Urban ecological element regulation-based rainfall flood toughness optimization method, equipment and medium

Abstract

The invention discloses a rainfall flood toughness optimization method and device based on urban ecological element regulation and control and a medium, and relates to the field of urban rainfall flood toughness optimizing.The method comprises the steps that a rainfall flood disaster spatial distribution diagram of a research area is analyzed and determined based on a geographic remote sensing image; the constructed urban rainfall flood toughness evaluation system comprises toughness factors in three aspects of urban ecological factors, geographic space factors and human influence factors, and data of the toughness factors corresponding to the research area is obtained; with the data of the toughness factor as a dependent variable and the rainfall flood disaster spatial distribution diagram as an independent variable, calculating urban rainfall flood toughness spatial distribution by using an XGBoost model; an SHAP interpretability method is introduced to carry out interpretability analysis on model output, and the contribution degree of each toughness factor to rainfall flood toughness is obtained; and solving an optimal ecological element combination scheme by taking the firmness and redundancy of improving rainfall flood toughness as a target so as to reduce urban loss caused by rainstorm flood disasters.

Description

Technical Field

[0001] This application relates to the field of urban stormwater resilience optimization, and in particular to a method, equipment and medium for stormwater resilience optimization based on the regulation of urban ecological elements. Background Technology

[0002] Early stormwater disaster management primarily relied on traditional gray infrastructure construction. However, these projects were costly to build and maintain, had limited regulatory scope, and were insufficient in addressing the risk of urban inundation due to excessive runoff from regional stormwater. The current approach is gradually shifting towards a disaster prevention system that combines gray and blue-green infrastructure. Therefore, there is an urgent need for a stormwater resilience optimization method, equipment, and media based on the regulation of urban ecological elements to enhance urban stormwater resilience. Summary of the Invention

[0003] The purpose of this application is to provide a method, equipment, and medium for optimizing urban stormwater resilience based on the regulation of urban ecological elements, which can improve urban stormwater resilience and reduce the losses caused by rainstorm and flood disasters to cities.

[0004] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a method for optimizing stormwater resilience based on the regulation of urban ecological elements, including: Acquire geographic remote sensing images of the study area, and determine the spatial distribution map of rainstorm disasters in the study area based on the analysis of the geographic remote sensing images; Construct an urban stormwater resilience assessment system; the urban stormwater resilience assessment system includes three aspects of resilience factors: urban ecological elements, geospatial elements, and human impact elements; Obtain the data of the toughness factor corresponding to the study area; Using resilience factor data as the dependent variable and the spatial distribution map of stormwater disasters as the independent variable, the XGBoost (Extreme Gradient Boosting) model was used to calculate the spatial distribution of urban stormwater resilience. The spatial distribution of urban stormwater resilience was interpreted using the SHAP (Shapley Additive Explanations) method, and the contribution of each resilience factor to stormwater resilience was obtained. With the goal of enhancing the robustness and redundancy of urban stormwater resilience, a multi-objective genetic optimization algorithm is used to optimize the configuration scheme of the urban ecological elements, thereby obtaining the optimal combination scheme of ecological elements to complete the stormwater resilience optimization.

[0005] Optionally, based on the analysis of the geographic remote sensing images, a spatial distribution map of stormwater disasters in the study area is determined, specifically including: Based on geographic remote sensing images of rainstorm disasters during and before they occur, determine the spatial distribution areas of rainstorm disasters; Atmospheric correction and cloud masking were performed on the spatial distribution images of rainstorm disasters to obtain the masked images; Calculate the improved normalized water index based on the masked image; Based on the improved normalized water index, flood-prone water areas were identified, and the ArcGIS kernel density analysis tool was used to determine the spatial distribution map of stormwater disasters in the study area.

[0006] Optionally, the urban stormwater resilience assessment system includes: Resilience factors in urban ecological elements include vegetation cover, normalized difference vegetation index, wetland area, habitat quality, landscape connectivity, river network density, surface runoff, soil type, and soil permeability. Resilience factors in terms of geospatial elements include elevation, slope, and aspect. Resilience factors in terms of human impact include land use type, urban road density, water infrastructure density, emergency rescue station density, population density, and GDP per capita.

