Method and device for optimizing carbon sink benefit of green land

Abstract

The embodiment of the invention provides a green land carbon sink benefit optimization method and device. The method comprises the following steps: acquiring data related to carbon sequestration of a plurality of functional zones in a research area, and for each functional zone, determining vegetation carbon sequestration benefits of the functional zone based on the data related to the carbon sequestration; calculating the importance percentage of each item in the influence factor set of the function partition on the vegetation carbon sink benefit, representing the action degree of the influence factors on the greenbelt carbon sink through the importance percentage, realizing the quantification of the carbon sink influence factors, and determining a key factor from multiple influence factors according to the importance percentage, calculating a local standardized regression coefficient of the key factor to analyze the spatial influence of the key factor on the vegetation carbon sink benefit, determining an optimization strategy of the greenbelt carbon sink benefit of the function partition according to the key factor and an analysis result, and formulating the optimization strategy of the greenbelt carbon sink benefit for different function partitions in a targeted manner. And the comprehensive improvement of the urban green land carbon sequestration capability can be realized.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of ecological environment design, and in particular to a method and device for optimizing the carbon sink benefits of green land. Background Art

[0002] Under the premise of global climate change, reducing carbon emissions and achieving carbon reduction have become the focus of common concern of the international community.

[0003] Reducing emissions and increasing carbon emissions is an important direction for sustainable urban development. At present, the relevant research on the carbon sink capacity of green space is mainly based on ecological sources with weak human intervention. As the only carbon sink carrier in the urban ecosystem, there are relatively few studies on the carbon sink capacity of urban green space. The key influencing factors and linear relationships of carbon sinks in different urban functional areas are also unclear.

[0004] It can be seen that how to quantify the factors affecting urban green space carbon sequestration and optimize the carbon sequestration benefits to achieve a comprehensive improvement in the carbon sequestration capacity of urban green space is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, an embodiment of the present application provides a method and device for optimizing the carbon sequestration benefits of green spaces to at least solve or alleviate the above-mentioned problems.

[0006] According to one aspect of an embodiment of the present application, a method for optimizing green space carbon sink benefits is provided, the method comprising: Acquire a data set related to carbon sinks in the study area, wherein the data set includes data of multiple functional zones, and the multiple functional zones are obtained by dividing the study area into zones according to urban functions; For each of the functional zones, the vegetation carbon sink benefit of the functional zone is determined according to the data of the functional zone; the influencing factor set of the functional zone is obtained, the influencing factor set includes multiple influencing factors, and the multiple influencing factors include natural environment factors and human activity characteristic factors; the importance percentage of each influencing factor to the vegetation carbon sink benefit is determined, and the key factor is determined from the multiple influencing factors according to the importance percentage; the key factor is fitted with the vegetation carbon sink benefit, and the local standardized regression coefficient of the key factor is determined according to the fitting result, and the local standardized regression coefficient is used to characterize the relationship between the influencing factor and the vegetation carbon sink benefit in space; the spatial influence of the key factor on the vegetation carbon sink benefit is analyzed according to the local standardized regression coefficient to obtain the analysis result, and the analysis result is used to characterize the spatial heterogeneity of the vegetation carbon sink benefit; the optimization strategy of the green space carbon sink benefit of the functional zone is determined according to the key factor and the analysis result.

[0007] According to another aspect of the embodiments of the present application, an optimization device for the green space carbon sequestration benefit is provided. The device includes: An acquisition module, configured to acquire a dataset related to carbon sequestration in a research area, where the dataset includes data of multiple functional zones obtained by dividing the research area according to urban functions; A processing module, configured to, for each of the functional zones, determine the vegetation carbon sequestration benefit of the functional zone according to the data of the functional zone; acquire an influence factor set of the functional zone, where the influence factor set includes multiple influence factors, and the multiple influence factors include natural environment factors and human activity characteristic factors; determine the importance percentage of each influence factor on the vegetation carbon sequestration benefit, and determine key factors from the multiple influence factors according to the importance percentage; fit the key factors with the vegetation carbon sequestration benefit, and determine the local standardized regression coefficient of the key factors according to the fitting result, where the local standardized regression coefficient is used to characterize the relationship between the influence factor and the vegetation carbon sequestration benefit in space; analyze the spatial influence of the key factors on the vegetation carbon sequestration benefit according to the local standardized regression coefficient to obtain an analysis result, where the analysis result is used to characterize the spatial heterogeneity of the vegetation carbon sequestration benefit; and determine an optimization strategy for the green space carbon sequestration benefit of the functional zone according to the key factors and the analysis result.

[0008] According to another aspect of the embodiments of the present application, an electronic device is provided. The electronic device includes: a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus; the memory is used to store at least one executable instruction, and when the executable instruction is executed by the processor, it implements the optimization method for the green space carbon sequestration benefit provided in the above aspect.

[0009] According to another aspect of the embodiments of the present application, a computer storage medium is provided. A computer program is stored on the computer storage medium, and when the computer program is executed by a processor, it implements the optimization method for the green space carbon sequestration benefit described in the above aspect.

[0010] According to another aspect of the embodiments of the present application, a computer program product is provided. The computer program product includes computer instructions, and the computer instructions instruct a computing device to execute the optimization method for the green space carbon sequestration benefit described in the above aspect.

[0011] According to the optimization method of green space carbon sequestration benefits provided by the embodiments of the present application, a dataset related to carbon sequestration within the research area is obtained. This dataset includes data of multiple functional zones. For each functional zone, based on the data of this functional zone, the vegetation carbon sequestration benefits of this functional zone are determined. Then, an impact factor set of this functional zone is obtained, and the impact factor set includes natural environmental factors and human activity characteristic factors. The importance percentage of each of these impact factors on the vegetation carbon sequestration benefits is determined, and the degree of influence of the impact factors on the green space carbon sequestration is represented by this importance percentage, realizing the quantification of the influencing factors of the green space carbon sequestration. Subsequently, key factors are determined from multiple impact factors according to the importance percentage, and the local standardized regression coefficients of the key factors are calculated. The spatial influence of the key factors on the vegetation carbon sequestration benefits is analyzed based on the local standardized regression coefficients. Then, an optimization strategy for the green space carbon sequestration benefits of the functional zone is determined according to these key factors and the corresponding analysis results, formulating a targeted optimization strategy for the green space carbon sequestration benefits of different functional zones. Moreover, the impact factors not only include natural environmental factors but also take into account human activity characteristic factors, enabling the comprehensive improvement of the urban green space carbon sequestration capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0013] Figure 1 It is a schematic diagram of an exemplary system applied in an embodiment of the present application; Figure 2 It is a flowchart of the optimization method of green space carbon sequestration benefits in an embodiment of the present application; Figure 3 It is a schematic diagram of the importance percentage of impact factors on the green space carbon sequestration benefits in an embodiment of the present application; Figure 4 It is the marginal effect curve of each impact factor on the green space carbon sequestration capacity of each functional zone in an embodiment of the present application; Figure 5 It is a schematic diagram of the structural equation model of the spatial variation influence of the urban green space carbon sequestration capacity of a functional zone in an embodiment of the present application; Figure 6 It is a schematic diagram of the optimization device of green space carbon sequestration benefits in an embodiment of the present application; Figure 7 It is a schematic diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The present application will be described based on embodiments below, but the present application is not limited to these embodiments. In the following detailed description of the present application, some specific details are described in detail. Those skilled in the art can fully understand the present application without the description of these details. In order to avoid obscuring the essence of the present application, well-known methods, processes, and procedures are not described in detail. Additionally, the drawings are not necessarily drawn to scale.

[0015] First, some nouns or terms that appear during the description of the embodiments of the present application are applicable to the following explanations.

[0016] Carbon sink refers to the ability of plants to absorb carbon dioxide in the atmosphere through photosynthesis and fix it in vegetation and soil. The carbon sink amount refers to the change in the carbon storage of the forest carbon pool over a certain period. It helps achieve the goal of emission reduction and carbon sequestration by reducing the concentration of greenhouse gases in the atmosphere. Forests, grasslands, agricultural and other ecosystems are important carbon sinks and play an important role in global climate change by absorbing and storing carbon dioxide.

