A method and device for quantifying the stress effect of urban expansion on green space

Abstract

Embodiments of the present application provide a method and device for quantifying the stress effect of urban expansion on green space. The method comprises: obtaining urban expansion data and green space data of a plurality of urban areas; the urban expansion data comprises a plurality of urban expansion characteristics, and the green space data comprises a plurality of green space characteristics; clustering the plurality of urban areas according to various green space characteristics in the green space data of the plurality of urban areas; for any one cluster, training a machine learning model using the urban expansion data and the green space data of the urban areas in the cluster to obtain a green space data prediction model corresponding to the cluster; and using an interpreter model to interpret the prediction model to determine the positive and negative and strength of the stress effect of various urban expansion characteristics on green space characteristics under the cluster. In this way, the stress effect of urban expansion on green space can be effectively quantified by combining machine learning and an interpreter.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental protection, and particularly relates to a method and device for quantifying the stress effect of urban expansion on green space. BACKGROUND

[0002] Although global rapid urbanization brings opportunities for economic and social development, it also brings major challenges to sustainable development. At present, most cities have experienced rapid urban expansion, and the most prominent performance in space is the expansion of urban construction land, i.e., the conversion of urban green space including farmland, forest, grassland, wetland, etc. into non-porous surfaces (e.g., roads, houses, buildings), which is often irreversible. Urban green space is the carrier of urban ecological system. Urban green space has various environmental effects, psychological and economic benefits, such as reducing air pollution and urban heat island effect, increasing land carbon storage, reducing stress and promoting health, etc. The negative impact of urban expansion on urban green space is called "ecological pressure" or "stress effect", which will lead to the degradation of urban green space function, further affecting the function and pattern of urban ecological system. In order for urbanization to be carried out in a more sustainable way, how to quantify the "stress effect" caused by urban expansion in urban planning and use the index to guide regional urban planning is an urgent problem. SUMMARY

[0003] In a first aspect, an embodiment of the present application provides a method for quantifying the stress effect of urban expansion on green space, the method comprising:

[0004] obtaining urban expansion data and green space data of a plurality of urban areas; wherein the urban expansion data comprises a plurality of urban expansion features, and the green space data comprises a plurality of green space features;

[0005] clustering the plurality of urban areas according to the various green space features in the green space data of the plurality of urban areas, to obtain a plurality of clustering clusters;

[0006] for any one clustering cluster, taking the urban expansion data of the urban areas in the clustering cluster as samples and taking the corresponding green space data as labels, training a machine learning model to obtain a green space data prediction model corresponding to the clustering cluster; using an interpreter model to interpret the green space data prediction model corresponding to the clustering cluster, to determine the positive and negative and strength of the stress effect of various urban expansion features on green space features under the clustering cluster.

[0007] In some possible implementation manners of the first aspect, the multiple urban expansion features are respectively a change in urban construction land area, a change in development intensity, a change in the number of buildings, a change in the number of high-rise buildings, a change in average building height, an area-weighted fractal dimension index, a maximum patch index change, a landscape shape index, a population density change, and a night light index change.

[0008] In some possible implementation manners of the first aspect, clustering the multiple urban areas according to the various green space features in the green space data of the multiple urban areas comprises:

[0009] According to the various green space features in the green space data of the multiple urban areas, the multiple urban areas are clustered using a K-Medoids algorithm.

[0010] In some possible implementation manners of the first aspect, the machine learning model is a GBRT model, and the explainer model is a SHAP model.

[0011] In some possible implementation manners of the first aspect, the explainer model is used to interpret the green space data prediction model corresponding to the cluster, to determine the positive and negative and strength of the stress effect of the various urban expansion features on the green space features in the cluster, comprising:

[0012] The SHAP model is used to interpret the green space data prediction model corresponding to the cluster, to calculate the Shapley values of the various urban expansion features on the green space features in the cluster, and to determine the positive and negative and strength of the stress effect of the various urban expansion features on the green space features in the cluster according to the positive and negative and size of the Shapley values.

