A sponge city design method and system

Abstract

The present invention provides a sponge city design method and system, relating to the field of sponge city data processing technology. The method comprises obtaining information; simulating the waterlogging situation in the urban area using an agent-based model based on the information to obtain a waterlogging distribution map; constructing a graphical model based on the drainage system data; and constructing a drainage pipeline layout optimization model based on the graphical model and the waterlogging distribution map. The drainage pipeline layout optimization model includes an objective function and constraints, the objective function including minimizing the sum of the construction cost of the drainage pipeline and a penalty for insufficient drainage capacity. The constraints include flow balance constraints at the drainage points, capacity constraints of the drainage pipelines, drainage capacity constraints in the flood-prone areas, and drainage capacity constraints in the drainage bottleneck areas. The method then solves the drainage pipeline layout optimization model based on hypergeometric distribution sampling. The present invention takes into account the differences between different urban areas and significantly improves the design results of sponge cities.

Description

Technical Field

[0001] The present invention relates to the technical field of sponge city data processing, and in particular to a sponge city design method and system. Background Art

[0002] Traditional sponge city design often ignores the differences between different areas of the city. When optimizing the design plan, it usually only considers a single project and cannot achieve comprehensive optimization of the design plan. In the decision-making process, it relies less on data and more on experience and qualitative analysis, making it difficult for the design to achieve the expected results. Summary of the Invention

[0003] The purpose of the present invention is to provide a sponge city design method and system to improve the above problems. In order to achieve the above objectives, the technical solutions adopted by the present invention are as follows:

[0004] In the first aspect, this application provides a sponge city design method, including:

[0005] obtaining information including historical rainfall data, topographic data, ground cover data, and drainage data for an urban area;

[0006] Simulating waterlogging conditions in the urban area using an agent-based model based on the information to obtain a waterlogging distribution map, wherein the waterlogging distribution map includes waterlogging-prone areas and drainage bottleneck areas;

[0007] Constructing a graph model based on the drainage system data, wherein the nodes in the graph model are drainage points and the edges in the graph model are drainage pipes;

[0008] Constructing a drainage pipeline layout optimization model based on the graphical model and the waterlogging distribution map, the drainage pipeline layout optimization model including an objective function and constraints, the objective function including minimizing the sum of the construction cost of the drainage pipeline and a penalty for insufficient drainage capacity, and the constraints including a flow balance constraint of the drainage point, a capacity constraint of the drainage pipeline, a drainage capacity constraint of the flood-prone area, and a drainage capacity constraint of the drainage bottleneck area;

[0009] The drainage pipe layout optimization model is solved based on hypergeometric distribution sampling to obtain a drainage pipe design solution.

[0010] Secondly, this application also provides a sponge city design system, including:

[0011] an acquisition module, the acquisition module being used to acquire information, the information including historical rainfall data, terrain data, ground cover data, and drainage system data of an urban area;

[0012] a simulation module configured to simulate waterlogging conditions in the urban area using an agent-based model based on the information to obtain a waterlogging distribution map, wherein the waterlogging distribution map includes waterlogging-prone areas and drainage bottleneck areas;

[0013] a first construction module, configured to construct a graph model based on the drainage system data, wherein nodes in the graph model are drainage points and edges in the graph model are drainage pipes;

[0014] a second construction module, configured to construct a drainage pipe layout optimization model based on the graphical model and the waterlogging distribution map, the drainage pipe layout optimization model including an objective function and constraints, the objective function including minimizing the sum of the construction cost of the drainage pipe and a penalty for insufficient drainage capacity, and the constraints including a flow balance constraint of the drainage point, a capacity constraint of the drainage pipe, a drainage capacity constraint of the flood-prone area, and a drainage capacity constraint of the drainage bottleneck area;

[0015] A solution module is used to solve the drainage pipe layout optimization model based on hypergeometric distribution sampling to obtain a drainage pipe design solution.

[0016] In a third aspect, the present application also provides a sponge city design device, including:

[0017] memory for storing computer programs;

[0018] A processor is used to implement the steps of the sponge city design method when executing the computer program.

[0019] In a fourth aspect, the present application also provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned steps based on a sponge city design method are implemented.

[0020] The beneficial effects of the present invention are as follows: the present invention adopts a sponge city design method and system, takes into account the differences between different areas of the city in the sponge city design, integrates diverse data to achieve comprehensive optimization of the sponge city design, and greatly improves the design effect of the sponge city.

[0021] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 This is a schematic flow chart of a sponge city design method according to an embodiment of the present invention;

[0024] Figure 2 A logical diagram of a sponge city design method described in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of a sponge city design device described in an embodiment of the present invention.