[0017] The vegetation carbon sink benefit refers to the comprehensive value derived from the absorption of carbon dioxide in the atmosphere by vegetation through photosynthesis and its fixation in biomass (such as tree trunks, branches and leaves) or soil, thereby reducing the concentration of greenhouse gases. It not only includes the direct carbon sequestration effect, but also covers the resulting ecological, economic and social benefits. Among them, the ecological benefits include regulating the climate (such as reducing local temperature), protecting biodiversity, conserving water sources, reducing soil erosion, etc.; the economic benefits are realized through carbon sink trading (such as forestry carbon sink projects) to obtain economic benefits, or obtaining financial support through the ecological compensation mechanism; the social benefits include improving the living environment, enhancing public environmental awareness, and promoting sustainable development.

[0018] Figure 1 An exemplary computer system is shown. The computer system includes an electronic device 101 and a server 102.

[0019] The electronic device 101 installs and runs an application program, and the application program is applicable to the optimization method of the green space carbon sink benefit provided by the embodiments of the present application. For example, during the execution of the optimization method of the green space carbon sink benefit, relevant parameters are set through the application program.

[0020] The electronic device 101 is connected to the server 102 via a wireless network or a wired network. The server 102 includes at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. The server 102 is used to support the operation of applications on the electronic device, that is, to provide background services for the applications running on the electronic device 101. For example, a database is established on the server 102 to store the dataset related to carbon sinks in the research area, as well as the impact factor set of each functional area, etc.; Another example is that the server 102 can also execute all or part of the optimization steps of the green space carbon sink benefit.

[0021] Optionally, the server 102 undertakes the main computing work, and the electronic device 101 undertakes the secondary computing work; or, the server 102 undertakes the secondary computing work, and the electronic device 101 undertakes the main computing work; or, a distributed computing architecture is adopted between the server 102 and the electronic device 101 for collaborative computing. In the embodiments provided in this application, the case where the electronic device undertakes the main computing work is taken as an example for description.

[0022] Based on the above system, an embodiment of this application provides an optimization method for the green space carbon sink benefit. Taking the case where this method is executed by the electronic device as an example, this method will be described in detail through the following multiple embodiments.

[0023] Figure 2 It is a flowchart of the optimization method for the green space carbon sink benefit in an embodiment of this application. As Figure 2 shown, this method includes the following steps: Step 210, obtain the dataset related to carbon sinks in the research area. The dataset includes data of multiple functional areas, and the multiple functional areas are obtained by dividing the research area according to urban functions.

[0024] The dataset related to carbon sinks in the research area is stored in the database. When used later, obtain the data related to carbon sinks from the database, and this data includes meteorological data, NDVI (Normalized Difference Vegetation Index), land use data, and socioeconomic data.

[0025] The dataset is pre-collected and stored in a database. Exemplarily, for meteorological data, data provided by multiple ground meteorological stations in the study area and its surrounding areas can be used. For example, data from 30 ground meteorological stations in the study area and its surrounding areas can be used. For the meteorological data provided by each meteorological station, a meteorological interpolation model is used to interpolate the meteorological data of each station, generate the spatial distribution of meteorological data matching each meteorological station, and merge the spatial distributions of meteorological data corresponding to multiple meteorological stations to obtain a smooth climate data map, which is used to show the spatial distribution of climate in the study area. At positions without direct observation data, the estimated value of this position can be deduced by the interpolation model based on the existing measurement data. Exemplarily, the above meteorological interpolation model can be the ANUsplin (ANU surface interpolation, spatial interpolation based on spline functions) model.

[0026] For NDVI, multi-spectral images with a 30-meter resolution from Landsat 8 and Sentinel-2 satellites of Earth Explorer or Copernicus Open Access Hub can be used, and the multi-spectral images are processed such as radiometric correction, atmospheric correction, and cloud detection to match the target resolution. For example, the target resolution can be 20-meter resolution, or 30-meter resolution, or 35-meter resolution, etc.

[0027] For land use data, data within a certain time period can be used. For example, a land dataset from 1999 to 2019 can be used.

[0028] For socio-economic data, open-source data can be used. For example, road data provided by the Open Street Map software can be used. Among them, socio-economic data includes: GDP (Gross Domestic Product), population density, and road data. The socio-economic data needs to be projected and resampled to generate raster data of GDP, population density, and road density in the study area for multiple time periods.

[0029] After obtaining the above data related to carbon sinks, normalization processing is performed on it to eliminate the scale differences between variables and ensure that the influence weights of each variable on the results are reasonable during model training, thereby improving the stability and accuracy of the model. Among them, the data normalization process is as follows: Remote sensing data (such as NDVI) is stored as raster data in a specified format, such as raster data in GeoTIFF format; non-raster data (such as population density, GDP) is first converted into raster data through interpolation or rasterization. Then, based on the raster data, the minimum value, maximum value, mean value, and standard deviation of each variable are determined for the modeling analysis of the remote sensing model.

[0030] The research area can be based on cities. Each city has multiple functional zones planned, and the planning of the functional zones takes into account multiple aspects, such as historical development, geographical factors, economic needs, transportation and infrastructure, and planning strategies. For example, the functional zones of City A include the whole region, the central urban area, the development zone, and the ecological protection area. Another example is that the functional zones of City B include the central business district, the residential area, the industrial area, the cultural and educational area, and the ecological protection area. The carbon sink data in the dataset can be stored corresponding to the functional zones.

[0031] Step 220: For each functional zone, determine the vegetation carbon sink benefit according to the data of the functional zone; obtain the set of influencing factors of the functional zone, where the set of influencing factors includes multiple influencing factors, and the multiple influencing factors include natural environmental factors and human activity characteristic factors; determine the importance percentage of each influencing factor on the vegetation carbon sink benefit, and determine the key factors from the multiple influencing factors according to the importance percentage; fit the key factors with the vegetation carbon sink benefit, and determine the local standardized regression coefficient of the key factors according to the fitting result; analyze the spatial impact of the key factors on the vegetation carbon sink benefit according to the local standardized regression coefficient to obtain the analysis result; determine the optimization strategy of the green space carbon sink benefit of the functional zone according to the key factors and the analysis result.

[0032] Among them, the local standardized regression coefficient is used to characterize the relationship between the influencing factor and the vegetation carbon sink benefit in space. The analysis result is used to characterize the spatial heterogeneity of the vegetation carbon sink benefit.

[0033] a) Determine the vegetation carbon sink benefit of the functional zone according to the data of the functional zone, including: determine the NPP (Net Primary Productivity) of the functional zone according to the remote sensing data of the functional zone; determine the vegetation carbon sink benefit of the functional zone according to the NPP of the functional zone.

[0034] Exemplarily, for each grid after rasterizing the functional zone, calculate the NPP corresponding to the grid according to the remote sensing data of the grid; determine the vegetation carbon sink benefit of the grid according to the NPP corresponding to the grid, and finally obtain the vegetation carbon sink benefits of each grid in the whole functional zone.

[0035] The calculation of NPP can be realized by using a remote sensing model. For example, use the CASA (Carnegie-Ames-Stanford Approach, a process-based terrestrial ecosystem) model to calculate NPP.

[0036] Exemplarily, the calculation formula of NPP is:

[0037] In the formula, Indicates the carbon absorption of vegetation at a single pixel value x and time t (single day), with the unit of grams of organic carbon per square meter per day (gC / m 2 · a). In the formula, Indicates at a single pixel value And time The photosynthetically active radiation absorbed by plants at (single day), with the unit of megajoules per square in unit time (MJ / m 2 / t), Indicates at a single pixel value And time The light use efficiency at (single day).

[0038] In the embodiments of the present application, the Moderate Resolution Imaging Spectroradiometer NPP dataset is also used to verify the accuracy of the calculation results given by the CASA model. Exemplarily, based on the above net primary productivity of vegetation, the MOD17A3 data with a resolution of 500 meters is resampled to the target resolution. For example, the MOD17A3 data with a resolution of 500 meters is resampled to a resolution of 30 meters. Multiple samples are selected in the study area (such as selecting 1000 samples) to evaluate the correlation between the NPP of the MOD17A3 data and the estimated values of the CASA model. Among them, the vegetation cover data, climate data, and time series data are raster data, and the pixel is the smallest unit of the raster data.