[0013] In some possible implementation manners of the first aspect, the method further comprises:

[0014] Based on the dependence graph of the SHAP model, the trend and threshold of the stress effect of the various urban expansion features on the green space features in the cluster are determined.

[0015] In some possible implementation manners of the first aspect, the method further comprises:

[0016] The positive and negative and strength of the stress effect of the various urban expansion features on the green space features in each cluster are spatially mapped, to obtain the spatial distribution difference of the stress effect of the various urban expansion features on the green space features.

[0017] In the second aspect, an embodiment of the present application provides a device for quantifying the stress effect of urban expansion on green space, the device comprising:

[0018] The acquisition module is configured to acquire urban expansion data and green space data of a plurality of urban areas, wherein the urban expansion data comprises a plurality of urban expansion features, and the green space data comprises a plurality of green space features;

[0019] The clustering module is configured to cluster the plurality of urban areas according to the plurality of green space features in the green space data of the plurality of urban areas, to obtain a plurality of clustering clusters.

[0020] The explanation module is configured to, for any one clustering cluster, train a machine learning model by taking the urban expansion data of the urban areas in the clustering cluster as samples and taking the corresponding green space data as labels, to obtain a green space data prediction model corresponding to the clustering cluster; and use an explainer model to explain the green space data prediction model corresponding to the clustering cluster, to determine the positive or negative and strength of the stress effect of each urban expansion feature on the green space feature under the clustering cluster.

[0021] In a third aspect, an electronic device is provided, which includes at least one processor, and a memory connected with the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0022] In a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, and the computer instructions are used to enable a computer to perform the method described above.

[0023] In the embodiments of the present application, the stress effect of urban expansion on green space can be effectively quantified by combining machine learning and an explainer, which provides a scientific basis for formulating effective urban planning strategies and green space protection measures.

[0024] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0025] The above and other features, advantages, and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings, which illustrate, by way of example, the principles of the present application. The drawings provided are for purposes of better understanding the present application, and are not to be construed as limiting the present application, wherein the same or similar reference numerals in the drawings denote the same or similar elements, and wherein:

[0026] Figure 1 A flowchart of a method for quantifying the stress effect of urban expansion on green space according to an embodiment of the present application is shown in FIG. 4;

[0027] Figure 2 A schematic diagram of a clustering result is shown in FIG. 5;

[0028] Figure 3 A schematic diagram of the trend of the stress effect of the partial urban expansion feature on the green space feature under the partial clustering cluster;

[0029] Figure 4 A threshold diagram of the stress effect of the urban expansion feature on the green space feature under the clustering cluster;

[0030] Figure 5 A schematic diagram of the spatial distribution difference of the stress effect of the partial urban expansion feature on the green space feature;

[0031] Figure 6 A structural diagram of a device for quantifying the stress effect of urban expansion on green space provided by an embodiment of the present application;

[0032] Figure 7 A structural diagram of an exemplary electronic device capable of implementing an embodiment of the present application. DETAILED DESCRIPTION

[0033] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0034] In addition, the term "and / or" in the present application merely describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.

[0035] To solve the technical problems in the background art, the embodiments of the present application provide a method, device, equipment and storage medium for quantifying the stress effect of urban expansion on green space. Specifically, urban expansion data and green space data of a plurality of urban areas are obtained; the urban expansion data includes a plurality of urban expansion features, and the green space data includes a plurality of green space features; the plurality of urban areas are clustered according to various green space features in the green space data of the plurality of urban areas; for any one clustering cluster, a machine learning model is trained using the urban expansion data and the green space data of the urban areas in the clustering cluster, to obtain a green space data prediction model corresponding to the clustering cluster; an interpreter model is used to interpret the prediction model, to determine the positive and negative and strength of the stress effect of various urban expansion features on the green space feature under the clustering cluster.

[0036] In this way, the stress effect of urban expansion on green space can be effectively quantified by combining machine learning and an interpreter, thereby providing a scientific basis for formulating effective urban planning strategies and green space protection measures.

