Urban drainage green measure vertical layout control optimization method, device, equipment and medium

Abstract

The invention relates to an urban drainage green measure vertical layout control optimization method, device and equipment and a medium, and the method comprises the steps: determining a plurality of layout evaluation indexes according to a to-be-laid green measure region, a waterlogging water accumulation amount, a green measure retention amount and to-be-drained urban population information through employing a GIS geographic analysis technology, determining a layout priority coefficient of each green measure type in each catchment area on the basis of a fuzzy comprehensive evaluation method according to the plurality of layout evaluation indexes and the weight corresponding to each layout evaluation index, and adopting a preset green measure vertical collaborative optimization algorithm to determine the layout priority coefficient of each green measure type in each catchment area according to the layout priority coefficient and the to-be-laid green measure parameters. And obtaining a Pareto optimal solution set of green measure total outflow and green measure layout total cost of all catchment areas in the city to be subjected to drainage management, and determining an optimal green measure layout scheme of the area to be subjected to green measure layout in each catchment area. The flood control efficiency of the urban drainage system can be remarkably improved.

Description

Technical Field

[0001] This application relates to the field of drainage control, and particularly to an optimization method for vertical layout control of urban drainage green measures, a corresponding device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Traditional urban rainwater management relies on drainage networks and grey infrastructure, with the goal of quickly discharging rainwater from urban areas through a centralized system. However, the accelerating urbanization process has led to a significant increase in impervious surfaces, which shortens the rainwater collection time and increases the peak flow. Existing drainage systems often cannot be quickly expanded or updated, thus exacerbating the flood risk. To address the environmental impact brought by urbanization, sustainable low impact development (LID) strategies have been introduced. As the urban rainwater management space becomes increasingly scarce, the research focus has shifted to enhancing the multi-dimensional design of green measures and optimizing their allocation strategies, so as to maximize the feasibility and effectiveness of these spaces in rainwater management.

[0003] Early studies were relatively general and rough in land use classification and sub-basin characterization. Ahiablame and Shakya (2016) used land use reclassification techniques and found that different levels of low impact development (LID) implementation led to significant differences in runoff control rates (ranging from 3% to 47%). In the later stage, remote sensing technology and high-precision satellite images have been used for more detailed land use classification. Randall et al. (2019) used WorldView-3 images and GEOBIA to classify land use and modeled multiple low impact development (LID) deployment scenarios. Recently, to further improve the accuracy and efficiency of land use classification, semantic segmentation algorithms based on convolutional neural networks (CNNs), such as FCN (Long et al., 2015), U-Net (Yang et al., 2021), SegNet (Son et al., 2022), and Deeplabv3+ (Rahman et al., 2021), have been used to automatically identify detailed land use conditions. These advanced algorithms can achieve pixel-level segmentation and capture more detailed land use features in satellite images. However, there is currently no dedicated land use detection and feasibility assessment method for vertical low impact development (LID) allocation.

[0004] (Jia et al., 2012; Kong et al., 2017; Xie et al., 2017) introduced independent green measure modules, such as green roofs, rain gardens, and permeable pavements, into the modeling tool. However, these green modules can only be laid out and connected on a two-dimensional scale. (Liu et al., 2015) adopted a series of models in the research to more accurately simulate these water flow dynamics. (Gao et al., 2019) showed that comprehensive measures are superior to single measures in runoff control, and the research by (Zhang et al., 2021) indicated that the cascading chain of green measures can more effectively reduce runoff than parallel connections. However, they mainly focus on planar layout and ignore the potential of vertical space combination.

[0005] To reasonably evaluate local conditions and the applicability of various factors (Hou et al., 2019; Huang et al., 2024) considered the hydrological and geological characteristics of the soil, as well as the influence of relevant parameters (such as soil type, slope, and hydraulic conductivity) on the feasibility of green measure allocation. Heidari (2022) went further and incorporated the priorities of different stakeholders (such as municipal authorities, builders, and planners) into consideration, and used a multi-criteria decision-making method to evaluate ten indicators to determine the most effective green measures. The development in green measure allocation is towards a more comprehensive approach, but the evaluation is mainly carried out in planar layout. The suitability of green measures in the vertical direction has not been integrated, and the existing technologies mainly have the following technical defects, which include:

[0006] First, insufficient data fineness: Traditional land use classification methods (such as visual interpretation of remote sensing) have low accuracy and are difficult to support the precise layout of green measures.

[0007] Second, there is no dedicated feasibility evaluation method: There is no special land use detection and feasibility evaluation method for vertical low impact development (LID) allocation.

[0008] Third, planar layout limitation: Existing methods mostly focus on two-dimensional plane optimization and cannot make full use of urban vertical space resources (such as building roofs, underground pipe networks), resulting in the potential of flood control not being fully explored.

[0009] Fourth, single priority evaluation: Existing evaluation systems mostly rely on a single indicator (such as runoff reduction rate) and lack comprehensive priority evaluation in multiple dimensions (land use, waterlogging risk, population density, etc.).

[0010] In summary, in order to adapt to the problems in the existing technologies that mostly focus on two-dimensional plane optimization, cannot make full use of urban vertical space resources, and result in the potential of flood control not being fully explored, the applicant has made corresponding explorations to solve this problem. Summary of the Invention

[0011] The purpose of this application is to solve the above problems and provide an optimization method for vertical layout control of urban drainage green measures, a corresponding device, an electronic device, and a computer-readable storage medium.

[0012] To meet the various objectives of this application, the following technical solutions are adopted:

[0013] An optimization method for vertical layout control of urban drainage green measures proposed to meet one of the objectives of this application includes:

[0014] In response to an instruction to optimize the layout control of green measures in the urban area to be drained, a preset semantic segmentation model is used to perform land identification and segmentation on the remote sensing image of the urban area to be drained, and a preset vertical feasibility evaluation module is called to evaluate the feasibility of vertical layout of green measures on the remote sensing image of the urban area to be drained, so as to determine the areas where green measures are to be laid out in each catchment area. Among them, the urban area to be drained includes multiple catchment areas, and each catchment area includes multiple areas where green measures are to be laid out;

[0015] Call the vertical hydrodynamic coupling simulation model that integrates grey measures and green measures, and input the preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the corresponding waterlogging accumulation volume and green measure retention volume of the urban area to be drained;

[0016] Use GIS geographical analysis technology to determine multiple layout evaluation indicators based on the areas where green measures are to be laid out, the waterlogging accumulation volume, the green measure retention volume, and the population information of the urban area to be drained. Based on the fuzzy comprehensive evaluation method, according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator, determine the layout priority coefficient of each green measure type in each catchment area;

[0017] Obtain the parameters of the green measures to be laid out corresponding to the areas where green measures are to be laid out in the urban area to be drained, and use a preset vertical collaborative optimization algorithm for green measures. According to the layout priority coefficient and the parameters of the green measures to be laid out, obtain the Pareto optimal solution set of the total outflow of green measures and the total cost of green measure layout in all catchment areas of the urban area to be drained, and determine the optimal green measure layout plan for the areas where green measures are to be laid out in each catchment area.

[0018] Optionally, the step of calling the vertical hydrodynamic coupling simulation model that integrates grey measures and green measures, and inputting the preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the corresponding waterlogging accumulation volume and green measure retention volume of the urban area to be drained includes:

[0019] Calculate and determine the rainfall intensity corresponding to the city to be drained according to the preset rainfall intensity calculation formula, and determine the rainfall amount corresponding to the city to be drained according to the fourth product between the rainfall intensity corresponding to the city to be drained and the preset rainfall duration;

[0020] Input the rainfall amount into the preset vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation amount and the green measure storage amount corresponding to the city to be drained. Among them, the waterlogging accumulation amount includes the green measure storage amount and the remaining flood flow, and the green measure storage amount includes the above-ground storage amount and the underground storage amount.

[0021] Optionally, the steps of determining the layout priority coefficient of each green measure type in each catchment area based on the fuzzy comprehensive evaluation method according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator include:

[0022] Obtain multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator. Among them, the layout evaluation indicators include one or any combination of land use, vertical layout suitability, building density, population density, and waterlogging risk;

[0023] Based on the fuzzy comprehensive evaluation method, determine multiple evaluation grades of the layout evaluation indicators in each catchment area according to the difference between the maximum value and the minimum value of the layout evaluation indicators, and normalize each layout evaluation indicator to a membership degree value within the interval [0,1] by using a preset membership degree function to determine the normalized membership degree value of the layout evaluation indicators in each catchment area;

[0024] Construct a membership degree matrix corresponding to each catchment area according to the normalized membership degree value of the layout evaluation indicators in each catchment area and the multiple evaluation grades of the layout evaluation indicators in each catchment area;

[0025] Use the analytic hierarchy process to determine the importance weights of each layout evaluation indicator, and determine the layout priority coefficient of each green measure type in each catchment area according to the third product between the membership degree matrix and the importance weights of each layout evaluation indicator.