[0039] Optionally, the vegetation carbon sink benefit can be represented by the vegetation carbon sink capacity. The calculation formula of the vegetation carbon sink capacity is: ; In the formula, the coefficients of 1.62 and 0.45 are obtained through the carbon fixation process and carbon conversion efficiency of vegetation. UGCSC is the vegetation carbon sink capacity, representing the average carbon sink per unit time, with the unit of grams per square in unit time (g / m 2 / t).

[0040] b) Obtain the set of impact factors for the functional partition. The set of impact factors includes multiple impact factors, and the multiple impact factors include natural environmental factors and human activity characteristic factors.

[0041] Establish a set of influencing factors that affect the carbon sink benefits of green space in functional zoning. First, preliminary screening is required to establish a candidate influencing factor pool based on multi-source data fusion. The candidate influencing factor pool includes natural environment factors and human activity characteristic factors. Among them, natural environment factors include climate influencing factors and non-climatic natural influencing factors. Therefore, the candidate factor pool mainly includes three categories of factors: climate influencing factors, non-climatic natural influencing factors and human activity characteristic factors. It can also include other categories of influencing factors, such as landscape factors; combined with literature research and domain knowledge, the dynamic weight screening algorithm (Dynamic Weight Screening Algorithm, DWSA) is used to screen out factors that are theoretically strongly correlated with the carbon sink benefits of the functional zoning. For example, based on weight factors such as literature weight, data quality score and acquisition cost, the dynamic factor weight is calculated to screen factors that are theoretically strongly correlated with carbon sink benefits. Through data cleaning, interpolation and normalization, the spatiotemporal resolution of each factor is ensured to match remote sensing data such as NDVI, and the correlation between each factor and urban carbon sink capacity is evaluated through correlation analysis. Factors with low correlation or redundant factors are eliminated to construct an influencing factor set.

[0042] Exemplarily, multiple candidate impact factors of functional partitions are obtained; the literature support, data quality score and acquisition cost corresponding to each candidate impact factor are obtained; the dynamic factor weight of each candidate impact factor is calculated, and the calculation formula of the dynamic factor weight is as follows: ; Add the candidate influencing factors whose dynamic factor weight is greater than the weight threshold to the influencing factor set of the functional partition; where W DF is the dynamic factor weight, LS is the literature support, R DQ is the data quality score, and AC is the acquisition cost.

[0043] Optionally, the multiple influencing factors include at least some of the following: average annual temperature, average annual precipitation, solar radiation; slope, altitude; population density, gross domestic product, human footprint index, green space coverage, night light index; landscape connectivity index, landscape shape index, and landscape patch density.

[0044] Among them, the average annual temperature, average annual precipitation and solar radiation are climate influencing factors; slope and altitude are non-climatic influencing factors; population density, gross domestic product, human footprint index and green space coverage rate are characteristic factors of human activities; landscape connectivity index (CONTAG), landscape shape index (Landscape Shape Index, LSI) and landscape patch density are landscape indicators, that is, landscape factors.

[0045] The calculation formulas for monthly mean temperature (TEM) and monthly precipitation (PRE) (based on the Anusplin interpolation model) are: ; ; In the formula, represents the longitude of the location where the pixel is located, represents the latitude of the location where the pixel is located, represents the monthly average temperature of the pixel obtained by interpolation, represents the monthly average precipitation of the pixel obtained by interpolation. The observed values of meteorological monthly temperature and meteorological monthly precipitation are extended to each pixel in the study area using the ANUsplin interpolation model.

[0046] The formula for calculating the average value SR of daily solar radiation is: ; In the formula, represents the solar radiation intensity on the j-th day, and its unit is watts per square meter (W / m 2 ).

[0047] The formula for calculating the slope (calculated based on digital elevation model data) is: ; In the formula, Slope is the slope, z is the elevation value, / and / represent the elevation change rates along the X and Y directions respectively. The altitude values corresponding to each pixel are extracted through the Digital Elevation Model (DEM), and the altitude value on each pixel represents the altitude of that location.

[0048] The population density ( ) is calculated as: ; In the formula, Population is the population quantity of a single pixel, Area is the area of a single pixel area, and its unit is square kilometers (km 2 ).

[0049] The formula for calculating GDP (allocated to grid cells in combination with remote sensing geographic boundary data) is: ; In the formula, is the GDP of the i-th single pixel, is the area of the i-th single pixel, is the total area of single pixels, is the total GDP.

[0050] The calculation formula for Land Use Functions (LUF) is as follows: ; In this formula, m is the total number of land use types in the landscape, is the frequency or intensity of the J-th land use change, is the pixel area of the J-th land use, Area is the total pixel area, and the land use change frequency (such as the number of times of conversion from farmland to construction land) is obtained from multi-temporal remote sensing classification data.

[0051] The calculation formula for the night light index is as follows: ; In the formula, is the night light brightness value of pixel i, and n is the total number of pixels in the study area. The night light index can directly reflect the spatial distribution and intensity of human activities.

[0052] Based on the above night light index, population density, GDP, and land use intensity, the human footprint index is calculated as follows. The calculation formula for the human footprint index is as follows: ; In the formula, NLI is the night light index, GDP is the gross domestic product per unit area, LUF is the land use intensity, , , , are weight factors.

[0053] The green space coverage rate The calculation formula is as follows: ; In the formula, Green Area is the total area of pixels with NDVI higher than the set threshold, and Total Area is the total pixel area.

[0054] The connectivity index is used to measure the connectivity between different types of patches in the landscape. Its calculation formula is as follows: ; In the formula, is the boundary frequency between types and , and m is the total number of land use types in the landscape.

[0055] The calculation formula for the landscape shape index LPI is as follows: ; In the formula, Represents the area of the largest patch in the landscape, Represents the total area of the entire study area.

[0056] The patch density PD calculation formula is: ; In the formula, N is the total number of patches, and A is the total landscape area.

[0057] The above landscape metrics can be obtained by importing the above NDVI and land use data into the landscape pattern analysis software Fragstats and calculating through this software.

[0058] c) Determine the percentage of importance of each influencing factor to the vegetation carbon sequestration benefit, and determine the key factors from multiple influencing factors according to the percentage of importance.

[0059] Optionally, sort multiple influencing factors according to the percentage of importance, and determine the key factors that meet the screening criteria according to the sorting; for example, sort multiple influencing factors in descending order of the percentage of importance, and determine the top S influencing factors as the key factors, where S is a positive integer greater than 1. Or, alternatively, the influencing factors with a percentage of importance greater than or equal to the percentage threshold can be determined as the key factors.

[0060] Optionally, calculate the percentage of importance of each influencing factor to the vegetation carbon sequestration benefit through the Boosted Regression Trees (BRT) model, and then determine the key factors from multiple influencing factors according to the percentage of importance. Exemplarily, input the vegetation carbon sequestration benefit into the boosted regression tree model, and output the percentage of importance of each influencing factor to the vegetation carbon sequestration benefit through the boosted regression tree model.

[0061] Before using the boosted regression tree model, first construct a boosted regression tree model with the carbon sequestration capacity as the dependent variable and multiple influencing factors as the independent variables; determine the vegetation carbon sequestration benefit of each grid after rasterizing the functional partition as the characteristic variable, input the characteristic variable into the boosted regression tree model, and optimize the boosted regression tree model through cross-validation to obtain the optimized boosted regression tree model. Specifically, the process of determining the key factors affecting the carbon sequestration ability includes: taking the vegetation carbon sequestration benefits (such as UGCSC) of the whole region, central urban area, development zone, and ecological protection area as the dependent variable, and slope, altitude, temperature, rainfall, solar radiation, human footprint index, greening coverage rate, landscape shape index, connectivity index, patch density, etc. as the independent variables, and establishing a boosted regression tree model. The model fitting can be implemented by calling packages such as "caret", "gbm", and "dismo" in R4.1.0 software. For the optimization training of the model, a self-supervised learning training method is adopted.

