation report is automatically generated, including recommendations for corridor width, vegetation restoration types, and priority construction sequences. The report is output in PDF format and also provides an interactive web map service, making it easy for planning decision-makers to view and analyze the planning results from multiple dimensions.

[0028] In summary, this invention, by pre-constructing a spatial correlation calculation model, replaces the traditional simple distance or buffer analysis, enabling a quantitative assessment of the correlation strength between candidate ecological nodes. This makes the representation of ecological correlation between nodes more closely resemble real ecological processes. The ecological network construction scheme generated based on this core data can accurately match the ecological endowments and construction conditions of different regions. At the same time, the spatial planning suggestions in the output stage are all based on the correlation strength represented by the spatial correlation quantity, ensuring the specificity and operability of the planning guidance, significantly improving the practicality and implementation efficiency of the planning scheme, and providing reliable technical support for the scientific planning and efficient implementation of urban green space ecological networks.

[0029] In one optional implementation, the step of extracting urban green space patches based on preprocessed data and screening candidate ecological nodes from the urban green space patches includes: Based on the preprocessed data, an object-oriented classification method was used to extract urban green space patches. The landscape pattern index of each green space patch was calculated using the moving window analysis method. Based on the landscape pattern index, candidate ecological nodes that meet the preset ecological function requirements are selected from the green patches.

[0030] Specifically, the extraction of green patches adopts an object-oriented classification method. First, the preprocessed high-resolution remote sensing image is divided into homogeneous regions by a multi-scale segmentation algorithm. The segmentation scale parameter is dynamically adjusted between 20 and 50 according to the regional characteristics. Then, a classification rule set is constructed based on the normalized vegetation index threshold, texture features and shape rules to accurately identify various types of green patches. Finally, morphological opening and closing operations are used to eliminate small noise and form complete vector boundaries of green patches.

[0031] The moving window analysis method is used to calculate the landscape pattern index. The window size can be flexibly set from 3×3 pixels to 11×11 pixels according to the scale of the study area. For example, for small-scale, densely patched areas such as urban built-up areas, a small window of 3×3 pixels can be selected to capture fine features, while for large-scale, sparsely patched areas such as suburbs, a large window of 11×11 pixels can be selected to reflect the overall pattern. In this embodiment, the landscape pattern indices selected are all set around the ecological function potential of green space patches, including shape index and connectivity index. The shape index is characterized by fractal dimension (FD), which can quantify the complexity of the shape of green space patches. The closer the value is to 1, the simpler and more regular the patch shape is; the closer it is to 2, the more complex and irregular the shape is. The calculation formula is as follows: ; in, The perimeter of the plaque. This represents the area of ​​the patch.

[0032] The connectivity index is calculated based on the probabilistic connectivity model, and the formula is as follows: ; in, and Let i and j be the areas of patches i and j, respectively. To determine the probability of a functional connection between patches i and j, the maximum diffusion distance of a typical dispersing species is set to 5000 meters. The connection probability decreases exponentially with increasing distance, and the decay coefficient is set to 0.001 based on the species' mobility.

[0033] After calculating the landscape pattern index of all green space patches, all extracted green space patches are comprehensively screened according to the preset ecological function requirements. The preset ecological function requirements can be combined with the ecological planning goals of specific cities, and comprehensively consider the threshold range of core indicators such as patch area, fractal dimension shape index, and connectivity index. Finally, green space patches with sufficient area, complex shape, good connectivity, and able to meet the preset ecological function requirements are selected and identified as candidate ecological nodes, providing core basic support for subsequent spatial correlation calculation and ecological network construction.

[0034] This invention employs an object-oriented classification method to extract urban green space patches, effectively overcoming the noise interference problem of traditional pixel-level classification. This significantly improves the completeness and accuracy of green space patch boundary identification. By using a moving window analysis method to calculate the landscape pattern index, the ecological function potential of green space patches can be comprehensively and objectively quantified, ensuring the scientific and ecological rationality of the selection criteria. The selected candidate ecological nodes can serve as high-quality core units for ecological network construction, providing reliable support for subsequent spatial correlation calculations and ecological corridor extraction. This also significantly enhances the stability and ecological service capacity of the finally constructed urban green space ecological network.