[0026] Markings in the figure: 800, a sponge city design device; 801, a processor; 802, a memory; 803, a multimedia component; 804, an I / O interface; 805, a communication component. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0029] Example 1:

[0030] This embodiment provides a sponge city design method.

[0031] See also Figure 1 and Figure 2, the figure shows that the method includes step S100, step S200, step S300, step S400, and step S500.

[0032] Step S100: Acquire information, the information including historical rainfall data, terrain data, ground cover data, and drainage system data of the urban area;

[0033] Step S100 specifically includes:

[0034] Acquiring historical rainfall data, and performing data cleaning, time format conversion, and standardization on the historical rainfall data;

[0035] The main sources of historical rainfall data are: Meteorological Bureau website, environmental monitoring stations, and online meteorological data platforms.

[0036] Acquiring terrain data, and performing data cleaning, projection conversion, interpolation processing, and standardization processing on the terrain data, wherein the terrain data includes geographic information system data and satellite image data, and the projection conversion converts the terrain data into a unified projection coordinate system;

[0037] Acquiring ground cover data, and performing data cleaning, classification processing, projection conversion, and standardization processing on the ground cover data, wherein the ground cover data includes remote sensing images, and the classification processing includes classifying the ground cover types of the remote sensing images using a supervised or unsupervised classification algorithm;

[0038] Drainage system data is obtained, and the ground cover data is cleaned, projected, converted, and standardized.

[0039] The main methods of data cleaning are: removing missing values and outliers, and using interpolation methods to fill missing values.

[0040] The classification process includes:

[0041] Extracting spectral features of each pixel in the remote sensing image to obtain a feature set;

[0042] Selecting representative ground cover type sample points from the feature set and constructing training data based on the ground cover type sample points, wherein the ground cover types include grass, buildings, and roads;

[0043] Assigning a corresponding ground cover type label to each ground cover type sample point;

[0044] Training a preset support vector machine model according to the training data to obtain a trained support vector machine model;

[0045] The feature set is classified according to the trained support vector machine model to obtain a classification result, wherein the classification result includes the ground cover type of each pixel point.

[0046] Different types of ground cover have a direct impact on infiltration and runoff, for example:

[0047] Grassland and green space: With high permeability, rainwater can quickly penetrate into the ground, reducing surface runoff and generating less surface runoff;

[0048] Buildings and roads: They have low permeability, making it difficult for rainwater to penetrate. Most of the rainwater will form surface runoff, which generates a large amount of surface runoff and increases the burden on the drainage system.

[0049] By accurately classifying ground cover types, it's possible to determine the amount of infiltration and runoff in each area, thereby optimizing drainage system design. Specifically, each ground cover type has a corresponding permeability and runoff coefficient, which can be obtained from literature, standards, or field measurements. Based on the area, rainfall, and the corresponding permeability and runoff coefficients for each ground cover type, the permeability and runoff volume for each area can be calculated.

[0050] Step S200: simulating the waterlogging situation in the urban area using an agent-based model according to the information to obtain a waterlogging distribution map, wherein the waterlogging distribution map includes waterlogging-prone areas and drainage bottleneck areas;

[0051] The step S200 specifically includes:

[0052] Evenly dividing the urban area into a plurality of grid cells;

[0053] Constructing a rainfall agent, including setting the rainfall intensity, rainfall pattern and rainfall duration of each grid cell according to the historical rainfall data and the IDF curve;

[0054] The IDF curve is the intensity-frequency-duration curve, which shows the relationship between different rainfall intensities, frequencies and durations.

[0055] Constructing a terrain elevation proxy, including setting the elevation and slope of each of the grid cells according to the terrain data;

[0056] Constructing a water flow state agent, including setting an initial water depth and an initial water flow velocity to zero, wherein the initial water depth and the initial water flow velocity vary with the rainfall intensity, rainfall pattern, and rainfall duration;

[0057] Constructing a drainage system agent, including setting pipe capacity, drainage speed, pipe connection relationship and pipe structure parameters of the drainage pipe in each grid unit according to the drainage system data;

[0058] Constructing a ground cover agent, including setting the infiltration and runoff of each of the grid cells according to the ground cover data;

[0059] updating the water flow velocity and water depth of each grid cell according to the rainfall agent, the terrain elevation agent, the water flow state agent, the drainage system layout agent, and the ground cover agent to generate a water accumulation distribution map;

[0060] All the grid cells where the water depth exceeds a preset depth threshold are marked on the water distribution map as the flood-prone areas, and all the grid cells where the water flow speed is lower than a preset speed are marked on the water distribution map as the drainage bottleneck areas.

