Bayesian-based ecological system service space tradeoff collaborative optimization method and device

Identifying hot spots for coastal wetland ecosystem service coordination and trade-offs through Bayesian network model, solving the problem of the inability to optimize ecosystem service coordination in the existing technology, and realizing spatial optimization and scientific management of ecosystem services.

CN118917466AActive Publication Date: 2024-11-08XIAMEN UNIV

Patent Information

Application Number
CN202410962953.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-08
Estimated Expiration
2044-07-18

AI Technical Summary

Technical Problem

The existing technology cannot accurately identify hot spots in China's coastal wetland ecosystem service coordination and trade-offs, and cannot effectively optimize the ecosystem service coordination relationship of coastal wetlands, affecting ecological protection and restoration work.

Method used

Using Bayesian-based ecosystem service space trade-off collaborative optimization method, by obtaining ecological space database, calculating blue carbon storage, biodiversity maintenance capabilities and coastal protection capabilities, combining natural and social factors, a Bayesian network model is constructed and identified Key drivers and potential areas of collaboration for ecosystem services.

Benefits of technology

The spatial optimization of ecosystem services has been achieved, the trade-offs and synergy relationships of ecosystem services have been clarified, the impact mechanism of ecosystem services has been clarified, and the scientific reference for ecosystem construction and restoration has been provided, which has promoted global climate change adaptation and biodiversity. promise.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917466A_ABST
    Figure CN118917466A_ABST
Patent Text Reader

Abstract

The invention provides a Bayesian-based ecological system service space tradeoff collaborative optimization method and device, and relates to the field of ecology and statistics. According to the method, an ecological space database of a target area is obtained, a fishing net tool and a cutting tool of ArcGIS software are adopted to generate a grid layer with a specified size for the target area, and a pixel set of the target area is obtained; according to the ecological space database and the pixel set, calculating the blue carbon reserve, the biodiversity maintenance capability and the coast protection capability of the target area, namely three ecological system services; further, obtaining a coupling coordination degree so as to analyze the overall coordination level between the ecosystem services; and constructing a Bayesian-based ecological system service collaborative prediction model by adopting Networa software, identifying key driving factors, and outputting probability distribution of corresponding nodes so as to simulate and analyze potential collaborative influence under different scenes. The method can accurately identify and clarify the trade-off cooperation relationship of key ecosystem services such as coastal wetlands, and realizes the cooperation space optimization of the ecosystem services.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of ecology and statistical technology, and in particular to a Bayesian-based method and device for collaborative optimization of ecosystem service spatial trade-offs. Background Art

[0002] As an important natural resource for mankind, coastal wetlands provide key ecosystem services such as blue carbon storage, biodiversity maintenance and coastal protection. Exploring the trade-offs and synergies of key ecosystem services in coastal wetlands and revealing the spatial distribution information of synergistic benefits will help optimize resource allocation and improve the protection level of coastal wetlands. However, current research still lacks a national-scale map of key ecosystem services and trade-offs in China's coastal wetlands. More importantly, the synergistic potential of key ecosystem services has not been fully explored, and it is impossible to accurately identify the hotspots of synergy and trade-offs in China's coastal wetland ecosystem services, which poses a challenge to the precise protection and restoration of coastal wetlands. At the same time, considering that ecosystem service functions are affected by the complex interactions between ecosystems and social systems, complex models need to be developed to predict the synergistic potential of ecosystem services by coupling natural, socioeconomic and ecological factors.

[0003] As an important decision support work, Bayesian network can integrate multiple information such as ecological processes and socio-economic activities of ecosystem services and their complex causal relationships based on expert experience and quantitative analysis, effectively infer the possibility of future events and allow cartographic expression to help simulate the synergistic potential between ecosystem services. Therefore, drawing the spatial distribution map of key ecosystem services of blue carbon storage, biodiversity conservation and coastal protection in my country's coastal wetlands, clarifying the spatial trade-off synergy relationship of ecosystem services, exploring the spatial pattern and driving force of coastal wetland ecosystem service synergy, simulating the spatial distribution of potential synergistic areas, and optimizing the spatial pattern of ecosystem service synergy are of great theoretical and practical significance for the smooth implementation of ecological protection and ecological restoration of my country's coastal wetlands and the sustainable management of coastal wetland resources.

[0004] In view of this, the applicant filed this application after studying the existing technology. Summary of the invention

[0005] The present invention aims to provide a Bayesian-based method and device for collaborative optimization of ecosystem service spatial trade-offs, so as to overcome the shortcomings of existing methods such as the inability to accurately identify hotspots of coastal wetland ecosystem service synergy and trade-offs, and to achieve collaborative optimization of key ecosystem services.

[0006] In order to solve the above technical problems, the present invention is implemented through the following technical solutions:

[0007] A Bayesian-based collaborative optimization method for spatial trade-offs of ecosystem services, including:

[0008] S1, obtaining an ecological space database of the target area, wherein the ecological space database includes a basic geographic data set, a blue carbon reserve data set, a species space data set, a climate and environment data set, and a socio-economic data set;

[0009] S2, according to the ecological space database, using the fishing net tool and the clipping tool of ArcGIS software to generate a grid layer of a specified size for the target area to obtain a pixel set of the target area;

[0010] S3, calculating the total biocarbon stock of the target area, i.e., the blue carbon stock, based on the blue carbon stock data set and the pixel set of the target area, combining the aboveground biomass and the underground biomass;

[0011] S4, according to the species spatial data set and the pixel set of the target area, each pixel of the target area is regarded as a spatial unit, and the species richness and rarity range of the target area are obtained, and the biodiversity maintenance capacity of the target area is obtained by spatially superimposing the layers of the species richness and the rarity range; wherein the species richness is the total number of species distributed in each spatial unit; the rarity range is obtained by calculating the weighted sum of the proportion of the species distributed in the spatial unit in the global range area;

[0012] S5, according to the climate and environment data set and the socio-economic data set, the exposure index under different scenarios is estimated using the InVEST model, and the coastal protection capacity of the target area is evaluated by the difference in the relative exposure index under two different scenarios;

[0013] S6, based on the blue carbon storage, biodiversity maintenance capacity and coastal protection capacity, i.e. the three ecosystem services, the coupling coordination degree is obtained to evaluate and analyze the overall coordination level between ecosystem services;

[0014] S7, based on the ecological space database, screen out the exploratory variables that affect the ecosystem services to obtain natural factors and social factors; then use ArcGIS and zoning statistical tools to calculate the natural factors and social factors of the target area pixels;

[0015] S8, using Netica software to build an ecosystem service collaborative prediction model based on a Bayesian network, using the natural breakpoint method to discretize the natural factors, the social factors, the ecosystem services and the coupling coordination degree as input variable nodes of the collaborative prediction model, and outputting the probability distribution of the ecosystem services and the coupling coordination degree nodes;

[0016] S9, based on the probability distribution of the ecosystem service and the coupling coordination degree node, evaluate the impact of natural and social driving factors on ecosystem services and their synergy through sensitivity analysis, identify the key driving factors of ecosystem service synergy and the optimal combination of environmental variables under different synergy scenarios, and simulate the potential synergy areas of ecosystem services under different scenarios.