[0026] Optionally, the steps of determining the total outflow of green measures include:

[0027] Obtain the number of catchment areas, the number of green measure types, the unit time outflow of green measures in each catchment area, and the area of green measures in each catchment area of the city to be drained;

[0028] Calculate and determine the first product between the outflow per unit time of each green measure type in each catchment area and the outflow green measure area of each green measure type in each catchment area to determine the green measure outflow water volume of each green measure type in each catchment area;

[0029] Based on the green measure outflow water volume of each green measure type in each catchment area, the number of catchment areas in the urban area to be drained, and the number of green measure types, determine the total green measure outflow of all catchment areas in the urban area to be drained.

[0030] Optionally, the steps for determining the total cost of green measure layout include:

[0031] Obtain the number of catchment areas in the urban area to be drained, the number of green measure types, the layout priority coefficient of each type of green measure in each catchment area, the cost per unit area of each type of green measure, and the layout area of each type of green measure in each catchment area;

[0032] Calculate and determine the second product between the layout priority coefficient of each type of green measure in each catchment area, the cost per unit area of each type of green measure, and the layout area of each type of green measure in each catchment area;

[0033] Based on the number of catchment areas in the urban area to be drained, the number of green measure types, and the second product, determine the total cost of green measure layout of all catchment areas in the urban area to be drained.

[0034] Optionally, adopt a preset vertical collaborative optimization algorithm for green measures. According to the layout priority coefficient and the green measure parameters to be laid out, to obtain the Pareto optimal solution set of the total green measure outflow and the total cost of green measure layout of all catchment areas in the urban area to be drained, the steps for determining the optimal green measure layout plan for the areas where green measures are to be laid out in each catchment area include:

[0035] Call the preset vertical collaborative optimization algorithm for green measures. According to the layout priority coefficient and the green measure parameters to be laid out, with the total green measure outflow and the total cost of green measure layout of all catchment areas as the dual optimization objectives, and the layout areas of different green measure types in each catchment area as the constraints, use the Gaussian regression model to perform probability modeling based on the non - linear update between each green measure parameter to be laid out in each catchment area and the response value of the objective function, to predict the expected mean and variance of the objective function values of the potential sample points corresponding to the areas where green measures are to be laid out, where the green measure parameters to be laid out represent the green measure sample points corresponding to each type of green measure to be laid out in each catchment area;

[0036] According to the probability distribution of the Gaussian regression model, use the preset expected hypervolume improvement algorithm to calculate the acquisition scores of each potential sample point, and select the sample point with the highest score as the target for the next function evaluation;

[0037] Repeat the above steps. By quantifying the expected gain of the newly added samples to the hypervolume measure of the existing Pareto front, iteratively generate the Pareto optimal solution set that meets the constraint conditions to determine the optimal green measure layout plan for the areas where green measures are to be arranged in each catchment area.

[0038] Optionally, the types of green measures include green roofs, rain gardens, and permeable pavements;

[0039] The areas where green measures are to be arranged include one or any combination of commercial buildings, office buildings, hospitals, schools, hotels, transportation buildings, sports buildings, and residential communities;

[0040] The vertical collaborative optimization algorithm for green measures is a multi-objective Bayesian optimization algorithm;

[0041] The optimal green measure layout plan represents obtaining the types of green measures and their corresponding optimal layout areas for the areas where green measures are to be arranged in each catchment area by solving the Pareto front of the total outflow of green measures and the total cost of green measure layout in the urban area to be drained and managed.

[0042] A vertical layout control optimization device for urban drainage green measures provided to meet another object of the present application includes:

[0043] An area to be arranged determination module, configured to respond to an instruction for controlling and optimizing the layout of green measures in the urban area to be drained and managed, use a preset semantic segmentation model to perform land identification and segmentation on the remote sensing image of the urban area to be drained and managed, and call a preset vertical feasibility evaluation module to perform a feasibility evaluation of the vertical layout of green measures on the remote sensing image of the urban area to be drained and managed, so as to determine the areas where green measures are to be arranged in each catchment area. Among them, the urban area to be drained and managed includes multiple catchment areas, and each catchment area includes multiple areas where green measures are to be arranged;

[0044] A feasibility data determination module, configured to call a vertical hydrodynamic coupling simulation model that integrates grey measures and green measures, and input a preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation amount and the green measure retention amount corresponding to the urban area to be drained and managed;

[0045] The layout priority determination module is configured to use GIS geographical analysis technology to determine multiple layout evaluation indicators based on the area where green measures are to be laid out, the accumulated water volume of waterlogging, the storage volume of green measures, and the population information of the city to be drained. Based on the fuzzy comprehensive evaluation method, according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator, the layout priority coefficient of each green measure type in each catchment area is determined;

[0046] The optimal solution determination module is configured to obtain the green measure parameters to be laid out corresponding to the area where green measures are to be laid out in the city to be drained, and use a preset vertical collaborative optimization algorithm for green measures. According to the layout priority coefficient and the green measure parameters to be laid out, to obtain the Pareto optimal solution set of the total outflow of green measures and the total cost of green measure layout in all catchment areas of the city to be drained, and determine the optimal green measure layout plan for the area where green measures are to be laid out in each catchment area.

[0047] An electronic device provided to meet another object of the present application includes a central processing unit and a memory. The central processing unit is used to call and run a computer program stored in the memory to execute the steps of the vertical layout control optimization method for urban drainage green measures described in the present application.

[0048] A computer-readable storage medium provided to meet another object of the present application stores a computer program implemented based on the vertical layout control optimization method for urban drainage green measures in the form of computer-readable instructions. When the computer program is called and run by a computer, it executes the steps included in the corresponding method.

[0049] Compared with the prior art, the present application focuses on two-dimensional plane optimization in the prior art and cannot make full use of urban vertical space resources, resulting in the problem that the potential for flood control and regulation has not been fully explored. The present application includes but is not limited to the following beneficial effects:

[0050] First, the present application can significantly improve the flood control efficiency of the urban drainage system. By constructing a vertical runoff transfer model that links the above-ground and underground and multiple floors of buildings, it can more comprehensively simulate the urban rainwater flow process, break through the limitations of traditional two-dimensional plane models, and thus significantly improve the storage capacity. This multi-layer linkage modeling method can accurately predict the runoff situation after rainfall, help formulate more effective drainage plans, and reduce the risks of urban waterlogging and floods;

[0051] Second, the present application can optimize resource allocation and measure implementation efficiency. By comprehensively considering multiple indicators such as land use, vertical layout suitability, waterlogging risk, building density, and population density, and quantifying the priority through the fuzzy evaluation method, it can accurately identify the areas that need to be processed first, which not only helps improve the scientificity of resource allocation but also enhances the efficiency and effect of measure implementation;

[0052] Thirdly, the present application can achieve a balance between flood control and economic costs. By using a multi-objective Bayesian optimization algorithm to generate Pareto optimal solutions, it can balance flood control effectiveness (such as minimizing the total outflow) and economic costs (such as minimizing the layout cost). This method can provide multiple optimization solutions for decision-makers, supporting them to flexibly select the best solution according to the actual budget and requirements, so as to ensure the best flood control effect with limited resources.

[0053] Fourthly, the present application predicts the effects of the green measures to be laid out (such as the total outflow and layout cost) through a Gaussian process regression model, and selects the optimal area for green measure layout through the expected hypervolume improvement algorithm. This dynamic optimization method can adjust and update the green measure layout plan in real time, so as to achieve the flexibility and adaptability of urban drainage management.

[0054] Fifthly, the present application can reduce the operation cost and environmental impact of the drainage system. By optimizing the layout of green measures, it can not only effectively reduce the outflow of the drainage system and reduce the probability of waterlogging and floods, but also reduce the construction and maintenance costs of the drainage system by reducing excessive infrastructure construction (such as expensive underground drainage pipe networks). At the same time, the vertical layout optimization of green measures such as rain gardens and permeable pavements helps to improve the urban ecological environment, increase urban green spaces, and enhance the sustainability of the city.