[0035] In one optional implementation, the step of using a pre-built spatial correlation calculation model to calculate the spatial correlation between each of the candidate ecological nodes includes: Based on land use type and slope data of the target area, an ecological resistance surface is constructed; The minimum cumulative resistance model is used to calculate the minimum cumulative resistance path from each candidate ecological node to all other candidate ecological nodes, as well as the minimum cumulative resistance value of the corresponding path. Based on the minimum cumulative resistance value and the pre-constructed spatial correlation calculation equation, the spatial correlation between any two candidate ecological nodes is calculated.

[0036] Specifically, an ecological resistance surface is constructed based on land use type data and slope data of the target area. Land use type reflects the degree of obstruction of ecological flow by different land cover, while slope data reflects the impact of topographic relief on species migration. By spatially superimposing these two types of data and assigning resistance coefficients, a basic resistance surface that reflects the ease or difficulty of ecological flow in the region can be obtained.

[0037] The minimum cumulative resistance model is used to calculate the minimum cumulative resistance path from each candidate ecological node to all other candidate ecological nodes and the corresponding minimum cumulative resistance value. The minimum cumulative resistance model can simulate the cumulative resistance experienced by species when spreading from the source patch to the target patch. By calculating the cumulative resistance value of different paths, the path with the least resistance is identified, that is, the path through which the ecological flow is most likely to pass. This path and its corresponding cumulative resistance value reflect the ease or difficulty of ecological connection between two candidate ecological nodes and are important parameters for subsequent spatial correlation calculation.

[0038] Based on the obtained minimum cumulative resistance value and the pre-constructed spatial correlation calculation equation, the spatial correlation between any two candidate ecological nodes is calculated. Preferably, the spatial correlation calculation equation is constructed based on a gravity model, comprehensively considering patch area, Euclidean distance, and minimum cumulative resistance value. The calculation formula is as follows: ; in, and Let i and j be the areas of patches i and j, respectively. The Euclidean distance between the two patches is... The minimum cumulative resistance value between two patches is given, with patch area in hectares and Euclidean distance in meters. The minimum cumulative resistance value is a dimensionless value, and the final spatial correlation result is a standardized relative value, ranging from 0 to 1.

[0039] The spatial correlation quantity calculated by this formula can comprehensively reflect the patch quality, distance effect and resistance effect, thereby objectively quantifying the ecological correlation strength between candidate ecological nodes.

[0040] This invention constructs an ecological resistance surface through multi-source data fusion and calculates spatial correlation quantities by combining the minimum cumulative resistance model and the gravity model. This effectively improves the scientificity and accuracy of ecological correlation strength assessment. Compared with traditional methods that only consider distance or a single resistance factor, this implementation can more realistically reflect the actual ecological connections between ecological nodes in complex urban environments. It provides a reliable quantitative basis for subsequent key node identification, ecological corridor extraction, and ecological network optimization, and significantly enhances the rationality and feasibility of urban green space ecological network construction schemes.

[0041] In one optional implementation, constructing the ecological resistance surface based on land use type and slope data of the target area includes: Obtain land use type, slope data, and corresponding land use resistance coefficient and slope resistance coefficient for the target area; wherein, each land use type corresponds to a land use resistance coefficient, and each slope range corresponds to a slope resistance coefficient. Based on the land use resistance coefficient, the slope resistance coefficient, and the pre-set land use resistance weight and slope resistance weight, the ecological resistance surface of the target area is generated by weighted summation.

[0042] Specifically, land use type and slope data of the target area are obtained from multi-source geographic information data, and corresponding resistance coefficients are matched for the two types of data respectively. Each land use type corresponds to a unique land use resistance coefficient, and each slope range corresponds to a unique slope resistance coefficient.