[0007] Optionally, the habitat quality assessment steps are as follows: use landscape spatial pattern analysis to measure, identify, and segment land use data, define forest, grassland, and water land use types as foreground elements, define other land use types as background elements, and set the patch edge width to 30; the analysis results identify land use grid data into 7 types of landscape elements, namely core area, island, pore, edge area, ring road area, bridging area, and branch line, among which the core area is the ecological source area; Habitat quality was assessed using the InVEST model (Integrated Valuation of Ecosystem Services and Trade-offs). Farmland, impervious surfaces, bare land, and major roads and railways, which are heavily impacted by human activities and cause significant ecological damage, were selected as stress sources. A parameter table for the stress factor model was constructed. The InVEST model's formula for assessing habitat quality is as follows: ; in, Land use type Middle grid Habitat quality index; Land use type Habitat suitability; Land use type Middle grid The level of habitat stress; It is the half-saturation constant; This is a scaling factor.

[0008] Optionally, using Conefor 2.6 software, the potential connectivity index and the overall connectivity index are selected to measure landscape connectivity. The landscape connectivity calculation formula is as follows: ; ; Landscape connectivity includes the potential connectivity index. and overall connectivity index ; Total number of plaques; , plaques , The area; Total landscape area; For species to move to patches and The maximum probability between; Indicates plaque , The number of connections between them.

[0009] Optionally, surface runoff data can be calculated using the runoff curve number method, with the following formula: ; ; in, Surface runoff, For rainfall, This is the initial loss amount. For potential retention volume, This represents the number of runoff curves.

[0010] Optionally, the calculation formula for the XGBoost model is: ; ; in, Represent the objective function; Let be the loss function, representing the th Predicted values ​​for each sample Compared with the true value The error between them is based on data from the resilience factor in the urban stormwater resilience assessment system; Represents the regularization function; For iteration rounds; Indicates the first The number of leaf nodes in a tree; Indicates the first The weight of each leaf; The regularization coefficient is . This is the splitting threshold.

[0011] Optionally, the multi-objective genetic optimization algorithm is the NSGA-II algorithm.

[0012] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the above-mentioned stormwater resilience optimization method based on the regulation of urban ecological elements.

[0013] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned stormwater resilience optimization method based on the regulation of urban ecological elements.

[0014] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, equipment, and medium for optimizing stormwater resilience based on the regulation of urban ecological elements. It determines the spatial distribution map of stormwater disasters in the study area through analysis of geographic remote sensing images. The constructed urban stormwater resilience assessment system includes resilience factors from three aspects: urban ecological elements, geographic spatial elements, and anthropogenic influence factors. Data on the corresponding resilience factors for the study area are obtained. Using the resilience factor data as the dependent variable and the spatial distribution map of stormwater disasters as the independent variable, the spatial distribution of urban stormwater resilience is calculated using the XGBoost model. The SHAP interpretability method is used to interpret the spatial distribution of urban stormwater resilience, obtaining the contribution of each resilience factor to stormwater resilience. With the goal of improving the robustness and redundancy of urban stormwater resilience, the optimal combination of ecological elements is optimized, thereby improving urban stormwater resilience and reducing the losses caused by rainstorms and floods to the city. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is an application environment diagram of a stormwater resilience optimization method based on the regulation of urban ecological elements in one embodiment of this application.

[0017] Figure 2 This is a flowchart illustrating a method for optimizing stormwater resilience based on the regulation of urban ecological elements, provided as an embodiment of this application.

[0018] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] The stormwater resilience optimization method based on urban ecological element regulation provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send geographic remote sensing images of the study area to server 104. After receiving the geographic remote sensing images of the study area, server 104 analyzes the images to determine the spatial distribution map of stormwater disasters in the study area, constructs an urban stormwater resilience assessment system, obtains data on resilience factors corresponding to the study area, uses the resilience factor data as features, and constructs a training set using the spatial distribution map of stormwater disasters as labels. This training yields an urban stormwater resilience simulation model, which is interpreted using the SHAP attribution analysis model to obtain the contribution of each resilience factor to stormwater resilience. Based on the contribution, and with the goal of improving the robustness and redundancy of urban stormwater resilience, the optimal ecological element combination scheme is optimized. Server 104 can then feed back the obtained optimal ecological element combination scheme for the study area to terminal 102. In addition, in some embodiments, the stormwater resilience optimization method based on the regulation of urban ecological elements can also be implemented by the server 104 or the terminal 102 alone. For example, the terminal 102 can directly optimize the stormwater resilience based on the geographic remote sensing images of the study area, or the server 104 can obtain the geographic remote sensing images of the study area from the data storage system and optimize the stormwater resilience based on the geographic remote sensing images of the study area.

