Urban ecosystem service tradeoff and cooperative relationship analysis method and device

Abstract

The invention discloses an urban ecosystem service tradeoff and cooperative relationship analysis method and device. The method comprises the following steps: dividing a target region according to different spatial scales to obtain sample sets corresponding to the spatial scales respectively; acquiring basic geographic information data of the target area in different time periods; according to the basic geographic information data, calculating service evaluation results of each ecological system service in the target area and each sample in different time periods; according to a service evaluation result, calculating a pairwise trade-off cooperative relationship of each ecological system service under a plurality of spatial scales and time sequences; the samples are clustered according to the service evaluation results of the samples to obtain a plurality of service clusters, and the service clusters are used for representing overall tradeoff cooperation features of multiple ecological system services; and determining a management strategy of each ecological system service according to the pairwise trade-off cooperation relationship and the overall trade-off cooperation characteristics. According to the invention, tradeoff and collaboration characteristics of each ecological system service can be identified under multiple spatial scales and multiple time sequences.

Description

Technical Field

[0001] This invention relates to the field of ecosystem service relationship research technology, specifically to methods and apparatus for analyzing trade-offs and synergistic relationships of urban ecosystem services. Background Technology

[0002] With the accelerating pace of urbanization, the structure and function of urban ecosystems are being increasingly disturbed, posing a severe challenge to the capacity to provide ecosystem services. Urban ecosystem services (UES), as a crucial foundation for the natural environment to support human socio-economic activities, encompass multiple aspects such as material supply, environmental regulation, and cultural experiences. Their scientific assessment and coordinated management have become one of the core issues for sustainable urban development.

[0003] However, existing research lacks a comprehensive assessment system for analyzing ecosystem services. Traditional methods often focus on one or a few types of services, such as provisioning or regulating functions, neglecting the diversity and integrity of ecosystem services and failing to fully reflect the multifunctional characteristics of urban ecosystems. Furthermore, traditional methods often provide only a superficial identification of service relationships. Current analyses of synergies and trade-offs among ecosystem services primarily focus on overall correlation assessments, lacking a systematic characterization of spatial heterogeneity, scale sensitivity, and temporal dynamics. This makes it difficult to meet the needs of refined management and regulation. Therefore, there is an urgent need to construct a comprehensive, logically clear, and feasible integrated analysis methodology for urban ecosystem services. This methodology should enable spatial assessment of multiple service types, scientifically identify multidimensional interactions between services, and promote regional collaborative governance and optimized allocation of ecological functions through service clustering. Summary of the Invention

[0004] This invention provides a method and apparatus for analyzing trade-offs and synergies in urban ecosystem services, addressing the problems of incomplete assessment systems and coarse identification of service relationships in existing technologies when analyzing ecosystem services.

[0005] In a first aspect, the present invention provides a method for analyzing the trade-offs and synergies of urban ecosystem services, comprising: dividing a target area according to different spatial scales to obtain sample sets corresponding to each spatial scale, wherein each sample set contains multiple samples, and each sample corresponds to a sub-region obtained after dividing the target area; acquiring basic geographic information data of the target area at different time periods; calculating the service assessment results of various ecosystem services in the target area and each sample at different time periods based on the basic geographic information data; calculating the pairwise trade-off and synergy relationships of various ecosystem services at multiple spatial scales and multiple time series based on the service assessment results of various ecosystem services in the target area and each sample at different time periods; clustering each sample according to the service assessment results of various ecosystem services in multiple time periods to obtain multiple service clusters, wherein the service clusters are used to characterize the overall trade-off and synergy characteristics among multiple ecosystem services; and determining the management strategies for each ecosystem service based on the pairwise trade-off and synergy relationships and the overall trade-off and synergy characteristics of each ecosystem service.

[0006] The method provided in this invention divides the target area according to different spatial scales, constructs multiple sample sets based on different spatial scales, and calculates the service assessment results of various ecosystem services in the target area and each sample at different time periods. This yields the assessment results of various ecosystem services at different spatial scales and time series. Based on this, the method analyzes the pairwise trade-offs and synergies of various ecosystem services at multiple spatial scales and time series, as well as the overall trade-offs and synergies. This invention can identify the synergistic and conflict characteristics of various ecosystem services at multiple spatial scales and time series, providing a basis for the scientific formulation of ecological space management policies.

[0007] In one alternative implementation, ecosystem services include multiple services such as food supply services, water conservation services, soil conservation services, carbon sequestration services, water purification services, habitat quality services, and leisure tourism services.

[0008] In one optional implementation, the pairwise trade-off relationships include overall static trade-off relationships, overall dynamic trade-off relationships, local trade-off relationships, and local dynamic trade-off relationships. Based on the service assessment results of various ecosystem services in the target area and for each sample at different time periods, the pairwise trade-off relationships of each ecosystem service at multiple spatial scales and multiple time series are calculated. This includes: calculating the overall static trade-off relationships of various ecosystem services based on the service assessment results of various ecosystem services in the target area within the same time period; calculating the overall dynamic trade-off relationships of various ecosystem services based on the changes in the service assessment results of various ecosystem services in the target area at different time periods; calculating the local static trade-off relationships of various ecosystem services at different spatial scales for different sample sets based on the service assessment results of various ecosystem services for each sample within the same time period; and calculating the local dynamic trade-off relationships of various ecosystem services at different spatial scales for different sample sets based on the changes in the service assessment results of various ecosystem services for each sample at different time periods.

[0009] In one optional implementation, the overall static trade-off synergy relationship of various ecosystem services is calculated based on the service assessment results of various ecosystem services in the target area within the same time period. This includes: calculating the correlation coefficient between each pair of ecosystem services based on the service assessment results of various ecosystem services in the target area within the same time period; comparing the correlation coefficient with a preset significance threshold; and determining, based on the comparison result, that the overall static trade-off synergy relationship between each pair of ecosystem services is not significant, or is a synergy relationship, or is a trade-off relationship.

[0010] In one optional implementation, the overall dynamic trade-off and synergy relationship of various ecosystem services is calculated based on the changes in the service assessment results of various ecosystem services in the target area at different time periods. This includes: calculating the correlation coefficient between each pair of ecosystem services based on the changes in the service assessment results of various ecosystem services in the target area at different time periods; comparing the correlation coefficient with a preset significance threshold; and determining, based on the comparison result, that the overall static trade-off and synergy relationship between each pair of ecosystem services is either non-significant, synergistic, or trade-off.

[0011] In one optional implementation, for any sample set, the step of calculating the local static trade-off synergy of various ecosystem services at the spatial scale corresponding to the current sample set based on the service assessment results of various ecosystem services in each sample within the same time period includes: determining multiple service pairs composed of various ecosystem services, where one service pair corresponds to two ecosystem services; if the service assessment results of various ecosystem services follow a normal distribution, calculating the deviation product of the service pair in the current sample based on the service assessment results of the ecosystem services in the service pair in the current sample and the service assessment results in other samples in the current sample set; determining the correlation coefficient critical value based on the sample size and a preset significance level, and calculating the local covariance judgment critical value accordingly; and then... The product of differences is compared with the local covariance judgment threshold. Based on the comparison result, the local static trade-off synergy relationship of the service pair in the current sample is determined to be either non-significant, synergistic, or trade-off. If the service assessment results of each ecosystem service do not follow a normal distribution, the rank difference of the service pair in the current sample is calculated based on the service assessment results of each ecosystem service in the current sample and its ranking in the sample set. The correlation coefficient threshold and the rank difference judgment threshold are determined according to the preset significance level and sample size. The rank difference is compared with the rank difference judgment threshold. Based on the comparison result, the local static trade-off synergy relationship of the service pair in the current sample is determined to be either non-significant, synergistic, or trade-off.