[0043] Regarding the specific values ​​assigned to the resistance coefficients, this implementation method employs optimized design to adapt to the actual characteristics of the urban ecological environment. For land use type data, the resistance coefficient values ​​for each type of land are limited to a reasonable range of 1 to 100. For example, the resistance coefficient for construction land is set to 100, the resistance coefficient for main roads is set to 90, the resistance coefficient for secondary roads is set to 70, the resistance coefficient for forest land is set to 10, the resistance coefficient for grassland is set to 20, the resistance coefficient for water area is set to 30, the resistance coefficient for cultivated land is set to 40, and the resistance coefficient for unused land is set to 50. For slope data, the range is divided and assigned values ​​according to slope grade: the resistance coefficient for gentle slope areas of 0 to 5 degrees is set to 10, the resistance coefficient for gentle slope areas of 5 to 15 degrees is set to 30, the resistance coefficient for steep slope areas of 15 to 25 degrees is set to 60, and the resistance coefficient for extremely steep slope areas above 25 degrees is set to 80.

[0044] Based on pre-set land use resistance weights and slope resistance weights, a weighted summation method is used to spatially superimpose the two types of resistance data. In this embodiment, considering the dominant influence of land use type on ecological flow and the auxiliary influence of slope, the land use resistance weight is set to 0.7 and the slope resistance weight is set to 0.3. Finally, the comprehensive resistance value of each pixel is calculated by the formula "Comprehensive resistance value = land use resistance coefficient × 0.7 + slope resistance coefficient × 0.3", thereby generating a continuous and accurate comprehensive ecological resistance surface covering the entire target area.

[0045] The embodiments of the present invention construct an ecological resistance surface by refining the resistance coefficient assignment of land type and slope grade, and combining it with reasonable weight allocation, which can truly reflect the ecological resistance distribution characteristics of complex urban surface environment.

[0046] In one optional implementation, identifying key nodes from the candidate ecological nodes based on the spatial correlation quantity includes: An ecological network graph is constructed using the candidate ecological nodes as network nodes and the spatial correlation between each candidate ecological node as the network edge weight. Calculate the betweenness centrality of each network node in the ecological network graph, and select a preset number of network nodes as the first key nodes based on the betweenness centrality; wherein, the betweenness centrality is the proportion of network nodes that appear on the shortest path between all pairs of nodes. The ecological network graph is iteratively analyzed using a node deletion method. The network connectivity after node deletion is calculated, and nodes whose network connectivity decreases by more than a preset first decrease threshold after deletion are marked as second key nodes. The set of key nodes is obtained by taking the union of the first key node and the second key node.

[0047] Specifically, the selected candidate ecological nodes are used as network nodes, and the calculated spatial correlation between each candidate ecological node is used as the weight of the network edge to build an ecological network graph based on spatial correlation. This network graph can intuitively represent the ecological correlation between candidate ecological nodes.

[0048] Furthermore, the betweenness centrality of each network node in the ecological network graph is calculated. Betweenness centrality is defined as the proportion of the node that appears on the shortest path between all pairs of nodes in the network. Its value directly reflects the pivotal position of the node in the ecological network. The higher the betweenness centrality, the more critical the node is to the transmission and diffusion of ecological flow in the network. In this embodiment, the top 10% of network nodes in terms of betweenness centrality are selected and identified as the first critical node.

[0049] Next, the node deletion method is used to iteratively analyze the ecological network graph, that is, to remove individual candidate ecological nodes in the network in turn, and simultaneously calculate and observe the degree of change in network connectivity indicators after node deletion. In this implementation method, the first decrease threshold is preset to 30%. If the network connectivity decreases by more than 30% after deleting a certain node, it indicates that the node is a core node that maintains the overall connectivity of the network, and it is marked as the second key node.

[0050] The union of the first and second critical nodes is taken to obtain a preliminary set of critical nodes. To avoid functional redundancy caused by nodes being too close in space, the preliminary set is further optimized through spatial proximity analysis. Duplicate nodes with a distance of less than 100 meters in the set are merged (nodes with larger area and better ecological quality are retained first), and the final set of critical ecological nodes is determined.

[0051] This invention combines the node deletion method with the betweenness centrality criterion. The former reflects the functional contribution of a node to the overall network connectivity, while the latter characterizes its mediating role in the network information flow. The two complement each other and can effectively improve the accuracy of key node identification, which is significantly better than the single index method. It can more accurately identify the core nodes that play a key supporting role in the overall network connectivity and avoid the problem of missing important nodes due to ignoring the network topology.