[0062] Then, based on the enhanced regression tree model (or the optimized enhanced regression tree model), count the number of times each influencing factor serves as a branch node in the decision tree, and calculate the reduction in error of the model's prediction when each influencing factor serves as a branch node; perform a weighted sum of the number of times each influencing factor serves as a branch node and its corresponding reduction in error, and normalize the weighted sum to the importance percentage corresponding to each influencing factor.

[0063] Finally, the enhanced regression tree model can directly output the importance percentage as the sorting result of the key factors affecting the vegetation carbon sequestration benefit. For example, the enhanced regression tree model screens and outputs the sorting result of the key factors. Exemplarily, for the importance value obtained after the weighted sum, after normalization processing, the importance percentage is obtained. The normalization calculation formula is: ; is the importance percentage of the q-th factor, is the original importance value of the q-th factor, is the original importance value of the k-th factor, and Q is the total number of factors.

[0064] After obtaining the importance percentage, dynamic weight correction is also performed. The correction calculation formula is: = 0.8 × + 0.2 × ; where, represents the updated importance value of the q-th factor in this round of iteration, represents the historical importance value of the -th factor in the previous round of iteration, represents the newly obtained importance value of the -th factor in the current calculation.

[0065] As Figure 3 shows, based on the enhanced regression tree model, the following importance percentages (%) of climate change and human activity variables for the urban green space carbon sequestration capacity (UGCSC) of different functional zones in the study area are calculated. Note: BJ refers to the whole region; CUZ refers to the central urban area; DEZ refers to the development zone; ECZ refers to the ecological protection area.

[0066] The following results are obtained based on the regression tree model: In the entire area (BJ) of City A in the study area, the impact factor that has the greatest impact on the carbon sequestration benefit is slope, with an importance ratio of 78.9%; in the ecological conservation area (ECZ), the impact factor that has the greatest impact on the carbon sequestration benefit is slope, with an importance ratio of 73.8%; in the development zone (DEZ), the impact factor that has the greatest impact on the carbon sequestration benefit is altitude, with an importance ratio of 79.9%; in the central urban area (CUZ), the impact factor that has the greatest impact on the carbon sequestration benefit is temperature, with an importance percentage of 45.7%. The importance percentage can identify the key dominant factors and guide the construction of urban green spaces. The key dominant factor is the factor among the key factors that dominates the impact on the carbon sequestration benefit.

[0067] Exemplarily, the above key factors can be impact factors without multicollinearity.

[0068] d) Fit the key factors with the vegetation carbon sequestration benefit, and determine the local standardized regression coefficients of the key factors according to the fitting results.

[0069] Optionally, the vegetation carbon sequestration benefit is weighted by a Gaussian kernel function to construct a spatial weight matrix of the vegetation carbon sequestration benefit. The spatial weight matrix is used to measure the spatial similarity and influence degree between different geographical units. The geographical unit refers to the grid after rasterizing the functional partition; the Akaike Information Criterion (AIC) or Bayesian Information Criterion (BIC) is used to calculate the optimal bandwidth value of each key factor. The optimal bandwidth value is used to optimize the regression fitting of the key factor to the vegetation carbon sequestration benefit; based on the spatial weight matrix and the optimal bandwidth values of each key factor, the key factors and the vegetation carbon sequestration benefit are fitted through a Multi-scale Geographically Weighted Regression (MGWR) model to obtain the fitting results corresponding to each key factor; for each key factor, the local regression coefficients corresponding to each grid are extracted according to the fitting results, and the local regression coefficients are standardized to obtain the local standardized regression coefficients of the key factors.

[0070] The spatial weight matrix of the vegetation carbon sink benefit affects the recognition and fitting effect of the multi-scale geographically weighted regression model on the spatial heterogeneity between variables, and the fitting effect can be tested using this spatial weight matrix. Moreover, the optimal bandwidth value of each influencing factor can optimize the regression fitting of this influencing factor to the vegetation carbon sink benefit. Therefore, before fitting the key factors and the vegetation carbon sink benefit, the Gaussian kernel function is used to weight the spatial data of the vegetation carbon sink benefit to construct a spatial weight matrix; and AIC or BIC is used as the basis for bandwidth selection to determine the optimal bandwidth value of each key factor, so as to ensure that the MGWR model can reflect the spatial heterogeneity and scale differences between variables.

[0071] Subsequently, for each key factor, based on the spatial weight matrix and the optimal bandwidth value of this key factor, the MGWR model is used to fit and analyze the vegetation carbon sink benefit and this key factor to obtain the fitting result of this key factor; from the fitting result of this key factor, the local regression coefficients corresponding to each grid are extracted, and the local regression coefficients are standardized to obtain the local standardized regression coefficients of this key factor under different grids. e) Analyze the spatial impact of the key factor on the vegetation carbon sink benefit based on the local standardized regression coefficients to obtain the analysis result.

[0072] For each key factor, based on the local standardized regression coefficients of this key factor, identify the spatial heterogeneity of this key factor on the vegetation carbon sink benefit to obtain the identification result, and complete the spatial quantitative assessment of the influence intensity of this key factor to obtain the assessment result. The above identification result and assessment result are included in the above analysis result.

[0073] In steps d) and e), the MGWR model is used to determine the spatial impact of the key factor on the vegetation carbon sink benefit, identify the spatial heterogeneity of the key factor on the vegetation carbon sink benefit, and complete the spatial quantitative assessment of the influence intensity of each factor.

[0074] Optionally, first, obtain the spatial data of the vegetation carbon sink benefit and the spatial distribution data of multiple potential influencing factors within the target area. Select the Gaussian kernel function as the spatial weighting function to perform spatial weighting processing on the carbon sink benefit data. Construct a spatial weight matrix according to the spatial position relationship to measure the spatial similarity and potential spatial influence degree between any two geographical units. The expression of the spatial weight matrix is as follows: ; where is the spatial weight between unit and unit , represents the spatial distance between unit and unit , is the bandwidth parameter.

[0075] To determine the optimal bandwidth value for each key factor, AIC or BIC is used for bandwidth optimization. For the spatial response scales of different variables, by traversing different bandwidth values to minimize the AIC / BIC value, the optimal bandwidth value is determined, enabling the model to reflect the scale differences and heterogeneity characteristics of variables in space.

[0076] Based on the constructed spatial weight matrix and the optimal bandwidth value of each key factor, an MGWR model is constructed to perform a fitting analysis on the relationship between the vegetation carbon sequestration benefit and multiple key factors. The form of the MGWR model is as follows: ; where, is the vegetation carbon sequestration benefit value of unit α, is the spatial location at which the local intercept term represents the basic value or background level of the vegetation carbon sequestration benefit when all key factors are zero at the α-th unit location in the study area, is the value of the k-th key factor unit , represents the regression coefficient of key factor k at the location ( , ) with a bandwidth of , ([[]] , ) represents a certain location of unit , is the unit corresponding residual term, and Q is the total number of key factors.

[0077] According to the fitting results of the model, the local regression coefficients of each key factor in each geographical grid unit are extracted. To achieve comparability and visual analysis, all coefficients are standardized using the following formula: ; where, and are the mean and standard deviation of all local regression coefficients of key factor k respectively, represents the local regression coefficient of key factor k at the location ([[]] , ), is the local regression coefficient at the location of unit after standardization, that is, the local standardized regression coefficient at the location of unit .

[0078] Finally, based on the spatial distribution of the local standardized regression coefficients, the identification of the influence intensity of key factors on the vegetation carbon sequestration benefit in different regions is realized. This process can be further deepened by means such as spatial visualization maps, cluster analysis, or local significance tests, so as to support the formulation of subsequent green space optimization and nature-based solution strategies.

[0079] In the embodiment of the present application, the following results are obtained based on MGWR: The local standardized regression coefficients of the vegetation carbon sequestration benefit are calculated through a multi-scale geographically weighted regression model to quantify the spatial heterogeneity of the independent variable (i.e., the key factor) on the dependent variable (i.e., the vegetation carbon sequestration benefit). Based on this method, the spatial heterogeneity effects of each key factor on the urban green space carbon sequestration capacity are scientifically identified and quantified, providing a scientific basis and technical support for optimizing the layout of urban green infrastructure and enhancing the carbon sequestration benefit.