[0037] The method, device, equipment and storage medium for quantifying the stress effect of urban expansion on green space provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0038] Figure 1 The flowchart of the method for quantifying the stress effect of urban expansion on green space provided by the embodiments of the present application is shown in Figure 1 As shown in the figure, the method 100 for quantifying the stress effect of urban expansion on green space can include the following steps:

[0039] S110, obtaining urban expansion data and green space data of a plurality of urban areas.

[0040] The urban area is a unit area of 500m*500m, the urban expansion data includes a plurality of urban expansion features, and the green space data includes a plurality of green space features. Specifically, the plurality of urban expansion features are respectively a change in urban construction land area (LC), a change in development intensity (DI), a change in the number of buildings (BN), a change in the number of high-rise buildings (HB), a change in the average building height (MHB), an area-weighted fractal dimension index (FRAC), a change in the maximum patch index (LPI), a landscape shape index (LSI), a change in population density (POP), and a change in night light index (LD); the plurality of green space features are respectively a green space area (AREA), a green space pattern (GPCA), and a green space function (NPP). It should be noted that the above features are all change amounts of data in the starting year and the ending year. Since the value ranges and units of different features are different, in order to better compare and model, the data is normalized to -100 to 100 (without changing the positive and negative value domain of the index) through the constructed model.

[0041] As an example, the above urban expansion features and green space features are selected by the following steps:

[0042] The urban expansion characteristics (also referred to as urban expansion indicators) are selected from the aspects of urban expansion intensity, urban expansion pattern, and social economy. The urban expansion intensity aims to describe the characteristics of urban construction land in two-dimensional and three-dimensional space. Five characteristics, i.e., the change in urban construction land area (LC), the change in development intensity (DI), the change in the number of buildings (BN), the change in the number of high-rise buildings (HB), and the change in the average building height (MHB), are used to describe the urban expansion intensity. The urban expansion pattern aims to describe the shape and structure of urban construction land in space. Sixteen characteristics are selected, including six area edge characteristics, three shape characteristics, and seven aggregation characteristics. All the characteristics are calculated by Fragstats4.2. The sixteen characteristics are screened by PCA. In the case of keeping the explained variance ratio of 95%, the characteristics are reduced from 16 dimensions to 5 dimensions. Finally, five characteristics, i.e., the area weighted fractal dimension index (FRAC), the change in the largest patch index (LPI), the landscape shape index (LSI), the area weighted contiguity index (CONTIG), and the change in the aggregation index (AI), are selected as the spatial pattern description of urban expansion. At present, the types and density of POI, GDP, the income of the tertiary industry, industrial pollution degree, population, and the night light index are often selected to represent the economic and social development. Based on the time dimension and data accuracy, two characteristics, i.e., the change in population density (POP) and the change in the night light index (LD), are selected as the urban expansion description in the aspect of social economy.

[0043] The variance inflation coefficient is used to test the multicollinearity of the above twelve characteristics. The characteristics with a value greater than 10 are deleted. Finally, the area weighted contiguity index (CONTIG) and the change in the aggregation index (AI) are screened out. The remaining ten characteristics are selected as the urban expansion characteristics to describe the changes of urban expansion in three dimensions. The specific selected characteristics can be shown in Table 1.

[0044] Table 1

[0045]

[0046]

[0047]

[0048] The description of green space here is mainly from three aspects, including green space area (AREA), green space pattern (GPCA), and green space function (NPP), as shown in Table 2. AREA mainly selects the area of five land use types of forest land, grassland, wetland, and cultivated land. It is found that the shape and connectivity of GPCA are mainly affected by the urban built-up area, so two features, area-weighted fractal dimension index (FRAC AM) and area-weighted adjacency index (CONTIG AM), are mainly selected, and PCA is used to synthesize the two features. The meaning of the synthesized feature is that the closer the GPCA value is to 0, the worse the connectivity of the patch is, and the more fragmented the shape is. On the contrary, it also indicates that the shape regularity and connectivity of the patch are enhanced. Green space function selects vegetation net primary productivity change (NPP) to describe.