[0052] In one optional implementation, extracting the ecological corridors connecting the key nodes includes: The connection threshold is determined based on the spatial correlation quantity; the connection threshold is a critical value used to distinguish between effective and ineffective connections between ecological nodes. Based on the connection threshold, the key nodes are used as the starting and ending points of the path. The minimum path algorithm is used to search for and extract the path with the minimum cumulative resistance value on the ecological resistance surface, which is used as the ecological corridor connecting the corresponding key nodes.

[0053] Specifically, the connection threshold is a critical value used to clearly distinguish between effective and ineffective connections between ecological nodes. Its core function is to filter out node connections with weak spatial correlations that lack practical ecological significance, ensuring that the subsequently extracted ecological corridors can truly carry out the function of ecological flow transmission. In practical applications, mature statistical grading methods such as the natural breakpoint method and the percentile method can be used to analyze all spatial correlation values ​​obtained in the previous calculation. For example, the natural breakpoint method can be used to identify the natural break characteristics of the distribution of spatial correlation values, and the critical value of the high correlation intensity interval can be selected as the connection threshold. Alternatively, the threshold can be adaptively adjusted based on the ecological planning needs and topographic features of the target area to ensure the scientific nature and regional adaptability of the connection threshold.

[0054] Using the identified key nodes as the starting and ending points of the path, and based on the pre-constructed ecological resistance surface, the minimum path algorithm is used to perform path search and extraction operations. Specifically, key node pairs with spatial correlation greater than or equal to the connection threshold are selected and used as the target node combinations for corridor connection. Then, on the ecological resistance surface, for each target node pair, the minimum path algorithm is used to calculate and extract the path with the minimum cumulative resistance value. This path is the ecological corridor connecting the corresponding key nodes.

[0055] The ecological corridors extracted in this invention can accurately connect key nodes, forming the core connecting framework of the urban green space ecological network, and providing precise spatial guidance for subsequent green space layout optimization and planning construction.

[0056] In one optional implementation, the calculation of the ecological connectivity, land use cost, and planning compatibility of the target area to generate an ecological network construction scheme includes: Calculate the ecological connectivity, land use cost, and planning compatibility of the area to be planned; Construct an objective function that aims to maximize the weighted sum of the ecological connectivity, the land use cost, and the planning compatibility; The objective function is solved using a multi-objective genetic algorithm to generate an ecological network construction scheme.

[0057] Specifically, the three core indicators of the area to be planned are calculated first: ecological connectivity, land use cost, and planning compatibility. Ecological connectivity can be quantified using the Global Corridor Network Connectivity Index (GCI). By calculating the proportion of effective connection paths between all key ecological node pairs, the overall connectivity level of the ecological network is comprehensively represented. The higher the index value, the higher the efficiency of ecological flow transmission within the network. Land use cost is calculated based on the actual construction cost of the target area, comprehensively estimating land acquisition costs, demolition compensation costs, and infrastructure construction costs. The calculation data are all from benchmark land prices, recent land transaction prices, and engineering construction cost standards published by the urban planning department. The final output is the land use cost quantification result in "ten thousand yuan / hectare". Planning compatibility is based on the territorial spatial planning, the control detailed planning, and related special plans. The consistency between the green space layout scheme and various plans is judged and scored. The scoring standard adopts a three-level quantitative system: 1 point is awarded for green space layout that fully complies with planning requirements, 0.5 points are awarded for partial compliance with planning and which can be made compliant through minor adjustments, and 0 points are awarded for conflict with planning requirements and which cannot be coordinated. This achieves accurate quantification of planning compatibility.

[0058] Based on the above three core indicators, a multi-objective optimization model is constructed. The optimal ecological network construction scheme is obtained through intelligent algorithms. The objective function takes maximizing ecological connectivity, minimizing land use costs, and maximizing planning compatibility as its core objectives. The three objectives are integrated in a weighted sum form. The specific calculation formula is as follows: ; in, For ecological connectivity, For land use costs, For planning compatibility scoring, , , These are the weighting coefficients for ecological connectivity, land use cost, and planning compatibility, respectively, to meet the following requirements. 1.