[0080] f) Determine the optimization strategy for the green space carbon sequestration benefit of the functional area according to the key factors and the analysis results.

[0081] Optionally, analyze the change trend between the key factor and the vegetation carbon sequestration benefit, determine the interval where the key factor has a significant impact on the vegetation carbon sequestration benefit, and obtain the threshold range of the key factor; construct a structural equation model according to the key factor and its threshold range, and generate the influence path and action intensity of the key factor on the vegetation carbon sequestration benefit through the structural equation model; determine the optimization strategy for the carbon sequestration benefit of the functional area according to the influence path, action intensity and analysis results.

[0082] Exemplarily, determine the key dominant factor from the key factors. For example, determine the dominant factor as the key factor with the largest percentage of importance; analyze the change trend between the key dominant factor and the vegetation carbon sequestration benefit, determine the interval where the key dominant factor has a significant impact on the vegetation carbon sequestration benefit, and obtain the threshold range of the key dominant factor; construct a structural equation model according to the key dominant factor and its threshold range, and generate the influence path and action intensity of the key dominant factor on the vegetation carbon sequestration benefit through the structural equation model; determine the optimization strategy for the carbon sequestration benefit of the functional area according to the influence path, action intensity and analysis results.

[0083] For example, according to the partial dependence plot between the key factor and the vegetation carbon sequestration benefit, analyze the change trend between the key factor and the vegetation carbon sequestration benefit. Specifically, based on the existing results, use the partial dependence plot (PDP) in the BRT model to analyze the marginal effects of key indicators of climate change and human activities (i.e., human activity characteristic factors) on the green space carbon sequestration capacity of the functional area. The goal of the partial dependence plot is to show the marginal impact of a single factor (or a group of factors) on the model prediction results. By fixing other factors and gradually changing the value of the target factor, observe the change of the model prediction value (such as the carbon sequestration capacity), so as to analyze the role of the target factor.

[0084] For the target factor and the model prediction , the partial dependence value is calculated as: ; In the formula, is the target factor, that is, the target factor is the kth key factor, represents the values of other factors, is the prediction function of the model, and S is the total number of key factors. The partial dependence plot shows the mean trend of the model prediction value when the value of the target factor changes. The partial dependence value here can be used to represent the marginal effect of key indicators of climate change and human activities on the green space carbon sink capacity of the functional partition corresponding to the target key dominant factor.

[0085] Based on the partial dependence plot, determine the change trend between the key dominant factor and the vegetation carbon sink benefits of each functional partition in the study area, and respectively estimate the significant interval of the impact of each target key dominant factor on the carbon sink capacity and the critical point of the decreasing marginal effect. Taking the carbon sink capacity as an example to represent the carbon sink benefit, as Figure 4 shown, it shows the change trend of the key factor corresponding to the whole area of City A and the vegetation carbon sink capacity. For the "slope" within the range of 0 - 30°, set value points of 0°, 5°, 10°... and keep the values of other factors unchanged. The partial dependence plot shows that the marginal effect of the slope on the carbon sink capacity is significant within the range of 0 - 13.5°. When the slope reaches 13.5°, its incremental effect tends to be stable. When the slope is in the range of 13.5 - 30°, its marginal effect weakens. Thus, the embodiment of the present application determines the optimized threshold of the slope to be 13.5°. Based on this method, scientifically determine the threshold range of the key dominant factor, providing theoretical support and optimization basis for improving the urban green space carbon sink capacity and guiding the green space construction.

[0086] Optionally, the above PDP is output by an enhanced regression tree model. For example, input the vegetation carbon sink benefit into the enhanced regression tree model, and output the partial dependence plot between the influencing factor and the vegetation carbon sink benefit through the enhanced regression tree model; then, according to the partial dependence plot between the key factor and the vegetation carbon sink benefit, analyze the change trend between the key factor and the vegetation carbon sink benefit.

[0087] Subsequently, aiming at increasing carbon sinks and reducing carbon emissions, construct a structural equation model by combining the key dominant factor and its threshold range, and propose optimization strategies for the carbon sink benefits of different functional partitions in the study area.

[0088] Optionally, the structural equation model is: ; Wherein, is the matrix of the action path coefficients between the endogenous latent variables, and T is the matrix of the influence path coefficients between the exogenous latent variables and the endogenous latent variables. is the random disturbance term. are the endogenous latent variables. are the exogenous latent variables. The endogenous latent variable is the vegetation carbon sequestration benefit, and the exogenous latent variables are the key factors.

[0089] To study the comprehensive action mechanism of UGCSC with climate change, human activities, and landscape pattern, the SEM structural equation model framework can be constructed using the SPSS add-in AMOS. The structural equation model uses a system of linear equations to represent the relationship between the measured variables and the latent variables. The latent variables cannot be directly observed and need to be estimated by the measured variables.

[0090] The structural equation model - measurement model is: ; ; In the structural equation model, X and Y are the exogenous measured variables and the endogenous measured variables respectively. and are the exogenous latent variable and the endogenous latent variable respectively. is on the factor loading matrix. is on the factor loading matrix. and are the measurement errors. In the embodiments of the present application, the exogenous latent variables are climate factors (annual average temperature, precipitation, solar radiation), terrain factors (slope, altitude), human activity characteristic factors (green space coverage rate, night light index), landscape factors (connectivity index (CONTAG), landscape shape index (LSI), and patch density (PD)), and the endogenous latent variable is the carbon sequestration capacity UGCSC.

[0091] The measured variables are the evaluation indicators of the latent variables. The measured variables are slope, altitude, temperature, solar radiation, rainfall, human footprint index, greening coverage rate, landscape shape index, CONTAG, patch density, etc. For example, the latent variable (climate factor) is composed of the measured variables (annual average temperature), (annual average precipitation), (Solar radiation) are jointly reflected. In the measurement model, the existing manifest variables (such as climate factors, terrain factors, and human activity characteristic factors) are associated and defined with the corresponding latent variables. Among them, climate factors are exogenous latent variables measured by manifest variables such as annual average temperature, precipitation, and solar radiation; terrain factors are exogenous latent variables measured by manifest variables such as slope and elevation; human activity characteristic factors are exogenous latent variables measured by manifest variables such as green space coverage rate and night light index. The carbon sequestration capacity is an endogenous latent variable, which is characterized by manifest variables such as vegetation coverage rate, normalized difference vegetation index (NDVI), and net primary productivity (NPP). Based on the theory and research questions, the causal paths of latent variables are defined by the structural equation.

[0092] The structural equation model - the structural model is: ; In the structural equation model - structural model is the coefficient matrix of the action paths between endogenous latent variables; is the coefficient matrix of the influence paths between exogenous latent variables and endogenous latent variables. is the random disturbance term. In the embodiments of the present application, the latent variables are terrain, climate, human activities, landscape pattern, etc. In the structural model, the path relationships of exogenous latent variables to endogenous latent variables are defined to reveal the influence paths and action intensities of climate factors, terrain factors, and human activity characteristic factors on the carbon sequestration capacity. For example, the climate factor quantifies the marginal effects of changes in annual average temperature and precipitation on the carbon sequestration capacity through its path coefficient; the human activity characteristic factor quantifies the combined effects of green space coverage rate and night light index on the carbon sequestration capacity through the path coefficient.