[0022] The terminal 102 can be, but is not limited to, various desktop computers and laptops. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0023] In one exemplary embodiment, such as Figure 2 As shown, a method for optimizing stormwater resilience based on the regulation of urban ecological elements is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 206.

[0024] Step 201: Obtain geographic remote sensing images of the study area, and determine the spatial distribution map of rain and flood disasters in the study area based on the analysis of the geographic remote sensing images.

[0025] Step 202: Construct an urban stormwater resilience assessment system. The urban stormwater resilience assessment system includes resilience factors in three aspects: urban ecological elements, geospatial elements, and human impact elements. The resilience factors are configured to evaluate urban stormwater resilience from one or more of four dimensions: robustness, redundancy, speed, and resource availability.

[0026] Step 203: Obtain the data of the toughness factor corresponding to the study area.

[0027] Step 204: Using the resilience factor data as the dependent variable and the spatial distribution map of stormwater disasters as the independent variable, the XGBoost model is used to calculate the spatial distribution of urban stormwater resilience.

[0028] Step 205: Use the SHAP interpretability method to interpret the spatial distribution of urban stormwater resilience and obtain the contribution of each resilience factor to stormwater resilience.

[0029] Step 206: With the goal of improving the robustness and redundancy of urban stormwater resilience, a multi-objective genetic optimization algorithm is used to optimize the configuration scheme of the urban ecological elements to obtain the optimal combination scheme of ecological elements, thereby completing the stormwater resilience optimization.

[0030] By implementing steps 201 to 206 above, and comprehensively considering the interaction between urban ecological elements and stormwater processes, the allocation of ecological elements is optimized to improve urban stormwater resilience. The model includes steps such as data collection and preprocessing, identification and quantification of urban ecological elements, stormwater process simulation, construction of a resilience assessment index system, optimization algorithm design, and model verification and optimization. The model in this application can provide scientific decision support for urban planners and managers, helping to formulate reasonable urban ecological construction and flood control planning strategies, reduce the losses caused by rainstorms and floods to cities, and promote sustainable urban development.

[0031] This application presents a stormwater resilience optimization method based on the regulation of urban ecological elements. The expansion of urban hardened areas leads to reduced rainfall infiltration, increased runoff generation, and accelerated runoff concentration. Simultaneously, the long-standing phenomenon of prioritizing above-ground infrastructure over underground infrastructure in China has resulted in low standards for municipal pipe network construction and aging drainage systems, exacerbating severe urban flooding problems. Under the concept of resilience, urban ecological elements play a crucial role in urban flood disaster regulation. This application enhances urban stormwater resilience by comprehensively considering the interaction between urban ecological elements and stormwater processes and optimizing the allocation of these elements.

[0032] In step 201 above, determining the spatial distribution map of rainstorm disasters in the study area based on the analysis of the geographic remote sensing images specifically includes: determining the spatial distribution area image of rainstorm disasters based on geographic remote sensing images when rainstorm disasters occur and when they do not occur; performing atmospheric correction and cloud masking on the spatial distribution area image of rainstorm disasters to obtain the masked image; calculating the improved normalized water index based on the masked image; obtaining the flood water body area based on the improved normalized water index; and using ArcGIS kernel density analysis tools to determine the spatial distribution map of rainstorm disasters in the study area.