[0012] In one optional implementation, for any sample set, the step of calculating the local dynamic trade-off and synergy relationship of each ecosystem service at the spatial scale corresponding to the current sample set based on the change in the service assessment results of each ecosystem service in different time periods includes: determining multiple service pairs composed of various ecosystem services, where one service pair corresponds to two ecosystem services; determining the direction of change of the service assessment results of the ecosystem services in the service pair in different time periods in the current sample based on the direction of change of the two ecosystem services in the service pair; and determining whether the local dynamic trade-off and synergy relationship of the service pair in the current sample is not significant, or a synergy relationship, or a trade-off relationship, based on the direction of change of the two ecosystem services in the service pair.

[0013] In one optional implementation, the samples are clustered according to the service assessment results of various ecosystem services across multiple time periods to obtain multiple service clusters. This includes: determining the sum of squared intra-cluster errors corresponding to different numbers of clusters using the elbow rule and plotting curves; identifying multiple inflection points with the largest error decrease rate based on the curves, and determining multiple candidate cluster numbers based on the inflection points; calculating the silhouette coefficients corresponding to each candidate cluster number; using the candidate cluster number corresponding to the silhouette coefficient closest to 1 as the target cluster number; constructing the model architecture and training parameters of the self-organizing map model, wherein the model architecture is constructed based on the target cluster number; iteratively training the self-organizing map model based on the similarity between each sample and each neuron in the self-organizing map model through a competitive learning mechanism and a neighborhood weight update strategy; obtaining the code vectors of each neuron in the trained self-organizing map model, and assigning each sample to the corresponding neuron to obtain multiple service clusters.

[0014] Secondly, this invention provides an apparatus for analyzing the trade-offs and synergies of urban ecosystem services, comprising: a multi-scale sample acquisition module, used to divide a target area according to different spatial scales to obtain sample sets corresponding to each spatial scale, wherein each sample set contains multiple samples, and each sample corresponds to a sub-region obtained after dividing the target area; an information acquisition module, used to acquire basic geographic information data of the target area at different time periods; a service assessment module, used to calculate the service assessment results of various ecosystem services of the target area and each sample at different time periods based on the basic geographic information data; a pairwise relationship identification module, used to calculate the pairwise trade-off and synergy relationships of various ecosystem services at multiple spatial scales and multiple time series based on the service assessment results of various ecosystem services of the target area and each sample at different time periods; a clustering module, used to cluster each sample according to the service assessment results of various ecosystem services of all samples at multiple time periods to obtain multiple service clusters, wherein the service clusters are used to characterize the overall trade-off and synergy characteristics among multiple ecosystem services; and a management module, used to determine the management strategies for various ecosystem services based on the pairwise trade-off and synergy relationships and overall trade-off and synergy characteristics of various ecosystem services.

[0015] Thirdly, the present invention provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the ecosystem service analysis method of the first aspect or any corresponding embodiment described above.

[0016] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the ecosystem service analysis method of the first aspect or any corresponding embodiment described above.

[0017] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the ecosystem service analysis method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of the ecosystem service trade-off and synergy analysis method according to an embodiment of the present invention; Figure 3 This refers to the grain yield of different spatial units within the target area in different years according to embodiments of the present invention; Figure 4 This refers to the water production of different spatial units within the target area in different years according to embodiments of the present invention; Figure 5 This refers to the soil retention amount of different spatial units within the target area in different years according to embodiments of the present invention; Figure 6 This refers to the carbon storage of different spatial units within the target region in different years according to embodiments of the present invention; Figure 7 This refers to the TN output of different spatial units within the target area in different years according to embodiments of the present invention; Figure 8 This refers to the TP output of different spatial units within the target area in different years according to embodiments of the present invention; Figure 9 This refers to the habitat quality index of different spatial units within the target area in different years according to embodiments of the present invention; Figure 10 This refers to the cultural service index of different spatial units within the target area in different years according to embodiments of the present invention. Figure 11 This is a Spearman Correlation heatmap of various ecosystem services at different time periods and spatial scales according to an embodiment of the present invention; Figure 12This is a Spearman Correlation heatmap of the changes in various ecosystem services at different spatial scales according to embodiments of the present invention; Figure 13 This invention relates to the local static and local dynamic trade-off relationships between carbon sequestration services and leisure tourism services at different time periods and scales, according to embodiments of the present invention. Figure 14 This is a service cluster obtained by setting the cluster number to 6 according to an embodiment of the present invention; Figure 15 This is a structural block diagram of an urban ecosystem service trade-off and synergy analysis device according to an embodiment of the present invention; Figure 16 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0021] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0022] As an optional application scenario of this invention, such as Figure 1 As shown, the system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0023] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0024] According to an embodiment of the present invention, an embodiment of a method for analyzing trade-offs and synergies in urban ecosystem services is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] This embodiment provides a method for analyzing trade-offs and synergies in urban ecosystem services, which can be used on the aforementioned mobile terminals, such as mobile phones and tablets (the implementing entity is described in conjunction with the actual situation). Figure 2 This is a flowchart of the urban ecosystem service trade-off and synergy analysis method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Divide the target region according to different spatial scales to obtain sample sets corresponding to each spatial scale. Each sample set contains multiple samples, and each sample corresponds to a sub-region obtained after dividing the target region.

[0026] In one optional embodiment, the target area can be divided into different grid areas according to different grid scales, or the target area can be divided according to different scales such as street scale, district scale, etc. For example, different grid scales can be 500m, 1000m, 2000m, etc.

[0027] In one optional embodiment, after dividing the target region according to a spatial scale, each sub-region obtained after the division is taken as a sample. All sub-regions in the target region divided according to the spatial scale form a sample set. By dividing the target region multiple times according to different spatial scales, multiple sample sets can be obtained. Different sample sets correspond to different spatial scales. All samples in each sample set can be spliced ​​together to obtain a complete target region.

[0028] Step S202: Obtain basic geographic information data of the target area at different time periods.

[0029] In one optional embodiment, the basic geographic information data includes land use / cover type (LULC) data, digital elevation model (DEM) data, normalized difference vegetation index (NDVI), soil data, bedrock depth data, precipitation data, evapotranspiration data, species distribution data, road traffic data, points of interest (POI) data, population density data, gross domestic product (GDP) data, administrative division layers, and nature reserve distribution data. In another optional embodiment, the acquired data also includes yearbook data from different years.

[0030] Step S203: Calculate the service assessment results of various ecosystem services in the target area and for each sample at different time periods based on the basic geographic information data.

[0031] In an optional embodiment, in order to systematically characterize the spatial heterogeneity, scale sensitivity and temporal dynamics of ecosystem services, this embodiment of the invention calculates the service assessment results for the target area as a whole and for samples at different spatial scales over different time periods.

[0032] In one optional embodiment, the ecosystem service indicator system covers three core categories of ecosystem services: provisioning services, regulating services, and cultural services. Provisioning services refer to the various material products that the ecosystem provides to humans and are actually utilized, including but not limited to agricultural products, forestry products, livestock products, fishery resources, and eco-energy. Regulating services refer to the regulatory functions that the ecosystem performs in maintaining or improving the human living environment through ecological processes, including functions such as water conservation, soil retention, ecological carbon sequestration, and water purification. Cultural services refer to the ways in which the ecosystem enhances the quality of human life by providing non-material ecological benefits such as leisure tourism and landscape aesthetics.