[0093] The present application uses standardized residuals, standardized root mean square residuals (SRMR), root mean square error of approximation (RMSEA), chi-square to degrees of freedom ratio ( / df), goodness of fit index (GFI), and comparative fit index (CFI) to test the simulation results. Generally, it is considered that, When / df < 3, P < 0.05, RMSEA < 0.05, SRMR < 0.08, GFI > 0.95, and CFI > 0.95, the model fits well. Among them, P represents the path coefficient. When the goodness-of-fit index of the structural model of the present invention meets the requirements, the path relationship among terrain, climate, human activities, landscape pattern, and UGCSC will be obtained. The main influencing factors (i.e., key dominant factors) of UGCSC change are judged according to the significance and the magnitude of the standardized path coefficient, and the influence direction of each key factor on UGCSC change, i.e., positive influence and negative influence, is judged according to the sign of the standardized path coefficient. According to the path relationship from the independent variable to the dependent variable, the influence mechanism of each key factor on UGCSC change is obtained, so as to judge the direct influence and indirect influence of each influencing factor on UGCSC, and thus the total influence of each influencing factor on UGCSC is obtained. Based on the total influence of each influencing factor on UGCSC, targeted carbon sink benefit optimization strategies can be proposed for different functional zones of the study area.

[0094] In this embodiment, three SEM structural equation model frameworks are constructed for different functional zones of City A by using the SPSS (Statistical Product and Service Solutions, statistical software package for social sciences) add-in AMOS (Analyze of Moment Structures, matrix structure analysis), namely, the structural equation model of the relationship between the coefficient of variation of urban green space carbon sink capacity and its driving factors in the central urban area, the structural equation model of the relationship between the urban green space carbon sink capacity and its driving factors in the development zone, and the structural equation model of the relationship between the urban green space carbon sink capacity and its driving factors in the ecological protection area. Each functional zone corresponds to its own structural equation model.

[0095] In the embodiment of the present application, the following results are obtained based on the Structural Equation Modeling (SEM): The coefficient of determination (R 2 ) of the carbon sink capacity is calculated through the structural equation model to quantify the total explanatory ability of exogenous latent variables (climate factor, terrain factor, human activity characteristic factor) on the endogenous latent variable carbon sink capacity. In this embodiment, it is shown that the exogenous latent variables defined in the model can explain 69% of the spatial coefficient of variation of the urban green space carbon sink capacity in the central urban area of City A, 86% of the spatial coefficient of variation of the urban green space carbon sink capacity in the development zone of City A, and 83% of the spatial coefficient of variation of the urban green space carbon sink capacity in the ecological protection area of City A.

[0096] The following takes the structural equation model of the relationship between the coefficient of variation of the urban green space carbon sink capacity in the central urban area of City A and its driving factors in the embodiment of the application as an example for disclosure: Among them, slope, altitude, temperature, solar radiation and carbon sink capacity all have a highly significant positive correlation (p < 0.05). Among them, the exogenous latent variable topographic factor composed of altitude and slope has the greatest impact on carbon sink capacity (the total standardized path coefficient is 0.61, the direct impact is 0.61, and the indirect impact is 0.10); rainfall, human footprint index, connectivity index and carbon sink capacity all have a highly significant positive correlation (p < 0.05); among them, although the measured variables green space coverage rate, landscape shape index, and patch density have a significant negative correlation with their latent variables (p < 0.05), while the exogenous latent variable human activity characteristic factor and landscape model factor have a highly significant negative correlation with carbon sink capacity (p < 0.05, the direct impact of the human activity characteristic factor is -0.23, and the indirect impact is -0.36; the direct impact of the landscape model factor is -0.16, and the indirect impact is -0.04). Therefore, the green space coverage rate, landscape shape index, and patch density have a significant positive correlation with carbon sink capacity (p < 0.05). Therefore, in the central urban area of City A, the topographic factor can be optimized by setting the threshold to guide the optimization of urban green space. The two points of the present invention are that by quantitatively analyzing the influencing factor set, it can be obtained that some measured variables are negatively correlated with exogenous latent variables, and the urban carbon sink capacity can still be promoted. For example, the higher the green space coverage rate, the more restricted the space for human activities, which has an inhibitory effect on the carbon sink capacity. However, due to the interaction between the green space coverage rate and human activities, the green space coverage rate and carbon sink capacity are positively correlated. The higher the green space coverage rate, the better the carbon sink benefit.

[0097] Summarizing the above three structural models, the optimization strategies and bases are as follows: Based on the model training results of the central urban area of City A, as Figure 5 shown (the numbers next to the arrows are the standardized path coefficients), in the central urban area model of City A, the topographic factor has the greatest impact on carbon sink capacity (the total standardized path coefficient is 0.61, the direct impact is 0.61, and the indirect impact is 0.10). The optimization strategy is to strengthen the control of the optimization threshold of slope and altitude in terrain shaping. The optimization threshold of the slope for urban green space construction in the central urban area of City A is 15.5°, and the optimization threshold of altitude is 250 meters (meter, m).

[0098] Based on the model training results of the development zone of City A, the topographic factor has the greatest impact on carbon sink capacity (the total standardized path coefficient is 0.99, the direct impact is 0.99, and the indirect impact is 0.17). The optimization strategy is to strengthen the control of the optimization threshold of slope and altitude in terrain shaping. The optimization threshold of the slope for urban green space construction in the development zone of City A is 9.7°, and the optimization threshold of altitude is 1205.7m.

[0099] Based on the training results of the ecological reserve model in City A, the landscape model factor has the greatest impact on the carbon sink capacity (the total standardized path coefficient is 0.26, the direct impact is 0.26, and the indirect impact is 0.32). The optimization strategy is to increase the connectivity index, and the optimization threshold of the connectivity index is 71.5.

[0100] In summary, the optimization method for the green space carbon sink benefit provided in this embodiment obtains a dataset related to carbon sinks in the research area. This dataset includes data for multiple functional areas. For each functional area, the vegetation carbon sink benefit of the functional area is determined based on the data of the functional area. Then, an impact factor set for the functional area is obtained. The impact factor set includes natural environment factors and human activity characteristic factors. The percentage of importance of each of these impact factors on the vegetation carbon sink benefit is determined, and the degree of influence of the impact factors on the green space carbon sink is represented by this percentage of importance, realizing the quantification of the influencing factors of the green space carbon sink. Subsequently, key factors are determined from multiple impact factors according to the percentage of importance, and the local standardized regression coefficients of the key factors are calculated. The spatial impact of the key factors on the vegetation carbon sink benefit is analyzed based on the local standardized regression coefficients. Then, based on these key factors and the corresponding analysis results, an optimization strategy for the green space carbon sink benefit of the functional area is determined, formulating an optimization strategy for the green space carbon sink benefit targeted at different functional areas. Moreover, the impact factors not only include natural environment factors but also consider human activity characteristic factors, enabling the comprehensive improvement of the urban green space carbon sink capacity.

[0101] Corresponding to the above method embodiment, Figure 6 The schematic diagram of an optimization device for green space carbon sink benefit is shown. As Figure 6 shown, the optimization device for green space carbon sink benefit includes: An acquisition module 401, configured to acquire a dataset related to carbon sinks in the research area. The dataset includes data for multiple functional areas, and the multiple functional areas are obtained by dividing the research area according to urban functions; The processing module 402 is configured to, for each functional partition, determine the vegetation carbon sequestration benefit of the functional partition according to the data of the functional partition; obtain the set of impact factors of the functional partition, where the set of impact factors includes multiple impact factors, and the multiple impact factors include natural environmental factors and human activity characteristic factors; determine the importance percentage of each impact factor on the vegetation carbon sequestration benefit, and determine the key factors from the multiple impact factors according to the importance percentage; fit the key factors with the vegetation carbon sequestration benefit, and determine the local standardized regression coefficient of the key factors according to the fitting result, where the local standardized regression coefficient is used to characterize the relationship between the impact factor and the vegetation carbon sequestration benefit in space; analyze the spatial impact of the key factors on the vegetation carbon sequestration benefit according to the local standardized regression coefficient, and obtain the analysis result, where the analysis result is used to characterize the spatial heterogeneity of the vegetation carbon sequestration benefit; and determine the optimization strategy for the green space carbon sequestration benefit of the functional partition according to the key factors and the analysis result.

[0102] In some embodiments, the processing module 402 determines the optimization strategy for the carbon sequestration benefit of the functional partition according to the key factors, including: analyzing the change trend between the key factors and the vegetation carbon sequestration benefit, determining the interval where the key factors have a significant impact on the vegetation carbon sequestration benefit, and obtaining the threshold range of the key factors; constructing a structural equation model according to the key factors and their threshold range, and generating the impact path and action intensity of the key factors on the vegetation carbon sequestration benefit through the structural equation model; and determining the optimization strategy for the carbon sequestration benefit of the functional partition according to the impact path, action intensity and analysis result.