[0017] The present invention also provides a Bayesian-based ecosystem service spatial trade-off collaborative optimization device, comprising:

[0018] A database acquisition unit, used to acquire an ecological space database of a target area, wherein the ecological space database includes a basic geographic data set, a blue carbon reserve data set, a species space data set, a climate and environment data set, and a socio-economic data set;

[0019] A pixel set generation unit is used to generate a grid layer of a specified size in the target area using the fishing net tool and the clipping tool of the ArcGIS software according to the ecological space database to obtain a pixel set of the target area;

[0020] A blue carbon reserve calculation unit is used to calculate the total biocarbon reserve of the target area, i.e., the blue carbon reserve, based on the blue carbon reserve data set and the pixel set of the target area, combined with the aboveground biomass and the underground biomass;

[0021] A biodiversity maintenance capacity calculation unit, used to obtain the biodiversity maintenance capacity of the target area, according to the species spatial data set and the pixel set of the target area, each pixel of the target area is regarded as a spatial unit, and the species richness and rarity range of the target area are obtained, and the biodiversity maintenance capacity of the target area is obtained by spatially superimposing the layers of the species richness and the rarity range; wherein the species richness is the total number of species distributed in each spatial unit; the rarity range is obtained by calculating the weighted sum of the proportion of the species distributed in the spatial unit in the global range area;

[0022] A coastal protection capacity calculation unit is used to estimate the exposure index under different scenarios using the InVEST model based on the climate and environmental data set and the socio-economic data set, and to obtain the coastal protection capacity of the target area by evaluating the difference in relative exposure indexes under two different scenarios;

[0023] A coupling coordination degree calculation unit is used to obtain the coupling coordination degree according to the blue carbon storage, biodiversity maintenance capacity and coastal protection capacity, that is, the three ecosystem services, so as to evaluate and analyze the overall coordination level between ecosystem services;

[0024] A driving factor acquisition unit is used to screen out exploratory variables that affect the ecosystem services according to the ecological space database to obtain natural factors and social factors; and then use ArcGIS and zoning statistical tools to calculate the natural factors and social factors of the target area pixels;

[0025] A Bayesian model building unit is used to build a Bayesian-based ecosystem service collaborative prediction model. Netica software is used to build a Bayesian network-based ecosystem service collaborative prediction model. The natural factors, social factors, ecosystem services and coupling coordination degree are processed by natural breakpoint method for data discretization, and then used as input variable nodes of the collaborative prediction model. The probability distribution of the ecosystem service and the coupling coordination degree node is obtained as output;

[0026] The analysis unit is used to evaluate the impact of natural and social driving factors on ecosystem services and their synergy through sensitivity analysis based on the probability distribution of the ecosystem services and the coupling coordination degree nodes, identify the key driving factors of ecosystem service synergy and the optimal combination of environmental variables under different synergy scenarios, and simulate the potential synergy areas of ecosystem services under different scenarios.

[0027] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0028] The present invention integrates the existing ecological spatial database, uses the species richness and rarity range indicators of biodiversity and the InVEST model to obtain the blue carbon reserves, biodiversity maintenance capacity and coastal protection capacity of the target area, so as to analyze the spatial distribution characteristics of ecosystem services.

[0029] Then, the trade-off and synergy relationship of ecosystem services was analyzed based on spatial autocorrelation analysis, self-organizing map network and coupling coordination degree, and the spatial clustering phenomenon between two ecosystem services and the spatial combination characteristics and overall coordination level of the three ecosystem services were explained.

[0030] Furthermore, by integrating natural and social factors, ecosystem services and coupling coordination, a Bayesian network collaborative prediction model of ecosystem services is constructed to identify the key driving factors affecting synergy. By setting scenarios with different synergy targets, the spatial distribution of potential synergy areas is identified to comprehensively consider the coordination and potential synergy of ecosystem services and achieve spatial optimization of ecosystem service synergy.

[0031] The method of the present invention can be used to explore the spatial distribution of key ecosystem services such as my country's coastal wetlands, clarify the trade-offs and synergies of ecosystem services, clarify the impact mechanism of ecosystem service synergy, and simulate the distribution of potential synergy areas, so as to achieve spatial optimization of ecosystem service synergy. This will help provide spatial management information for decision makers in ecosystem construction and restoration, provide scientific reference for spatial management of my country's coastal wetlands, and promote the implementation of global climate change adaptation and biodiversity commitments at the national and local levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A schematic diagram of a Bayesian-based ecosystem service spatial trade-off collaborative optimization method provided in Example 1 of the present invention.

[0034] Figure 2 A flowchart of a Bayesian-based ecosystem service spatial trade-off collaborative optimization method provided in Example 1 of the present invention.

[0035] Figure 3 Schematic diagram of the Bayesian network model of national coastal wetland ecosystem services provided in Example 1 of the present invention.

[0036] Figure 4 Schematic diagram of bivariate spatial autocorrelation analysis of pairwise ecosystem services of my country's coastal wetlands provided in Example 1 of the present invention.

[0037] Figure 5 A schematic diagram of a Bayesian-based ecosystem service spatial trade-off collaborative optimization device provided in Example 2 of the present invention.

[0038] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0040] Embodiment 1

[0041] Embodiment 1 of the present invention provides a Bayesian-based ecosystem service spatial trade-off collaborative optimization method, which can be implemented by a Bayesian-based ecosystem service spatial trade-off collaborative optimization device (hereinafter referred to as the collaborative optimization device), and in particular, executed by one or more processors in the collaborative optimization device.

[0042] In this embodiment, the collaborative optimization computing device may be an electronic device equipped with a processor, the processor having a computer program of the Bayesian-based ecosystem service spatial trade-off collaborative optimization method and the computer program can be executed, such as a computer, a smart phone, a smart tablet, etc.

[0043] In recent years, exploring the trade-offs and synergies of ecosystem services at national and regional scales has become an important research area. Trade-offs refer to the interactions of ecosystem services, where an increase in one service leads to a decrease in other services; synergies are manifested as a synchronous effect of a common increase (or decrease) among ecosystem services. Trade-offs and synergies between ecosystem services are common. For example, effective nutrient retention in wetlands may accelerate vegetation succession, leading to changes in species abundance and a decrease in biodiversity; and the denitrification capacity of wetlands shows a positively correlated synergistic relationship with water conservation potential.