[0033] To analyze ecosystem services, it is necessary to construct an indicator system for ecosystem services. In the process of constructing the indicator system, based on clear evaluation objects and evaluation units, and following the principles of scientificity, overall coordination, regional differences and operability, multiple indicators were constructed in this embodiment of the invention, including agricultural products, water conservation, soil conservation, carbon sequestration, water purification, habitat quality and leisure tourism, from three major categories of ecosystem service functions, as shown in Table 1.

[0034] Table 1. Urban Ecosystem Service Assessment Index System

[0035] Based on the multiple indicators shown in Table 1, in this embodiment of the invention, ecosystem services are broken down into multiple ecosystem services corresponding to each indicator. One indicator corresponds to one ecosystem service. In step S203, the service evaluation results of each ecosystem service are calculated, which is actually calculating the value of each indicator.

[0036] Step S204: Based on the service assessment results of various ecosystem services in the target area and each sample at different time periods, calculate the pairwise trade-offs and synergies of various ecosystem services at multiple spatial scales and multiple time series.

[0037] In an optional embodiment, the service assessment results for each ecosystem service at different time periods and spatial scales have been calculated in step S203. Therefore, the pairwise trade-offs and synergies of each ecosystem service at multiple spatial scales and multiple time series can be determined based on the calculation results of step S203.

[0038] In an optional embodiment, a pairwise trade-off relationship refers to a trade-off relationship between any two ecosystem services. The trade-off relationship between any two ecosystem services can be that there is no significant relationship, or a synergistic relationship, or a trade-off relationship.

[0039] In one alternative embodiment, since various ecosystem services have spatial heterogeneity, scale sensitivity and temporal dynamics, two ecosystem services may exhibit different trade-offs and synergies in different regions, or at different spatial scales, or in different time periods.

[0040] Step S205: Cluster the samples according to the service assessment results of various ecosystem services in multiple time periods to obtain multiple service clusters. The service clusters are used to characterize the overall trade-off and synergistic features among multiple ecosystem services.

[0041] In an optional embodiment, step S204 involves pairwise analysis of the relationships between various ecosystem services, while step S205 involves analysis of the relationships between all ecosystem services.

[0042] In an alternative embodiment, a service cluster refers to a combination of ecosystem services that recurs in geospatial space. It can be used to identify the trade-offs and synergies of a service set, thereby enabling the joint management of multiple ecosystem services.

[0043] Step S206: Determine the management strategies for each ecosystem service based on the pairwise trade-offs and synergies of each ecosystem service and the overall trade-offs and synergies characteristics.

[0044] The method provided in this invention divides the target area according to different spatial scales, constructs multiple sample sets based on different spatial scales, and calculates the service assessment results of various ecosystem services in the target area and each sample at different time periods. This yields the assessment results of various ecosystem services at different spatial scales and time series. Based on this, the method analyzes the pairwise trade-offs and synergies of various ecosystem services at multiple spatial scales and time series, as well as the overall trade-offs and synergies characteristics. This invention can identify the synergies and conflicts of various ecosystem services at multiple spatial scales and time series, providing a basis for the scientific formulation of ecological space management policies.

[0045] In one optional embodiment, ecosystem services include multiple services such as food supply services, water conservation services, soil conservation services, carbon sequestration services, water purification services, habitat quality services, and recreational tourism services. When calculating the service assessment results of each ecosystem service using basic geographic information data of the target area obtained in step S202 at different time periods, a unified projection transformation is performed on all basic geographic information datasets to ensure that all types of spatial data have a consistent spatial reference coordinate system, thus constructing a standardized dataset. If statistical yearbook data is used when calculating various ecosystem services, the statistical yearbook data is also digitized.

[0046] In an optional embodiment, for food supply services, due to the significant linear correlation between the Normalized Difference Vegetation Index (NDVI) and food yield, this embodiment of the invention constructs a spatialized representation model to allocate food yield statistics to specific spatial units, thereby achieving a spatialized assessment of food supply services. For example, as... Figure 3 The figure shows the grain yield of different spatial units within the target area in different years.

[0047] In one optional embodiment, when calculating the service assessment results of food supply services, areas with NDVI values ​​greater than zero within the cultivated land area are first selected as effective food production areas. Based on this, food production data (unit: tons / hectare) provided in statistical yearbooks are weighted and allocated according to the spatial distribution characteristics of cultivated land NDVI values, achieving a spatial mapping of food output from macroscopic statistical values ​​to microscopic grid scales. The calculation formula is as follows:

[0048] In the formula, Indicates the first The grain supply (tons / hectare) of the sub-region corresponding to each sample. To calculate the total grain output of the target region in the statistical yearbook, For the first NDVI values ​​of sub-regions corresponding to each sample This is the sum of NDVI for all cultivated land subregions within the target area.

[0049] In an optional embodiment, for water conservation services, this embodiment of the invention uses the water yield of the target area and each sample at different times as the service assessment result of water conservation services in the corresponding time period. This embodiment of the invention provides a service assessment method based on the Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model. Water conservation services refer to the function of an ecosystem in intercepting and storing precipitation through its structure and ecological processes, enhancing soil infiltration capacity, thereby maintaining soil moisture, replenishing groundwater, regulating river flow, and improving the amount of available water resources in the region. In this embodiment of the invention, the annual water yield (AWY) module in the InVEST model is used to perform water balance simulation based on the Budyko hydrothermal coupling equilibrium assumption, and the water yield is calculated based on sub-region pixels by combining correction factors such as climate, soil, topography, and vegetation type. The water yield is the difference between precipitation and actual evapotranspiration, which is the water supply. The level of water yield can, to some extent, reflect the ability of underlying vegetation and soil to retain precipitation. Generally, a higher water yield indicates a weaker water retention and conservation capacity of the ecosystem; conversely, a lower water yield indicates a relatively stronger conservation capacity. For example, such as... Figure 4 The figure shows the water production of different spatial units within the target area in different years.

[0050] In this model, the annual water production of each sub-region ( The calculation formula is:

[0051] In the formula, Let be the annual water yield (mm) of the subregion corresponding to sample x in ecosystem j. denoted as the annual actual evapotranspiration (mm) of the subregion corresponding to sample x in ecosystem j. denoted as , representing the annual precipitation (mm) of the sub-region corresponding to sample x.

[0052] The ratio of vegetation evapotranspiration to precipitation was simulated using the Budyko curve function, and the formula is as follows:

[0053] In the formula, This represents the potential evapotranspiration (mm) of the subregion corresponding to sample x in ecosystem j. The parameters are adjusted to reflect the ability of natural climate and soil characteristics to regulate the evapotranspiration process.

[0054] The potential evapotranspiration is calculated as follows:

[0055] In the formula, It represents the vegetation evapotranspiration coefficient, which is determined by the moderating effect of different land use types on evapotranspiration; The reference evapotranspiration (mm) represents the subregion corresponding to sample x.

[0056]

[0057] In the formula, The effective water content (mm) of the plant in the subregion corresponding to sample x is determined by the product of the vegetation available water capacity (PAWC) and the minimum value of the vegetation root restriction depth and the effective root depth. The Z-value is a seasonal factor that characterizes the relationship between precipitation and other water temperature characteristics. It is determined by comparing simulation results with actual conditions. In one specific embodiment, the Z-value is set to 19.3. Under this condition, the model results match the data in the annual water resources bulletins of the study area.