[0049] Table 2

[0050]

[0051]

[0052] S120, according to various green space features in the green space data of the plurality of urban areas, clustering the plurality of urban areas to obtain a plurality of clustering clusters.

[0053] In some embodiments, the clustering algorithm used here is the K-Medoids algorithm. Specifically, the K-Medoids algorithm uses the object closest to the center as the center point. PAM is the most widely used method to implement the K-Medoids algorithm. Here, each 500m*500m urban area is regarded as a sample, and the data set used for clustering contains N samples, each of which is defined by AREA, GPCA, and NPP, three green space features, that is, each sample has three dimensions. In the K-Medoids algorithm, the value of K needs to be set in advance and repeatedly verified. According to related technologies, the extended variance method can be used to determine the value of K. Here, K is expected to be less than an acceptable error, and according to the analysis of the landscape features of the study area by urban planning and landscape planning professionals, its approximate range is determined. In addition, the clustering results of different K values are compared here, and the most suitable K value is found. In the clustering process, if the value of K is too large, the clustering clusters obtained are more, and the similarity of some types is higher. If the value of K is too small, the degenerated types with different characteristics may be clustered into one type, thereby affecting the subsequent analysis.

[0054] As an example, the K-Medoids algorithm is implemented by the kmedoids package of python, and the specific steps are as follows:

[0055] 1) Randomly select K points as center points in all samples, denoted as OK Then the Euclidean distance of the rest of the points (denoted as M, M = N - O K ) to the center point is calculated, denoted as D (O,M) The formula for calculating the Euclidean distance is as follows:

[0056]

[0057] x M =(x 1M ,x 2M ,…,x iM ) and x O =(x 1O ,x 2O ,…,x iO );

[0058] 2) According to the value D (O, M), the point M is assigned to the cluster where the nearest center point O K is located, and the initial cluster is obtained.

[0059] 3) Replace the center point O K with the remaining point M, and evaluate the cost caused by this action, that is, the difference in the Euclidean distance of the point M in the cluster to the center point O K before and after replacement, denoted as C MK . Calculate the total cost T MK to determine whether the point OM can replace the center point O K , and the formula for calculating the total cost T MK is as follows:

[0060]

[0061] Where T MK < 0 indicates that after the above replacement, the total deviation of the cluster becomes smaller, and the point O M replaces the center point O K to become the new center point.

[0062] 4) Repeat steps 2) and 3) until T MK no longer changes.

[0063] It should be noted that the advantage of clustering here is:

[0064] The composition and development characteristics of green space in different urban areas are different. If a unified model is constructed to fit the relationship between urban expansion and green space, the explanatory power of the model will be weakened, and the stress effect of urban expansion on green space cannot be accurately explained. Here, the K-Medoids algorithm is used to divide the urban areas into several clusters with similar green space characteristics. It can be known that the urban expansion characteristics in the same cluster have similar influence on the stress of green space. Subsequently, each cluster can be modeled and analyzed to accurately capture the stress effect of urban expansion on green space.

[0065] In S130, for any one cluster, the urban expansion data of the urban areas in the cluster is taken as the sample, and the corresponding green space data is taken as the label. The machine learning model is trained to obtain the green space data prediction model corresponding to the cluster. The interpreter model is used to explain the green space data prediction model corresponding to the cluster, and the positive and negative and strength of the stress effect of various urban expansion characteristics on green space characteristics under the cluster are determined.