[0044] Spatial mapping and statistical analysis are common methods for assessing the trade-offs and synergies of ecosystem services. Spatial mapping helps to show the distribution characteristics and combination types of various ecosystem services in space, including spatial autocorrelation, ecosystem service clusters, and spatial overlay methods. Spatial autocorrelation analysis uses the positive and negative values ​​of the Moran index (reflecting positive or negative correlation) and the LiSA cluster diagram (reflecting high and low clustering characteristics) to measure the spatial trade-offs or synergies between two ecosystem services.

[0045] Ecosystem service clusters use cluster analysis and principal component analysis to divide the combination pattern of multiple ecosystem services in space, and reflect the trade-off or synergy between services through the co-occurrence of high and low values ​​of different ecosystem services in the cluster. As an important natural resource for mankind, coastal wetlands provide key ecosystem services such as blue carbon storage, biodiversity maintenance and coastal protection. The dual pressures of climate change and human activities have brought severe challenges to the sustainable supply and coordinated development of key ecosystem services, and it is urgent to strengthen the protection and restoration of coastal ecosystems. Maximizing the protection of coastal wetlands with synergistic benefits is crucial to the sustainable management of wetland resources.

[0046] like Figure 1-Figure 2 As shown, a Bayesian-based ecosystem service spatial trade-off collaborative optimization method includes steps S1 to S9.

[0047] S1, obtaining an ecological space database of the target area, wherein the ecological space database includes a basic geographic data set, a blue carbon reserve data set, a species space data set, a climate and environment data set, and a socio-economic data set.

[0048] The coastal wetland spatial distribution data used in this embodiment, namely the ecological spatial database, comes from the study of Zhang et al. (2022), which uses Sentinel 2 satellite images in 2020 to extract the spatial distribution of Chinese mangroves and salt marshes at a resolution of 10m. The present invention can also use other wetland datasets for calculation, which will not be repeated here.

[0049] Basic geographic data, including administrative unit (province, city, county and special administrative region) vector data, comes from the National Administration of Surveying, Mapping and Geoinformation. Mangrove soil and biomass carbon storage data, i.e., blue carbon storage data set, comes from the Global MangroveWatch (GMW) data set (https: / / www.globalmangrovewatch.org / ); salt marsh soil carbon storage data set comes from the study of Fan and Li (2024). Mangrove and salt marsh species distribution information vector data, i.e., species spatial data set, comes from the IUCN Red List of Threatened Species (https: / / www.iucnredlist.org / ).

[0050] Climate and environmental data include annual average temperature, annual average precipitation, minimum sea temperature, sea salinity, tidal range, elevation (DEM) and slope. Annual average temperature and annual average precipitation are from China Meteorological Data Service Center. Minimum sea temperature is from NASA's multi-sensor ultra-high resolution daily sea surface temperature dataset. National coastal seawater salinity data is from the GOFS 3.1 reanalysis dataset (https: / / www.hycom.org / dataserver / gofs-3pt1 / reanalysis). The vector point data is interpolated by kriging to obtain the national offshore seawater salinity raster data. Tidal range data is from the National Ocean Science Data Center. The hourly tide level data from 202 tide gauge stations in my country's coastal zone from 2020 to 2022 are collected to estimate the average tidal range. The national coastal tidal range data is obtained by kriging spatial interpolation. Slope data is calculated and generated in ArcGIS software from DEM data, which is from NASA's DEM dataset.

[0051] The socioeconomic data include national gross domestic product (GDP), population density, nighttime light data, national nature reserve boundaries, electricity consumption, land reclamation and offshore aquaculture data. GDP, nighttime light data and global nature reserve boundaries are from the Resources and Environmental Science and Data Center of the Chinese Academy of Sciences. Population density is from worldpop (https: / / hub.worldpop.org / geodata / ). National electricity consumption raster data are from Chen et al. (2022) with a spatial resolution of 1 km. National land reclamation and coastline geomorphic type data are from Sajjad et al. (2018). Visual interpretation is used to map the spatial distribution of land reclamation in my country from 1995 to 2015 and identify the three types of artificial, natural and tidal coastlines in my country. Offshore aquaculture vector data are from the National Earth System Science Data Center. After obtaining the relevant data, they are uniformly converted into the WGS1984UTM Zone 49N projection coordinate system.

[0052] S2, according to the ecological space database, the target area is generated into a grid layer of a specified size using the fishing net tool and the clipping tool of the ArcGIS software to obtain a pixel set of the target area.

[0053] In this embodiment, ArcGIS software is a series of geographic information system (GIS) software developed and maintained by Esri, which is designed to help users edit, use and manage geographic information.

[0054] S3, according to the blue carbon reserve data set and the pixel set of the target area, the total biocarbon reserve of the target area, i.e., the blue carbon reserve, is calculated by combining the aboveground biomass and the underground biomass.

[0055] In this embodiment, blue carbon stocks refer to organic carbon captured and stored from the atmosphere by coastal and marine ecosystems, which can effectively mitigate and adapt to climate change.

[0056] Therefore, this embodiment quantifies the spatial distribution of blue carbon reserves serving coastal wetlands in my country's coastal zone by integrating reliable and available blue carbon reserve data sets of mangroves and salt marshes. The blue carbon reserves of mangroves in my country are calculated by spatially superimposing soil and biomass carbon reserve raster data. The aboveground biomass data is combined with lidar, 30m resolution DEM and ground observation verification to invert the canopy height of global mangroves, and then the aboveground biomass of mangroves is estimated using the allometric growth equation. The underground biomass is estimated by the allometric index, and the total biocarbon reserve is calculated in combination with the aboveground biomass. The calculation formula is as follows:

[0057] c i =α×(b iabove +b ibe低值 );b ibe低值 =β×b iavove ;

[0058] Among them, c i is the total biomass carbon stock of pixel i, b iabove is the aboveground biomass of pixel i; b ibe低值 is the underground biomass of pixel i; α and β are preset weight coefficients; according to experience, α is set to 0.5 and β is set to 0.38.

[0059] Considering that soil organic carbon is the main component of salt marsh carbon sinks and the spatial distribution data of salt marsh biomass in my country is missing, soil carbon storage data is used to characterize the distribution of blue carbon storage in salt marsh wetlands in my country. ArcGIS software is used to spatially overlay mangrove and salt marsh blue carbon storage layers to draw a blue carbon storage map of coastal wetlands in my country.

[0060] S4, based on the species spatial data set and the pixel set of the target area, each pixel of the target area is regarded as a spatial unit to obtain the species richness and rarity range of the target area, and the biodiversity maintenance capacity of the target area is obtained by spatially superimposing the layers of the species richness and the rarity range; wherein the species richness is the total number of species distributed in each spatial unit; the rarity range is obtained by calculating the weighted sum of the proportion of the species distributed in the spatial unit in the global range area.

[0061] Preferably, the calculation formula for the rarity range is:

[0062]

[0063] Among them, Rarity iis the rarity range index of pixel i, N is the total number of species in the target area, j is a single species, A j is the total area of ​​the jth species in the target area, S ij is the area of ​​the jth species distributed in pixel i, S i is the area of ​​pixel i.

