Method and apparatus for layout of green infrastructure

Abstract

This invention provides a method and apparatus for the layout of green infrastructure, which can be applied to the fields of urban planning and stormwater management. The layout method includes: acquiring a regional dataset of a target area, a set of physical attribute parameters of the green infrastructure, a preference dataset, and multiple evaluation functions; initializing the layout location and area of ​​the green infrastructure in the target area based on the regional dataset to obtain an initial layout scheme; querying target data from the regional dataset, the set of physical attribute parameters, and the preference dataset based on the initial layout scheme, and inputting the initial layout scheme and the target data into the evaluation functions to obtain evaluation values; adjusting the initial layout scheme according to flood resilience values, perceived preference values, and cost values ​​until a predetermined termination condition is met, obtaining multiple layout schemes and their corresponding evaluation values; and laying out the green infrastructure based on layout requirements and the evaluation values ​​of the multiple layout schemes.

Description

Technical Field

[0001] This invention relates to the field of urban planning and stormwater management technology, and more specifically to a method and apparatus for the layout of green infrastructure. Background Technology

[0002] With global climate change and rapid urbanization, urban flooding has increasingly impacted urban safety and residents' quality of life. The deployment of green infrastructure can effectively alleviate pressure on urban drainage systems and reduce the risk of urban flooding, and is widely used in urban construction. Currently, in determining the layout of green infrastructure, the neglect of users' preferences for green infrastructure has led to low implementation efficiency, reducing both the efficiency of green infrastructure deployment and the user experience. Summary of the Invention

[0003] In view of the above problems, the present invention provides a method and apparatus for laying out green infrastructure to improve the efficiency of green infrastructure layout and user experience.

[0004] One aspect of the present invention provides a method for laying out green infrastructure, comprising: acquiring a regional dataset of a target area, a set of physical attribute parameters of green infrastructure to be laid out in the target area, a dataset of user preferences for green infrastructure in the target area, and multiple evaluation functions for evaluating the layout performance of green infrastructure; initializing the layout location and area of ​​green infrastructure in the target area based on the regional dataset to obtain an initial layout scheme; querying target data from the regional dataset, the set of physical attribute parameters, and the preference dataset based on the initial layout scheme, and inputting the initial layout scheme and the target data into the evaluation functions to obtain an evaluation value of the initial layout scheme, wherein the evaluation value includes at least a flood resilience value for evaluating the impact of the initial layout scheme on flood prevention in the target area, a perceived preference value for user satisfaction with the initial layout scheme, and a cost value for the costs incurred by the initial layout scheme; adjusting the initial layout scheme according to the flood resilience value, the perceived preference value, and the cost value until a predetermined termination condition is reached to obtain multiple layout schemes and their corresponding evaluation values; and laying out the green infrastructure based on the layout requirements and the evaluation values ​​of the multiple layout schemes.

[0005] According to an embodiment of the present invention, the target area includes multiple sub-catchments, and the regional dataset includes land use type identifiers of the target area; based on the regional dataset, the layout location and layout area of ​​green infrastructure in the target area are initialized to obtain an initial layout scheme, including: based on the land use type identifiers and predetermined layout area conditions, the layout location and layout area of ​​green infrastructure in each sub-catchment are allocated to obtain the initial layout scheme.

[0006] According to an embodiment of the present invention, green infrastructure includes green roofs, rain gardens, and bioretention ponds. Based on land use type identification and predetermined layout area conditions, the layout location and layout area of ​​green infrastructure in each sub-catchment are allocated to obtain an initial layout scheme, including: placing green roofs in building sub-areas with land use type identification as buildings, and the layout area of ​​the green roofs does not exceed the total roof area of ​​the buildings in the building sub-area; placing rain gardens and bioretention ponds in ground sub-areas with land use type identification as impermeable ground or roadside green space; for each sub-catchment, the total layout area of ​​all green infrastructure in the sub-catchment does not exceed the transformation area threshold of the sub-catchment.