[0066] Specifically, for any one cluster, the urban expansion data of the urban areas in the cluster is taken as the sample, and the corresponding green space data is taken as the label. The GBRT model is trained to obtain the green space data prediction model corresponding to the cluster. The SHAP model is used to explain the green space data prediction model corresponding to the cluster, and the Shapley value of various urban expansion characteristics on green space characteristics under the cluster is calculated. According to the positive and negative and size of the Shapley value, the positive and negative and strength of the stress effect of various urban expansion characteristics on green space characteristics under the cluster are determined. That is, the Shapley value is positive, which is positive contribution to the stress of green space; the Shapley value is negative, which is negative contribution to the stress of green space. Thus, the stress effect of urban expansion on green space is quantified, and the key urban expansion characteristics affecting urban green space in each dimension are summarized. On this basis, the dependence plot of the SHAP model can be used to determine the trend and threshold of the stress effect of various urban expansion characteristics on green space characteristics under the cluster. At the same time, the positive and negative and strength of the stress effect of various urban expansion characteristics on green space characteristics under each cluster can be spatially mapped to obtain the spatial distribution difference of the stress effect of various urban expansion characteristics on green space characteristics, and visualized.

[0067] As an example, both GBRT and SHAP models are used here to explore the relative importance of each feature of urban expansion on green space features and the marginal effect between them, to determine the type of stress, the difference in contribution. GBRT model is a machine learning model based on decision tree regression model and gradient boosting model. GBRT model is based on gradient boosting method, which combines many decision trees into a "strong learner" in an iterative way to improve prediction accuracy. The main advantage of GBRT model is to reduce the residual error of the last iteration by calculating it every time. New regression tree models are built according to the gradient direction of residual error reduction. These iterations gradually build a more complete regression tree model. Finally, the prediction result is obtained by integrating the prediction results of the regression tree model.

[0068] Machine learning models can often achieve the expected accuracy, but their application is often limited because the features of the model cannot be reasonably explained. Therefore, it is difficult to obtain suggestions that are meaningful to the application. To solve this problem, SHAP model is proposed to explain the output of machine learning model. The explanation of SHAP model is to attribute the output value to the Shapley value of each feature. SHAP model provides a method based on game theory and local explanation to estimate the contribution of each feature. In SHAP model, the contribution of each feature to the model output is allocated according to its marginal contribution, in other words, SHAP model can calculate the Shapley value of each feature to measure its impact on the final output value.

[0069] Therefore, the results of GBRT model are input into SHAP model here to explain the stress relationship between urban expansion and green space. SHAP model uses the shap package of python. GBRT model uses the scikit-learn package in python. The selected 10 urban expansion features are used as independent variables, and AREA, GPCA and NPP are used as dependent variables. The model introduces some randomness to reduce overfitting, and uses ten-fold cross-validation to ensure its stability. Because the features of each cluster are different, the parameters (such as the complexity of the tree and the learning rate) need to be set respectively, and adjusted according to the goodness of fit of the model.

[0070] GBRT model:

[0071] Training sample T = ((x1, y1), (x2, y2),..., (xn, yn)), differentiable loss function L(y, F(x)) and iteration number M. The specific training steps of GBRT model are as follows:

[0072] 1) Initialize the model

[0073]

[0074] 2) for m = 1 to M:

[0075] a. Compute the so-called pseudo-residuals:

[0076]

[0077] b. Fit the base learner (e.g. tree learner) hm(x) to the pseudo-residuals, i.e. train it on the training set.

[0078] c. Compute the multiplier γ by solving the following one-dimensional optimization problem m :

[0079]

[0080] d. Update the model:

[0081] F m (x) = F m―1 (x) + γh m (x) ;

[0082] 3) End of iteration, output final model: F(x) = FM(x).

[0083] SHAP model:

[0084]

[0085] where g is the explained model; M is the number of input features; Z represents the presence of the corresponding feature (1 or 0); is the attribution value (Shapely value) of each feature, is a constant. All possible combinations of features (including different orders) in tree models must be calculated for Shapely values. Then use the weighted sum method to calculate the total. The calculation formula is as follows:

[0086]

[0087] where, is the contribution rate of feature k; K is the number of features; x represents a data point, |z'| is the number of non-zero items in z'; f(x) is the output of the original model, i.e. the value of the three features in green space. Its formula is:

[0088]

[0089] where α0 is the benchmark value, representing the output when all input parameters are missing, usually the average of the target variable in all samples; g(x') is the explained model.