[0064] This embodiment obtains spatial vector data of animal, plant, fungus, and algae species in coastal wetland ecosystems based on IUCN Red List data, and uses the clipping tool of ArcGIS software to obtain the spatial distribution information of species in the study area.

[0065] The biodiversity maintenance map is constructed by spatially superimposing the species richness and rarity range layers. Two biodiversity indicators, species richness and range size rarity, characterize the biodiversity maintenance capacity of coastal wetlands. These two indicators are considered important and complementary, and are widely used to reflect the biodiversity maintenance capacity and provide decision-making references for ecological protection as direct and effective key indicators.

[0066] Species richness is used to represent the total number of species distributed in each spatial unit. Rarity range reflects the size of species distribution range and the importance of their aggregation by calculating the weighted sum of the proportion of species distributed in a spatial unit to the global range area.

[0067] S5. Based on the climate and environmental data set and the socio-economic data set, the InVEST model is used to estimate the exposure index under different scenarios, and the coastal protection capacity of the target area is evaluated by the difference in the relative exposure index under two different scenarios.

[0068] This embodiment simulates two scenarios with and without mangrove and salt marsh habitats, and uses the degree of reduction in coastal exposure caused by floods and storm surges to characterize the strength of coastal protection functions. This embodiment uses the coastal vulnerability module of the InVEST model to estimate the exposure index under different scenarios. This module couples seven biophysical vectors or grid maps of landforms, topography, habitats, net sea level changes, wind exposure, wave exposure, and potential contours of huge waves and a coastal population density grid map to evaluate the vulnerability levels of topography, surface undulation, natural habitats, wave exposure, and wind exposure (as shown in Table 1) and the degree of population risk affected by natural disasters, and estimates the relative exposure index of coastal areas to erosion or flooding.

[0069] In this embodiment, the InVEST model, whose full name is the Integrated Valuation of Ecosystem Services and Trade-offs, aims to provide a scientific basis for decision makers to weigh the benefits and impacts of human activities by simulating the changes in the quantity and value of the ecosystem service system under different land cover scenarios.

[0070] Preferably, the calculation formula of the exposure index is:

[0071]

[0072] Where CVI is the exposure index, n is the total number of coastal vulnerability indicators of the InVEST model, R k is the vulnerability level corresponding to the kth indicator.

[0073] The data and sources required for the coastal vulnerability model include: DEM, slope, population density, coastal wetlands and geomorphological data; wave energy, maximum tidal range, maximum wind speed and significant wave height data are all from the third generation wave numerical prediction model (WAVEWATCH III); water depth measurement and continental shelf vector data are from the InVEST model data set. After inputting the above data into the InVEST coastal vulnerability model, the relative exposure index of my country's coastal areas with and without mangrove and salt marsh habitats was obtained, and the difference between the relative exposure index of the two scenarios was used to represent the coastal protection capacity of coastal wetlands in my country's coastal areas.

[0074] Table 1 Indicator calculation method of InVEST coastal vulnerability model

[0075]

[0076] S6, based on the blue carbon storage, biodiversity maintenance capacity and coastal protection capacity, i.e. the three ecosystem services, the coupling coordination degree is obtained to evaluate and analyze the overall coordination level between ecosystem services.

[0077] In order to further explore the spatial trade-off and synergy relationship of the three services, this example uses the bivariate spatial autocorrelation model of Geoda software to perform spatial autocorrelation analysis between ecosystem services and identify the spatial high and low clustering characteristics of pairwise services; combines the self-organizing map neural network to identify ecosystem service clusters, and quantifies the overall synergy level of the three ecosystem services based on the coupling coordination degree model, and explores the typical spatial clustering characteristics and synergy status of the three ecosystem services.

[0078] (1) Spatial autocorrelation analysis

[0079] In this embodiment, the spatial autocorrelation analysis is applicable to analyzing whether variables are clustered in spatial distribution, including global spatial autocorrelation and local spatial autocorrelation.

[0080] Global spatial autocorrelation analysis can reflect the degree of association and overall distribution characteristics between each spatial unit and the adjacent spatial units in the target study area, which is represented by the global autocorrelation index Moran's I index. When the value is greater than 0, it means that the two variables are positively correlated in spatial distribution as a whole. When the value is less than 0, it means that the two variables are negatively correlated in spatial distribution as a whole.

[0081] Local spatial autocorrelation analysis is used to identify the spatial association pattern and significance degree between local regional variables. The local autocorrelation index Local Moran's I is used to grasp the spatial agglomeration and spatial heterogeneity between local regional elements. Under the significance test (P<0.05), the LiSA agglomeration diagram (Local Indicators of Spatial Association) is drawn to reflect the aggregation phenomenon of "high-high aggregation", "low-low aggregation", "high-low aggregation" or "low-high aggregation" of two variables in the local area, which is used to explore the synergistic relationship of mutual gain or attenuation or the trade-off relationship between variables in space.

[0082] The calculation formulas for the two key indices are as follows:

[0083]

[0084] Among them, Moran's I represents the global autocorrelation index, Moran's I∈[-1,1]; S 2 is the variance, L is the total number of pixels, X i and X j are the attribute values ​​of pixel i and pixel j in the target area, respectively. is the average value of the pixel attributes, k ij The spatial weight matrix established for the k-nearest neighbor spatial relationship; Local Moran's I is the local autocorrelation index.

[0085] In this embodiment, since the complex relationship between trade-offs and synergies is difficult to be fully revealed at a larger spatial scale, this study analyzes the correlation between ecosystem services from a grid scale. Combined with the spatial scope of the study area and the relatively fragmented distribution of coastal wetlands, the study area was divided into 2km*2km grids. The fishing net tool of ArcGIS software was used to generate a grid layer of a specified size, which was intersected with the coastal wetland map layer of my country through the clipping tool, and finally 24,846 wetland pixels (2km*2km) in the study area were obtained. Then, based on the zoning statistics tool of ArcGIS, the average values ​​of the three ecosystem services for each wetland pixel were calculated and standardized. Finally, the local bivariate spatial autocorrelation analysis of Geoda software was used to spatially visualize which areas showed trade-offs, synergies or insignificant spatial relationships between paired ecosystem services.