[0055] Furthermore, through this multi-level and multi-objective optimization model, it is possible to effectively integrate various resources of the urban drainage system, scientifically and reasonably layout green drainage measures, significantly improve flood control effectiveness, reduce economic costs at the same time, and improve the urban environmental quality, providing strong support for the sustainable development of the city. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0057] Figure 1 is a schematic flowchart of the vertical layout control optimization method for urban drainage green measures in an embodiment of the present application;

[0058] Figure 2 is an exemplary architecture adopted by the vertical layout control optimization method for urban drainage green measures in an embodiment of the present application;

[0059] Figure 3 is an exemplary network architecture of the Deeplabv3+ model in an embodiment of the present application;

[0060] Figure 4Schematic diagram of the preliminary land use type segmentation image and the refined land use type segmentation image in the embodiments of the present application;

[0061] Figure 5 Schematic flow chart of runoff transfer and interaction calculation between simulated multi - layer green measures and underground pipe networks in the embodiments of the present application;

[0062] Figure 6 Schematic diagram of the vertical hydrodynamic coupling simulation model integrating grey infrastructure and green measures in the embodiments of the present application;

[0063] Figure 7 Schematic diagram of determining the surface storage SS in the embodiments of the present application;

[0064] Figure 8 Schematic diagram of determining the underground storage US in the embodiments of the present application;

[0065] Figure 9 Flow chart of determining the layout priority coefficient of each type of green measure in each catchment area in the embodiments of the present application;

[0066] Figure 10 Comprehensive display diagram of the layout priorities of various green measure types in each catchment area of the urban area to be drained in the embodiments of the present application;

[0067] Figure 11 Principle block diagram of the vertical layout control optimization device for urban drainage green measures in the embodiments of the present application;

[0068] Figure 12 Schematic diagram of the structure of the computer device in the embodiments of the present application. Detailed implementation manners

[0069] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present application, and should not be construed as limiting the present application.

[0070] Those skilled in the art can understand that, unless specifically stated, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of this application means the presence of the stated features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any unit and all combinations of one or more of the associated listed items.

[0071] Those skilled in the art can understand that, unless otherwise defined, all terms used herein (including technical terms and scientific terms) have the same meaning as the general understanding of those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted in an idealized or overly formal sense unless specifically defined as here.

[0072] Those skilled in the art can understand that the "client", "terminal", and "terminal device" used herein include both devices with a wireless signal receiver that only has the ability to receive and no ability to transmit, and devices with receiving and transmitting hardware that can perform two-way communication on a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers, tablet computers, etc., which have a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service), which can combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant), which may include a radio frequency receiver, pager, Internet / intranet access, web browser, notepad, calendar, and / or GPS (Global Positioning System) receiver; conventional laptop and / or palm-top computers or other devices, which are conventional laptop and / or palm-top computers or other devices with and / or including a radio frequency receiver. The "client", "terminal", and "terminal device" used herein can be portable, transportable, installed in a vehicle (air, sea, and / or land), or suitable for and / or configured to run locally, and / or run in a distributed manner at any other location on the earth and / or in space. The "client", "terminal", and "terminal device" used herein can also be a communication terminal, an Internet access terminal, a music / video playback terminal, for example, it can be a PDA, MID (Mobile Internet Device), and / or a mobile phone with music / video playback function, or can also be a smart TV, a set-top box, and other devices.

[0073] The hardware referred to by names such as "server", "client", and "service node" in this application is essentially an electronic device with the equivalent capabilities of a personal computer, and is a hardware device with the necessary components disclosed by the von Neumann principle, including a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. The computer program is stored in its memory, and the central processing unit loads the program stored in the external memory into the memory for execution, executes the instructions in the program, and interacts with the input / output devices to complete specific functions.

[0074] It should be noted that the concept of "server" in this application can similarly be extended to apply to server clusters. According to the network deployment principles understood by those skilled in the art, the servers should be logically divided. Physically, these servers can either be independent of each other but can be invoked through interfaces, or integrated into a single physical computer or a set of computer clusters. Those skilled in the art should understand this flexibility and should not be restricted by this in the implementation manner of the network deployment method of this application.

[0075] One or several technical features of this application, unless clearly specified, can either be deployed on the server and accessed by the client remotely invoking the online service interface provided by the server, or directly deployed and run on the client for access.

[0076] The neural network models cited or possibly cited in this application, unless clearly specified, can either be deployed on a remote server and remotely invoked on the client, or deployed on a client with sufficient device capabilities for direct invocation. In some embodiments, when it runs on the client, its corresponding intelligence can be obtained through transfer learning to reduce the requirements for the client's hardware operation resources and avoid over-occupying the client's hardware operation resources.

[0077] All kinds of data involved in this application, unless clearly specified, can either be remotely stored on the server or stored on the local terminal device, as long as it is suitable for being invoked by the technical solution of this application.

[0078] Those skilled in the art should be aware that although the various methods of this application are described based on the same concept and thus show commonality with each other, unless otherwise specified, these methods can all be executed independently. Similarly, for each of the embodiments disclosed in this application, they are all proposed based on the same inventive concept. Therefore, for concepts with the same expression, as well as concepts that are only appropriately transformed for convenience although the concept expressions are different, they should be equivalently understood.

[0079] For each of the embodiments to be disclosed in this application, unless clearly indicated as mutually exclusive, the relevant technical features involved in each embodiment can be cross-combined to flexibly construct new embodiments, as long as such combination does not deviate from the creative spirit of this application and can meet the needs in the prior art or solve certain deficiencies in the prior art. Those skilled in the art should be aware of this flexibility.

[0080] Please refer to Figure 1 and Figure 2 , in one embodiment of the vertical layout control optimization method for urban drainage green measures of this application, it includes:

[0081] Step S10: In response to the instruction to optimize the layout control of green measures for the urban area to be drained, use a preset semantic segmentation model to perform land identification and segmentation on the remote sensing image of the urban area to be drained, and call a preset vertical feasibility evaluation module to evaluate the feasibility of vertically laying green measures on the remote sensing image of the urban area to be drained, so as to determine the areas where green measures are to be laid in each catchment area. Among them, the urban area to be drained includes multiple catchment areas, and each catchment area includes multiple areas where green measures are to be laid;

[0082] The urban drainage green measure vertical layout control system in the terminal device can respond to the instruction to optimize the layout control of green measures for the urban area to be drained, use a preset semantic segmentation model to perform land identification and segmentation on the remote sensing image of the urban area to be drained, and call a preset vertical feasibility evaluation module to evaluate the feasibility of vertically laying green measures on the remote sensing image of the urban area to be drained, so as to determine the areas where green measures are to be laid in each catchment area. Among them, the urban area to be drained includes multiple catchment areas, and each catchment area includes multiple areas where green measures are to be laid. The basic network architecture of the semantic segmentation model is the Deeplabv3+ model, etc.; The areas where green measures are to be laid include one or any combination of commercial buildings, office buildings, hospitals, schools, hotels, transportation buildings, sports buildings, and residential communities;

[0083] In some embodiments, based on the semantic segmentation model, perform image segmentation on the remote sensing image of the urban area to be drained, and perform automatic identification and geometric quantization evaluation on the land use of the urban area to be drained. Among them, the basic network architecture of the semantic segmentation model is the Deeplabv3+ model, etc.

[0084] In this embodiment, the Deeplabv3+ model is taken as an example, which does not limit the present application. It is necessary to collect in advance the data sets for training the Deeplabv3+ model, processing the prior knowledge mask, and the study area. The training of the Deeplabv3+ model depends on the land cover data set LoveDA provided by the First University. This data set contains remote sensing images and their corresponding label images. The LoveDA data set covers a total of 5,987 images in multiple cities in a certain country. The resolution of each image is 0.3 meters, and the size is 1024×1024 pixels. The study area is located in the south-central part of a certain city, covering an area of about 5,012.19 hectares, with an altitude ranging from 1,497 to 1,882 meters, and the elevation decreasing from south to northeast.

[0085] Furthermore, to train and validate the segmentation model, image samples of urban areas were selected from the dataset. The land use types represented by these samples were carefully classified into seven categories: vacant land, buildings, roads, water systems, wasteland, green spaces, and farmland. The prior knowledge mask combined data from OpenStreetMap and the dataset of the Second University. OSM was mainly used to refine and supplement information on roads, water systems, and buildings, while the dataset of the Second University focused on improving forest and green space data. In addition, the high-resolution satellite map used for identifying and segmenting the study area was sourced from Google Maps, with an image resolution of 0.275×0.275 meters.