[0090] When analyzing the impact of urban expansion on green space, it is often helpful to quantify the relative importance of each independent variable. The relative importance can be calculated by taking the average of the absolute values of all Shapley values corresponding to each feature:

[0091]

[0092] where I k represents the relative importance of the feature; N represents the number of samples.

[0093] In summary, the present application at least achieves the following technical effects:

[0094] 1) The present application conducts an in-depth analysis of the impact of urban expansion and green space through innovative methods. It not only decomposes urban expansion and green space into three dimensions, but also describes these two areas in more detail and comprehensively by selecting multiple indicators. This multi-dimensional analysis method can more accurately capture the changes in green space during urban development, thereby providing more accurate data support for urban planners. Through this method, the specific impact of urban expansion on green space can be better understood, including the reduction of green space area, the degradation of ecological function, and the loss of biodiversity, etc. In addition, this detailed description helps to identify and evaluate potential risks and opportunities in the process of urban expansion, providing a scientific basis for formulating effective urban planning strategies and green space protection measures. In summary, the application of the present application will greatly promote the sustainable development of cities and the rational use of green space.

[0095] 2) Unlike other methods that explore the impact of urban expansion on green space, the method provided by the present application is based on the actual situation of the city, and focuses on exploring the internal relationship between multiple indicators, non-linear change trends, and specific thresholds of green space impact through the calculation of long-term data changes. It can provide more accurate data reference for urban planning.

[0096] 3) The method of combining GBRT model and SHAP model introduced in the present application is an advanced data analysis technology aimed at improving the interpretability and prediction accuracy of the model. Not only can a powerful prediction model be obtained, but also the decision-making process of the model can be deeply understood. GBRT model provides strong prediction ability, while SHAP model provides in-depth explanation of these predictions. This combination can identify the factors that have the greatest impact on urban expansion and green space, as well as how these factors interact with each other. In this way, the technical solution can provide a clearer perspective for urban planners, helping them to develop more effective strategies to balance urban development and environmental protection.

[0097] 4) Unlike other qualitative research results, the present application assigns values to the effects of urban expansion on green space through classification and grading, and uses a combination of GBRT models and SHAP models to quantify and visualize the "stress effect", thereby achieving comprehensive quantitative evaluation of the effects of multiple factors and measuring the degree of influence of different factors.

[0098] 5) The method provided by the present application is suitable for quantitative evaluation of the "stress effect" in any region at a specific period. Moreover, the method has low requirements for data quantity and data type, and only requires obtaining land use data at two time points (the starting year and the ending year); all data can be obtained from remote sensing images.

[0099] The following takes a city (referred to as A) as an example to illustrate the method 100 for quantifying the stress effect of urban expansion on green space provided by the embodiment of the present application, as follows:

[0100] (1) Obtain urban expansion data and green space data of multiple urban areas in city A.

[0101] Among them, the urban area is a unit area of 500m*500m, the urban expansion data includes multiple urban expansion characteristics, and the green space data includes multiple green space characteristics. Specifically, the multiple urban expansion characteristics are the change of urban construction land area (LC), the change of development intensity (DI), the change of the number of buildings (BN), the change of the number of high-rise buildings (HB), the change of the average building height (MHB), the area-weighted fractal dimension index (FRAC), the change of the maximum patch index (LPI), the landscape shape index (LSI), the change of population density (POP), and the change of night light index (LD); the multiple green space characteristics are green space area (AREA), green space pattern (GPCA), and green space function (NPP). It is worth noting that the above characteristics are the change of the data of the starting year and the ending year. Since the value ranges and units of different characteristics are different, in order to better compare and model, the data are normalized to -100 to 100 (without changing the positive and negative value domain of the index) through the constructed model.