[0033] The specific process of extracting the spatial distribution map of urban stormwater disasters includes: based on geographic remote sensing images, identifying the water body range during the disaster and during normal periods, and the difference between the two is the spatial distribution area of ​​stormwater disasters. Geographic remote sensing images can be obtained through the Google Earth engine platform. Using the geographic remote sensing images of Landsat 4, 5, 7, 8 and 9 obtained from this website, the data obtained from multiple satellites can avoid the errors caused by a single image source and improve the calculation accuracy. After completing the acquisition of geographic remote sensing images, atmospheric correction and cloud masking are performed, and the Modified Normalized Difference Water Index (MNDWI) is calculated. The calculation formula is shown in the following formula (1). Subsequently, the kernel density analysis tool is used in ArcGIS to determine the spatial distribution of flood disasters in the study area, which is recorded as the spatial distribution map of stormwater disasters in the study area.

[0034] (1); in, To improve the normalized water index for the study area, The reflectivity of the green band, This represents the reflectivity in the shortwave infrared band.

[0035] Resilience, as an abstract concept, is difficult to directly link with the physical environment. This application, based on an in-depth analysis of the 4R attributes of resilience, provides a more concrete explanation of the role of resilience in various aspects through a detailed breakdown. These attributes include: robustness (the system's ability to withstand torrential rain and flooding without damage or performance degradation); speed (the system's ability to recover promptly, avoid losses and system paralysis); redundancy (the degree to which system units are replaceable, ensuring they can still meet usage requirements even if the system is degraded or loses function); and resource availability (the ability to assess the current situation, determine priorities, and propose solutions to restore system function by identifying and allocating resources such as materials, information, technology, and human resources). To analyze the response of urban ecosystem elements to stormwater resilience, this application constructs an urban stormwater resilience assessment system from three aspects: urban ecological elements, geospatial elements, and anthropogenic influence elements, as shown in Table 1.

[0036] Table 1 Urban Rainfall Resilience Assessment System

[0037] As shown in Table 1, the urban stormwater resilience assessment system includes: Resilience factors in urban ecological elements include vegetation cover, normalized difference vegetation index, wetland area, habitat quality, landscape connectivity, river network density, surface runoff, soil type, and soil permeability. Resilience factors in terms of geospatial elements include elevation, slope, and aspect. Resilience factors in terms of human impact include land use type, urban road density, water infrastructure density, emergency rescue station density, population density, and GDP per capita.

[0038] Data on resilience factors in the urban stormwater resilience assessment system were obtained, and the data sources are shown in Table 2.

[0039] Table 2. Data Sources for Resilience Factors in the Urban Rainfall Resilience Assessment System

[0040] In addition to the directly available data, the data for the three factors of habitat quality, landscape connectivity, and surface runoff in Table 2 need to be calculated.

[0041] (1) The habitat quality assessment steps are as follows: First, the land use data is measured, identified and segmented using Landscape Spatial Pattern Analysis (MSPA). Woodland, grassland and water land use types are defined as foreground elements, and other land use types are defined as background elements. The edge width of the patch (a patch is a basic unit of landscape pattern. It refers to a relatively homogeneous nonlinear area that is different from the surrounding background) is 30. The analysis results identify the land use grid data into 7 types of landscape elements, namely core area, island, pore, edge area, ring road area, bridging area and branch line, among which the core area is the ecological source area.

[0042] The InVEST model was used to assess habitat quality: Farmland, impervious surfaces, bare land, and major roads and railways—areas with high levels of human activity and significant ecological damage—were selected as stress sources. A parameter table for the stress factor model was constructed based on previous research and the ecological environment of the study area. The InVEST model's formula for calculating the habitat quality index is as follows: (2); in, Land use type Middle grid Habitat quality index; Land use type Habitat suitability; Land use type Middle grid The habitat stress level is determined based on the user's research findings and the ecological environment of the study area; It is the half-saturation constant; This is a scaling factor.

[0043] (2) Based on the calculation of ecological source area and habitat quality above, Conefor 2.6 software is used to select the Possible Connectivity Index (PC) and Overall Connectivity Index (IIC) to measure landscape connectivity. The landscape connectivity calculation formulas are shown in equations (3) and (4) below.

[0044] (3); (4); Landscape connectivity includes the potential connectivity index. and overall connectivity index ; Total number of plaques; , plaques , The area; Total landscape area; For species to move to patches and The maximum probability between; Indicates plaque , The number of connections between them.