[0086] During the training process of the Deeplabv3+ model, two data augmentation techniques, random reflection and random rotation, were implemented using the "imageDataAugmenter" function in Matlab. After data augmentation, the sizes of the training set and validation set were expanded to 2082 and 462 images respectively. The model was trained using the Stochastic Gradient Descent with Momentum optimizer (SGDM), with the momentum value set to 0.9. In terms of training parameters, the initial learning rate was set to 0.001, the maximum number of iterations was 30, and the mini-batch size was 1. The experiment was completed on a Windows 10 system equipped with an Intel Core i5-10200H CPU and an NVIDIA GeForce RTX 2060 GPU (6GB video memory).

[0087] In this embodiment, based on the Deeplabv3+ algorithm, automatic identification and segmentation of urban land use were performed to obtain information on land use types, areas, and spatial distributions.

[0088] Please refer to Figure 3 , the Deeplabv3+ model consists of an encoder and a decoder. Among them, the encoder mainly includes a deep convolutional neural network (DCNN) using the ResNet-18 feature extraction network and an Atrous Spatial Pyramid Pooling module (ASPP) for fusing multi-scale information. The features extracted by ResNet-18 are fed into ASPP, where the semantic information of objects at different scales is captured through parallel convolutional layers, and then feature concatenation and fusion are performed. In the decoder, the high-level feature map enlarged by 4 times is concatenated with the downsampled low-level feature map for feature fusion, and then the segmentation image is output.

[0089] Based on the constructed Deeplabv3+ model, by constructing a dataset, performing model training and testing, after the model performance indicators meet the standards, the remote sensing image of the study area is input to obtain a preliminary segmentation image of the land use type in the study area. The local initial segmentation results of the land use types in the urban area for drainage management are as Figure 4As shown in Figure (a), it can be seen that the Deeplabv3+ model can accurately identify most land types, but it is not sensitive enough when dealing with satellite maps with complex details and chaotic edges, and the boundaries of recognition and segmentation are relatively blurred. By using the prior knowledge mask (OSM mask data) obtained from previous processing, the initially segmented image is corrected and supplemented in detail to obtain a more refined land use type segmentation image. A partial map of the obtained result is shown in Figure 4 Figure (b).

[0090] Furthermore, based on analyses such as GIS attribute extraction and spatial connection, a feasibility assessment of the vertical layout of green measures is carried out to obtain information on the buildings related to the vertical layout and the land use types around them.

[0091] The finely processed image is imported into GIS software to extract building information from it, and the POI dataset containing building attributes is imported synchronously. Through georegistration, the specific types of buildings are identified, including 8 types such as commercial buildings, office buildings, hospitals, schools, hotels, transportation buildings, sports buildings, and residential communities. On this basis, 5 types of building types suitable for implementing green measures, namely commercial buildings, office buildings, hospitals, schools, and hotels, are selected, and buffers are created as the layout areas of green measures based on their boundaries. Finally, the refined land use segmentation image is cropped according to the contour of the buffer to obtain the type distribution and area of the land use around the buildings, and spatial extraction and data statistics are carried out.

[0092] In a further embodiment, 3 performance indicators are used to evaluate the performance of the Deeplabv3+ model. The performance indicators adopted are introduced in detail below, and they include:

[0093] 1. Pixel Accuracy (PA), that is, the ratio of the number of correctly classified pixels to the total number of pixels, and its expression is:

[0094]

[0095] 2. Mean Pixel Accuracy (MPA), that is, the average value of the accuracy rates of various land use types, and its expression is:

[0096]

[0097] 3. Intersection over Union (IoU), which reflects the degree of overlap between the image segmentation prediction result and the ground truth of the original image, and its expression is:

[0098]

[0099] Among them, true positive (TP) represents the pixels where the model correctly predicts the actual land use type; false positive (FP) represents the pixels where the model wrongly predicts the actual land use type; false negative (FN) represents the pixels where the model wrongly predicts the actual non - this land use type; true negative (TN) represents the pixels where the model correctly predicts the actual non - this land use type; A P represents the pixel area of the land use type predicted by the model; A r is the actual pixel area of the land use type.

[0100] In some embodiments, the types of green measures include green roofs, rain gardens, and permeable pavements; the areas where green measures are to be arranged include one or any combination of commercial buildings, office buildings, hospitals, schools, hotels, transportation buildings, sports buildings, and residential communities; the vertical collaborative optimization algorithm for green measures is a multi - objective Bayesian optimization algorithm; the optimal green measure arrangement plan represents obtaining the types of green measures and their corresponding optimal arrangement areas in the areas where green measures are to be arranged in each catchment area by solving the Pareto front of the total out - flow of green measures and the total cost of green measure arrangement in the urban area to be drained and managed.

[0101] Step S20: Invoke the vertical hydrodynamic coupling simulation model integrating grey measures and green measures, and input the preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the corresponding waterlogging accumulation volume and the retention volume of green measures in the urban area to be drained and managed;

[0102] After using the preset semantic segmentation model to perform land identification and segmentation on the remote - sensing image of the urban area to be drained and managed and invoking the preset vertical feasibility evaluation module to evaluate the vertical feasibility of arranging green measures on the remote - sensing image of the urban area to be drained and managed to determine the areas where green measures are to be arranged in each catchment area, then invoke the vertical hydrodynamic coupling simulation model integrating grey measures and green measures, and input the preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the corresponding waterlogging accumulation volume and the retention volume of green measures in the urban area to be drained and managed;

[0103] In some embodiments, the step of invoking the vertical hydrodynamic coupling simulation model integrating grey measures and green measures and inputting the preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the corresponding waterlogging accumulation volume and the retention volume of green measures in the urban area to be drained and managed includes:

[0104] Step S201: Calculate and determine the rainfall intensity corresponding to the urban area to be drained and managed according to the preset rainstorm intensity calculation formula, and determine the rainfall amount corresponding to the urban area to be drained and managed according to the fourth product between the rainfall intensity corresponding to the urban area to be drained and managed and the preset rainfall duration;

[0105] Step S202: Input the rainfall into a preset vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation volume and the retention volume of green measures corresponding to the urban area to be drained. Among them, the waterlogging accumulation volume includes the retention volume of green measures and the remaining flood flow, and the retention volume of green measures includes the above-ground retention volume and the underground retention volume.

[0106] Specifically, the vertical hydrodynamic coupling simulation model integrating grey measures and green measures refers to the vertical hydrodynamic coupling simulation model integrating grey infrastructure (such as drainage pipelines) and green measures. Input the preset rainfall into the vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation volume and the retention volume of green measures corresponding to the urban area to be drained. Please refer to Figure 5 and Figure 6 , where Figure 5 is a schematic flow diagram for simulating the runoff transfer and interaction calculation between multi-layer green measures and underground pipe networks, Figure 6 is the vertical hydrodynamic coupling simulation model integrating grey infrastructure (such as drainage pipelines) and green measures; construct the vertical hydrodynamic coupling simulation model integrating grey infrastructure (such as drainage pipelines) and green measures to simulate the runoff transfer and interaction calculation between multi-layer green measures and underground pipe networks. The general formula is as follows:

[0107] P = SI + D + SS + US + RFV,

[0108] where P represents the rainfall, which is the input of the entire vertical hydrodynamic coupling simulation model; SI represents the soil infiltration volume, D represents the pipe network discharge volume, SS represents the above-ground retention volume, US represents the underground retention volume, and RVF represents the remaining flood flow. The rainfall intensity change over time at different return periods can be simulated according to the rainfall intensity calculation formula of the urban area to be drained. Among them, the expression of the rainfall intensity calculation formula corresponding to the urban area to be drained is:

[0109]

[0110] where q represents the rainfall flow per hectare per second, with the unit of liters per second per hectare ((L / s) / hm 2 ); P is the return period of rainstorm occurrence, which represents the average number of years that a rainstorm event with a specific intensity occurs within a certain period of time. The value of P can be 50, with the unit of year; t represents the duration of the rainfall event, with the unit of minute;

[0111] Rainwater first undergoes the natural infiltration process of the underlying surface soil. The formula for calculating the soil infiltration volume SI of the region according to the Horton infiltration formula is as follows:

[0112]

[0113] Among them, f min is the minimum infiltration rate, f max is the maximum infiltration rate, f min and f max can be obtained by combining the soil composition with the empirical value of the permeability coefficient. K d is the attenuation coefficient, which can be obtained by empirical method, and i is the rainfall rate.