[0086] (2) Ecosystem service cluster

[0087] When evaluating and analyzing the overall coordination level between ecosystem services, ecosystem service clusters are used to analyze the synergy or trade-off relationship between ecosystem services in the target area. Ecosystem service clusters refer to the phenomenon of co-occurrence and aggregation of multiple ecosystem services in space or time. The combination characteristics of multiple ecosystem services in the cluster, which show a trade-off or mutual gain, represent the trade-off and synergy relationship. Self-organizing maps (SOM), as an unsupervised learning neural network, can be used to identify ecosystem service clusters formed in space and visualize the results, which is helpful to analyze the trade-off and synergy relationship of the three ecosystem services in the study area from the perspective of service clusters. First, the pixels in the target area are taken as the research unit and regarded as a spatial combination unit (i.e., "cluster"). The kohonen package of R language (a module in the self-organizing map neural network) is used to identify the ecosystem service clusters in the target area. After multiple experiments, when the number of ecosystem service clusters reaches 5 preset numbers (other preset numbers can also be used according to actual needs), the spatial combination characteristics of ecosystem services are more reasonable and have higher interpretability. Therefore, they are divided into 5 types of ecosystem service clusters and displayed spatially in ArcGIS software.

[0088] (3) Coupling coordination

[0089] The coupling coordination model is an effective method to test the coordinated development of multiple interacting functions. The coupling coordination index (D) is used to describe whether the ecosystem services are mutually promoted at a high level or mutually restricted at a low level. Therefore, this study introduced the model to identify the overall coordination level of each wetland pixel between blue carbon storage, biodiversity maintenance and coastal protection. A high value of coupling coordination represents a high value of synergy between the three services. The specific information is shown in Table 2.

[0090] The formula of the coupling coordination degree is as follows:

[0091]

[0092] T=aU1+bU2+cU3;

[0093] Among them, D is the coupling coordination degree; C is the coupling degree, which indicates the degree of interaction between ecosystem services; T is the multifunctional level of ecosystem services; U1, U2 and U3 are blue carbon storage, biodiversity maintenance capacity and coastal protection capacity, that is, ecosystem services; a, b, c are the corresponding weight coefficients of U1, U2 and U3, respectively.

[0094] Table 2 Types and characteristics of coupling coordination of three ecosystem services

[0095]

[0096] S7, based on the ecological space database, screen out the exploratory variables that affect the ecosystem services to obtain natural factors and social factors; then use ArcGIS and zoning statistical tools to calculate the natural factors and social factors of the target area pixels.

[0097] The change of ecological functions of coastal wetlands is the result of the combined action of multiple driving factors. In terms of natural factors, rising temperatures usually promote the carbon storage capacity of coastal wetland soils and have an important impact on species abundance, productivity and vegetation growth. In terms of social factors, high-intensity human activities such as economic development, land reclamation and aquaculture are key factors leading to the encroachment of coastal wetlands and ecosystem degradation. Thus, exploratory variables affecting the three ecosystem services were screened out, including 7 natural factors (average annual temperature, average annual precipitation, average annual minimum sea temperature, seawater salinity, DEM, slope, tidal range variables) and 5 social factors (GDP, electricity consumption, distance from reclamation, distance from offshore marine aquaculture, whether located in a protected area), and a coordinated prediction model of coastal wetland ecosystem services based on Bayesian networks was constructed, which consists of three layers of nodes: driving factors (natural factors + social factors) and two layers of target variables: three ecosystem services and coupling coordination degree.

[0098] S8, using Netica software to build an ecosystem service collaborative prediction model based on a Bayesian network, using the natural breakpoint method to discretize the natural factors, social factors, ecosystem services and the coupling coordination degree as the input variable nodes of the collaborative prediction model, and outputting the probability distribution of the ecosystem service and the coupling coordination degree node.

[0099] In this embodiment, Netica software is a professional Bayesian network analysis tool used to build, analyze and optimize Bayesian network models.

[0100] The Bayesian network is a graphical network based on probabilistic reasoning, which consists of two parts. One is the causal network, which is a directed acyclic graph that uses arrows to connect the causal relationships between variables; the other is a conditional probability table that quantifies the relationship and strength between variables in this network, providing the conditional probability of each possible state occurring at the target node.

[0101] The original formula is: P(A|B)=P(A,B) / P(B)=P(B|A)P(A) / P(A);

[0102] Where: P(A|B) and P(B|A) are conditional probabilities (or posterior probabilities), representing the probability of event A occurring when event B occurs or the probability of event B occurring when event A occurs; P(A,B) represents the probability of events A and B occurring at the same time, that is, the joint probability; P(A) and P(B) are prior probabilities (or marginal probabilities), representing the probability of event A or B occurring.

[0103] Applying the Bayesian network to this embodiment, the optimization formula is:

[0104]

[0105] Among them, X1, X2, …, X m represents each variable node in the directed acyclic graph of the Bayesian network, m is the total number of variable nodes, P(X1,X2,…,X m ) is the joint probability obtained by multiplying the local conditional probability distributions, X i ∈[X1,X m ], is the i-th variable node, parents(X i ) is event X i The parent node of .

[0106] Then the Bayesian network model parameter learning is carried out. In view of the diversity of spatial scale and range of each data set source, the data needs to be preprocessed to create a unified geographic database. The present invention uses ArcGIS10.2 to resample all driving factor raster layers to 30m, and uses the zoning statistics tool to calculate the driving factor value of the wetland pixel in the study area. The Bayesian network input data requires that each node is discrete data, and the natural breakpoint method is used to discretize the data of each variable node, which is mainly divided into three states: low (low value), Medium (medium value), and High (high value). The classification results of each variable state are shown in Table 3.

[0107] Due to the loss of wetland pixels caused by missing social and natural factor data and resampling failure in some coastal areas, these NoData wetland pixels were deleted, and the number of samples finally input into the Bayesian network model totaled 20,586. The total sample points were randomly divided into a training set (70%) and a test set (30%) using SPSS software, and the training set was imported into the Bayesian network for learning, thereby obtaining the probability distribution of the nodes.

[0108] Table 3 Bayesian network model node status

[0109]

[0110]

[0111] S9, based on the probability distribution of the ecosystem service and the coupling coordination degree node, evaluate the impact of natural and social driving factors on ecosystem services and their synergy through sensitivity analysis, identify the key driving factors of ecosystem service synergy and the optimal combination of environmental variables under different synergy scenarios, and simulate the potential synergy areas of ecosystem services under different scenarios.

[0112] In this example, the impact of natural and social driving factors on ecosystem services and their synergy is evaluated through sensitivity analysis, and the key driving factors of ecosystem service synergy are clarified. Then four scenarios with different synergy targets are set, and the optimal environmental variable combination of different synergy scenarios is identified through the sensitivity analysis results and conditional probability table of the Bayesian network model. By capturing the key state combination of the first two key factors corresponding to the maximum probability of high value of each ecosystem service, it is spatially visualized to simulate the potential synergy area of ​​ecosystem services under different scenarios. Finally, it is superimposed with the coupling coordination degree results to divide the priority level of the protection priority area.

[0113] In another preferred embodiment, four cases, namely Guangxi Zhuang Autonomous Region, Guangdong Province, Hong Kong Special Administrative Region of China, Macao Special Administrative Region of China (hereinafter referred to as Guangdong, Hong Kong and Macao), Zhejiang Province and Jiangsu Province, are selected to construct a Bayesian network model of coastal wetland ecosystem services at the regional scale.