[0058]

[0059]

[0060] In the formula, Let x be the maximum soil depth in the sub-region corresponding to sample x. Let x be the root depth of the subregion corresponding to sample x. The available water content for plants in the subregion corresponding to sample x. , , , These represent the contents of sand, silt, clay, and organic carbon in the sub-region corresponding to sample x, respectively.

[0061] Based on the water yield simulation results, and combined with digital elevation model (DEM) data, the runoff path and topographic index (TI) of the raster cells are calculated. The residence time of runoff on the surface is calculated using parameters such as soil saturated hydraulic conductivity and surface runoff velocity coefficient. The regional water conservation capacity R is further calculated using the following formula:

[0062] In the formula, For water conservation capacity, The surface velocity coefficient, For terrain index, For soil saturated hydraulic conductivity, This refers to the water production.

[0063] In an optional embodiment, this invention provides a method for assessing soil conservation services in urban ecosystems based on the InVEST model. Soil conservation refers to the ecological function of an ecosystem in effectively reducing rainfall erosion and controlling soil loss through vegetation cover, topographic structure, and surface processes, thereby achieving soil and water conservation. This invention utilizes the Sediment Delivery Ratio (SDR) module in the InVEST model to assess soil conservation services in the study area. This module, based on the Revised Universal Soil Loss Equation (RUSLE), estimates the potential soil erosion (RKLS) and the actual soil loss (USLE) under vegetated conditions. The difference between the two is the service assessment result of soil conservation services. For example, as shown... Figure 5 The figure shows the soil retention in different spatial units within the target area in different years.

[0064] The formula for calculating the service assessment results of soil conservation services is as follows:

[0065] In the formula, For soil retention in the study area, This represents the potential soil erosion in bare land conditions. The figures represent actual soil erosion, all in tons (ha / a). -1 .

[0066] The formulas for calculating potential soil erosion and actual soil loss are as follows:

[0067]

[0068] In the formula, The erosivity factor is the rainfall erosivity factor (unit: MJ·mm·(ha·h·a)). -1 ); Soil erodibility factor (unit: t·ha·h·(ha·MJ·mm)); The slope-length factor (dimensionless) is calculated using DEM data; Vegetation cover was calculated using NDVI data, with vegetation cover and management factors (dimensionless). Soil conservation measures factor (dimensionless).

[0069] Rainfall erosivity factor in the model The calculation formula is as follows:

[0070] In the formula, For the first Annual rainfall (mm) and The coefficients of determination for the annual rainfall model are 0.0534 and 1.6548, respectively.

[0071] Soil erodibility factors The calculation formula is as follows:

[0072] in, As an intermediate variable determined by soil particle composition and organic carbon content, the specific calculation formula is as follows:

[0073] In the formula, , , The contents of sand, powder, and clay particles are respectively (%). The percentage content of soil organic carbon is equal to the soil organic matter content divided by 1.724; 0.

[0074] In an optional embodiment, this invention provides a method for assessing urban ecosystem carbon sequestration services based on the InVEST model. The total carbon storage of the target area and corresponding sub-areas of each sample at different time periods is used as the service assessment result of carbon sequestration services for the target area and each sample at different time periods. Carbon sequestration refers to the function of an ecosystem in absorbing atmospheric carbon dioxide through plant photosynthesis, synthesizing organic matter, and fixing carbon in plants and soil, thereby reducing the concentration of atmospheric carbon dioxide. This invention utilizes the Carbon Storage and Sequestration (CSS) module in the InVEST model to quantitatively assess the carbon storage and carbon sequestration service function of different land use types within the study area. This module divides ecosystem carbon storage into four basic carbon pools: aboveground biogenic carbon, belowground biogenic carbon, soil carbon, and dead organic carbon. Aboveground biogenic carbon is the carbon in all surviving plants above the soil; belowground biogenic carbon is the carbon in the living root system of plants; soil carbon is the organic carbon in mineral and organic soils; and dead organic carbon is the carbon in litter, deadwood, and garbage. The carbon density per unit area for each land use type is determined by summing the carbon densities of the above four carbon pools. The calculation formula is as follows:

[0075] In the formula, This represents the carbon density per unit area (t / ha). , , , The carbon density values ​​(t / ha) are for aboveground biomass carbon, belowground biomass carbon, soil carbon, and dead organic carbon, respectively.

[0076] The total carbon storage in the study area is calculated by weighting the carbon density of different land use types with their area, as shown in the following formula:

[0077] In the formula, Indicates the first Area (ha) of each land use type. This represents the total carbon density per unit area (t / ha) for the corresponding land use type. This refers to the number of land use types.

[0078] For example, such as Figure 6 The figure shows the carbon storage in different spatial units within the target region in different years.

[0079] In the InVEST CSS model, the carbon density of a particular land use type is usually considered a constant. In this invention, carbon density data are derived from literature, with measured or estimated data from southern regions, particularly the Yangtze River Delta, selected whenever possible. Soil carbon density values ​​are based on the average values ​​of existing regional studies; other carbon density values ​​are adjusted based on data from neighboring regions. The final carbon density values ​​for different land use types are shown in Table 2.

[0080] Table 2 Carbon density values ​​for each land use type in the study area (unit: t / ha)

[0081] In one optional embodiment, this invention provides a method for assessing urban ecosystem water purification services based on the InVEST model. Water purification refers to the function of an ecosystem in reducing the concentration of pollutants in water and purifying the aquatic environment through physical and biochemical processes such as adsorption, degradation, and biological absorption. This invention uses the Nutrient Delivery Ratio (NDR) module of the InVEST model to quantify the purification capacity of urban ecosystems for nitrogen (N) and phosphorus (P) elements in runoff. First, watershed hydrological analysis is performed using DEM data to extract spatial elements such as flow direction, flow rate, river chain, and catchment area. Then, based on the nutrient loading coefficients of various land use types, the nitrogen and phosphorus output of each sub-region unit is estimated. Combining the interception capacity of different vegetation types, the deposition and retention levels of nitrogen and phosphorus during the migration process from upstream to downstream are simulated to obtain the spatial distribution of nutrient output in each sub-region within the study area. The higher the average nitrogen and phosphorus output of a sub-region, the worse the water purification service function.

[0082] In the model, the total nutrient output of the study area is the sum of the outputs of all sub-regions within the watershed, calculated using the following formula:

[0083]

[0084] In the formula, The total nutrient output of the watershed, For the first Nutrient output of each sample corresponding to a subregion, in kg·a -1 . and These are the surface and underground nutrient loads, respectively, in kg·ha. -1 ·a -1 . and These represent the surface and underground nutrient output rates, respectively.

[0085] Nutrient loading consists of two parts: surface runoff and groundwater runoff, representing the nutrient output from the sediment-bound and dissolved portions, respectively. The calculation formula is as follows:

[0086]

[0087]

[0088]

[0089] In the formula, This represents the proportion of underground nutrient load to total nutrient load and is applicable to nitrogen calculations; phosphorus is typically transported primarily through the surface. For the first Nutrient load adjusted for the sub-region corresponding to each sample For the first Nutrients in the sub-region corresponding to each sample The initial load, It is the first The potential runoff index of the sub-region corresponding to each sample For the first Nutrient runoff index for each sample's corresponding sub-region This refers to the average runoff index of the sub-region corresponding to this sample. In practical applications, It is often defined as the rapid flow index or precipitation.