[0114] Furthermore, the rainwater exceeding the soil infiltration capacity flows into the pipe network system. The pipe network discharge D is calculated by the difference between the node inflow NIF and the waterlogging accumulation TFV (i.e., the total overflow of the system). The formula is as follows:

[0115] D = NIF - TFV,

[0116] where NIF is the node inflow and TFV is the waterlogging accumulation, which can be solved by the hydrodynamic simulation model.

[0117] Furthermore, please refer to Figure 7 , the waterlogging accumulation is then introduced into the above-ground storage facilities, and the outflow of the green measures of the superstructure is introduced into the green measures of the lower building. The vertical runoff connection and conversion are carried out through the green measures on different building floors, so that the runoff at different heights within the same plot can undergo iterative calculations of various green measures. The expression of the above-ground storage SS includes:

[0118]

[0119] where Q SS1(j) represents the inflow rate of the jth floor building, q SS1(j) represents the overflow rate of the jth floor building, e SS1(j) represents the evaporation rate of the jth floor building, A j represents the green measure area of the jth floor building, SS represents the above-ground storage, represents the area ratio of different floors, which is used to normalize the flow; q SS1(j) , e SS1(j) can adopt the calibrated values in the SWMM model.

[0120] Furthermore, please refer to Figure 8 , the water flow exceeding the above-ground storage capacity will overflow to the plot with green measures in the underground infiltration and storage facilities, that is, the final outflow q SS1(1) of the above-ground storage facilities serves as the inflow of the area with green measures in the underground infiltration and storage facilities, and the water volume transfer and conversion are further carried out through the structural layers of different types of measures. The successfully intercepted water volume is specifically calculated according to the LID control unit. The expression of the underground storage US is:

[0121]

[0122] Among them, q SS1(1) represents the final outflow of the surface detention area, and A ss represents the green measure area of the surface outflow layer, and A US represents the area of the green measures of the underground infiltration and storage facilities. q1 represents the surface layer overflow rate of the underground infiltration and storage facilities, q4 represents the outflow rate of the storage layer of the underground infiltration and storage facilities, e1 represents the evaporation rate of the surface layer of the underground infiltration and storage facilities, e2 represents the evaporation rate of the paving layer of the underground infiltration and storage facilities, e3 represents the evaporation rate of the soil layer of the underground infiltration and storage facilities, and e4 represents the evaporation rate of the storage layer of the underground infiltration and storage facilities.

[0123] In some embodiments, the SWMM model of the urban to be drained and managed may include 136 catchment areas, 117 pipe network nodes, 117 pipelines and 17 drainage outlets. Other input information includes: the catchment area and slope percentage, which are obtained by calculating the fine land classification image and DEM data through the ArcGIS tool; the impermeability percentage, which is the proportion of the impervious area in the fine land classification result, and is obtained by weighted averaging according to different land use types and their corresponding parameters in combination with the area; the input information of the pipeline mainly includes pipeline diameter, pipe length, node elevation, etc.

[0124] After running the SWMM model, comparing the outflow of the catchment area with the vertical layout control optimization method of the urban drainage green measures of the present application, in the simulation scenario of a single measure, the results of the model of the present method are highly consistent with those of the SWMM model, and the fitting degrees of the model of the present method under the three measures of rain gardens, green roofs and permeable pavements can reach 0.773, 0.999 and 0.971 respectively; for the synergistic effect of multiple measures in the vertical simulation scenario, the fitting degree index of the model of the present method reaches 0.924, the simulation performance is good, and the vertical layout of multiple measures not only greatly reduces the outflow, but also significantly delays the outflow time.

[0125] Step S30: Use GIS geographical analysis technology to determine multiple layout evaluation indicators according to the area where green measures are to be laid out, the waterlogging accumulation volume, the detention volume of green measures, and the population information of the urban to be drained and managed, and determine the layout priority coefficient of each green measure type in each catchment area based on the fuzzy comprehensive evaluation method according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator;

[0126] Call the vertical hydrodynamic coupling simulation model that integrates gray measures and green measures, input the preset rainfall into the vertical hydrodynamic coupling simulation model. After determining the waterlogging accumulation volume corresponding to the city to be drained and the storage volume of green measures, use GIS geographical analysis technology to determine multiple layout evaluation indicators based on the area where green measures are to be arranged, the waterlogging accumulation volume, the storage volume of green measures, and the population information of the city to be drained. Based on the fuzzy comprehensive evaluation method, according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator, determine the layout priority coefficient of each green measure type in each catchment area; wherein, the green measure types include green roofs, rain gardens, permeable pavements, etc.

[0127] In some embodiments, the step of determining the layout priority coefficient of each green measure type in each catchment area based on the fuzzy comprehensive evaluation method according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator includes:

[0128] Step S301, obtain multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator, wherein the layout evaluation indicators include one or any combination of land use, vertical layout suitability, building density, population density, and waterlogging risk;

[0129] Step S302, based on the fuzzy comprehensive evaluation method, according to the difference between the maximum value and the minimum value of the layout evaluation indicators, determine multiple evaluation grades of the layout evaluation indicators in each catchment area, and use a preset membership function to normalize each layout evaluation indicator to a membership value within the interval [0, 1] to determine the normalized membership value of the layout evaluation indicators in each catchment area;

[0130] Step S303, according to the normalized membership value of the layout evaluation indicators in each catchment area and the multiple evaluation grades of the layout evaluation indicators in each catchment area, construct a membership matrix corresponding to each catchment area;

[0131] Step S304, use the analytic hierarchy process to determine the importance weights of each layout evaluation indicator, and according to the third product of the membership matrix and the importance weights of each layout evaluation indicator, determine the layout priority coefficient of each green measure type in each catchment area.

[0132] Specifically, the GIS geographical analysis technology is adopted to construct an evaluation set including five layout evaluation indexes, namely land use property, vertical layout suitability, waterlogging risk, building density and population density, according to the area where green measures are to be arranged, the accumulated waterlogging volume, the retention volume of green measures and the population information of the city to be drained. Each layout evaluation index is divided into five levels from I to V. A higher priority means more in line with the layout conditions and should be considered first. Among them, land use property (LUP) represents the applicability of green measures in different land types, assigns corresponding weights to various land types, and performs weighted calculation in combination with the land area to obtain the layout potential of various measures in different regions; vertical layout suitability (VLS) represents a detailed analysis of specific measures based on the land type area around the building to determine the feasibility of vertical layout; building density (BD) represents the quantification of the urgency of layout measures by calculating the proportion of buildings in the catchment area; population density (PD) represents the calculation of the per capita floor area of each catchment area in combination with the population database; waterlogging risk (WR) represents the statistical total overflow of the system by calculating the node overflow of the regional pipe network system based on the hydrodynamic model, which is used to reflect the degree of waterlogging risk.

[0133] Further, please refer to Figure 9 , and based on the fuzzy comprehensive evaluation method, normalize each layout evaluation index and calculate the layout priority coefficient of each type of green measure in each catchment area. The specific process is as follows:

[0134] Step S210: Normalize each layout evaluation index into a membership value within the interval [0, 1] by using a preset membership function, and divide 5 intervals according to the difference between the maximum value and the minimum value of the layout evaluation index to determine multiple evaluation levels of the layout evaluation index in each catchment area; on this basis, according to the normalized membership value of the layout evaluation index in each catchment area and the multiple evaluation levels of the layout evaluation index in each catchment area, construct a membership matrix corresponding to each catchment area, where the membership matrix is an evaluation fuzzy matrix R, and the expression of the evaluation fuzzy matrix R is:

[0135]

[0136] Among them, r ij is an element in the evaluation fuzzy matrix R, which represents the evaluation grade membership value of each catchment area under different layout evaluation indexes; m represents the number of evaluation indexes; n represents the number of evaluation levels.

[0137] Step S220: Through literature review and expert consultation, use the analytic hierarchy process to determine the weights of each layout evaluation index to construct a weight matrix W (w1, w2,..., w i) Among them, the weights of land use, vertical layout suitability, waterlogging risk, building density, and population density are 0.195, 0.462, 0.195, 0.074, and 0.074 respectively.