[0102] (2) According to various green space characteristics in the green space data of the multiple urban areas, the K-Medoids algorithm is used to cluster the multiple urban areas to obtain multiple clustering clusters. The clustering result can be as shown in Figure 2 .

[0103] (3) For any one cluster, the city expansion data of the urban area in the cluster is taken as a sample, and the corresponding green space data is taken as a label to train the machine learning model, so as to obtain a green space data prediction model corresponding to the cluster. The explainer model is used to explain the green space data prediction model corresponding to the cluster, and the positive and negative and strength of the stress effect of various city expansion features on green space features under the cluster are determined. On this basis, the trend and threshold of the stress effect of various city expansion features on green space features under the cluster can also be determined based on the dependence plot of the SHAP model, as shown in Figure 3 、 Figure 4 At the same time, the positive and negative and strength of the stress effect of various city expansion features on green space features under each cluster can also be spatially mapped to obtain the spatial distribution difference of the stress effect of various city expansion features on green space features, and visualized display, as shown in Figure 5 .

[0104] It should be noted that for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the order of the described actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0105] The above is the introduction of the method embodiment, and the following will further illustrate the scheme of the present application through the device embodiment.

[0106] Figure 6 The structural diagram of a device for quantifying the stress effect of city expansion on green space provided by the embodiment of the present application is shown in Figure 6 , and the device 600 for quantifying the stress effect of city expansion on green space can include:

[0107] The acquisition module 610 is configured to acquire city expansion data and green space data of a plurality of urban areas; wherein the city expansion data includes a plurality of city expansion features, and the green space data includes a plurality of green space features.

[0108] The clustering module 620 is configured to cluster the plurality of urban areas according to various green space features in the green space data of the plurality of urban areas, to obtain a plurality of cluster groups.

[0109] The explanation module 630 is configured to, for any one cluster, take the urban expansion data of the urban area in the cluster as a sample and the corresponding green space data as a label, train a machine learning model to obtain a green space data prediction model corresponding to the cluster; and use an explainer model to explain the green space data prediction model corresponding to the cluster to determine the positive or negative and strength of the stress effect of various urban expansion features on the green space features under the cluster.

[0110] It can be understood that, Figure 6 The modules / units in the device 600 for quantifying the stress effect of urban expansion on green space have the functions of implementing Figure 1 The functions of each step in the method 100 for quantifying the stress effect of urban expansion on green space are achieved, and the corresponding technical effects are achieved. For the sake of brevity, they will not be repeated here.

[0111] Figure 7 A structural diagram of an exemplary electronic device capable of implementing embodiments of the present application. The electronic device 700 is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device 700 can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components of the electronic device shown in the present application, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed in the present application.

[0112] As shown in the figure, Figure 7 The electronic device 700 can include a computing unit 701 that can perform various appropriate actions and processes according to computer programs stored in a read-only memory (ROM) 702 or loaded into a random access memory (RAM) 703 from a storage unit 708. Various programs and data required for the operation of the electronic device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0113] Various components in the electronic device 700 are connected to the I / O interface 705, including an input unit 706 such as a keyboard, a mouse, etc., an output unit 707 such as various types of displays, a speaker, etc., a storage unit 708 such as a magnetic disk, an optical disk, etc., and a communication unit 709 such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunications networks.

[0114] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs various methods and processes described above, such as the method 100. For example, in some embodiments, the method 100 can be implemented as a computer program product, including a computer program tangibly embodied in a computer readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the method 100 described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the method 100 by any other appropriate means, such as by means of firmware.

[0115] The various embodiments described above in the present disclosure can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0116] Program code to implement methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a function / operation specified in the flowchart and / or block diagram. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a remote machine or a server.

[0117] In the context of the present application, a computer readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include one or more lines of electrical connections, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0118] It should be noted that the present application also provides a non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions are used to make a computer execute the method 100 and achieve the corresponding technical effects achieved by the embodiments of the present application. For brevity, the description will not be repeated here.