[0114] Bayesian network analysis of national coastal wetland ecosystem services Figure 3 As shown in the figure, it includes 16 nodes (12 child nodes, 4 parent nodes) and 34 connecting lines to reflect the correlation between variables. On this basis, all node data of four case studies in Guangxi Zhuang Autonomous Region, Guangdong, Hong Kong and Macao, Zhejiang Province, and Jiangsu Province were extracted for parameter learning again to generate a regional-scale coastal wetland Bayesian network.

[0115] In this embodiment, the Bayesian network model is verified by using confusion matrix. By using SPSS software to randomly extract test sets (30% of the data) at national and regional scales, the test sample data of the whole country and Guangxi Zhuang Autonomous Region, Guangdong, Hong Kong and Macao, Zhejiang Province, and Jiangsu Province are 6169, 569, 443, 1368 and 496 respectively, participating in the accuracy verification of each model. The prediction accuracy is calculated using the error matrix evaluation model, with blue carbon reserves, biodiversity maintenance, coastal protection and coupling coordination as target nodes. As shown in Table 4, the national Bayesian model is 82%, 81%, 82%, and 72% respectively, and the overall accuracy of the Guangxi Zhuang Autonomous Region, Guangdong, Hong Kong and Macao, Zhejiang Province, and Jiangsu Province is 88%, 80%, 85%, and 92%, indicating that the model has good prediction performance and the simulation results are relatively reliable, which can meet the prediction of the probability of occurrence of the target node state under different scenarios.

[0116] Table 4 Prediction accuracy of each target node of Bayesian network in China and case regions

[0117]

[0118]

[0119] Taking into account that stakeholders in different regions may have different public preferences for different ecosystem services of coastal wetlands, and trade-offs among ecosystem services are difficult to avoid, this study set up four synergy scenarios that prioritize high-value synergies between two services and overall synergy among three services, as shown in Table 5. These scenarios are considered to be equally important and are used to simulate the spatial distribution of potential synergy areas for ecosystem services.

[0120] Table 5 Scenario settings for different collaborative goals

[0121] scene describe BC_CS scenario Prioritize the highest probability of maintaining high values ​​of blue carbon stocks and biodiversity BC_CP scenario Prioritize the greatest probability of biodiversity maintenance and coastal protection CS_CP scenario Prioritizing blue carbon storage and the greatest probability of coastal protection BC_CS_CP scenario Considering the high probability of high values ​​of blue carbon storage, biodiversity maintenance and coastal protection

[0122] Sensitivity analysis can measure the degree of influence of driving factors on target variables, and quantify it through variance reduction percentage. The greater the variance reduction percentage, the stronger the degree of influence of driving factors on target variables. The present invention identifies the important driving factors (i.e., key variables) of each ecosystem service based on the variance reduction results. At the same time, the conditional probability table of the Bayesian network can also capture all possible combinations of driving factor states under the probability of occurrence of different states (low value, medium value, high value) of ecosystem services. The state of the key variable corresponding to the maximum probability of occurrence of the high value of the ecosystem service is defined as the key state of the key variable. The present invention captures the key state combination of the first two key factors corresponding to the maximum probability of occurrence of the high value of each ecosystem service, visualizes it in space, and simulates the potential synergistic area of ​​ecosystem services under different scenarios.

[0123] According to the spatial distribution map of key ecosystem services of my country's coastal wetlands, the existing blue carbon stock database, biodiversity model and InVEST model were used to quantify the spatial distribution of blue carbon stocks, biodiversity maintenance and coastal protection ecosystem services of mangroves and salt marsh coastal wetlands across the country. To facilitate the comparison of the three services and subsequent spatial clustering analysis, they were standardized and divided into six levels from low to high using the natural breakpoint method.

[0124] The results show that the three ecosystem service functions of blue carbon storage, biodiversity maintenance and coastal protection in my country's coastal wetlands present a similar spatial distribution pattern, that is, a differentiation law that gradually decreases from south to north. From the perspective of spatial distribution, the high values ​​of blue carbon storage services are mainly concentrated in Guangxi Zhuang Autonomous Region, Hainan Province, Guangdong, Hong Kong and Macao (Zhanjiang City), while Shandong Province and Jiangsu Province are relatively low. In terms of biodiversity maintenance services, Hainan Province, Guangdong, Hong Kong and Macao, Guangxi Zhuang Autonomous Region, and Fujian Province present high values. These regions have sufficient rainfall, which has promoted species composition and richness to a certain extent. The low values ​​are mainly distributed in Liaoning Province, Hebei Province, and Shandong Province. The high value of coastal protection services is more significant in Guangxi Zhuang Autonomous Region, and Guangdong, Hong Kong and Macao, Hainan Province, Jiangsu Province, and Shanghai are relatively high.

[0125] The spatial correlation between the three ecosystem services was obtained through bivariate spatial autocorrelation analysis. The global spatial autocorrelation index Moran's I was 0.241, 0.305, and 0.234, respectively, indicating that there was a spatial positive correlation between the two services, among which biodiversity maintenance and coastal protection services had the highest spatial positive correlation. Geoda was used to draw the bivariate local spatial autocorrelation LISA cluster map (such as Figure 4 The four spatial aggregation patterns at a significant level (P < 0.05) between two ecosystem services were characterized, including the spatial synergistic relationship of high-high aggregation and low-low aggregation, or the spatial trade-off relationship of low-high aggregation and high-low aggregation.

[0126] The coupling coordination model was used to classify and analyze the coupling coordination levels of the three services, and the dominant service cluster types of the region were combined to explore the clustering characteristics of ecosystem services in different synergy states.

[0127] The key state subsets of key variables of different synergy scenarios (i.e., Table 5) are spatially visualized to show the spatial distribution of potential synergy areas of coastal wetland ecosystem services in various regions.

[0128] The current coupling and coordination level and future synergy potential of coastal wetland ecosystem services are comprehensively considered to determine the ecological protection priority areas and ecological restoration areas and their priority levels.

[0129] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0130] The method of the present invention can be used to explore the spatial distribution of key ecosystem services such as my country's coastal wetlands, clarify the trade-offs and synergies of ecosystem services, clarify the impact mechanism of ecosystem service synergy, and simulate the distribution of potential synergy areas, so as to achieve spatial optimization of ecosystem service synergy. This will help provide spatial management information for decision makers in ecosystem construction and restoration, provide scientific reference for spatial management of my country's coastal wetlands, and promote the implementation of global climate change adaptation and biodiversity commitments at the national and local levels.