[0103] In some embodiments, the structural equation model is: ; where is the matrix of action path coefficients between endogenous latent variables, T is the matrix of impact path coefficients between exogenous latent variables and endogenous latent variables, is the random disturbance term, are the endogenous latent variables, are the exogenous latent variables, the endogenous latent variable is the vegetation carbon sequestration benefit, and the exogenous latent variable is the key factor.

[0104] In some embodiments, the processing module 402 analyzes the change trend between the key factors and the vegetation carbon sequestration benefit, including: inputting the vegetation carbon sequestration benefit into the boosted regression tree model, and outputting the partial dependence plot between the impact factor and the vegetation carbon sequestration benefit through the boosted regression tree model; and analyzing the change trend between the key factors and the vegetation carbon sequestration benefit according to the partial dependence plot between the key factors and the vegetation carbon sequestration benefit.

[0105] In some embodiments, the processing module 402 determines the importance percentages of various influencing factors on the vegetation carbon sequestration benefit, and determines key factors from the multiple influencing factors according to the importance percentages, including: inputting the vegetation carbon sequestration benefit into the enhanced regression tree model, and outputting the importance percentages of various influencing factors on the vegetation carbon sequestration benefit through the enhanced regression tree model; sorting the multiple influencing factors according to the importance percentages, and determining the key factors that meet the screening conditions according to the sorting.

[0106] In some embodiments, the processing module 402 is further configured to construct an enhanced regression tree model with the carbon sequestration capacity as the dependent variable and multiple influencing factors as the independent variables; determine the vegetation carbon sequestration benefits of each grid after rasterizing the functional partition as the characteristic variables, input the characteristic variables into the enhanced regression tree model, and optimize the enhanced regression tree model through cross-validation to obtain an optimized enhanced regression tree model.

[0107] In some embodiments, the processing module 402 outputs the importance percentages of various influencing factors on the vegetation carbon sequestration benefit through the enhanced regression tree model, including: based on the enhanced regression tree model, counting the number of times each influencing factor serves as a branch node in the decision tree, and calculating the error reduction amount of the model predicting each influencing factor as a branch node; performing a weighted sum on the number of times each influencing factor serves as a branch node and the corresponding error reduction amount, and normalizing the weighted sum to the importance percentage corresponding to each influencing factor.

[0108] In some embodiments, the processing module 402 obtains the set of influencing factors for the functional partition, including: obtaining multiple candidate influencing factors for the functional partition; obtaining the literature support degree, data quality score, and acquisition cost corresponding to each candidate influencing factor; calculating the dynamic factor weight of each candidate influencing factor, and the calculation formula of the dynamic factor weight W is as follows: ; adding the candidate influencing factors with the dynamic factor weight greater than the weight threshold to the set of influencing factors for the functional partition; where W DF is the dynamic factor weight, LS is the literature support degree, R DQ is the data quality score, and AC is the acquisition cost.

[0109] In some embodiments, the multiple influencing factors include at least some of the following: annual average temperature, annual average precipitation, solar radiation; slope, altitude; population density, gross domestic product, human footprint index, green space coverage rate; landscape connectivity index, landscape shape index, landscape patch density.

[0110] In some embodiments, the processing module 402 fits multiple impact factors with the vegetation carbon sequestration benefit, and determines the local standardized regression coefficients of the key factors according to the fitting results, including: weighting the vegetation carbon sequestration benefit through a Gaussian kernel function to construct a spatial weight matrix of the vegetation carbon sequestration benefit, where the spatial weight matrix is used to measure the spatial similarity and influence degree between different geographical units, and the geographical unit refers to the grid after rasterizing the functional area; calculating the optimal bandwidth value of each key factor by using the Akaike information criterion or the Bayesian information criterion, where the optimal bandwidth value is used to optimize the regression fitting of the key factor to the vegetation carbon sequestration benefit; fitting the key factor and the vegetation carbon sequestration benefit through a multi-scale geographically weighted regression model based on the spatial weight matrix and the optimal bandwidth values of each key factor to obtain the fitting results corresponding to each key factor; for each key factor, extracting the local regression coefficients corresponding to each grid according to the fitting results, and performing standardization processing on the local regression coefficients to obtain the local standardized regression coefficients of the key factor.

[0111] It should be noted that the optimization device for the green space carbon sequestration benefit in this embodiment is used to implement the corresponding optimization method for the green space carbon sequestration benefit in the foregoing method embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be elaborated here.

[0112] Figure 7 It is a schematic block diagram of an electronic device provided by an embodiment of the present application. The specific implementation of the electronic device in the specific embodiment of the present application is not limited. Exemplarily, the electronic device may be a server or a terminal. As Figure 7 shown, the electronic device may include: a processor 502, a communication interface 504, a memory 506, and a communication bus 508. Among them: The processor 502, the communication interface 504, and the memory 506 communicate with each other through the communication bus 508.

[0113] The communication interface 504 is used to communicate with other electronic devices or servers.

[0114] The processor 502 is used to execute the program 510, and specifically may execute the relevant steps in any of the foregoing method embodiments for optimizing the green space carbon sequestration benefit.

[0115] Specifically, the program 510 may include program codes, and the program codes include computer operation instructions.

[0116] The processor 502 may be a CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. One or more processors included in the intelligent device may be of the same type of processor, such as one or more CPUs; or may be of different types of processors, such as one or more CPUs and one or more ASICs.

[0117] RISC-V is an open-source instruction set architecture based on the reduced instruction set (RISC) principle, which can be applied to various aspects such as microcontrollers and FPGA chips. Specifically, it can be applied in the fields of Internet of Things security, industrial control, mobile phones, personal computers, etc. And because it takes into account the reality of small size, fast speed, and low power consumption in its design, it is especially suitable for modern computing devices such as warehouse-scale cloud computers, high-end mobile phones, and tiny embedded systems. With the rise of artificial intelligence Internet of Things (AIoT), the RISC-V instruction set architecture has received more and more attention and support, and is expected to become the next-generation CPU architecture widely used.

[0118] The computer operation instructions in the embodiments of the present application may be computer operation instructions based on the RISC-V instruction set architecture. Correspondingly, the processor 502 may be designed based on the RISC-V instruction set. Specifically, the chip of the processor in the electronic device provided in the embodiments of the present application may be a chip designed using the RISC-V instruction set. This chip can execute executable code based on the configured instructions, thereby implementing the optimization method of the green land carbon sink benefit in the above embodiments.

[0119] The memory 506 is used to store the program 510. The memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0120] The program 510 is specifically used to cause the processor 502 to execute the optimization method of the green land carbon sink benefit in any of the foregoing embodiments.

[0121] For the specific implementation of each step in the program 510, reference may be made to the corresponding steps and descriptions in the corresponding units in any of the foregoing embodiments of the optimization method of the green land carbon sink benefit, which will not be elaborated here. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, which will not be repeated here.

[0122] The present application also provides a computer-readable storage medium storing instructions for causing a machine to execute the optimization method of the green land carbon sink benefit as described herein. Specifically, a system or device equipped with the storage medium may be provided, on which software program codes for implementing the functions of any one of the above-described embodiments are stored, and the computer (or CPU or MPU) of the system or device is caused to read and execute the program codes stored in the storage medium.

[0123] In this case, the program code read from the storage medium itself can implement the functions of any one of the above-described embodiments, so the program code and the storage medium storing the program code constitute a part of the present application.

[0124] Examples of the storage medium for providing the program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer via a communication network.

[0125] The embodiments of the present application also provide a computer program product including computer instructions that direct a computing device to perform any corresponding operation in the above-described method embodiments.