[0138] Step S230: Finally, fuse the above steps to construct a multi-index evaluation system for the priority of vertical layout of green measures, calculate the layout priority coefficient P of green measures, and quantify the layout priority of each type of green measure in each catchment area. Among them, the number of layout evaluation indicators and the number of evaluation levels of the three types of green measures are the same. The expression of the layout priority coefficient P is:

[0139] P = W × R = (P1, P2,..., P3),

[0140] where W represents the weight matrix, which contains the weight values of each layout priority index, and P represents the layout priority coefficient of green measures, which represents the layout priority coefficient of each type of green measure in each catchment area.

[0141] Through the above steps, the layout priority coefficients of the three types of green measures, namely green roofs, rain gardens, and permeable pavements, in each catchment area can be calculated and determined. The comprehensive layout priority coefficients and the priority levels in the spatial layout of these three types of green measures are as Figure 10 shown. Among them, the lower the layout priority coefficient of each type of green measure in each catchment area, the more priority should be given to the layout of this type of green measure.

[0142] Step S40: Obtain the parameters of the green measures to be laid out corresponding to the areas where green measures are to be laid out in the city to be drained. Adopt a preset vertical collaborative optimization algorithm for green measures. According to the layout priority coefficient and the parameters of the green measures to be laid out, obtain the Pareto optimal solution set of the total outflow of green measures and the total cost of green measure layout in all catchment areas of the city to be drained, and determine the optimal green measure layout plan for the areas where green measures are to be laid out in each catchment area.

[0143] Using GIS geographical analysis technology, multiple layout evaluation indicators are determined based on the area where green measures are to be arranged, the accumulated water volume of waterlogging, the retention volume of green measures, and the population information of the city to be drained. Based on the fuzzy comprehensive evaluation method, according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator, after determining the layout priority coefficient of each green measure type in each catchment area, the green measure parameters to be arranged corresponding to the area where green measures are to be arranged in the city to be drained are obtained. Using a preset vertical collaborative optimization algorithm for green measures, according to the layout priority coefficient and the green measure parameters to be arranged, a Pareto optimal solution set of the total outflow of green measures and the total cost of green measure layout in all catchment areas of the city to be drained is obtained, and the optimal green measure layout plan for the area where green measures are to be arranged in each catchment area is determined. Among them, the vertical collaborative optimization algorithm for green measures is a multi-objective Bayesian optimization algorithm; the optimal green measure layout plan represents obtaining the green measure type and its corresponding best layout area of the area where green measures are to be arranged in each catchment area by solving the Pareto front of the total outflow of green measures and the total cost of green measure layout in the city to be drained.

[0144] In some embodiments, the steps of determining the total outflow of green measures include:

[0145] Step S401, obtaining the number of catchment areas, the number of green measure types, the unit time outflow of green measures in each catchment area, and the area of green measures in each catchment area of the city to be drained;

[0146] Step S402, calculating and determining the first product between the unit time outflow of each green measure type in each catchment area and the outflow green measure area of each green measure type in each catchment area to determine the green measure outflow water volume of each green measure type in each catchment area;

[0147] Step S403, based on the green measure outflow water volume of each green measure type in each catchment area, the number of catchment areas, and the number of green measure types of the city to be drained, to determine the total outflow of green measures in all catchment areas of the city to be drained.

[0148] Specifically, the expression of the total outflow of green measures is:

[0149]

[0150] where Q represents the green measure outflow water volume in all catchment areas of the city to be drained, and its unit is m 3 , n represents the number of catchment areas of the city to be drained, and the value of n can be 136, etc.; m represents the number of green measure types, and the value of m can be 3, etc.; qlid(ij) Denote the unit - time outflow of the \(j\) - th green measure in the \(i\) - th catchment area, with the unit of \(mm / h\); \(A\) lid(ij) Denote the outflow green - measure area of the \(j\) - th green measure in the \(i\) - th catchment area, with the unit of \(m\) 2 .

[0151] In some embodiments, the steps of determining the total cost of green - measure layout include:

[0152] Step S4001: Obtain the number of catchment areas in the city to be drained, the number of green - measure types, the layout - priority coefficient of each type of green measure in each catchment area, the unit - area cost of each type of green measure, and the layout area of each type of green measure in each catchment area;

[0153] Step S4002: Calculate and determine the second product among the layout - priority coefficient of each type of green measure in each catchment area, the unit - area cost of each type of green measure, and the layout area of each type of green measure in each catchment area;

[0154] Step S4003: Determine the total cost of green - measure layout for all catchment areas in the city to be drained according to the number of catchment areas in the city to be drained, the number of green - measure types, and the second product.

[0155] Specifically, the expression of the total cost of green - measure layout is:

[0156]

[0157] Where \(C\) represents the total cost of laying out all green measures in all catchment areas of the city to be drained, \(n\) represents the number of catchment areas in the city to be drained, \(m\) represents the number of green - measure types, and the value of \(m\) can be 3, etc.; \(P\) ij Represents the layout - priority coefficient of the \(j\) - th green measure in the \(i\) - th catchment area, \(C\) j Represents the unit - area cost of the \(j\) - th green measure, with the unit of \(yuan / m\) 2 ; \(A\) ij Represents the layout area of the \(j\) - th green measure in the \(i\) - th catchment area, with the unit of \(m\) 2 .

[0158] In some embodiments, using a preset vertical collaborative optimization algorithm for green measures, according to the layout - priority coefficient and the parameters of the green measures to be laid out, to obtain the Pareto - optimal solution set of the total outflow of green measures and the total cost of green - measure layout in all catchment areas of the city to be drained, the steps of determining the optimal green - measure layout plan for the areas where the green measures to be laid out in each catchment area include:

[0159] Step S40001: Invoke a preset vertical collaborative optimization algorithm for green measures. Based on the layout priority coefficient and the parameters of the green measures to be laid out, with the total outflow of green measures in all catchments and the total cost of laying out green measures as the dual optimization objectives, and with the layout areas of different types of green measures in each catchment as the constraint conditions, use a Gaussian regression model to perform probability modeling according to the non-linear update between each parameter of the green measures to be laid out in each catchment and the response value of the objective function, so as to predict the expected mean and variance of the objective function values of the potential sample points corresponding to the areas where the green measures are to be laid out. Among them, the parameters of the green measures to be laid out represent the green measure sample points corresponding to each type of green measure to be laid out in each catchment.

[0160] Step S40002: Use a preset expected hypervolume improvement algorithm to calculate the acquisition score of each potential sample point according to the probability distribution of the Gaussian regression model, and select the sample point with the highest score as the target for the next function evaluation.

[0161] Step S40003: Repeat the above steps. By quantifying the expected gain of the hypervolume measure of the existing Pareto front by the newly added samples, iteratively generate a Pareto optimal solution set that meets the constraint conditions to determine the optimal layout plan of the green measures in the areas where the green measures are to be laid out in each catchment.

[0162] Specifically, first, according to each catchment in the urban area to be drained, determine different types of green measures, such as rain gardens, green roofs, permeable pavements, etc., and define the layout areas of each type of green measure in different catchments. Among them, the layout areas of each catchment are affected by various factors such as geographical location and land use. For the parameters of the green measures to be laid out in each catchment, such as the areas of rain gardens, permeable pavements, and green roofs, etc., predict the green measure areas corresponding to each type of green measure to be laid out in each catchment through a Gaussian process regression model. Gaussian process regression can calculate the expected mean and variance of the objective function values of the potential green measure sample points to be laid out corresponding to the areas where the green measures are to be laid out by associating the measured data with the predicted data. Through the Gaussian process regression model, obtain the expected mean and variance of the objective function values of the green measure sample points to be laid out corresponding to the areas where the green measures are to be laid out, as the input of the multi-objective Bayesian optimization algorithm. Among them, the collaborative optimization algorithm for green measure layout is the multi-objective Bayesian optimization algorithm.

[0163] Call the preset collaborative optimization algorithm for green measure layout. With the layout areas of different green measure types in each catchment area as the constraint conditions, use the Gaussian process regression model to perform probability modeling based on the non-linear update between each green measure parameter to be laid out in each catchment area and the response value of the objective function. After predicting the expected mean and variance of the objective function values of the potential green measure sample points corresponding to the green measure areas to be laid out, use the preset expected hypervolume improvement algorithm to calculate the acquisition score of each potential sample point according to the probability distribution of the Gaussian regression model, and select the sample point with the highest score as the target for the next function evaluation; after obtaining the expected mean and variance of the green measure parameters to be laid out corresponding to the green measure areas to be laid out through the Gaussian process regression model, use the preset expected hypervolume improvement algorithm to calculate the acquisition score of each green measure area to be laid out according to the expected mean and variance of the green measure parameters to be laid out corresponding to the green measure areas to be laid out, and select the green measure area to be laid out with the highest score as the target for the next function evaluation;

[0164] More specifically, use the expected hypervolume improvement (EHVI) algorithm, combined with the predicted expected mean and variance of the objective function values of the potential green measure sample points corresponding to the green measure areas to be laid out, to evaluate the "acquisition score" of each potential green measure area to be laid out. The expected hypervolume improvement (EHVI) algorithm selects the area with the largest improvement (hypervolume) by calculating the improvement degree of each scheme for the next layout evaluation. According to the calculation results, select the sample point with the highest acquisition score as the target for the next round of function evaluation. The green measure layout scheme for the area involved in this sample point is considered to be the area that is most likely to optimize the flow rate and cost currently.