[0119] In addition, the present application also provides a computer program product, which includes a computer program, and the computer program realizes the method 100 when executed by a processor.

[0120] It should be understood that various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in different order, as long as the desired results of the technical solutions disclosed in the present application can be achieved, and the present application does not limit here.

[0121] The above specific embodiments do not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement and improvement within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method of quantifying the coercive effect of urban expansion on green space, characterized in that, The method comprises: obtaining urban expansion data and green space data of a plurality of urban areas; wherein the urban expansion data comprises a plurality of urban expansion features, and the green space data comprises a plurality of green space features; clustering the plurality of urban areas according to the various green space features in the green space data of the plurality of urban areas to obtain a plurality of clustering clusters; training a machine learning model by taking the urban expansion data of the urban areas in the clustering cluster as samples and taking the corresponding green space data as labels, to obtain a green space data prediction model corresponding to the clustering cluster; and using an interpreter model to interpret the green space data prediction model corresponding to the clustering cluster, to determine the positive and negative and strength of the stress effect of the various urban expansion features on the green space features under the clustering cluster.

2. The method of claim 1, wherein, The plurality of urban expansion features are respectively changes in urban construction land area, development intensity, number of buildings, number of high-rise buildings, average building height, area-weighted fractal dimension index, maximum patch index change, landscape shape index, population density change, and night light index change. The plurality of green space features are respectively green space area, green space pattern, and green space function.

3. The method of claim 1, wherein, The clustering of the plurality of urban areas according to the various green space features in the green space data of the plurality of urban areas comprises: using a K-Medoids algorithm to cluster the plurality of urban areas according to the various green space features in the green space data of the plurality of urban areas.

4. The method of claim 1, wherein, The machine learning model is a GBRT model, and the interpreter model is a SHAP model.

5. The method of claim 4, wherein, The interpretation of the green space data prediction model corresponding to the clustering cluster by using the interpreter model to determine the positive and negative and strength of the stress effect of the various urban expansion features on the green space features under the clustering cluster comprises: using a SHAP model to interpret the green space data prediction model corresponding to the clustering cluster, calculating the Shapley value of the various urban expansion features on the green space features under the clustering cluster, and determining the positive and negative and strength of the stress effect of the various urban expansion features on the green space features under the clustering cluster according to the positive and negative and size of the Shapley value.

6. The method of claim 5, wherein, The method further comprises: determining the trend and threshold of the stress effect of the various urban expansion features on the green space features under the clustering cluster based on a dependence graph of the SHAP model.

7. The method of claim 5, wherein, The method further comprises: spatially mapping the positive and negative and strength of the stress effect of the various urban expansion features on the green space features under each clustering cluster to obtain spatial distribution differences of the stress effect of the various urban expansion features on the green space features.

8. A device for quantifying the stress effect of urban expansion on green space, characterized in that, The device comprises: an acquisition module configured to acquire urban expansion data and green space data of a plurality of urban areas; wherein the urban expansion data comprises a plurality of urban expansion features, and the green space data comprises a plurality of green space features; a clustering module configured to cluster the plurality of urban areas according to the various green space features in the green space data of the plurality of urban areas to obtain a plurality of clustering clusters; and a training module configured to train a machine learning model by taking the urban expansion data of the urban areas in the clustering cluster as samples and taking the corresponding green space data as labels, to obtain a green space data prediction model corresponding to the clustering cluster; and an interpreter module configured to interpret the green space data prediction model corresponding to the clustering cluster by using an interpreter model, to determine the positive and negative and strength of the stress effect of the various urban expansion features on the green space features under the clustering cluster. An explanation module is configured to, for any one cluster, train a machine learning model using urban expansion data of urban areas in the cluster as samples and corresponding green space data as labels, to obtain a green space data prediction model corresponding to the cluster; and use an explainer model to explain the green space data prediction model corresponding to the cluster, to determine the positive or negative and strength of the stress effect of various urban expansion features on green space features under the cluster.

9. An electronic device, comprising: The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-7.

Images