[0059] Furthermore, a non-dominated sorting genetic algorithm with an elite strategy (NSGA-II) is used to solve the objective function. This algorithm can efficiently handle multi-objective optimization problems and generate a Pareto optimal solution set that takes into account the needs of all parties. The algorithm parameters adopt the optimal configuration verified by a large number of experiments: the population size is set to 200, the number of iterations is set to 500, the crossover probability is 0.8, the mutation probability is 0.1, and the selection strategy is tournament selection (tournament size is 3). At the same time, in order to ensure the practical feasibility of the optimization results, the feasibility of each generation of the population is checked during the algorithm operation. Individuals that obviously do not meet the actual constraints, such as corridor crossing insurmountable natural barriers or construction costs exceeding the preset budget limit, are automatically excluded. Finally, the optimal ecological network construction scheme that meets the actual needs is output.

[0060] The embodiments of this invention employ a multi-objective genetic algorithm to achieve a dynamic trade-off between ecological connectivity, land cost, and planning compatibility, generating feasible and implementable optimization solutions, thus overcoming the limitations of traditional methods that prioritize ecology over implementation or cost over functionality.

[0061] Secondly, embodiments of the present invention provide an ecological network construction device based on spatial correlation quantities, see [link to previous document]. Figure 2 This is a schematic diagram of an embodiment of an ecological network construction device based on spatial correlation quantities provided by the present invention.

[0062] like Figure 2 As shown, the device includes: Data acquisition module 21 is used to acquire and preprocess multi-source geographic information data of the target area, including high-resolution remote sensing images, land use classification data, digital elevation models, and urban road network data. The ecological node extraction module 22 is used to extract urban green space patches based on preprocessed data and select candidate ecological nodes from the urban green space patches. The spatial correlation calculation module 23 is used to calculate the spatial correlation between each of the candidate ecological nodes using a pre-built spatial correlation calculation model. The ecological corridor extraction module 24 is used to identify key nodes from the candidate ecological nodes based on the spatial correlation quantity, and extract the ecological corridors connecting the key nodes. The scheme generation module 25 is used to calculate the ecological connectivity, land use cost and planning compatibility of the target area, and generate an ecological network construction scheme. The output module 26 is used to output a spatial planning suggestion report for the target area based on the key nodes, the ecological corridors, and the ecological network construction scheme.

[0063] In one optional implementation, the step of extracting urban green space patches based on preprocessed data and screening candidate ecological nodes from the urban green space patches includes: Based on the preprocessed data, an object-oriented classification method was used to extract urban green space patches. The landscape pattern index of each green space patch was calculated using the moving window analysis method. Based on the landscape pattern index, candidate ecological nodes that meet the preset ecological function requirements are selected from the green patches.

[0064] In one optional implementation, the step of using a pre-built spatial correlation calculation model to calculate the spatial correlation between each of the candidate ecological nodes includes: Based on land use type and slope data of the target area, an ecological resistance surface is constructed; The minimum cumulative resistance model is used to calculate the minimum cumulative resistance path from each candidate ecological node to all other candidate ecological nodes, as well as the minimum cumulative resistance value of the corresponding path. Based on the minimum cumulative resistance value and the pre-constructed spatial correlation calculation equation, the spatial correlation between any two candidate ecological nodes is calculated.

[0065] In one optional implementation, constructing the ecological resistance surface based on land use type and slope data of the target area includes: Obtain land use type, slope data, and corresponding land use resistance coefficient and slope resistance coefficient for the target area; wherein, each land use type corresponds to a land use resistance coefficient, and each slope range corresponds to a slope resistance coefficient. Based on the land use resistance coefficient, the slope resistance coefficient, and the pre-set land use resistance weight and slope resistance weight, the ecological resistance surface of the target area is generated by weighted summation.