[0165] According to the foregoing steps S40001 and S40003, repeatedly execute the multi-objective Bayesian optimization algorithm. In each iteration, the new green measure layout scheme will be adjusted based on the current predicted results of the outflow and cost, minimizing the total outflow and layout cost as much as possible. Through multiple rounds of iteration, gradually adjust the green measure layout scheme until the Pareto optimal solution set of the total outflow and layout total cost of the green measures in all catchment areas is solved. In each iteration, according to the feedback of the two objective functions of the total green measure outflow function and the total green measure layout cost function, use the Bayesian optimization algorithm to further adjust the parameters to ensure the convergence of the global optimal solution, so as to determine the optimal green measure layout scheme for the green measure areas to be laid out in each catchment area. Among them, the optimal green measure layout scheme represents the optimal green measure type and its corresponding optimal green measure area of the green measure areas to be laid out in each catchment area selected from the Pareto optimal solution set where the total outflow of the green measures and the layout total cost in the urban area to be drained meet the constraint conditions.

[0166] As can be seen from the above embodiments, compared with the prior art, the present application addresses the problems in the prior art where most efforts are focused on two-dimensional plane optimization, unable to fully utilize the vertical urban space resources, resulting in the potential of flood control not being fully exploited. The present application includes but is not limited to the following beneficial effects:

[0167] First, the present application can significantly improve the flood prevention efficiency of the urban drainage system. By constructing a vertical runoff transfer model that links the above-ground and underground and multiple floors of buildings, it can more comprehensively simulate the process of urban rainwater flow, breaking through the limitations of traditional two-dimensional plane models, and thus significantly improving the storage capacity. This multi-layer linkage modeling method can accurately predict the runoff situation after rainfall, helping to formulate more effective drainage plans and reducing the risks of urban waterlogging and floods;

[0168] Second, the present application can optimize the resource allocation and the implementation efficiency of measures. By comprehensively considering multiple indicators such as land use, vertical layout suitability, waterlogging risk, building density, and population density, and quantifying the priorities through the fuzzy evaluation method, it can accurately identify the areas that need to be processed first, which not only helps to improve the scientific nature of resource allocation but also enhances the efficiency and effect of measure implementation;

[0169] Third, the present application can achieve the balance between flood prevention and economic costs. By using the multi-objective Bayesian optimization algorithm to generate Pareto optimal solutions, it can balance the flood prevention efficiency (such as minimizing the total outflow) and economic costs (such as minimizing the layout cost). This method can provide multiple optimization solutions for decision-makers, supporting them to flexibly select the best solution according to the actual budget and requirements, so as to ensure the best flood prevention effect with limited resources;

[0170] Fourth, the present application predicts the effects of the green measures to be laid out (such as total outflow and layout cost) through the Gaussian process regression model, and selects the optimal areas for green measure layout through the expected hypervolume improvement algorithm. This dynamic optimization method can adjust and update the green measure layout plan in real time, thus realizing the flexibility and adaptability of urban drainage management.

[0171] Fifth, the present application can reduce the operation cost and environmental impact of the drainage system. By optimizing the layout of green measures, it can not only effectively reduce the outflow of the drainage system, reduce the probability of waterlogging and floods, but also reduce the construction and maintenance costs of the drainage system by reducing excessive infrastructure construction (such as expensive underground drainage pipelines). At the same time, the optimization of the vertical layout of green measures such as rain gardens and permeable pavements helps to improve the urban ecological environment, increase urban green spaces, and enhance the sustainability of the city.

[0172] Furthermore, through this multi-level and multi-objective optimization model, various resources of the urban drainage system can be effectively integrated, green drainage measures can be scientifically and reasonably arranged, the flood control efficiency can be significantly improved, the economic cost can be reduced, and the urban environmental quality can be improved, providing strong support for the sustainable development of the city.

[0173] Please refer to Figure 11 A vertical layout control optimization device for green measures of urban drainage, provided to meet one of the purposes of this application, includes a to-be-laid area determination module 1100, a feasibility data determination module 1200, a layout priority determination module 1300, and an optimal solution determination module 1400. Among them, the to-be-laid area determination module 1100 is set to respond to an instruction for optimizing the layout control of green measures for the to-be-drained management city, use a preset semantic segmentation model to perform land identification and segmentation on the remote sensing image of the to-be-drained management city, and call a preset vertical feasibility evaluation module to perform a feasibility evaluation of the vertical layout of green measures on the remote sensing image of the to-be-drained management city, so as to determine the to-be-laid green measure areas in each catchment area. Among them, the to-be-drained management city includes multiple catchment areas, and each catchment area includes multiple to-be-laid green measure areas; the feasibility data determination module 1200 is set to call a vertical hydrodynamic coupling simulation model that combines grey measures and green measures, and input a preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation volume and the storage volume of green measures corresponding to the to-be-drained management city; the layout priority determination module 1300 is set to use GIS geographical analysis technology to determine multiple layout evaluation indicators based on the to-be-laid green measure areas, the waterlogging accumulation volume, the storage volume of green measures, and the population information of the to-be-drained management city, and determine the layout priority coefficient of each green measure type in each catchment area based on the fuzzy comprehensive evaluation method according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator; the optimal solution determination module 1400 is set to obtain the to-be-laid green measure parameters corresponding to the to-be-laid green measure areas of the to-be-drained management city, and use a preset vertical collaborative optimization algorithm for green measures to obtain the Pareto optimal solution set of the total outflow of green measures and the total layout cost of green measures in all catchment areas of the to-be-drained management city, and determine the optimal green measure layout plan for the to-be-laid green measure areas in each catchment area.

[0174] Based on any embodiment of this application, please refer to Figure 12 Another embodiment of this application further provides an electronic device, which can be implemented by a computer device, such as Figure 12As shown, it is a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database can store a control information sequence. When the computer-readable instructions are executed by the processor, the processor can implement an optimization method for vertical layout control of urban drainage green measures. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device can store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute the optimization method for vertical layout control of urban drainage green measures of the present application. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art can understand, Figure 12 The structure shown in it is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0175] In this embodiment, the processor is used to execute Figure 11 the specific functions of each module in it. The memory stores the program code and various types of data required to execute the above modules. The network interface is used for data transmission between the user terminal and the server. The memory in this embodiment stores the program code and data required to execute all modules in the optimization device for vertical layout control of urban drainage green measures of the present application. The server can call the program code and data of the server to execute the functions of all modules.

[0176] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute the steps of the optimization method for vertical layout control of urban drainage green measures according to any embodiment of the present application.

[0177] The present application also provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by one or more processors, the steps of the optimization method for vertical layout control of urban drainage green measures according to any embodiment of the present application are implemented.

[0178] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments of the present application can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a computer-readable storage medium such as a magnetic disk, an optical disc, a read-only memory (ROM), or a random access memory (RAM), etc.

[0179] The above are only some implementation manners of the present application. It should be noted that for those of ordinary skill in the technical field, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. A vertical layout control optimization method for green measures of urban drainage, characterized in that, Including: Responding to the instruction to optimize the layout control of green measures for urban drainage management, using a preset semantic segmentation model to identify and segment the land in the remote sensing image of the urban area to be drained, and invoking a preset vertical feasibility evaluation module to evaluate the feasibility of vertical layout of green measures in the remote sensing image of the urban area to be drained, so as to determine the areas where green measures are to be laid out in each catchment area. Among them, the urban area to be drained includes multiple catchment areas, and each catchment area includes multiple areas where green measures are to be laid out; Invoking a vertical hydrodynamic coupling simulation model that integrates grey measures and green measures, and inputting a preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation amount and the storage amount of green measures corresponding to the urban area to be drained; Using GIS geographical analysis technology to determine multiple layout evaluation indicators based on the areas where green measures are to be laid out, the waterlogging accumulation amount, the storage amount of green measures, and the population information of the urban area to be drained. Based on the fuzzy comprehensive evaluation method, according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator, to determine the layout priority coefficient of each type of green measure in each catchment area; Obtaining the parameters of the green measures to be laid out corresponding to the areas where green measures are to be laid out in the urban area to be drained, and using a preset vertical collaborative optimization algorithm for green measures. According to the layout priority coefficient and the parameters of the green measures to be laid out, to obtain the Pareto optimal solution set of the total outflows of green measures and the total layout costs of green measures in all catchment areas of the urban area to be drained, and determine the optimal layout scheme of green measures in the areas where green measures are to be laid out in each catchment area.