[0090] The formula for calculating Nutrient Extraction Rate (NDR) is as follows:

[0091] In the formula, and To correct the parameters, For terrain factors, Indicates the first The proportion of nutrients in a sub-region corresponding to a sample that was not retained by the downstream raster is calculated using the following formula:

[0092] In the formula, For the first The maximum nutrient retention efficiency of a sub-region corresponding to a sample is calculated using the following formula:

[0093] In the formula, For directly located in the first Effective nutrient retention efficiency of the downstream subregion corresponding to each sample. For the first The maximum nutrient retention efficiency that a sub-region corresponding to a sample can achieve. The step size factor is calculated using the following formula:

[0094] In the formula, It is the first The distance from the sub-region corresponding to each sample to its downstream sub-region For the first The intercept length corresponding to the land use type in the sub-region of each sample.

[0095] The biophysical parameters related to nutrient (N, P) output were set with reference to relevant literature and in consideration of the actual conditions of the study area, as detailed in Table 3. Unit load ( ), retention efficiency ( ) and maximum interception distance ( All parameters are assigned values ​​based on land use type. Parameters K and subsurface critical length are set to 2 and 200, respectively, and the grid-level cumulative flow threshold for the study area is set to 1000 to determine the effective water catchment range.

[0096] Table 3. Nutrient load and retention efficiency parameters of nitrogen (N) and phosphorus (P) for each land use type in the study area.

[0097] For example, such as Figure 7 The figure shows the TN output of different spatial units within the target region in different years, such as... Figure 8 The figure shows the TP output of different spatial units within the target area in different years.

[0098] In one optional embodiment, this invention provides a method for assessing urban ecosystem habitat quality services based on the InVEST model, aiming to evaluate the ecosystem's capacity to maintain biodiversity. This method utilizes the Habitat Quality (HQ) module in the InVEST model to assess habitat degradation and habitat quality levels in the study area. The HQ module, based on land use / land cover (LULC) type and considering ecological threat factors, assesses habitat quality levels at different scales. Areas with higher habitat quality levels typically have higher species richness; conversely, habitat degradation leads to a decline in biodiversity. The data required for the HQ module includes: land use / land cover data (LULC), threat factor layers, threat factor tables, relative habitat sensitivity to threat factors, and protected area data. The habitat quality calculation formula is as follows:

[0099] In the formula, For LULC type j in the first The habitat quality of each sample corresponds to a sub-region, ranging from [0, 1]. A larger value indicates higher habitat quality. is the habitat suitability coefficient for LULC type j, ranging from [0, 1], where 0 represents non-habitat and 1 represents the highest habitat suitability; For LULC type j in the first The habitat degradation level of each sample corresponding to a sub-region; This is a normalization constant, with a default value of 2.5; This is the half-saturation constant, with a default value of 0.05. Using this model typically requires calculating habitat quality twice, the first time... Set to 0.05, second time. Take half of the maximum habitat degradation value from the first calculation result.

[0100] The formula for calculating habitat degradation level is as follows:

[0101] During linear decay,

[0102] During exponential decay,

[0103] In the formula, The number of threat factors; Threat factor The total number of samples; Threat factor The weight of the value ranges from [0, 1], and the larger the value, the greater the threat to habitat integrity. The impact of threat factor r on habitat sample x in sample y is affected by distance, and the attenuation modes include linear attenuation and exponential attenuation, as shown in formulas 30 and 31. The accessibility coefficient of sample x is represented, ranging from [0, 1], where 0 indicates that it is protected and cannot be entered, and 1 indicates that it can be fully entered; The sensitivity of LULC type j to threat factor r is given by a value of [0, 1], where a larger value indicates greater sensitivity. The distance between habitat raster sample x and threat factor sample y; This represents the maximum influence distance of the threat factor r.

[0104] Habitat types selected were land use types that support species survival: woodland, water areas, grassland, and cultivated land. The suitability of each habitat, its relative sensitivity to threat factors, and the scope and weight of threat factors were determined based on expert opinions and relevant literature, as shown in Tables 4 and 5.

[0105] Table 4. Maximum Influence Distance and Weight of Threat Factors

[0106] Table 5 Habitat suitability and relative sensitivity to threat factors

[0107] For example, such as Figure 9 The figure shows the habitat quality index of different spatial units within the target area in different years.

[0108] In one optional embodiment, for leisure tourism services, this invention provides a method for evaluating urban ecosystem cultural services based on the maximum entropy (MaxEnt) model. Cultural services refer to the non-material benefits that humans obtain from an ecosystem through tourism and leisure activities such as spiritual experiences, knowledge acquisition, leisure and aesthetic experiences, and health and wellness. This invention uses the MaxEnt model to evaluate the capacity of urban ecosystem cultural services (CES) based on natural geographic data, cultural service POI data, and social survey data.

[0109] The cultural service dataset consists of Points of Interest (POIs) for scenic spots and historical sites. For example, this embodiment of the invention obtains POIs from 2010 and 2020 through the APIs of Gaode Maps and Baidu Maps. Combining attribute and keyword filtering methods, relevant categories such as scenic spots, tourist attractions, parks, and squares are selected, ultimately yielding 927 (2010) and 1269 (2020) valid cultural service point data points, respectively. The data points are categorized into three types based on their service characteristics: natural landscape value, leisure and entertainment value, and scientific and educational cultural value.

[0110] Environmental Variable Selection and Processing. Based on the CES indicator system proposed by the World Conservation Monitoring Centre (WCMC, 2010), this study selected the following environmental variables: natural condition indicators including elevation (DEM), slope (SLOPE), and normalized difference vegetation index (NDVI); and anthropogenic condition indicators including land use / cover (LULC), distance to road (DTR), and distance to water (DTW). To avoid multicollinearity, correlation analysis was performed on the environmental variables. The results showed that, except for elevation and slope, which had a relatively high correlation, the correlations among the other variables were all less than 0.45.

[0111] The cultural service capacity of urban ecosystems was assessed using the Maxent model. The Maxent model, based on the principle of maximizing information entropy, infers the most probable spatial distribution of cultural services under known samples and environmental constraints. Its information entropy calculation formula is as follows:

[0112] In the formula, This represents environmental variables, i.e., independent variables; for The probability of occurrence; Let be the entropy value. The probability distribution that satisfies the maximum entropy principle is:

[0113] This model maintains high accuracy even with limited sample data. The accuracy of the MaxEnt model is evaluated using the area under the receiver operating characteristic (ROC) curve (AUC). The accuracy of the model's predictions is directly proportional to the AUC value, with the following evaluation criteria: AUC values ​​of 0.9–1 indicate excellent predictions; 0.8–0.9 are good; 0.7–0.8 are average; 0.6–0.7 are poor; and <0.6 indicates failure. The MaxEnt model outputs the probability value for each sample. The strength of suitability for providing cultural services to the area under current environmental conditions; the higher the value, the more likely the grid is to provide a higher level of cultural services.

[0114] For example, such as Figure 10 The figure shows the cultural service index of different spatial units within the target area in different years.

[0115] In an optional embodiment, the pairwise trade-off synergies calculated in step S204 include overall static trade-off synergies, overall dynamic trade-off synergies, local trade-off synergies, and local dynamic trade-off synergies. Step S204, which calculates the pairwise trade-off synergies of various ecosystem services at multiple spatial scales and multiple time series based on the service assessment results of each ecosystem service in the target area and each sample at different time periods, specifically includes: Step a1: Calculate the overall static trade-off synergies of various ecosystem services based on the service assessment results of various ecosystem services in the target area within the same time period.