[0061] The above method can improve the generation accuracy and prediction ability of waterlogging distribution map, thereby providing more reliable data support for drainage system optimization.

[0062] Step S300: constructing a graph model based on the drainage system data, where nodes in the graph model are drainage points and edges in the graph model are drainage pipes;

[0063] The step S300 specifically includes:

[0064] Constructing a drainage pipe layout optimization model according to the graphical model and the water accumulation distribution map, including:

[0065] Construct an objective function, which is:

[0066] min∑ (i，j)∈E (C ij ·x ij +P·max(0,F ij -Capacity ij )

[0067] (i, j) represents the edge connecting node i to node j in the graph model, E represents the edge set of possible connections between all nodes in the graph model, C ij represents the pipeline construction cost from node i to node j, x ij is the decision variable, x ij Indicates whether to build a pipeline from node i to node j, x ij The value is 0 or 1, P represents the penalty coefficient for insufficient drainage capacity, F ij is the water flow from node i to node j, Capacity ij The capacity of the pipeline from node i to node j;

[0068] Constructing a flow balance constraint for the drainage point, wherein the flow balance constraint for the drainage point is that the inflow water flow of each node is equal to the outflow water flow;

[0069] Constructing a capacity constraint for the drainage pipe, wherein the capacity constraint for the drainage pipe is that the maximum flow of each drainage pipe does not exceed the capacity of the drainage pipe;

[0070] Constructing a drainage capacity constraint for the flood-prone area, wherein the drainage capacity constraint for the flood-prone area requires that the total capacity of all the drainage pipes in the flood-prone area is not less than a target drainage volume for the flood-prone area;

[0071] A drainage capacity constraint for the drainage bottleneck area is constructed, where the drainage capacity constraint for the drainage bottleneck area requires that the total capacity of all the drainage pipes in the drainage bottleneck area is not less than the target drainage volume of the drainage bottleneck area.

[0072] Step S400: Constructing a drainage pipe layout optimization model based on the graphical model and the waterlogging distribution map, the drainage pipe layout optimization model including an objective function and constraints. The objective function includes minimizing the sum of the construction cost of the drainage pipe and the penalty for insufficient drainage capacity. The constraints include a flow balance constraint of the drainage point, a capacity constraint of the drainage pipe, a drainage capacity constraint of the flood-prone area, and a drainage capacity constraint of the drainage bottleneck area.

[0073] Step S500: Solving the drainage pipe layout optimization model based on hypergeometric distribution sampling to obtain a drainage pipe design solution.

[0074] Step S500 specifically includes:

[0075] Initialization: randomly generating an initial solution that satisfies the constraints, and calculating an initial objective function value based on the initial solution and the objective function, taking the initial solution as the current solution, and taking the initial objective function value as the current objective function value, wherein the initial solution includes the decision variables generated corresponding to the randomly selected edge in the edge set;

[0076] Sampling: Generate candidate solutions that satisfy the constraints based on a hypergeometric distribution sampling function according to a preset total number of candidate options, a preset number of selected options, a preset number of samples, and a preset number of candidate solutions. The total number of candidate options is the total number of edges, the number of selected options is the number of edges selected in the current solution, the number of samples is the number sampled from the total number of candidate options each time a new candidate solution is generated, and the number of candidate solutions is the number of candidate solutions generated in each iteration.

[0077] Screening: Calculating the objective function value of each candidate solution based on the objective function, the preset pipeline construction cost, the penalty coefficient for insufficient drainage capacity, and the water flow rate, and screening out the candidate solution with the minimum objective function value;

[0078] Update: Update the current solution and the current objective function value by using the candidate solution with the minimum objective function value and its corresponding objective function value;

[0079] Repeat the above sampling, screening and updating steps until the preset maximum number of iterations is reached, and output the optimal solution, which is the drainage pipe design solution.

[0080] In step S500, candidate solutions that satisfy the constraints are generated based on a hypergeometric distribution sampling function according to a preset total number of candidate items, a preset number of selected items, a preset number of samples, and a preset number of candidate solutions, including:

[0081] Construct the adaptive parameter change formula:

[0082]

[0083] where α t represents the adaptive adjustment parameter at the tth iteration, where T represents the maximum number of iterations, and α0 represents the preset initial adaptive parameter;

[0084] Determine the current number of iterations, if but:

[0085] K′=min(K+α t ·N,N)

[0086] n′=min(n+α t N,N)

[0087] Determine the current number of iterations, if but:

[0088] K′=max(K-α t ·N,0)

[0089] n′=max(n-α t ·N,0)

[0090] In the above formula, K represents the preset number of selected items, N represents the preset total number of candidate items, n represents the preset number of samples, K′ represents the adjusted number of selected items, and n′ represents the adjusted number of samples;

[0091] Hypergeometric distribution sampling is performed according to the total number of candidate items, the adjusted number of selected items, the adjusted sampling number and the number of candidate solutions to generate candidate solutions that meet the constraint conditions.