[0131] Embodiment 2

[0132] like Figure 5 As shown, the second embodiment of the present invention further provides a Bayesian-based ecosystem service spatial trade-off collaborative optimization device, comprising:

[0133] A database acquisition unit, used to acquire an ecological space database of a target area, wherein the ecological space database includes a basic geographic data set, a blue carbon reserve data set, a species space data set, a climate and environment data set, and a socio-economic data set;

[0134] A pixel set generation unit is used to generate a grid layer of a specified size in the target area using the fishing net tool and the clipping tool of the ArcGIS software according to the ecological space database to obtain a pixel set of the target area;

[0135] A blue carbon reserve calculation unit is used to calculate the total biocarbon reserve of the target area, i.e., the blue carbon reserve, based on the blue carbon reserve data set and the pixel set of the target area, combined with the aboveground biomass and the underground biomass;

[0136] A biodiversity maintenance capacity calculation unit, used to obtain the biodiversity maintenance capacity of the target area, according to the species spatial data set and the pixel set of the target area, each pixel of the target area is regarded as a spatial unit, and the species richness and rarity range of the target area are obtained, and the biodiversity maintenance capacity of the target area is obtained by spatially superimposing the layers of the species richness and the rarity range; wherein the species richness is the total number of species distributed in each spatial unit; the rarity range is obtained by calculating the weighted sum of the proportion of the species distributed in the spatial unit in the global range area;

[0137] A coastal protection capacity calculation unit is used to estimate the exposure index under different scenarios using the InVEST model based on the climate and environmental data set and the socio-economic data set, and to obtain the coastal protection capacity of the target area by evaluating the difference in relative exposure indexes under two different scenarios;

[0138] A coupling coordination degree calculation unit is used to obtain the coupling coordination degree according to the blue carbon storage, biodiversity maintenance capacity and coastal protection capacity, that is, the three ecosystem services, so as to evaluate and analyze the overall coordination level between ecosystem services;

[0139] A driving factor acquisition unit is used to screen out exploratory variables that affect the ecosystem services according to the ecological space database to obtain natural factors and social factors; and then use ArcGIS and zoning statistical tools to calculate the natural factors and social factors of the target area pixels;

[0140] A Bayesian model building unit is used to build a Bayesian-based ecosystem service collaborative prediction model. Netica software is used to build a Bayesian network-based ecosystem service collaborative prediction model. The natural factors, social factors, ecosystem services and coupling coordination degree are processed by natural breakpoint method for data discretization, and then used as input variable nodes of the collaborative prediction model. The probability distribution of the ecosystem service and the coupling coordination degree node is obtained as output;

[0141] The analysis unit is used to evaluate the impact of natural and social driving factors on ecosystem services and their synergy through sensitivity analysis based on the probability distribution of the ecosystem services and the coupling coordination degree nodes, identify the key driving factors of ecosystem service synergy and the optimal combination of environmental variables under different synergy scenarios, and simulate the potential synergy areas of ecosystem services under different scenarios.

[0142] Embodiment 3

[0143] The third embodiment of the present invention also provides a Bayesian-based ecosystem service spatial trade-off collaborative optimization device, which includes a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement the Bayesian-based ecosystem service spatial trade-off collaborative optimization method as described above.

[0144] Embodiment 4

[0145] The fourth embodiment of the present invention also provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a device where the computer-readable storage medium is located, the Bayesian-based ecosystem service spatial trade-off collaborative optimization method as described above is implemented.

[0146] In several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed devices and methods may also be implemented in other ways.

[0147] The functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0148] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0149] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A Bayesian-based collaborative optimization method for ecosystem service spatial trade-offs, characterized in that: include: S1, obtaining an ecological space database of the target area, wherein the ecological space database includes a basic geographic data set, a blue carbon reserve data set, a species space data set, a climate and environment data set, and a socio-economic data set; S2, according to the ecological space database, using the fishing net tool and the clipping tool of ArcGIS software to generate a grid layer of a specified size for the target area to obtain a pixel set of the target area; S3, calculating the total biocarbon stock of the target area, i.e., the blue carbon stock, based on the blue carbon stock data set and the pixel set of the target area, combining the aboveground biomass and the underground biomass; S4, according to the species spatial data set and the pixel set of the target area, each pixel of the target area is regarded as a spatial unit, and the species richness and rarity range of the target area are obtained, and the biodiversity maintenance capacity of the target area is obtained by spatially superimposing the layers of the species richness and the rarity range; wherein the species richness is the total number of species distributed in each spatial unit; the rarity range is obtained by calculating the weighted sum of the proportion of the species distributed in the spatial unit in the global range area; S5, according to the climate and environment data set and the socio-economic data set, the exposure index under different scenarios is estimated using the InVEST model, and the coastal protection capacity of the target area is evaluated by the difference in the relative exposure index under two different scenarios; S6, based on the blue carbon storage, biodiversity maintenance capacity and coastal protection capacity, i.e. the three ecosystem services, the coupling coordination degree is obtained to evaluate and analyze the overall coordination level between ecosystem services; S7, based on the ecological space database, screen out the exploratory variables that affect the ecosystem services to obtain natural factors and social factors; then use ArcGIS and zoning statistical tools to calculate the natural factors and social factors of the target area pixels; S8, using Netica software to build an ecosystem service collaborative prediction model based on a Bayesian network, using the natural breakpoint method to discretize the natural factors, the social factors, the ecosystem services and the coupling coordination degree as input variable nodes of the collaborative prediction model, and outputting the probability distribution of the ecosystem services and the coupling coordination degree nodes; S9, based on the probability distribution of the ecosystem service and the coupling coordination degree node, evaluate the impact of natural and social driving factors on ecosystem services and their synergy through sensitivity analysis, identify the key driving factors of ecosystem service synergy and the optimal combination of environmental variables under different synergy scenarios, and simulate the potential synergy areas of ecosystem services under different scenarios.

2. A Bayesian-based ecosystem service spatial trade-off collaborative optimization method according to claim 1, characterized in that , the calculation formula of the total biomass carbon stock is as follows: c i =α×(b iabove +b ibe低值 ); b ibe低值 =β×b iabove ; Among them, c i is the total biomass carbon stock of pixel i, b iabove is the aboveground biomass of pixel i; b ibe低值 is the underground biomass of pixel i; α and β are preset weight coefficients; according to experience, generally, α is 0.5 and β is 0.

38.

3. A Bayesian-based ecosystem service spatial trade-off collaborative optimization method according to claim 2, characterized in that , the calculation formula of the rarity range is: Among them, Rarity i is the rarity range index of pixel i, N is the total number of species in the target area, j is a single species, A j is the total range area of ​​the jth species in the target area, S ij is the area of ​​the jth species distributed in pixel i, S i is the area of ​​pixel i.

4. The Bayesian-based ecosystem service spatial trade-off collaborative optimization method according to claim 3 is characterized in that: The calculation formula of the exposure index is: Where CVI is the exposure index, n is the total number of coastal vulnerability indicators of the InVEST model, R k is the vulnerability level corresponding to the kth indicator.