[0116] In an optional embodiment, step a1 specifically includes: Step a11: Calculate the correlation coefficients between pairs of ecosystem services based on the service assessment results of various ecosystem services in the target area during the same time period.

[0117] In an optional embodiment, the correlation coefficient between any two ecosystem services refers to the correlation coefficient between any two ecosystem services. In this embodiment of the invention, for each ecosystem service, the correlation coefficient between the ecosystem service and other ecosystem services is calculated, and the overall static trade-off synergy relationship between the ecosystem service and other ecosystem services is calculated based on relevant technologies.

[0118] In an optional embodiment, when the ecosystem services follow a normal distribution, the Pearson correlation coefficient is used to assess the linear correlation between services; when the normal distribution assumption is not met, the Spearman rank correlation coefficient is used to determine their rank correlation.

[0119] Step a12: Compare the correlation coefficient with the preset significance threshold. Based on the comparison results, determine whether the overall static trade-off synergy between any two ecosystem services is not significant, or a synergy, or a trade-off.

[0120] In an optional embodiment, if step a11 calculates the Pearson correlation coefficient between two ecosystem services, then it is compared with the significance threshold corresponding to the Pearson correlation coefficient; if step a11 calculates the Spearman rank n correlation coefficient between two ecosystem services, then it is compared with the significance threshold corresponding to the Spearman rank correlation coefficient.

[0121] In one optional embodiment, if the absolute value of the correlation coefficient is less than the significance threshold, the overall static trade-off synergy between the two types of ecosystem services is determined to be non-significant; if the absolute value of the correlation coefficient is greater than or equal to the significance threshold and the correlation coefficient is greater than 0, the overall static trade-off synergy between the two types of ecosystem services is determined to be synergistic; if the absolute value of the correlation coefficient is greater than or equal to the significance threshold and the correlation coefficient is less than 0, the overall static trade-off synergy between the two types of ecosystem services is determined to be a trade-off.

[0122] Step a2: Calculate the overall dynamic trade-off and synergy of various ecosystem services based on the changes in the service assessment results of various ecosystem services in the target area at different time periods.

[0123] In an optional embodiment, step a2 specifically includes: Step a21: Calculate the correlation coefficients between pairs of ecosystem services based on the changes in the service assessment results of various ecosystem services in the target area at different time periods.

[0124] In this embodiment of the invention, for each ecosystem service, the correlation coefficient between the ecosystem service and other ecosystem services is calculated based on the amount of change, and the overall dynamic trade-off and synergistic relationship between the ecosystem service and other ecosystem services is calculated based on relevant technologies.

[0125] In one alternative embodiment, when the changes in various ecosystem services follow a normal distribution, the Pearson correlation coefficient is used to assess the dynamic correlation between services; when the normal distribution assumption is not met, the Spearman rank correlation coefficient is used to determine their rank correlation.

[0126] Step a22: Compare the correlation coefficient with the preset significance threshold, and determine the overall static trade-off synergy between the two ecosystem services based on the comparison results: no significant relationship, synergy, or trade-off.

[0127] In an optional embodiment, if step a21 calculates the Pearson correlation coefficient between two ecosystem services, then it is compared with the significance threshold corresponding to the Pearson correlation coefficient; if step a21 calculates the Spearman rank n correlation coefficient between two ecosystem services, then it is compared with the significance threshold corresponding to the Spearman rank correlation coefficient.

[0128] In one optional embodiment, if the absolute value of the correlation coefficient is less than the significance threshold, the overall dynamic trade-off synergy between the two types of ecosystem services is determined to be non-significant; if the absolute value of the correlation coefficient is greater than or equal to the significance threshold and the correlation coefficient is greater than 0, the overall dynamic trade-off synergy between the two types of ecosystem services is determined to be synergistic; if the absolute value of the correlation coefficient is greater than or equal to the significance threshold and the correlation coefficient is less than 0, the overall dynamic trade-off synergy between the two types of ecosystem services is determined to be a trade-off.

[0129] Step a3: For different sample sets, calculate the local static trade-off synergies of various ecosystem services at different spatial scales based on the service assessment results of each sample within the same time period.

[0130] In an optional embodiment, step a3 specifically includes: Step a31: Identify multiple service pairs consisting of various ecosystem services, with one service pair corresponding to two ecosystem services.

[0131] If the service assessment results of each ecosystem service follow a normal distribution, proceed to steps a32 and a33; if the service assessment results of each ecosystem service do not follow a normal distribution, proceed to steps a34 and a35.

[0132] Step a32: Calculate the deviation product of the service pair in the current sample based on the service assessment results of the ecosystem services in the current sample and the service assessment results of other samples in the current sample set.

[0133] In an optional embodiment, a service pair corresponds to a first ecosystem service and a second ecosystem service. The deviation product of the service pair in the current sample is the product of the difference between the service evaluation result of the first ecosystem service in the current sample and the average value of the first ecosystem service in the current sample set, and the difference between the service evaluation result of the second ecosystem service and the average value of the second ecosystem service in the current sample set. ,in, Serving the primary ecosystem in the current sample The service evaluation results in the middle, The average value of serving the first ecosystem in the current sample set. Serving the second ecosystem in the current sample The service evaluation results in the middle, The average value of services provided to the second ecosystem in the current sample set.

[0134] Step a33: Determine the critical value of the correlation coefficient based on the sample size and the preset significance level, and calculate the critical value of the local covariance judgment accordingly. Compare the deviation product with the critical value of the local covariance judgment, and determine the local static trade-off relationship of the service pair in the current sample as either non-significant, a trade-off relationship, or a synergistic relationship.

[0135] In an optional embodiment, based on the sample size and a preset significance level (e.g. =0.05), determining the critical values ​​of the Pearson correlation coefficient for determining significant positive and negative correlations between service pairs. and ; According to the Pearson correlation coefficient formula:

[0136] Based on the above critical values, the corresponding local covariance determination critical values ​​are derived. and ; critical value and The calculation formulas are as follows:

[0137]

[0138] In the formula, The critical value for positive correlation significance is calculated using the following formula: , where n is the number of samples; The critical value for negative correlation is calculated using the following formula: ; , The standard deviations of the two service variables are given.

[0139] like Determine if a local static trade-off collaboration relationship is a collaboration relationship; if Determine if a local static trade-off relationship is a trade-off relationship; if If the local static trade-off synergy relationship is determined to be non-significant, then it is determined that there is no significant relationship.

[0140] Step a34: Calculate the rank difference of the service pair in the current sample based on the service assessment results of each ecosystem service in the current sample and the ranking results in the sample set.

[0141] In one optional embodiment, the service assessment results of each ecosystem service are sorted in ascending or descending order, and a rank is assigned (if values ​​are the same, an average rank is assigned), and the rank difference between each unit service is calculated. .

[0142] Step a35: Determine the critical value of the correlation coefficient and the critical value of the rank difference judgment based on the preset significance level and the number of samples. Compare the rank difference with the critical value of the average rank difference judgment. Based on the comparison result, determine whether the local static trade-off relationship of the service pair in the current sample is not significant, or a trade-off relationship, or a synergistic relationship.

[0143] In an alternative embodiment, the critical value of the Spearman correlation coefficient for positive and negative correlations is determined based on the sample size and significance level. and And according to the Spearman correlation coefficient formula:

[0144] Derive the corresponding critical value of the average rank difference. and .

[0145] Rank difference critical value and The calculation formulas are as follows:

[0146]

[0147] In the formula, This is the critical value for positive correlation significance; This is the critical value for significant negative correlation; This refers to the sample size, which is also the number of spatial units.

