Urban park exposure fairness assessment method based on population and social value weighting
The social value and population mobility of urban parks are evaluated through the SolVES model and the random forest model. Combined with the Gini coefficient method, the neglect of green space quality in the existing technology is solved, and a comprehensive assessment of the fairness of exposure of urban parks is achieved. The unfair factors are realized. The identification of the park has improved the social value and benefits.
Patent Information
- Application Number
- CN202411002048.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-26
AI Technical Summary
When evaluating the fairness of green space exposure in urban parks, the existing technology lacks consideration of the quality of green space (social value benefits), and fails to effectively consider the improvement of the park's cultural services, nature conservation awareness and livable environment for residents.
The SolVES model is used to evaluate the social value of ecological cultural services in urban parks, and a population and social value-weighted urban park exposure assessment model is constructed based on population mobility data. The Gini coefficient method is used to evaluate fairness, and the exposure unfairness is recognized through the random forest model. mechanism.
By weighted evaluation of the social value and benefits of urban parks, indicators are provided to measure the exposure level of parks, unfair factors are identified, social value and benefits of urban parks are improved, and park planning and construction are guided.
Smart Images

Figure CN119026978A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of urban park planning, and in particular relates to an urban park exposure fairness assessment method based on population and social value weighting. Background Art
[0002] Urban parks not only have multiple ecological functions such as purifying the environment and regulating the climate, but also promote residents to form a healthy lifestyle, reduce disease risks, and improve social relations. The exposure and fairness of urban parks have received increasing attention, and many policies emphasize the importance of improving the fairness of green space exposure. The fairness and quality of park green space are regarded as important evaluation criteria for park cities.
[0003] Previous studies on urban park green space exposure only considered the quantity of urban green space and assumed that it was evenly distributed, lacking consideration of the quality of green space (social value benefits). Urban parks provide rich cultural services for urban residents, which are of great significance to improving residents' sports and fitness levels, stimulating awareness of nature conservation, and building a livable urban environment. The assessment of their social value needs to be carried out using a multidisciplinary approach. Summary of the invention
[0004] The purpose of this invention is to provide an urban park exposure fairness assessment method based on population and social value weighting, which has guiding significance for improving the social value benefits and planning and construction of urban parks.
[0005] In order to achieve the above object, the solution of the present invention is:
[0006] A method for evaluating the equity of urban park exposure based on population and social value weighting includes the following steps:
[0007] Step 1: Use the SolVES model to evaluate the social value of the cultural services of the urban park ecosystem in the study area;
[0008] Step 2: Obtain the population mobility distribution point data in the study area;
[0009] Step 3: construct an urban park exposure assessment model weighted by population and social value;
[0010] Step 4: Using the street and town as the research scale, the Gini coefficient method was used to evaluate the fairness of urban park exposure;
[0011] Step 5: Use the random forest model to identify differences in the driving mechanisms of exposure inequality between streets and towns.
[0012] In the above step 1, the types of social value include the following four:
[0013] Recreation, which is described as "parks provide an ideal place for people to engage in a variety of outdoor leisure and recreation activities";
[0014] Natural scenery, which is described as “the aesthetic experience brought by the park, providing people with spiritual pleasure and aesthetic enjoyment”;
[0015] Sports and Wellness, which is described as “the park’s environment provides a sense of healing and recuperation both mentally and physically”;
[0016] Historical heritage, which is described as "the park maintains an important cultural and historical landscape that can pass on history and cultivate humanity."
[0017] In step 1 above, the input of the SolVES model is the environmental index data of the study area, including distance to roads, distance to water bodies, distance to residential areas, mountain shadows, elevation, normalized difference vegetation index, and land use type.
[0018] In the above step 1, the performance test method of the SolVES model is to use the training AUC to verify the model results: the AUC value is between 0 and 1; the closer the value is to 1, the higher the accuracy of the prediction result.
[0019] In the above step 2, the population flow data uses Baidu population heat map data to provide the hourly population as point data, and the spatial connection tool in Arc GIS is used to sample the original population data through the grid.
[0020] In step 3 above, the calculation formula of the urban park exposure assessment model is as follows:
[0021]
[0022] In the formula, V represents the park coverage within the buffer zone with the center point of the i-th grid as the centroid and a radius of b; i represents the average level of comprehensive social value in the corresponding buffer zone; n represents the total number of grids in the street; represents the population of the ith grid in the tth time period, UPE SV Urban park exposure levels weighted for population and social value.