[0092] The benefit of introducing adaptive parameters here is that it can ensure the efficiency and accuracy of subsequent hypergeometric distribution sampling.

[0093] The sponge city design method further includes optimizing the drainage pipe design scheme, and the optimizing the drainage pipe design scheme includes:

[0094] Constructing a complex network model according to the drainage pipe design scheme, wherein the nodes of the complex network model are the drainage points and the edges are the drainage pipes;

[0095] Calculating the degree centrality, betweenness centrality and clustering coefficient of each node according to the complex network model;

[0096] An optimization processing objective function is constructed, and the formula of the optimization processing objective function is:

[0097]

[0098] C D (i)=Degree(i)

[0099]

[0100] Among them, α, β, γ, and δ represent weight coefficients, and C D (i) represents the degree centrality of node i, C B (i) represents the betweenness centrality of node i, C(i) represents the clustering coefficient of node i, v represents the node set, f(x) is the objective function value, Degree(i) centrality represents the number of connections of node i, σ st represents the total number of shortest paths between node s and node t, σ st (i) represents the total number of shortest paths passing through node i, E i represents the actual number of edges between the neighbors of node i, k i represents the degree of node i;

[0101] Constructing an optimization processing constraint condition, wherein the optimization processing constraint condition includes that the degree centrality of each of the nodes is greater than or equal to 1;

[0102] The optimization processing objective function is solved according to the Bayesian optimization algorithm to obtain the optimal drainage pipeline design solution that meets the optimization processing constraints.

[0103] Using complex network theory and Bayesian optimization algorithms, sponge city designs can be effectively optimized. The above steps ensure that cost constraints are met while also improving network robustness and efficiency. Bayesian optimization is highly efficient in optimizing black-box functions and searching high-dimensional spaces, making it well-suited for parameter optimization in complex networks.

[0104] Using complex network theory to optimize sponge city design, especially combining it with the output of drainage system design solutions, can improve the efficiency, robustness and reliability of urban infrastructure, thereby better responding to complex environmental challenges and future changes. This approach can not only optimize existing designs, but also provide a scientific basis and decision-making support for urban planning and management.

[0105] In step S500, the optimization objective function is solved according to the Bayesian optimization algorithm to obtain the optimal drainage pipe design scheme that meets the optimization constraint conditions, including:

[0106] Randomly generate sample points, where the sample points are decision variables generated corresponding to edges randomly selected from the edge set, and calculate optimization objective function values corresponding to the sample points according to the optimization objective function;

[0107] Training the Gaussian process model, constructing training samples according to the sample points and the optimization processing objective function values corresponding to the sample points, and training the preset Gaussian process model through the training samples to obtain a trained Gaussian process model;

[0108] Selecting a new sampling point, selecting the new sampling point according to the acquisition function, and calculating a new optimization processing objective function value corresponding to the new sampling point according to the optimization processing objective function;

[0109] In this embodiment, the expected improvement function is used as the acquisition function, and the formula for selecting the new sample points according to the acquisition function is:

[0110] x new =arg max EI(x)

[0111] EI(x) represents the expected improvement function, x new Represents the new sample point.

[0112] Updating the model by adding the new sample points and the new optimization processing objective function values corresponding to the new sample points to the training samples to obtain new training samples, and retraining the Gaussian process model based on the new training samples;

[0113] Repeat the process of selecting new sampling points and updating the model until the preset maximum number of optimization process iterations is reached, and then output the optimal sampling point.

[0114] In this optimization process, the Gaussian process model effectively guided the selection of new sample points by predicting the objective function value and providing an uncertainty measure. By using the acquisition function, we were able to select the sample points with the highest improvement potential at each iteration, gradually approaching the optimal solution. The application of the Gaussian process model significantly improved optimization efficiency. By continuously iterating and updating the Gaussian process model, we gradually identified the optimal drainage pipeline construction plan, thereby optimizing the sponge city design.