[0045] (3) Surface runoff elements are calculated using the runoff curve number method (SCS-CN model). The surface runoff calculation formula is as follows: (5); (6); in, Surface runoff, For rainfall, This is the initial loss amount. For potential retention volume, The term refers to the runoff curve number (CN). This application introduces the calculation method for the runoff curve number (CN). The value of CN can be obtained by consulting relevant data for different land use types and soil conditions. The empirical conversion relationship between the two is shown in formula (6).

[0046] To construct the nonlinear relationship between urban stormwater resilience factor and flood disaster distribution, an XGBoost model was introduced to simulate and analyze urban stormwater resilience, and SHAP attribution analysis was used to interpret the model results.

[0047] The XGBoost model was used to simulate the spatial distribution of urban stormwater resilience. The resilience factor dataset was set as the dependent variable and the spatial distribution of urban stormwater disasters was set as the independent variable. A training dataset was established and input into the XGBoost model for training. Through multiple iterations, the model was brought as close as possible to the true value.

[0048] The XGBoost model is essentially an ensemble algorithm that establishes multiple estimators through residual fitting. Each iteration generates an estimator based on the previous iteration, ultimately ensuring the model's predictions approximate the actual values. This application uses the XGBoost model to construct an urban stormwater resilience simulation model. Let the resilience factor in the urban stormwater resilience assessment system be X, and the spatial distribution map of stormwater disasters be Y. A training dataset is established and input into the XGBoost model for training, obtaining the relationship between the resilience factor data and the spatial distribution map of stormwater disasters. The calculation formula for the XGBoost model is: (7); (8); in, Represent the objective function; Let be the loss function, representing the th Predicted values ​​for each sample Compared with the true value The error between them is based on data from the resilience factor in the urban stormwater resilience assessment system; This represents a regularization function to prevent the model from overfitting. For iteration rounds; Indicates the first The number of leaf nodes in a tree; Indicates the first The weights of the leaves of each tree; to suppress tree growth and prevent model overfitting, the following are added. and , The regularization coefficient is . This is the splitting threshold.

[0049] In XGBoost model construction, adjusting hyperparameters (including the number of trees, tree depth, minimum number of leaf node samples, etc.) is crucial for suppressing overfitting. Automated parameter tuning using a combination of grid search and cross-validation reduces time costs while effectively obtaining the optimal parameter combination. When applying this method, the appropriate parameter combination should be selected based on the study area and data characteristics; no specific limitations are imposed here.

[0050] Building upon the XGBoost model's simulation of urban stormwater resilience, this paper introduces SHAP to interpret the model results and analyze the relationship between ecological factors and urban stormwater resilience. SHAP values ​​are calculated by summing the average marginal contributions of each resilience factor to the model's predictions, thus determining the factor's contribution (importance) to the prediction results. The calculation formula is shown below: (9); in, Features The contribution, i.e., the Shapley value; The set of all features in the training set; Let S be the size of the feature subset S, and Indicates any that does not contain features A subset of; Indicates the subset S and features Model prediction results under the combined effect; This indicates the model prediction result based solely on a feature subset S.

[0051] The multi-objective genetic optimization algorithm in step 206 above can be the NSGA-II algorithm.

[0052] The above simulation and interpretive analysis of stormwater resilience revealed that urban ecological elements play a crucial role in improving stormwater resilience. Therefore, the multi-objective genetic optimization algorithm NSGA-II (Non-dominated SortingGenetic Algorithm II) was adopted to find the optimal combination of ecological elements with the goal of improving the robustness and redundancy of urban stormwater resilience.

[0053] This application needs to clarify the goal of improving urban stormwater resilience based on the current situation and stormwater disaster conditions of the study area. On this basis, optimization constraints are set for the resilience factors of urban ecological elements in the urban stormwater resilience assessment system, and the optimal solution for the allocation of ecological elements is obtained through operations such as cross-processing, variation and selection.