[0066] In one optional implementation, identifying key nodes from the candidate ecological nodes based on the spatial correlation quantity includes: An ecological network graph is constructed using the candidate ecological nodes as network nodes and the spatial correlation between each candidate ecological node as the network edge weight. Calculate the betweenness centrality of each network node in the ecological network graph, and select a preset number of network nodes as the first key nodes based on the betweenness centrality; wherein, the betweenness centrality is the proportion of network nodes that appear on the shortest path between all pairs of nodes. The ecological network graph is iteratively analyzed using a node deletion method. The network connectivity after node deletion is calculated, and nodes whose network connectivity decreases by more than a preset first decrease threshold after deletion are marked as second key nodes. The set of key nodes is obtained by taking the union of the first key node and the second key node.

[0067] In one optional implementation, extracting the ecological corridors connecting the key nodes includes: The connection threshold is determined based on the spatial correlation quantity; the connection threshold is a critical value used to distinguish between effective and ineffective connections between ecological nodes. Based on the connection threshold, the key nodes are used as the starting and ending points of the path. The minimum path algorithm is used to search for and extract the path with the minimum cumulative resistance value on the ecological resistance surface, which is used as the ecological corridor connecting the corresponding key nodes.

[0068] In one optional implementation, the calculation of the ecological connectivity, land use cost, and planning compatibility of the target area to generate an ecological network construction scheme includes: Calculate the ecological connectivity, land use cost, and planning compatibility of the area to be planned; Construct an objective function that aims to maximize the weighted sum of the ecological connectivity, the land use cost, and the planning compatibility; The objective function is solved using a multi-objective genetic algorithm to generate an ecological network construction scheme.

[0069] It should be noted that the ecological network construction device based on spatial correlation quantity provided in the embodiments of the present invention is used to execute all the process steps of the ecological network construction method based on spatial correlation quantity in the above embodiments. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0070] Thirdly, embodiments of the present invention provide an electronic device, see [link to previous document]. Figure 3 The diagram shown is a structural schematic of an electronic device provided in an embodiment of the present invention.

[0071] like Figure 3 As shown, the device includes: Memory 31 is used to store computer programs; Processor 32 is used to execute the computer program; When the processor 32 executes the computer program, it implements the ecological network construction method based on spatial correlation as described in any of the above embodiments.

[0072] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 32 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0073] The processor 32 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0074] The memory 31 can be used to store the computer programs and / or modules. The processor 32 implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory 31 and calling the data stored in the memory 31. The memory 31 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 31 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0075] It should be noted that the aforementioned electronic devices include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 3 The structural diagram is merely an example of the electronic device described above and does not constitute a limitation on the electronic device. It may include more components than shown in the diagram, or combine certain components, or use different components.

[0076] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed, implements the ecological network construction method based on spatial correlation quantities described in any of the above embodiments.

[0077] It should be understood that the present invention can implement all or part of the processes in the above-described method for constructing an ecological network based on spatial correlation quantities, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described method for constructing an ecological network based on spatial correlation quantities. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0078] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. It should be noted that, for those skilled in the art, several equivalent obvious modifications and / or equivalent substitutions can be made without departing from the technical principles of the present invention, and these obvious modifications and / or equivalent substitutions should also be considered within the scope of protection of the present invention.

Claims

1. A method for constructing an ecological network based on spatial correlation quantities, characterized in that, include: Acquire and preprocess multi-source geographic information data of the target area, including high-resolution remote sensing images, land use classification data, digital elevation models, and urban road network data; Urban green space patches are extracted based on the preprocessed data, and candidate ecological nodes are selected from the urban green space patches; The spatial correlation between each candidate ecological node is calculated using a pre-built spatial correlation calculation model. Based on the spatial correlation, key nodes are identified from the candidate ecological nodes, and ecological corridors connecting the key nodes are extracted. Calculate the ecological connectivity, land use cost, and planning compatibility of the target area to generate an ecological network construction scheme; Based on the key nodes, the ecological corridors, and the ecological network construction scheme, output a spatial planning recommendation report for the target area.

2. The method for constructing an ecological network based on spatial correlation quantities as described in claim 1, characterized in that, The process of extracting urban green space patches based on preprocessed data and selecting candidate ecological nodes from these patches includes: Based on the preprocessed data, an object-oriented classification method was used to extract urban green space patches. The landscape pattern index of each green space patch was calculated using the moving window analysis method. Based on the landscape pattern index, candidate ecological nodes that meet the preset ecological function requirements are selected from the green patches.