5. The Bayesian-based ecosystem service spatial trade-off collaborative optimization method according to claim 4, characterized in that: The formula of the coupling coordination degree is as follows: T=aU1+bU2+cU3; Among them, D is the coupling coordination degree; C is the coupling degree, which indicates the degree of interaction between ecosystem services; T is the multifunctional level of ecosystem services; U1, U2 and U3 are blue carbon storage, biodiversity maintenance capacity and coastal protection capacity, that is, ecosystem services; a, b, c are the corresponding weight coefficients of U1, U2 and U3, respectively.

6. A Bayesian-based collaborative optimization method for ecosystem service spatial trade-offs according to claim 5, characterized in that ,The probability distribution calculation formula of the ecosystem service collaborative prediction model based on Bayesian network is as follows: Among them, X1, X2, …, X m represents each variable node in the directed acyclic graph of the Bayesian network, m is the total number of variable nodes, P(X1,X2,…,X m ) is the joint probability obtained by multiplying the local conditional probability distributions, X i is the i-th variable node, parents(X i ) is event X i The parent node of .

7. A Bayesian-based collaborative optimization method for ecosystem service spatial trade-offs according to claim 6, characterized in that When evaluating and analyzing the overall coordination level between ecosystem services, Geoda software is used to conduct spatial autocorrelation analysis between ecosystem services. The spatial autocorrelation analysis includes global spatial autocorrelation analysis and local spatial autocorrelation analysis to analyze whether the variables show clustering in spatial distribution.

8. The Bayesian-based collaborative optimization method for ecosystem service spatial trade-offs according to claim 7 is characterized in that ,The global spatial autocorrelation analysis can reflect the degree of association and the overall distribution characteristics between each spatial unit and the adjacent spatial units in the target area, which is represented by the global autocorrelation index. When the global autocorrelation index value is greater than 0, it means that the two variables are overall positively correlated in spatial distribution; when the global autocorrelation index value is less than 0, it means that the two variables are overall negatively correlated in spatial distribution. The calculation formula is: Among them, Moran's I represents the global autocorrelation index, Moran's I∈[-1,1]; S 2 is the variance, L is the total number of pixels, X i and X j are the attribute values ​​of pixel i and pixel j in the target area, respectively. is the average value of the pixel attributes, k ij A spatial weight matrix for k-nearest neighbor spatial relationships; The local autocorrelation index represents the spatial agglomeration and spatial heterogeneity between local regional elements, and draws the LiSA agglomeration map under the significance test to analyze the synergistic trade-off relationship between the target regional variables in space. The calculation formula of the local autocorrelation index is: Among them, Local Moran's I is the local autocorrelation index.

9. A Bayesian-based ecosystem service spatial trade-off collaborative optimization method according to claim 8, characterized in that When evaluating and analyzing the overall coordination level between ecosystem services, ecosystem service clusters are used to analyze the synergy or trade-off relationship between ecosystem services in the target area. The ecosystem service cluster is a cluster of multiple ecosystem services in space or time. The combination characteristics of the increase and decrease or mutual gain between multiple ecosystem services in the cluster represent the trade-off and synergy relationship, specifically: The pixels in the target area are taken as the research unit and regarded as a spatial combination unit; The self-organizing map neural network was used to identify the ecosystem service clusters in the target area; When the number of identified ecosystem service clusters reaches a preset number, the identified ecosystem service clusters are spatially displayed in ArcGIS software to analyze the synergies or trade-offs presented in space.

10. A Bayesian-based collaborative optimization device for ecosystem service spatial trade-offs, characterized in that: include: A database acquisition unit, used to acquire an ecological space database of a target area, wherein the ecological space database includes a basic geographic data set, a blue carbon reserve data set, a species space data set, a climate and environment data set, and a socio-economic data set; A pixel set generation unit is used to generate a grid layer of a specified size in the target area using the fishing net tool and the clipping tool of the ArcGIS software according to the ecological space database to obtain a pixel set of the target area; A blue carbon reserve calculation unit is used to calculate the total biocarbon reserve of the target area, i.e., the blue carbon reserve, based on the blue carbon reserve data set and the pixel set of the target area, combined with the aboveground biomass and the underground biomass; A biodiversity maintenance capacity calculation unit, used to obtain the biodiversity maintenance capacity of the target area, according to the species spatial data set and the pixel set of the target area, each pixel of the target area is regarded as a spatial unit, and the species richness and rarity range of the target area are obtained, and the biodiversity maintenance capacity of the target area is obtained by spatially superimposing the layers of the species richness and the rarity range; wherein the species richness is the total number of species distributed in each spatial unit; the rarity range is obtained by calculating the weighted sum of the proportion of the species distributed in the spatial unit in the global range area; A coastal protection capacity calculation unit is used to estimate the exposure index under different scenarios using the InVEST model based on the climate and environmental data set and the socio-economic data set, and to obtain the coastal protection capacity of the target area by evaluating the difference in relative exposure indexes under two different scenarios; A coupling coordination degree calculation unit is used to obtain the coupling coordination degree according to the blue carbon storage, biodiversity maintenance capacity and coastal protection capacity, that is, the three ecosystem services, so as to evaluate and analyze the overall coordination level between ecosystem services; A driving factor acquisition unit is used to screen out exploratory variables that affect the ecosystem services according to the ecological space database to obtain natural factors and social factors; and then use ArcGIS and zoning statistical tools to calculate the natural factors and social factors of the target area pixels; A Bayesian model building unit is used to build a Bayesian-based ecosystem service collaborative prediction model. Netica software is used to build a Bayesian network-based ecosystem service collaborative prediction model. The natural factors, social factors, ecosystem services and coupling coordination degree are processed by natural breakpoint method for data discretization, and then used as input variable nodes of the collaborative prediction model. The probability distribution of the ecosystem service and the coupling coordination degree node is obtained as output; The analysis unit is used to evaluate the impact of natural and social driving factors on ecosystem services and their synergy through sensitivity analysis based on the probability distribution of the ecosystem services and the coupling coordination degree nodes, identify the key driving factors of ecosystem service synergy and the optimal combination of environmental variables under different synergy scenarios, and simulate the potential synergy areas of ecosystem services under different scenarios.

Citation Information

Patent Citations

  • Future ecological security pattern prediction and optimization method based on Bayesian network

    CN113505948A

  • Method for evaluating space-time response mechanism of ecosystem service tradeoff and synergistic effect

    CN115239054A

  • Multi-dimensional adaptive regulation and control method and system for water resource system

    CN116070886A

  • Ecological system service function evaluation method and system

    CN116384772A

  • Ecological system service scene optimal configuration method based on partial order theory

    CN117172584A

Cited By

  • Innovation space identification method and device based on innovation subject and innovation activity data, and storage medium

    CN119671796A

  • Urban ecosystem service tradeoff and cooperative relationship analysis method and device

    CN121504261A