[0115] Example 2:

[0116] This embodiment provides a sponge city design system, which includes:

[0117] an acquisition module, the acquisition module being used to acquire information, the information including historical rainfall data, terrain data, ground cover data, and drainage system data of an urban area;

[0118] a simulation module configured to simulate waterlogging conditions in the urban area using an agent-based model based on the information to obtain a waterlogging distribution map, wherein the waterlogging distribution map includes waterlogging-prone areas and drainage bottleneck areas;

[0119] a first construction module, configured to construct a graph model based on the drainage system data, wherein nodes in the graph model are drainage points and edges in the graph model are drainage pipes;

[0120] a second construction module, configured to construct a drainage pipe layout optimization model based on the graphical model and the waterlogging distribution map, the drainage pipe layout optimization model including an objective function and constraints, the objective function including minimizing the sum of the construction cost of the drainage pipe and a penalty for insufficient drainage capacity, and the constraints including a flow balance constraint of the drainage point, a capacity constraint of the drainage pipe, a drainage capacity constraint of the flood-prone area, and a drainage capacity constraint of the drainage bottleneck area;

[0121] A solution module is used to solve the drainage pipe layout optimization model based on hypergeometric distribution sampling to obtain a drainage pipe design solution.

[0122] The simulation module includes:

[0123] A division module, the division module is used to evenly divide the urban area into a plurality of grid units;

[0124] A third construction module is used to construct a rainfall agent, including setting the rainfall intensity, rainfall pattern and rainfall duration of each grid cell according to the historical rainfall data and the IDF curve;

[0125] a fourth construction module, the fourth construction module being used to construct a terrain elevation proxy, including setting the elevation and slope of each of the grid cells according to the terrain data;

[0126] a fifth construction module for constructing a water flow state agent, including setting an initial water depth and an initial water flow velocity to zero, wherein the initial water depth and the initial water flow velocity vary with the rainfall intensity, rainfall pattern, and rainfall duration;

[0127] a sixth construction module, the sixth construction module being used to construct a drainage system agent, including setting the pipe capacity, drainage speed, pipe connection relationship, and pipe structure parameters of the drainage pipe in each grid unit according to the drainage system data;

[0128] a seventh construction module, the seventh construction module being used to construct a ground cover agent, including setting the infiltration and runoff of each grid cell according to the ground cover data;

[0129] An updating module, configured to update the water flow velocity and water depth of each grid cell according to the rainfall proxy, the terrain elevation proxy, the water flow state proxy, the drainage system layout proxy, and the ground cover proxy, to generate a water accumulation distribution map;

[0130] A marking module is used to mark all the grid cells whose water depth exceeds a preset depth threshold as the flood-prone areas on the water accumulation distribution map, and to mark all the grid cells whose water flow speed is lower than a preset speed as the drainage bottleneck areas on the water accumulation distribution map.

[0131] The acquisition module includes:

[0132] a first acquisition module, the first acquisition module being used to acquire historical rainfall data, and perform data cleaning, time format conversion, and standardization processing on the historical rainfall data;

[0133] a second acquisition module, the second acquisition module being used to acquire terrain data and perform data cleaning, projection conversion, interpolation processing, and standardization processing on the terrain data, the terrain data including geographic information system data and satellite image data, the projection conversion converting the terrain data into a unified projection coordinate system;

[0134] a third acquisition module, the third acquisition module being configured to acquire ground cover data and perform data cleaning, classification processing, projection conversion, and standardization processing on the ground cover data, wherein the ground cover data includes remote sensing images, and the classification processing includes classifying the remote sensing images into ground cover types using a supervised or unsupervised classification algorithm;

[0135] The fourth acquisition module is used to acquire drainage system data and perform data cleaning, projection conversion and standardization on the ground cover data.

[0136] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0137] Example 3:

[0138] Corresponding to the above method embodiment, this embodiment further provides a sponge city design device. The sponge city design device described below and the sponge city design method described above can refer to each other.

[0139] Figure 3 FIG. 8 is a block diagram of a sponge city design device 800 according to an exemplary embodiment. Figure 3 As shown, the sponge city design device 800 may include: a processor 801 and a memory 802. The sponge city design device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0140] The processor 801 is used to control the overall operation of the sponge city design device 800 to complete all or part of the steps in the above-mentioned sponge city design method. The memory 802 is used to store various types of data to support the operation of the sponge city design device 800. Such data may include, for example, instructions for any application or method operating on the sponge city design device 800, as well as application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules. The above-mentioned other interface modules can be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the sponge city design device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 may include: Wi-Fi module, Bluetooth module, NFC module.