[0023] In step 4 above, the fairness formula for calculating urban park exposure is as follows:
[0024]
[0025] In the formula, g k is the park area based on social value assessment exposed to the kth population; m is the total population in the street town; Gini SVExpose equity for urban parks that consider social value benefits.
[0026] In step 5 above, a new random forest model is constructed between the Gini index and the variables, and the first three important variables are used to optimize the explanatory variable data set; during the training process of each decision tree, the same number of data set elements are randomly selected from all training samples for training; when constructing each branch node of the tree, a subset of all features is randomly selected, and the optimal segmentation method of the subset feature division is determined by purity calculation.
[0027] After adopting the above scheme, the beneficial effects of the present invention are as follows: first, the social value of the cultural services of the parks in the study area is evaluated by using the SolVES model, and the spatial distribution results of the social value of various cultural services are obtained; then, the population flow distribution point data in the study area is obtained; secondly, an indicator for measuring the exposure level of urban parks is constructed, which takes into account the social value benefits of urban park green spaces and the distribution of population flow; then, the fairness of urban park exposure based on population and social value weighting is evaluated by the Gini coefficient method; finally, the main factors leading to this unfairness are identified by using variance decomposition, and four typical areas with differentiated unfairness driving mechanisms are determined by combining random forests, interpretable machine learning methods (SHAP values) and hierarchical clustering methods. The present invention obtains the situation of urban population contact with high-quality urban parks by designing a population and social value weighted model, which has guiding significance for improving the construction of social value benefits of urban parks. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 is a flow chart of the present invention;
[0029] Figure 2 It is a flow chart of evaluating the social value of urban parks using the SolVES model in the present invention. DETAILED DESCRIPTION
[0030] The technical solutions and beneficial effects of the present invention will be described in detail below with reference to the accompanying drawings.
[0031] like Figure 1 As shown, the present invention provides an urban park exposure fairness assessment method based on population and social value weighting, comprising the following steps:
[0032] Step 1: Use the SolVES model to evaluate the social value of the cultural services of the urban park ecosystem in the study area. The specific evaluation process can be found in Figure 2 ;
[0033] In step 1, according to the main cultural service types provided by the urban park, the main cultural service social value types provided are classified, as shown in Table 1:
[0034] Table 1 Social value types and their descriptions
[0035]
[0036] In the first step, when using the SolVES model to evaluate the cultural services of urban parks, the environmental index data of the study area need to be input into the model. These data include distance to roads (DTR), distance to water bodies (DTW), distance to residential areas (DTRA), hill shadow (HILLSHADE), elevation (ELVE), normalized difference vegetation index (NDVI) and land use type (LULC);
[0037] The data collected from the questionnaires were digitized through mapping and tabulation in ArcGIS and used as training and test data for SolVES model simulation. When collecting data for the social value assessment of various cultural services, they were first standardized through specific software and EXCEL tables to avoid errors caused by complex workload during the point feature attribute input stage.
[0038] As a preferred embodiment of the present invention, the SolVES model in step one evaluates the social value of the cultural services of the urban park ecosystem in the study area, and the performance test method of the model is to use the training AUC to verify the results of the model: the value of AUC is between 0 and 1; the closer the value is to 1, the stronger the correlation between the environmental variables and the model, and the higher the accuracy of the prediction results.
[0039] Step 2: Obtain population flow distribution point data in the study area. The population flow data uses Baidu population heat map data to provide hourly population counts as point data. The spatial connection tool in Arc GIS is used to sample the original population data through a 100 m × 100 m grid;
[0040] Step 3: Construct an urban park exposure model weighted by population and social value, where the urban park exposure level calculation formula is as follows:
[0041]
[0042] In the formula, V represents the park coverage within the buffer zone with the center point of the i-th grid as the centroid and a radius of b; i represents the average level of comprehensive social value within the corresponding buffer zone; n represents the total number of grids within the street; represents the population of the ith grid in the tth time period, UPE SV Urban park exposure levels weighted for population and social value.
[0043] As a preferred embodiment of the present invention, the size of the designed grid in the above formula is 100 meters × 100 meters;
[0044] The buffer radius b for calculating park coverage is 500 meters;
[0045] Step 4: Using the street and town as the research scale, the Gini coefficient method is used to evaluate the fairness of urban park exposure. The calculation formula is as follows:
[0046]
[0047] In the formula, g k is the park area exposed to the kth population based on social value weighting; m is the total population in the street town; Gini SV Expose equity for urban parks that consider social value benefits.