[0054] For each study area, data on the resilience factors of urban ecological elements in that study area are obtained. The data of the resilience factors correspond to an initial scheme of ecological element combination for that study area. Based on the initial scheme of ecological element combination, the values ​​of at least one resilience factor among vegetation cover, normalized vegetation index, wetland area, habitat quality, and landscape connectivity are randomly changed to generate several ecological element combination schemes, which constitute an initial population. The initial population is iteratively optimized to obtain the optimal ecological element combination scheme.

[0055] First, based on vegetation cover, normalized vegetation index, wetland area, habitat quality, and landscape connectivity, the decision vector X is defined as an n-dimensional vector containing five resilience factors: (10); in, Indicates vegetation cover. Represents the normalized vegetation index. Indicates the area of ​​wetlands. Indicates habitat quality, Indicates landscape connectivity, superscript This indicates transpose.

[0056] The impact of urban ecological elements on stormwater resilience is mainly in terms of robustness and redundancy. Rational regulation of urban ecological elements is to enhance the robustness and redundancy of stormwater resilience.

[0057] Based on the ecological conditions of the study area, optimization measures such as increasing vegetation cover, improving habitat quality, increasing wetland area, and increasing landscape connectivity are set. In other words, constraints are set according to the actual situation of each ecological element and the status of urban development. =1,2,3,4,5(11) in, and They represent the first The lower and upper limits of the resilience factor.

[0058] In the process of improving ecological elements, constrained by urban socio-economic development and cost control, a multi-objective genetic algorithm is used to transform the relationship between the two into the following form in order to reasonably balance the relationship between them: (12); Wherein, objective function This is the stormwater resilience function, as described above; The cost of improving ecological elements should be minimized, as shown below: (13); in, To change the first The unit cost required for each resilience factor.

[0059] Based on the above methods, various stormwater resilience enhancement schemes were constructed, and the optimal combination of ecological elements was selected using non-dominated sorting.

[0060] (14); The above formulas can be used to classify combination schemes into different levels, where, and This represents two different combinations of ecological elements. and These represent the indices of the objective function.

[0061] To ensure the generation of diverse combinations, the crowding distance for each solution is calculated: (15); in, Ecological element combination scheme Crowding distance and These represent the current population at the [number]th [time]. The maximum and minimum values ​​on each target. For the first A combination scheme of ecological elements for a species.

[0062] The optimal combination of ecological elements is generated through iterative cycles of selection, crossover, and mutation operations.

[0063] When generating the next generation of solutions, a binary tournament selection method is used to compare the two solutions. and ,choose The conditions are: (16); in, , The respective schemes and Rank value; , The respective schemes and The degree of congestion.

[0064] A new scheme is generated using simulated binary crossover, with the two parent schemes being: and The generated offspring are: (17); (18); in, , They are respectively and offspring; It is a random number.

[0065] For offspring individuals Each variable Perform a mutation operation; the mutated variable for: (19); in, This is the disturbance calculated based on the multinomial distribution.

[0066] Repeat the above steps until the optimal combination of ecological elements is obtained.

[0067] This application has the following beneficial effects: 1. Construction of an Urban Rainfall Resilience Assessment System: With the acceleration of urbanization, urban topography has undergone drastic changes, with hard surfaces replacing natural surfaces on a large scale, runoff coefficients rising sharply, and evapotranspiration changing significantly. These changes have profoundly reshaped the urban hydrological cycle, leading to a sharp reduction in rainwater storage capacity and exacerbating the intensity and frequency of floods. This application addresses the problem of urban flooding caused by rainstorms. Based on the robustness, redundancy, speed, and resource availability of the resilience concept, it constructs an urban rainfall resilience assessment system from three aspects: urban ecological elements, geospatial elements, and human impact elements. This system establishes a bridge between the abstract concept of resilience and the urban problem of rainstorm-flooding. This system not only embodies the abstract connotation of "resilience" but also has the concrete characteristics of being observable, quantifiable, and controllable. From the perspective of the rational allocation of ecological elements, it transforms abstract goals into implementable and assessable practical measures, achieving a substantial improvement in urban rainfall resilience.