[0148] like If so, the local static trade-off collaboration relationship is determined to be a collaboration relationship; If so, the local static trade-off relationship is determined to be a trade-off relationship; If the local static trade-off synergy relationship is determined to be non-significant, then it is determined that there is no significant relationship.

[0149] Step a4: For different sample sets, calculate the local dynamic trade-offs and synergies of various ecosystem services at different spatial scales based on the changes in the service assessment results of various ecosystem services in different time periods for each sample.

[0150] In an optional embodiment, step a4 specifically includes: Step a41: Identify multiple service pairs consisting of various ecosystem services, with each service pair corresponding to two ecosystem services.

[0151] Step a42, based on the direction of change in the service assessment results of the ecosystem services in the service pair over different time periods in the current sample.

[0152] In an alternative embodiment, the changes in various ecosystem services can be reclassified to determine three different directions of change: if the change... 0, then =1 indicates the first direction of change; if the change amount 0, then =0 indicates the second direction of change; if the change amount 0, then =-1 indicates the third direction of change, where , representing n ecosystem services.

[0153] Step a43: Based on the direction of change of the two ecosystem services in the service pair, determine whether the local dynamic trade-off relationship of the service pair in the current sample is not significant, or a synergistic relationship, or a trade-off relationship.

[0154] In an alternative embodiment, if If the changes in the two ecosystem services are in the same direction, then the local dynamic trade-off relationship is determined to be a synergistic relationship; if If the changes in the two ecosystem services are in opposite directions, then the local dynamic trade-off relationship is determined to be a trade-off relationship; if This indicates that at least one ecosystem service has not changed significantly, and the local dynamic trade-off synergy is determined to be without significant correlation.

[0155] In one specific embodiment, the Spearman Correlation heatmaps of various ecosystem services obtained by performing steps a1-a4 above at different time periods and spatial scales are as follows: Figure 11 As shown, the Spearman Correlation heatmaps of the changes in various ecosystem services at different spatial scales are as follows: Figure 12 As shown.

[0156] In one specific embodiment, the local static trade-off and synergy relationships between carbon sequestration services and leisure tourism services at different time periods and scales are as follows: Figure 13 As shown.

[0157] In an optional embodiment, step S205 specifically includes the following steps: Step b1: Determine the sum of squared intra-cluster errors corresponding to different numbers of clusters using the elbow rule, and plot the curves. Step b2: Based on the curve, determine the multiple inflection points with the largest error decrease rate, and determine the number of multiple candidate clusters based on the inflection points.

[0158] Step b3: Calculate the silhouette coefficients corresponding to the number of each candidate cluster.

[0159] In an optional embodiment, the silhouette coefficient is used to comprehensively evaluate the inter-class separation and intra-class consistency of the clustering results.

[0160] Step b4: The number of candidate clusters corresponding to the silhouette coefficient closest to 1 is taken as the target number of clusters.

[0161] In this embodiment of the invention, the number of clusters that perform well with both the elbow method and the contour coefficient is selected as the input parameter of the self-organizing map model, which can ensure the stability and ecological interpretability of the service cluster partitioning.

[0162] Step b5: Construct the model architecture and training parameters of the self-organizing map model, wherein the model architecture is constructed based on the target number of clusters.

[0163] In one alternative embodiment, the number of neurons in the self-organizing map model is determined based on the target number of clusters. For example, if the target number of clusters is 5, then the number of neurons in the model architecture is 5.

[0164] In an optional embodiment, when constructing training parameters, it is necessary to set an initial neighborhood radius and fix a random seed. For example, the initial neighborhood radius can be set to 1 and the random seed can be fixed (set.seed = 2022) to ensure the repeatability of model training.

[0165] Step b6: Based on the similarity between each sample and each neuron in the self-organizing map model, the self-organizing map model is iteratively trained through a competitive learning mechanism and a neighborhood weight update strategy.

[0166] In an alternative embodiment, Euclidean distance can be used to measure the similarity between samples and neurons.

[0167] In an optional embodiment, since all samples are clustered in this embodiment of the invention, and each sample is obtained by segmenting the target region using different spatial scales, it is necessary to perform Z-score standardization on the ecosystem service data at different spatial scales before clustering the samples to eliminate the influence of dimensions and enhance comparability.

[0168] Step b7: Obtain the code vector of each neuron in the trained self-organizing map model, and assign each sample to the corresponding neuron to obtain multiple service clusters.

[0169] In one specific embodiment, when performing steps b1-b4 above, setting the cluster number to 6 results in the following service clusters: Figure 14 As shown.

[0170] In this embodiment of the invention, based on the results of high-resolution ecosystem service assessment, a self-organizing mapping model is introduced to identify service clusters, characterize the clustering and combination features of service functions within the city, and provide support for differentiated ecological management and zoning governance.

[0171] In this embodiment of the invention, a self-organizing mapping model is used to perform cluster analysis on multiple ecosystem service indicators at different time periods and spatial scales to divide service clusters and identify the composite spatial distribution characteristics of ecosystem services. A service cluster refers to a combination of ecosystem services that repeatedly occur in geographic space, which can be used to identify the synergistic characteristics between services, thereby enabling the joint management of multiple ecosystem services.

[0172] This embodiment also provides an urban ecosystem service analysis device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0173] This embodiment provides an urban ecosystem service analysis device, such as... Figure 15 As shown, it includes: The multi-scale sample acquisition module 1501 is used to divide the target region according to different spatial scales to obtain sample sets corresponding to each spatial scale. Each sample set contains multiple samples, and each sample corresponds to a sub-region obtained after dividing the target region. Information acquisition module 1502 is used to acquire basic geographic information data of the target area at different time periods; The service assessment module 1503 is used to calculate the service assessment results of various ecosystem services in the target area and for each sample at different time periods based on basic geographic information data. The pairwise relationship identification module 1504 is used to calculate the pairwise trade-off and synergistic relationships of various ecosystem services at multiple spatial scales and multiple time series based on the service assessment results of various ecosystem services in the target area and each sample at different time periods. The clustering module 1505 is used to cluster the samples according to the service assessment results of various ecosystem services in multiple time periods, and obtain multiple service clusters. The service clusters are used to characterize the overall trade-off and synergistic features among multiple ecosystem services. Management module 1506 is used to determine the management strategies for each ecosystem service based on the pairwise trade-offs and overall trade-offs of each ecosystem service.

[0174] The urban ecosystem service analysis device provided in this embodiment of the invention can execute the urban ecosystem service trade-off and synergy analysis method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0175] Figure 16 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0176] The following is a detailed reference. Figure 16 The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 1601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1602 or a program loaded from memory 1608 into random access memory (RAM) 1603. The RAM 1603 also stores various programs and data required for the operation of the electronic device. The processor 1601, ROM 1602, and RAM 1603 are interconnected via a bus 1604. An input / output (I / O) interface 1605 is also connected to the bus 1604.

[0177] Typically, the following devices can be connected to the I / O interface 1605: input devices 1606 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 1607 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; memory devices 1608 including, for example, magnetic tape, hard disk, etc.; and communication devices 1609. Communication device 1609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 16 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0178] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1609, or installed from a memory 1608, or installed from a ROM 1602. When the computer program is executed by the processor 1601, it performs the functions defined in the urban ecosystem service trade-off and synergy analysis method of the embodiments of the present invention.

[0179] Figure 16 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0180] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the urban ecosystem service trade-off and synergy analysis method shown in the above embodiments is implemented.