[0048] Step 5: Use the random forest model to identify differences in the driving mechanisms of exposure inequality between subdistricts and towns;
[0049] In step 5, the use of the random forest model to identify differences in driving mechanisms of exposure inequality between streets and towns is to construct a new random forest (RF) model between the Gini index and the variables, and use the first three important variables to optimize the explanatory variable data set; its "randomness" feature is reflected in the training process of each decision tree: the algorithm randomly selects the same number of data set elements from all training samples for training, and this method is called "bootstrap sampling"; when constructing each branch node of the tree, the algorithm randomly selects a subset of all features, and determines the optimal segmentation method of the subset feature division through purity calculation;
[0050] This embodiment uses a common machine learning explanation method SHAP (Shapley Additive Explanations) value to obtain an explanation of the impact of each feature on the final model prediction at the sample level.
[0051] We compiled multiple variables involving three core factors to explore the drivers of inequity in green space exposure weighted by population and social value. These variables consist of five key indicators divided into three categories: (a) park coverage, (b) population distribution concentration level (measured by the standard deviation of population numbers between grids), and (c) the level of social value of parks.
[0052] After rescaling all variables to the range of 0–1, Pearson correlation analysis was first applied to examine the significance of the correlation between the Gini index and the five variables;
[0053] To ensure that there was no multicollinearity among the variables, we built a multiple linear regression model to examine the variance inflation factor.
[0054] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.
[0055] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0056] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0058] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0059] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A method for evaluating the fairness of urban park exposure based on population and social value weighting, characterized by The steps include: Step 1: Use the SolVES model to evaluate the social value of the cultural services of the urban park ecosystem in the study area; Step 2: Obtain the population mobility distribution point data in the study area; Step 3: construct an urban park exposure assessment model weighted by population and social value; Step 4: Using the street and town as the research scale, the Gini coefficient method was used to evaluate the fairness of urban park exposure; Step 5: Use the random forest model to identify differences in the driving mechanisms of exposure inequality between streets and towns.
2. The method according to claim 1, characterized in that: In step 1, the social value types include the following four types: Recreation, which is described as "parks provide people with an ideal place to engage in a variety of outdoor leisure and recreation activities"; Natural scenery, which is described as "the aesthetic experience brought by the park, providing people with spiritual pleasure and aesthetic enjoyment"; Sports and wellness, which is described as "the park's environment provides a sense of healing and recuperation both mentally and physically"; Historical heritage, which is described as "the park maintains an important cultural and historical landscape that can pass on history and cultivate humanity." 3. The method according to claim 1, characterized in that: In step 1, the input of the SolVES model is the environmental index data of the study area, including distance to roads, distance to water bodies, distance to residential areas, mountain shadows, elevation, normalized vegetation index and land use type.
4. The method according to claim 1, characterized in that: In step 1, the performance test method of the SolVES model is to use the training AUC to verify the model results: the value of AUC is between 0 and 1; the closer the value is to 1, the higher the accuracy of the prediction result.
5. The method according to claim 1, characterized in that: In the step 2, the population flow data uses Baidu's population heat map data to provide the number of people per hour as point data, and the spatial connection tool in Arc GIS is used to sample the original population data through the grid.
6. The method according to claim 5, characterized in that: In step 3, the calculation formula of the urban park exposure assessment model is as follows: In the formula, V represents the park coverage within the buffer zone with the center point of the i-th grid as the centroid and a radius of b; i represents the average level of comprehensive social value in the corresponding buffer zone; n represents the total number of grids in the street; represents the population of the ith grid in the tth time period, UPE SV Urban park exposure levels weighted for population and social value.
7. The method according to claim 1, characterized in that: In step 4, the fairness formula for calculating urban park exposure is as follows: In the formula, g k is the park area based on social value assessment exposed to the kth population; m is the total population in the street town; Gini SV Expose equity for urban parks that consider social value benefits.
8. The method according to claim 1, characterized in that: In the step 5, a new random forest model is constructed between the Gini index and the variables, and the first three important variables are used to optimize the explanatory variable data set; during the training process of each decision tree, the same number of data set elements are randomly selected from all training samples for training; when constructing each branch node of the tree, a subset of all features is randomly selected, and the optimal segmentation method of the subset feature division is determined by purity calculation.
Citation Information
Cited By
Municipal garden automatic modeling method and system convenient for urban planning
CN121327954A