2. The vertical layout control optimization method for green measures of urban drainage according to claim 1, characterized in that, The step of invoking a vertical hydrodynamic coupling simulation model that integrates grey measures and green measures, and inputting a preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation amount and the storage amount of green measures corresponding to the urban area to be drained, includes: Calculating and determining the rainfall intensity corresponding to the urban area to be drained according to a preset rainfall intensity calculation formula, and determining the rainfall amount corresponding to the urban area to be drained according to the fourth product of the rainfall intensity corresponding to the urban area to be drained and a preset rainfall duration; Inputting the rainfall amount into a preset vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation amount and the storage amount of green measures corresponding to the urban area to be drained. Among them, the waterlogging accumulation amount includes the storage amount of green measures and the remaining flood flow, and the storage amount of green measures includes the above-ground storage amount and the underground storage amount.

3. The vertical layout control optimization method for green measures of urban drainage according to claim 1, characterized in that The step of determining the layout priority coefficient of each type of green measure in each catchment area based on the fuzzy comprehensive evaluation method according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator, includes: Obtaining multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator. Among them, the layout evaluation indicators include one or any combination of land use, vertical layout suitability, building density, population density, and waterlogging risk; Based on the fuzzy comprehensive evaluation method, according to the difference between the maximum value and the minimum value of the layout evaluation index, to determine multiple evaluation levels of the layout evaluation index in each catchment area, and use a preset membership function to normalize each layout evaluation index into a membership value within the interval [0, 1], so as to determine the normalized membership value of the layout evaluation index in each catchment area; According to the normalized membership value of the layout evaluation index in each catchment area and the multiple evaluation levels of the layout evaluation index in each catchment area, to construct a membership matrix corresponding to each catchment area; Use the analytic hierarchy process to determine the importance weights of each layout evaluation index, and according to the third product between the membership matrix and the importance weights of each layout evaluation index, to determine the layout priority coefficient of each green measure type in each catchment area.

4. The vertical layout control optimization method for urban drainage green measures according to claim 1, characterized in that, Steps to determine the total outflow of green measures, including: Obtain the number of catchment areas, the number of green measure types, the unit-time outflow of green measures in each catchment area, and the area of green measures in each catchment area of the city to be drained and managed; Calculate and determine the first product between the unit-time outflow of each green measure type in each catchment area and the outflow green measure area of each green measure type in each catchment area, so as to determine the green measure outflow water volume of each green measure type in each catchment area; According to the green measure outflow water volume of each green measure type in each catchment area, the number of catchment areas of the city to be drained and managed, and the number of green measure types, to determine the total outflow of green measures in all catchment areas of the city to be drained and managed.

5. The vertical layout control optimization method for green measures of urban drainage according to claim 1, characterized in that Steps to determine the total layout cost of green measures, including: Obtain the number of catchment areas, the number of green measure types, the layout priority coefficient of each type of green measure in each catchment area, the unit area cost of each type of green measure, and the layout area of each type of green measure in each catchment area of the city to be drained and managed; Calculate and determine the second product among the layout priority coefficient of each type of green measure in each catchment area, the unit area cost of each type of green measure, and the layout area of each type of green measure in each catchment area; According to the number of catchment areas of the city to be drained and managed, the number of green measure types, and the second product, to determine the total layout cost of green measures in all catchment areas of the city to be drained and managed.

6. The vertical layout control optimization method for urban drainage green measures according to claim 1, characterized in that Using a preset vertical collaborative optimization algorithm for green measures, according to the layout priority coefficient and the parameters of the green measures to be laid out, to obtain the Pareto optimal solution set of the total outflow of green measures and the total layout cost of green measures in all catchment areas of the city to be drained and managed. Steps to determine the optimal green measure layout plan for the area where the green measures to be laid out are located in each catchment area, including: Invoke the preset vertical collaborative optimization algorithm for green measures. According to the layout priority coefficient and the parameters of the green measures to be laid out, with the total outflow of green measures in all catchments and the total cost of green measure layout as the dual optimization objectives, and with the layout areas of different types of green measures in each catchment as the constraint conditions, use the Gaussian regression model to perform probability modeling based on the non-linear update between each parameter of the green measures to be laid out in each catchment and the response value of the objective function, so as to predict the expected mean and variance of the objective function values of the potential sample points corresponding to the areas where the green measures are to be laid out. Among them, the parameters of the green measures to be laid out represent the green measure sample points corresponding to each type of green measures to be laid out in each catchment; Use the preset expected hypervolume improvement algorithm to calculate the acquisition score of each potential sample point according to the probability distribution of the Gaussian regression model, and select the sample point with the highest score as the target for the next function evaluation; Repeat the above steps, and by quantifying the expected gain of the newly added samples to the hypervolume measure of the existing Pareto front, iteratively generate a Pareto optimal solution set that meets the constraint conditions to determine the optimal green measure layout plan for the areas where the green measures are to be laid out in each catchment.

7. The vertical layout control optimization method for urban drainage green measures according to any one of claims 1 to 6, characterized in that, The types of green measures include green roofs, rain gardens, and permeable pavements; The areas where the green measures are to be laid out include one or any combination of commercial buildings, office buildings, hospitals, schools, hotels, transportation buildings, sports buildings, and residential communities; The vertical collaborative optimization algorithm for green measures is a multi-objective Bayesian optimization algorithm; The optimal green measure layout plan represents that by solving the Pareto front of the total outflow of green measures and the total cost of green measure layout in the urban area to be drained, the types of green measures and their corresponding optimal layout areas for the areas where the green measures are to be laid out in each catchment are obtained.

8. An optimization device for vertical layout control of green measures for urban drainage, characterized in that, including: An area determination module to be laid out, configured to respond to an instruction for controlling and optimizing the layout of green measures in the urban area to be drained, use a preset semantic segmentation model to perform land identification and segmentation on the remote sensing image of the urban area to be drained, and call a preset vertical feasibility evaluation module to perform a feasibility evaluation of the vertical layout of green measures on the remote sensing image of the urban area to be drained, so as to determine the areas where the green measures are to be laid out in each catchment. Among them, the urban area to be drained includes multiple catchments, and each catchment includes multiple areas where the green measures are to be laid out; A feasibility data determination module, configured to call a vertical hydrodynamic coupling simulation model that integrates grey measures and green measures, and input a preset rainfall amount into the vertical hydrodynamic coupling simulation model to determine the waterlogging accumulation amount and the storage amount of green measures corresponding to the urban area to be drained; The layout priority determination module is configured to use GIS geographical analysis technology to determine multiple layout evaluation indicators based on the area where green measures are to be laid out, the accumulated water volume of waterlogging, the storage capacity of green measures, and the population information of the city to be drained. Based on the fuzzy comprehensive evaluation method, according to the multiple layout evaluation indicators and the weights corresponding to each layout evaluation indicator, to determine the layout priority coefficient of each type of green measure in each catchment area; The optimal solution determination module is configured to obtain the green measure parameters to be laid out corresponding to the area where green measures are to be laid out in the city to be drained, and use a preset vertical collaborative optimization algorithm for green measures. According to the layout priority coefficient and the green measure parameters to be laid out, to obtain the Pareto optimal solution set of the total outflow of green measures and the total cost of green measure layout in all catchment areas of the city to be drained, and determine the optimal green measure layout plan for the area where green measures are to be laid out in each catchment area.

9. An electronic device, comprising a central processing unit and a memory, characterized in that, The central processing unit is used to call and run the computer program stored in the memory to execute the steps of the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program implemented according to the method described in any one of claims 1 to 7 in the form of computer-readable instructions. When the computer program is called and run by the computer, it executes the steps included in the corresponding method.

Images