[0141] In an exemplary embodiment, a sponge city design device 800 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned sponge city design method.

[0142] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When executed by a processor, the program instructions implement the steps of the above-mentioned sponge city design method. For example, the computer-readable storage medium may be the aforementioned memory 802 including the program instructions. The program instructions may be executed by the processor 801 of the sponge city design device 800 to implement the above-mentioned sponge city design method.

[0143] Example 4:

[0144] Corresponding to the above method embodiment, this embodiment further provides a readable storage medium. The readable storage medium described below and the sponge city design method described above can refer to each other.

[0145] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a sponge city design method of the above-mentioned method embodiment.

[0146] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0147] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

[0148] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A sponge city design method, characterized in that: include: obtaining information including historical rainfall data, topographic data, ground cover data, and drainage data for an urban area; Simulating waterlogging conditions in the urban area using an agent-based model based on the information to obtain a waterlogging distribution map, wherein the waterlogging distribution map includes waterlogging-prone areas and drainage bottleneck areas; Constructing a graph model based on the drainage system data, wherein the nodes in the graph model are drainage points and the edges in the graph model are drainage pipes; Constructing a drainage pipeline layout optimization model based on the graphical model and the waterlogging distribution map, the drainage pipeline layout optimization model including an objective function and constraints, the objective function including minimizing the sum of the construction cost of the drainage pipeline and a penalty for insufficient drainage capacity, and the constraints including a flow balance constraint of the drainage point, a capacity constraint of the drainage pipeline, a drainage capacity constraint of the flood-prone area, and a drainage capacity constraint of the drainage bottleneck area; Solving the drainage pipe layout optimization model based on hypergeometric distribution sampling to obtain a drainage pipe design solution; The drainage pipe layout optimization model is solved based on hypergeometric distribution sampling to obtain the optimal drainage pipe design solution, including: Initialization: randomly generating an initial solution that satisfies the constraints, and calculating an initial objective function value based on the initial solution and the objective function, taking the initial solution as the current solution, and taking the initial objective function value as the current objective function value. The initial solution includes decision variables generated corresponding to randomly selected edges in the edge set, and the edge set is the edge set of all possible connections between nodes in the graphical model. Sampling: Generate candidate solutions that satisfy the constraints based on a hypergeometric distribution sampling function according to a preset total number of candidate options, a preset number of selected options, a preset number of samples, and a preset number of candidate solutions. The total number of candidate options is the total number of edges, the number of selected options is the number of edges selected in the current solution, the number of samples is the number sampled from the total number of candidate options each time a new candidate solution is generated, and the number of candidate solutions is the number of candidate solutions generated in each iteration. Screening: Calculating the objective function value of each candidate solution based on the objective function, the preset pipeline construction cost, the penalty coefficient for insufficient drainage capacity, and the water flow rate, and screening out the candidate solution with the minimum objective function value; Update: Update the current solution and the current objective function value by using the candidate solution with the minimum objective function value and its corresponding objective function value; Repeat the above sampling, screening and updating steps until the preset maximum number of iterations is reached, and output the optimal solution, which is the drainage pipe design solution.

2. A sponge city design method according to claim 1, characterized in that Based on the information, the waterlogging situation of the urban area is simulated by an agent-based model to obtain a waterlogging distribution map, including: Evenly dividing the urban area into a plurality of grid cells; Constructing a rainfall agent, including setting the rainfall intensity, rainfall pattern and rainfall duration of each grid cell according to the historical rainfall data and the IDF curve; Constructing a terrain elevation proxy, including setting the elevation and slope of each of the grid cells according to the terrain data; Constructing a water flow state agent, including setting an initial water depth and an initial water flow velocity to zero, wherein the initial water depth and the initial water flow velocity vary with the rainfall intensity, rainfall pattern, and rainfall duration; Constructing a drainage system agent, including setting pipe capacity, drainage speed, pipe connection relationship and pipe structure parameters of the drainage pipe in each grid unit according to the drainage system data; Constructing a ground cover agent, including setting the infiltration and runoff of each of the grid cells according to the ground cover data; updating the water flow velocity and water depth of each grid cell according to the rainfall agent, the terrain elevation agent, the water flow state agent, the drainage system layout agent, and the ground cover agent to generate a water accumulation distribution map; All the grid cells where the water depth exceeds a preset depth threshold are marked on the water distribution map as the flood-prone areas, and all the grid cells where the water flow speed is lower than a preset speed are marked on the water distribution map as the drainage bottleneck areas.