3. The method for constructing an ecological network based on spatial correlation quantities as described in claim 1, characterized in that, The calculation of spatial correlation between each candidate ecological node using a pre-built spatial correlation calculation model includes: Based on land use type and slope data of the target area, an ecological resistance surface is constructed; The minimum cumulative resistance model is used to calculate the minimum cumulative resistance path from each candidate ecological node to all other candidate ecological nodes, as well as the minimum cumulative resistance value of the corresponding path. Based on the minimum cumulative resistance value and the pre-constructed spatial correlation calculation equation, the spatial correlation between any two candidate ecological nodes is calculated.

4. The method for constructing an ecological network based on spatial correlation quantities as described in claim 3, characterized in that, The ecological resistance surface is constructed based on land use type and slope data of the target area, including: Obtain land use type, slope data, and corresponding land use resistance coefficient and slope resistance coefficient for the target area; wherein, each land use type corresponds to a land use resistance coefficient, and each slope range corresponds to a slope resistance coefficient. Based on the land use resistance coefficient, the slope resistance coefficient, and the pre-set land use resistance weight and slope resistance weight, the ecological resistance surface of the target area is generated by weighted summation.

5. The method for constructing an ecological network based on spatial correlation quantities as described in claim 1, characterized in that, The step of identifying key nodes from the candidate ecological nodes based on the spatial correlation includes: An ecological network graph is constructed using the candidate ecological nodes as network nodes and the spatial correlation between each candidate ecological node as the network edge weight. Calculate the betweenness centrality of each network node in the ecological network graph, and select a preset number of network nodes as the first key nodes based on the betweenness centrality; wherein, the betweenness centrality is the proportion of network nodes that appear on the shortest path between all pairs of nodes. The ecological network graph is iteratively analyzed using a node deletion method. The network connectivity after node deletion is calculated, and nodes whose network connectivity decreases by more than a preset first decrease threshold after deletion are marked as second key nodes. The set of key nodes is obtained by taking the union of the first key node and the second key node.

6. The method for constructing an ecological network based on spatial correlation quantities as described in claim 1, characterized in that, The extraction of the ecological corridors connecting the key nodes includes: The connection threshold is determined based on the spatial correlation quantity; the connection threshold is a critical value used to distinguish between effective and ineffective connections between ecological nodes. Based on the connection threshold, the key nodes are used as the starting and ending points of the path. The minimum path algorithm is used to search for and extract the path with the minimum cumulative resistance value on the ecological resistance surface, which is used as the ecological corridor connecting the corresponding key nodes.

7. The method for constructing an ecological network based on spatial correlation quantities as described in claim 1, characterized in that, The calculation of ecological connectivity, land use cost, and planning compatibility of the target area generates an ecological network construction scheme, including: Calculate the ecological connectivity, land use cost, and planning compatibility of the area to be planned; Construct an objective function that aims to maximize the weighted sum of the ecological connectivity, the land use cost, and the planning compatibility; The objective function is solved using a multi-objective genetic algorithm to generate an ecological network construction scheme.

8. An ecological network construction device based on spatial correlation quantities, characterized in that, include: The data acquisition module is used to acquire and preprocess multi-source geographic information data of the target area, including high-resolution remote sensing images, land use classification data, digital elevation models, and urban road network data. An ecological node extraction module is used to extract urban green space patches based on preprocessed data and to select candidate ecological nodes from the urban green space patches. The spatial correlation calculation module is used to calculate the spatial correlation between each of the candidate ecological nodes using a pre-built spatial correlation calculation model. An ecological corridor extraction module is used to identify key nodes from the candidate ecological nodes based on the spatial correlation quantity, and extract the ecological corridors connecting the key nodes. The scheme generation module is used to calculate the ecological connectivity, land use cost and planning compatibility of the target area, and generate ecological network construction schemes. The output module is used to output a spatial planning suggestion report for the target area based on the key nodes, the ecological corridors, and the ecological network construction scheme.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program; Wherein, when the processor executes the computer program, it implements the ecological network construction method based on spatial correlation as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the ecological network construction method based on spatial correlation as described in any one of claims 1 to 7.

Images