[0068] 2. A Rainfall Resilience Assessment Method Based on the XGBoost-SHAP Model: In recent years, the development of machine learning and deep learning has effectively processed multidimensional data and revealed nonlinear relationships between variables. The XGBoost model is an improvement on the gradient boosting decision tree model, incorporating regularization rules to reduce the risk of overfitting, effectively improving the efficiency and accuracy of the algorithm. However, machine learning is often considered a black box model, and the lack of interpretability severely limits its application. SHAP is a classic interpretable framework that provides shapley values ​​to encourage the contribution of each feature variable. Therefore, this application also introduces the XGBoost-SHAP model to simulate and interpret urban rainfall resilience. This application improves the simulation accuracy of urban rainfall resilience, accurately reflects the weaknesses in urban space in responding to rainstorms and floods, and identifies the contribution of different ecological elements, providing precise guidance for the optimal allocation of urban ecological elements and urban spatial planning.

[0069] 3. Optimization of Urban Ecological Elements Based on Multi-Objective Genetic Algorithm: This application employs the NSGA-II multi-objective genetic algorithm. By simulating the biological evolution process, it utilizes mechanisms such as population, genetic operations, and non-dominated sorting to simultaneously consider multiple objectives and maintain population diversity during the search process. It has the advantage of effectively converging to the Pareto optimal solution set and has been widely applied in multi-objective optimization problems. This application uses a multi-objective genetic algorithm to optimize the allocation of ecological elements from the perspective of improving urban stormwater resilience and redundancy. It provides scientific guidance for the rational planning and improvement of urban ecological elements, balances the spatial proportion of various ecological elements, and greatly improves the planning quality and implementation efficiency of urban response to stormwater disasters, providing scientific guidance for the construction of a blue-green-gray integrated disaster prevention system.

[0070] This application also provides an application scenario in which the above-mentioned stormwater resilience optimization method based on urban ecological element regulation is applied. Specifically, the stormwater resilience optimization method based on urban ecological element regulation provided in this embodiment can be applied in an urban stormwater resilience optimization scenario. The urban stormwater resilience optimization scenario includes a data acquisition stage, a stormwater resilience optimization chain, and an application stage of the optimal ecological element combination scheme. Geographic remote sensing images of the study area enter the stormwater resilience optimization chain from the data acquisition stage, obtain the optimal ecological element combination scheme through human-machine collaboration, and then enter the downstream application stage of the optimal ecological element combination scheme. The stormwater resilience optimization method based on urban ecological element regulation provided in this embodiment belongs to the stormwater resilience optimization chain. Specifically, in the process of optimizing the stormwater resilience of the study area, the spatial distribution map of stormwater disasters in the study area can be determined based on the analysis of geographic remote sensing images of the study area. A city stormwater resilience assessment system can be constructed, and data on the resilience factors corresponding to the study area can be obtained. Using the data of the resilience factors as the dependent variable and the spatial distribution map of stormwater disasters as the independent variable, the spatial distribution of urban stormwater resilience can be calculated using the XGBoost model. The spatial distribution of urban stormwater resilience can be interpreted using the SHAP interpretability method to obtain the contribution of each resilience factor to stormwater resilience. With the goal of improving the robustness and redundancy of urban stormwater resilience, the optimal combination of ecological elements can be optimized and solved.

[0071] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores stormwater resilience optimization data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a stormwater resilience optimization method based on the regulation of urban ecological elements.

[0072] Those skilled in the art will understand that Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0073] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0074] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0075] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0076] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0077] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0078] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0079] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for optimizing stormwater resilience based on the regulation of urban ecological elements, characterized in that, The stormwater resilience optimization method based on the regulation of urban ecological elements includes: Acquire geographic remote sensing images of the study area, and determine the spatial distribution map of rainstorm disasters in the study area based on the analysis of the geographic remote sensing images; Construct an urban stormwater resilience assessment system; the urban stormwater resilience assessment system includes three aspects of resilience factors: urban ecological elements, geospatial elements, and human impact elements; Obtain the data of the toughness factor corresponding to the study area; Using resilience factor data as the dependent variable and the spatial distribution map of stormwater disasters as the independent variable, the XGBoost model was used to calculate the spatial distribution of urban stormwater resilience. The spatial distribution of urban stormwater resilience was interpreted using the SHAP interpretability method, and the contribution of each resilience factor to stormwater resilience was obtained. With the goal of enhancing the robustness and redundancy of urban stormwater resilience, a multi-objective genetic optimization algorithm is used to optimize the configuration scheme of the urban ecological elements, thereby obtaining the optimal combination scheme of ecological elements to complete the stormwater resilience optimization.