3. The sponge city design method according to claim 2 is characterized in that , constructing a drainage pipe layout optimization model based on the graph model and the water accumulation distribution map, including: Construct an objective function, which is: min∑ (i，j)∈E (C ij ·x ij +P·max(0,F ij -Capacity ij )) (i, j) represents the edge connecting node i to node j in the graph model, E represents the edge set of possible connections between all nodes in the graph model, C ij represents the pipeline construction cost from node i to node j, x ij is the decision variable, x ij Indicates whether to build a pipeline from node i to node j, x ij The value is 0 or 1, P represents the penalty coefficient for insufficient drainage capacity, F ij is the water flow from node i to node j, Capacity ij The capacity of the pipeline from node i to node j; Constructing a flow balance constraint for the drainage point, wherein the flow balance constraint for the drainage point is that the inflow water flow of each node is equal to the outflow water flow; Constructing a capacity constraint for the drainage pipe, wherein the capacity constraint for the drainage pipe is that the maximum flow of each drainage pipe does not exceed the capacity of the drainage pipe; Constructing a drainage capacity constraint for the flood-prone area, wherein the drainage capacity constraint for the flood-prone area requires that the total capacity of all the drainage pipes in the flood-prone area is not less than a target drainage volume for the flood-prone area; A drainage capacity constraint for the drainage bottleneck area is constructed, where the drainage capacity constraint for the drainage bottleneck area is that the total capacity of all the drainage pipes in the drainage bottleneck area is not less than the target drainage volume of the drainage bottleneck area.

4. The sponge city design method according to claim 3 is characterized in that The sponge city design method also includes optimizing the drainage pipeline design scheme, and the optimizing the drainage pipeline design scheme includes: Constructing a complex network model according to the drainage pipe design scheme, wherein the nodes of the complex network model are the drainage points and the edges are the drainage pipes; Calculating the degree centrality, betweenness centrality and clustering coefficient of each node according to the complex network model; An optimization processing objective function is constructed, and the formula of the optimization processing objective function is: Among them, α, β, γ, and δ represent weight coefficients, and C D (i) represents the degree centrality of node i, C B (i) represents the betweenness centrality of node i, C(i) represents the clustering coefficient of node i, and V represents the node set; Constructing an optimization processing constraint condition, wherein the optimization processing constraint condition includes that the degree centrality of each of the nodes is greater than or equal to 1; The optimization processing objective function is solved according to the Bayesian optimization algorithm to obtain the optimal drainage pipeline design solution that meets the optimization processing constraints.

5. The sponge city design method according to claim 4 is characterized in that , solving the optimization processing objective function according to the Bayesian optimization algorithm, and obtaining the optimal drainage pipe design scheme that meets the optimization processing constraints, including: Randomly generate sample points, where the sample points are decision variables generated corresponding to edges randomly selected from the edge set, and calculate optimization objective function values corresponding to the sample points according to the optimization objective function; Training the Gaussian process model, constructing training samples according to the sample points and the optimization processing objective function values corresponding to the sample points, and training the preset Gaussian process model through the training samples to obtain a trained Gaussian process model; Selecting a new sampling point, selecting the new sampling point according to the acquisition function, and calculating a new optimization processing objective function value corresponding to the new sampling point according to the optimization processing objective function; Updating the model by adding the new sample points and the new optimization processing objective function values corresponding to the new sample points to the training samples to obtain new training samples, and retraining the Gaussian process model based on the new training samples; Repeat the process of selecting new sampling points and updating the model until the preset maximum number of optimization process iterations is reached, and then output the optimal sampling point.

6. The sponge city design method according to claim 1 is characterized in that , obtain information, including: Acquiring historical rainfall data, and performing data cleaning, time format conversion, and standardization on the historical rainfall data; Acquiring terrain data, and performing data cleaning, projection conversion, interpolation processing, and standardization processing on the terrain data, wherein the terrain data includes geographic information system data and satellite image data, and the projection conversion converts the terrain data into a unified projection coordinate system; Acquiring ground cover data, and performing data cleaning, classification processing, projection conversion, and standardization processing on the ground cover data, wherein the ground cover data includes remote sensing images, and the classification processing includes classifying the ground cover types of the remote sensing images using a supervised or unsupervised classification algorithm; Drainage system data is obtained, and the ground cover data is cleaned, projected, converted, and standardized.