[0181] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0182] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for analyzing trade-offs and synergies in urban ecosystem services, characterized in that, The method includes: The target region is divided according to different spatial scales to obtain sample sets corresponding to each spatial scale. Each sample set contains multiple samples, and each sample corresponds to a sub-region obtained after dividing the target region. Obtain basic geographic information data of the target area at different time periods; Based on the aforementioned basic geographic information data, the service assessment results of various ecosystem services in the target area and for each sample at different time periods are calculated. Based on the service assessment results of various ecosystem services in the target area and each sample at different time periods, the pairwise trade-offs and synergies of various ecosystem services at multiple spatial scales and multiple time series are calculated. Based on the service assessment results of various ecosystem services in multiple time periods, all samples are clustered to obtain multiple service clusters. These service clusters are used to characterize the overall trade-off and synergistic features among multiple ecosystem services. Management strategies for each ecosystem service are determined based on the pairwise trade-offs and overall trade-offs among them.

2. The method according to claim 1, characterized in that, The ecosystem services mentioned include multiple services such as food supply services, water conservation services, soil conservation services, carbon sequestration services, water purification services, habitat quality services, and leisure tourism services.

3. The method according to claim 1, characterized in that, The pairwise trade-off and synergy relationships include overall static trade-off and synergy relationships, overall dynamic trade-off and synergy relationships, local trade-off and synergy relationships, and local dynamic trade-off and synergy relationships. The calculation of pairwise trade-off and synergy relationships for each ecosystem service at multiple spatial scales and multiple time series, based on the service assessment results of each ecosystem service in the target area and for each sample at different time periods, includes: Calculate the overall static trade-off and synergy of various ecosystem services based on the service assessment results of various ecosystem services in the target area during the same time period; The overall dynamic trade-off and synergistic relationship of each ecosystem service is calculated based on the changes in the service assessment results of each ecosystem service in the target area over different time periods. For different sample sets, the local static trade-offs and synergies of various ecosystem services at different spatial scales are calculated based on the service assessment results of each ecosystem service in the same time period for each sample. For different sample sets, the local dynamic trade-offs and synergies of various ecosystem services at different spatial scales are calculated based on the changes in the service assessment results of various ecosystem services in different time periods for each sample.

4. The method according to claim 3, characterized in that, The calculation of the overall static trade-offs and synergies of various ecosystem services based on the service assessment results of various ecosystem services in the target area within the same time period includes: Calculate the correlation coefficients between any two ecosystem services based on the service assessment results of various ecosystem services in the target area during the same time period; The correlation coefficient is compared with a preset significance threshold. Based on the comparison results, the overall static trade-off synergy between any two ecosystem services is determined to be either non-significant, synergistic, or trade-off.

5. The method according to claim 3, characterized in that, The calculation of the overall dynamic trade-offs and synergies of various ecosystem services based on the changes in the service assessment results of various ecosystem services in the target area over different time periods includes: Calculate the correlation coefficients between any two ecosystem services based on the changes in the service assessment results of various ecosystem services in the target area over different time periods. The correlation coefficient is compared with a preset significance threshold. Based on the comparison results, the overall static trade-off synergy between any two ecosystem services is determined to be either non-significant, synergistic, or trade-off.

6. The method according to claim 3, characterized in that, For any given sample set, the steps for calculating the local static trade-offs and synergies of various ecosystem services at the spatial scale corresponding to the current sample set, based on the service assessment results of various ecosystem services in each sample within the same time period, include: Identify multiple service pairs that comprise various ecosystem services, with one service pair corresponding to two ecosystem services; If the service assessment results of each ecosystem service follow a normal distribution, calculate the deviation product of the service pair in the current sample based on the service assessment results of the ecosystem services in the current sample and the service assessment results in other samples in the current sample set; determine the critical value of the correlation coefficient based on the sample size and the preset significance level, and calculate the critical value of the local covariance judgment accordingly; compare the deviation product with the critical value of the local covariance judgment, and determine the local static trade-off synergy relationship of the service pair in the current sample based on the comparison result as follows: no significant relationship, synergy relationship, or trade-off relationship. If the service assessment results of each ecosystem service do not follow a normal distribution, then the rank difference of the service pair in the current sample is calculated based on the service assessment results of each ecosystem service in the current sample and its ranking in the sample set; the critical value of the correlation coefficient and the critical value of the rank difference are determined according to the preset significance level and the number of samples; the rank difference is compared with the critical value of the rank difference, and the local static trade-off synergy relationship of the service pair in the current sample is determined to be either non-significant, synergistic, or trade-off based on the comparison result.

7. The method according to claim 3, characterized in that, For any given sample set, the steps for calculating the local dynamic trade-offs and synergies of various ecosystem services at the spatial scale corresponding to the current sample set, based on the changes in the service assessment results of various ecosystem services in each sample over different time periods, include: Identify multiple service pairs that comprise various ecosystem services, with one service pair corresponding to two ecosystem services; Based on the changing direction of the service evaluation results of the ecosystem services in the service pair at different time periods in the current sample; Based on the direction of change of the two ecosystem services in the service pair, it is determined that the local dynamic trade-off relationship of the service pair in the current sample is either non-significant, a synergistic relationship, or a trade-off relationship.

8. The method according to claim 1, characterized in that, The samples are clustered according to the service assessment results of various ecosystem services across multiple time periods, resulting in multiple service clusters, including: The sum of squared intra-cluster errors corresponding to different numbers of clusters was determined using the elbow rule, and curves were plotted. Based on the curve, determine multiple inflection points with the largest error decrease rate, and based on the inflection points, determine multiple candidate cluster numbers; Calculate the silhouette coefficient corresponding to the number of each candidate cluster; The number of candidate clusters corresponding to the silhouette coefficient closest to 1 is taken as the target number of clusters; Construct the model architecture and training parameters of the self-organizing map model, wherein the model architecture is constructed based on the target number of clusters; Based on the similarity between each sample and each neuron in the self-organizing map model, the self-organizing map model is iteratively trained through a competitive learning mechanism and a neighborhood weight update strategy. Obtain the code vectors of each neuron in the trained self-organizing map model, and assign each sample to the corresponding neuron to obtain multiple service clusters.

9. A device for analyzing trade-offs and synergies in urban ecosystem services, characterized in that, The device includes: The multi-scale sample acquisition module is used to divide the target region according to different spatial scales to obtain sample sets corresponding to each spatial scale. Each sample set contains multiple samples, and each sample corresponds to a sub-region obtained after dividing the target region. The information acquisition module is used to acquire basic geographic information data of the target area at different time periods; The service assessment module is used to calculate the service assessment results of various ecosystem services in the target area and for each sample at different time periods based on the basic geographic information data. The pairwise relationship identification module is used to calculate the pairwise trade-off and synergistic relationships of various ecosystem services at multiple spatial scales and multiple time series based on the service assessment results of various ecosystem services in the target area and each sample at different time periods. The clustering module is used to cluster the samples according to the service assessment results of various ecosystem services in multiple time periods to obtain multiple service clusters. The service clusters are used to characterize the overall trade-off and synergistic features among multiple ecosystem services. The management module is used to determine the management strategies for each ecosystem service based on the pairwise trade-offs and overall trade-offs characteristics of each ecosystem service.

10. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the ecosystem service analysis method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the ecosystem service analysis method according to any one of claims 1 to 8.

12. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the ecosystem service analysis method according to any one of claims 1 to 8.

Images