2. The method for optimizing stormwater resilience based on the regulation of urban ecological elements according to claim 1, characterized in that, Based on the analysis of the aforementioned geographic remote sensing images, a spatial distribution map of rainfall and flood hazards in the study area was determined, specifically including: Based on geographic remote sensing images of rainstorm disasters during and before they occur, determine the spatial distribution areas of rainstorm disasters; Atmospheric correction and cloud masking were performed on the spatial distribution images of rainstorm disasters to obtain the masked images; Calculate the improved normalized water index based on the masked image; Based on the improved normalized water index, flood-prone water areas were identified, and the ArcGIS kernel density analysis tool was used to determine the spatial distribution map of stormwater disasters in the study area.

3. The method for optimizing stormwater resilience based on the regulation of urban ecological elements according to claim 1, characterized in that, The urban stormwater resilience assessment system includes: Resilience factors in urban ecological elements include vegetation cover, normalized difference vegetation index, wetland area, habitat quality, landscape connectivity, river network density, surface runoff, soil type, and soil permeability. Resilience factors in terms of geospatial elements include elevation, slope, and aspect. Resilience factors in terms of human impact include land use type, urban road density, water infrastructure density, emergency rescue station density, population density, and GDP per capita.

4. The method for optimizing stormwater resilience based on the regulation of urban ecological elements according to claim 3, characterized in that, The habitat quality assessment steps are as follows: land use data is measured, identified, and segmented using landscape spatial pattern analysis. Woodland, grassland, and water land use types are defined as foreground elements, while other land use types are defined as background elements, with a patch edge width of 30. The analysis results identify land use grid data into seven landscape elements: core area, island, pore, edge area, ring road area, bridging area, and branch line, among which the core area is the ecological source area. The InVEST model was used to assess habitat quality: farmland, impervious surfaces, bare land, and major highways and railways that are heavily impacted by human activities and cause significant damage to the ecological environment were selected as stress sources. A parameter table for the stress factor model was constructed, and the InVEST model was used to calculate habitat quality as follows: ； in, Land use type Middle grid Habitat quality index; Land use type Habitat suitability; Land use type Middle grid The level of habitat stress; It is the half-saturation constant; This is the scaling factor.

5. The method for optimizing stormwater resilience based on the regulation of urban ecological elements according to claim 4, characterized in that, Using Conefor 2.6 software, the potential connectivity index and the overall connectivity index were selected to measure landscape connectivity. The formula for calculating landscape connectivity is as follows: ； ； Landscape connectivity includes the potential connectivity index. and overall connectivity index ; Total number of plaques; , plaques , The area; Total landscape area; For species to move to patches and The maximum probability between; Indicates plaque , The number of connections between them.

6. The method for optimizing stormwater resilience based on the regulation of urban ecological elements according to claim 3, characterized in that, Surface runoff data are calculated using the runoff curve number method. The calculation formula is as follows: ； ； in, Surface runoff, For rainfall, This is the initial loss amount. For potential retention volume, This represents the number of runoff curves.

7. The method for optimizing stormwater resilience based on the regulation of urban ecological elements according to claim 1, characterized in that, The calculation formula for the XGBoost model is: ； ； in, Represent the objective function; Let be the loss function, representing the th Predicted values ​​for each sample Compared with the true value The error between them is based on data of resilience factors in the urban stormwater resilience assessment system; Represents the regularization function; For iteration rounds; Indicates the first The number of leaf nodes in a tree; Indicates the first The weight of each leaf; The regularization coefficient is . This is the splitting threshold.

8. The method for optimizing stormwater resilience based on the regulation of urban ecological elements according to claim 1, characterized in that, The multi-objective genetic optimization algorithm is the NSGA-II algorithm.

9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the stormwater resilience optimization method based on the regulation of urban ecological elements as described in any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the stormwater resilience optimization method based on the regulation of urban ecological elements as described in any one of claims 1-8.

Images