7. A sponge city design system, characterized in that: include: an acquisition module, the acquisition module being used to acquire information, the information including historical rainfall data, terrain data, ground cover data, and drainage system data of an urban area; a simulation module configured to simulate waterlogging conditions in the urban area using an agent-based model based on the information to obtain a waterlogging distribution map, wherein the waterlogging distribution map includes waterlogging-prone areas and drainage bottleneck areas; a first construction module, configured to construct a graph model based on the drainage system data, wherein nodes in the graph model are drainage points and edges in the graph model are drainage pipes; a second construction module, configured to construct a drainage pipe layout optimization model based on the graphical model and the waterlogging distribution map, the drainage pipe layout optimization model including an objective function and constraints, the objective function including minimizing the sum of the construction cost of the drainage pipe and a penalty for insufficient drainage capacity, and the constraints including a flow balance constraint of the drainage point, a capacity constraint of the drainage pipe, a drainage capacity constraint of the flood-prone area, and a drainage capacity constraint of the drainage bottleneck area; The drainage pipe layout optimization model is solved based on hypergeometric distribution sampling to obtain the optimal drainage pipe design solution, including: Initialization: randomly generating an initial solution that satisfies the constraints, and calculating an initial objective function value based on the initial solution and the objective function, taking the initial solution as the current solution, and taking the initial objective function value as the current objective function value. The initial solution includes decision variables generated corresponding to randomly selected edges in the edge set, and the edge set is the edge set of all possible connections between nodes in the graphical model. Sampling: Generate candidate solutions that satisfy the constraints based on a hypergeometric distribution sampling function according to a preset total number of candidate options, a preset number of selected options, a preset number of samples, and a preset number of candidate solutions. The total number of candidate options is the total number of edges, the number of selected options is the number of edges selected in the current solution, the number of samples is the number sampled from the total number of candidate options each time a new candidate solution is generated, and the number of candidate solutions is the number of candidate solutions generated in each iteration. Screening: Calculating the objective function value of each candidate solution based on the objective function, the preset pipeline construction cost, the penalty coefficient for insufficient drainage capacity, and the water flow rate, and screening out the candidate solution with the minimum objective function value; Update: Update the current solution and the current objective function value by using the candidate solution with the minimum objective function value and its corresponding objective function value; Repeat the above sampling, screening and updating steps until the preset maximum number of iterations is reached, and output the optimal solution, which is the drainage pipe design solution.

8. The sponge city design system according to claim 7 is characterized in that , the simulation module includes: A division module, the division module is used to evenly divide the urban area into a plurality of grid units; A third construction module is used to construct a rainfall agent, including setting the rainfall intensity, rainfall pattern and rainfall duration of each grid cell according to the historical rainfall data and the IDF curve; a fourth construction module, the fourth construction module being used to construct a terrain elevation proxy, including setting the elevation and slope of each of the grid cells according to the terrain data; a fifth construction module for constructing a water flow state agent, including setting an initial water depth and an initial water flow velocity to zero, wherein the initial water depth and the initial water flow velocity vary with the rainfall intensity, rainfall pattern, and rainfall duration; a sixth construction module, the sixth construction module being used to construct a drainage system agent, including setting the pipe capacity, drainage speed, pipe connection relationship, and pipe structure parameters of the drainage pipe in each grid unit according to the drainage system data; a seventh construction module, the seventh construction module being used to construct a ground cover agent, including setting the infiltration and runoff of each grid cell according to the ground cover data; An updating module, configured to update the water flow velocity and water depth of each grid cell according to the rainfall proxy, the terrain elevation proxy, the water flow state proxy, the drainage system layout proxy, and the ground cover proxy, to generate a water accumulation distribution map; A marking module is used to mark all the grid cells whose water depth exceeds a preset depth threshold as the flood-prone areas on the water accumulation distribution map, and to mark all the grid cells whose water flow speed is lower than a preset speed as the drainage bottleneck areas on the water accumulation distribution map.

9. The sponge city design system according to claim 7, characterized in that ,The acquisition module includes: a first acquisition module, the first acquisition module being used to acquire historical rainfall data, and perform data cleaning, time format conversion, and standardization processing on the historical rainfall data; a second acquisition module, the second acquisition module being used to acquire terrain data and perform data cleaning, projection conversion, interpolation processing, and standardization processing on the terrain data, the terrain data including geographic information system data and satellite image data, the projection conversion converting the terrain data into a unified projection coordinate system; a third acquisition module, the third acquisition module being configured to acquire ground cover data and perform data cleaning, classification processing, projection conversion, and standardization processing on the ground cover data, wherein the ground cover data includes remote sensing images, and the classification processing includes classifying the remote sensing images into ground cover types using a supervised or unsupervised classification algorithm; The fourth acquisition module is used to acquire drainage system data and perform data cleaning, projection conversion and standardization on the ground cover data.

Images