[0126] It should be noted that, according to the needs of implementation, each component / step described in the embodiments of the present application may be split into more components / steps, or two or more components / steps or partial operations of the components / steps may be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0127] The methods according to the embodiments of the present application may be implemented in hardware, firmware, or be implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or be implemented as computer code originally stored in a remote recording medium or a non-transitory machine-readable medium and to be stored in a local recording medium and downloaded via a network, so that the methods described herein can be processed by such software stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component (such as RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods described herein are implemented. In addition, when a general-purpose computer accesses the code for implementing the methods shown herein, the execution of the code converts the general-purpose computer into a dedicated computer for executing the methods shown herein.

[0128] Those of ordinary skill in the art can realize that the units and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of this application.

[0129] The above embodiments are only used to illustrate the embodiments of this application, rather than limiting the embodiments of this application. Those of ordinary skill in the relevant technical field can also make various changes and modifications without departing from the spirit and scope of the embodiments of this application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of this application. The patent protection scope of the embodiments of this application shall be defined by the claims.

Claims

1. An optimization method for the carbon sequestration benefit of green spaces, characterized in that, The method includes: Obtaining a dataset related to carbon sinks within the research area, where the dataset includes data of multiple functional zones obtained by dividing the research area according to urban functions; For each of the functional zones, determining the vegetation carbon sink benefit according to the data of the functional zone; obtaining a set of influencing factors for the functional zone, where the set of influencing factors includes multiple influencing factors, and the multiple influencing factors include natural environmental factors and human activity characteristic factors; determining the importance percentage of each of the influencing factors for the vegetation carbon sink benefit, and determining key factors from the multiple influencing factors according to the importance percentage; fitting the key factors with the vegetation carbon sink benefit, and determining the local standardized regression coefficient of the key factors according to the fitting result, where the local standardized regression coefficient is used to characterize the relationship between the influencing factor and the vegetation carbon sink benefit in space; analyzing the spatial impact of the key factors on the vegetation carbon sink benefit according to the local standardized regression coefficient to obtain an analysis result, where the analysis result is used to characterize the spatial heterogeneity of the vegetation carbon sink benefit; and determining an optimization strategy for the green space carbon sink benefit of the functional zone according to the key factors and the analysis result.

2. The method according to claim 1, characterized in that, The determining the optimization strategy for the carbon sink benefit of the functional zone according to the key factors and the analysis result includes: Analyzing the change trend between the key factors and the vegetation carbon sink benefit, determining the interval where the key factors have a significant impact on the vegetation carbon sink benefit, and obtaining the threshold range of the key factors; Constructing a structural equation model according to the key factors and the threshold range of the key factors, and generating the influence path and action intensity of the key factors on the vegetation carbon sink benefit through the structural equation model; Determining the optimization strategy for the carbon sink benefit of the functional zone according to the influence path, the action intensity and the analysis result.

3. The method according to claim 2, wherein The structural equation model is: ； Among them, is the matrix of action path coefficients between endogenous latent variables, T is the matrix of influence path coefficients between exogenous latent variables and endogenous latent variables, is the random disturbance term, is the endogenous latent variable, is the exogenous latent variable. The endogenous latent variable is the vegetation carbon sequestration benefit, and the exogenous latent variable is the key factor.

4. The method according to claim 2, characterized in that, The analyzing the change trend between the key factors and the vegetation carbon sink benefit includes: Inputting the vegetation carbon sink benefit into an enhanced regression tree model, and outputting a partial dependence graph between the influencing factors and the vegetation carbon sink benefit through the enhanced regression tree model; Analyzing the change trend between the key factors and the vegetation carbon sink benefit according to the partial dependence graph between the key factors and the vegetation carbon sink benefit.

5. The method according to claim 1, characterized in that, The determining the importance percentage of each of the influencing factors for the vegetation carbon sink benefit, and determining key factors from the multiple influencing factors according to the importance percentage includes: Inputting the vegetation carbon sink benefit into an enhanced regression tree model, and outputting the importance percentage of each of the influencing factors for the vegetation carbon sink benefit through the enhanced regression tree model; Sorting the multiple influencing factors according to the importance percentage, and determining the key factors that meet the screening conditions according to the sorting.

6. The method according to claim 5, characterized in that, The method further includes: Constructing the enhanced regression tree model with the carbon sink benefit as the dependent variable and the multiple influencing factors as the independent variables. Determine the vegetation carbon sequestration benefits of each grid after rasterizing the functional partition as characteristic variables, input the characteristic variables into the boosted regression tree model, and optimize the boosted regression tree model through cross-validation to obtain an optimized boosted regression tree model.

7. The method according to claim 6, wherein The output of the importance percentage of each of the influencing factors on the vegetation carbon sequestration benefits through the boosted regression tree model includes: Based on the boosted regression tree model, count the number of times each of the influencing factors serves as a branch node in the decision tree, and calculate the reduction in error of the model's prediction of each of the influencing factors as a branch node; perform a weighted sum of the number of times each of the influencing factors serves as a branch node and the corresponding reduction in error, and normalize the weighted sum to the importance percentage corresponding to each of the influencing factors.

8. The method according to claim 1, wherein The obtaining of the set of influencing factors for the functional partition includes: Obtain multiple candidate influencing factors for the functional partition; Obtain the literature support degree, data quality score, and acquisition cost corresponding to each candidate influencing factor; Calculate the dynamic factor weights of each of the candidate influencing factors, and the calculation formula for the dynamic factor weights is as follows: ； Add the candidate influencing factors with dynamic factor weights greater than the weight threshold to the set of influencing factors for the functional partition; Among them, W DF is the dynamic factor weight, LS is the literature support degree, R DQ is the data quality score, and AC is the acquisition cost.

9. The method according to claim 1, characterized in that The multiple influencing factors include at least some of the following: Annual average temperature, annual average precipitation, solar radiation; Slope, elevation; Population density, gross domestic product, human footprint index, green space coverage rate; Connectivity index of the landscape, landscape shape index, landscape patch density.

10. The method according to claim 1, characterized in that The fitting of the key factor and the vegetation carbon sequestration benefits, and determining the local standardized regression coefficient of the key factor according to the fitting result includes: Perform a weighted process on the vegetation carbon sequestration benefits through a Gaussian kernel function to construct a spatial weight matrix for the vegetation carbon sequestration benefits, and the spatial weight matrix is used to measure the spatial similarity and influence degree between different geographical units, and the geographical unit refers to the grid after rasterizing the functional partition; Adopt the Akaike information criterion or the Bayesian information criterion to calculate the optimal bandwidth value for each of the key factors, and the optimal bandwidth value is used to optimize the regression fitting of the key factor to the vegetation carbon sequestration benefits; Based on the spatial weight matrix and the optimal bandwidth values of each of the key factors, fit the key factor and the vegetation carbon sequestration benefits through a multi-scale geographically weighted regression model to obtain the fitting results corresponding to each of the key factors; For each of the key factors, extract the local regression coefficients corresponding to each grid according to the fitting result, and perform a standardized process on the local regression coefficients to obtain the local standardized regression coefficient of the key factor.

11. An optimization device for the carbon sequestration benefit of green spaces, characterized in that, The device includes: An acquisition module for acquiring a dataset related to carbon sequestration within a research area, and the dataset includes data of multiple functional partitions, and the multiple functional partitions are obtained by dividing the research area according to urban functions; A processing module, which is used to determine the vegetation carbon sequestration benefit of each of the functional partitions according to the data of the functional partition; obtain the set of impact factors of the functional partition, where the set of impact factors includes multiple impact factors, and the multiple impact factors include natural environmental factors and human activity characteristic factors; determine the percentage of importance of each of the impact factors to the vegetation carbon sequestration benefit, and determine the key factors from the multiple impact factors according to the percentage of importance; fit the key factors with the vegetation carbon sequestration benefit, and determine the local standardized regression coefficient of the key factors according to the fitting result, where the local standardized regression coefficient is used to characterize the relationship between the impact factor and the vegetation carbon sequestration benefit in space; analyze the spatial impact of the key factors on the vegetation carbon sequestration benefit according to the local standardized regression coefficient to obtain an analysis result, where the analysis result is used to characterize the spatial heterogeneity of the vegetation carbon sequestration benefit; determine the optimization strategy for the green space carbon sequestration benefit of the functional partition according to the key factors and the analysis result.

Images