[0007] According to an embodiment of the present invention, the initial layout scheme includes the facility layout area of ​​each type of green infrastructure in each sub-catchment; based on the initial layout scheme, target data is queried from a regional dataset, a set of physical attribute parameters, and a preference dataset, including: based on the identifier of the sub-catchment, querying the drainage network topology of the sub-catchment, the buildable impermeable area of ​​the sub-catchment, and physical attribute data matching the type of green infrastructure from the regional dataset and the set of physical attribute parameters, as first target data; based on the type of green infrastructure laid out in the sub-catchment, querying at least one preference data matching the type of green infrastructure from the preference dataset, as second target data; and based on the type of green infrastructure, querying the layout cost matching the type of green infrastructure from the set of physical attribute parameters, as third target data.

[0008] According to embodiments of the present invention, multiple evaluation functions include: a flood resilience function for evaluating the impact of green infrastructure on flood prevention in a target area; a cost function for evaluating the layout costs required for green infrastructure; and a perceived preference function for evaluating user satisfaction with the layout of green infrastructure. An initial layout plan and target data are input into the evaluation functions to obtain an evaluation value for the initial layout plan, including: predicting the total overflow volume of drainage network nodes and the total rainfall volume received by each sub-catchment area in the target area under a rainfall event based on the facility layout area and the first target data; inputting the total overflow volume of drainage network nodes and the total rainfall volume received by each sub-catchment area into the flood resilience function to output a flood resilience value; inputting the facility layout area and the second target data into the perceived preference function to output a perceived preference value; and inputting the facility layout area and the third target data into the cost function to output a cost value.

[0009] According to an embodiment of the present invention, an initial layout scheme is adjusted based on a flood resilience value, a perceived preference value, and a cost value until a predetermined termination condition is met, resulting in multiple layout schemes and their corresponding evaluation values. This includes: adjusting the layout location and area of ​​the initial layout scheme to obtain a first candidate layout scheme; inputting the first candidate layout scheme into an evaluation function to obtain its evaluation value; determining, based on the evaluation values ​​of the first candidate layout scheme and the initial layout scheme, which layout schemes require further adjustment; adjusting the layout location and area of ​​the layout schemes to be adjusted to obtain a second candidate layout scheme and its evaluation value; and repeating the process of determining which layout schemes require further adjustment, and repeating the process of adjusting the layout location and area of ​​the layout schemes to be adjusted, based on the evaluation values ​​of the first candidate layout scheme, the initial layout scheme, and the second candidate layout scheme, until a predetermined number of adjustments is reached or the evaluation function converges, resulting in multiple layout schemes and their corresponding evaluation values.

[0010] According to an embodiment of the present invention, the layout requirements include preset priority information for waterlogging resilience value, perceived preference value, and cost value; based on the layout requirements and the evaluation values ​​corresponding to multiple layout schemes, the green infrastructure is laid out, including: based on the preset priority information of the layout requirements, selecting a target evaluation value that matches the preset priority information from the evaluation values ​​corresponding to multiple layout schemes; and laying out the green infrastructure using the target layout scheme that corresponds to the target evaluation value among the multiple layout schemes.

[0011] According to an embodiment of the present invention, the preference data in the preference dataset is obtained in the following manner: obtaining user information; constructing a logistic regression model for various types of green infrastructure based on the user information and the probability of the user selecting various types of green infrastructure; processing the logistic regression model for various types of green infrastructure to obtain the user's initial preference data for various types of green infrastructure; and normalizing the initial preference data to obtain the preference data.

[0012] According to an embodiment of the present invention, the regional dataset includes at least one of the following: digital elevation data, land use type identifiers, drainage network topology, and buildable impermeable area of ​​each sub-catchment; the physical attribute parameter set includes at least one of the following: permeability, water storage depth, Manning coefficient, and layout cost of each type of green infrastructure.

[0013] Another aspect of the present invention provides a green infrastructure layout apparatus, comprising: a first acquisition module, configured to acquire a regional dataset of a target area, a set of physical attribute parameters of the green infrastructure to be laid in the target area, a dataset of user preferences for the green infrastructure in the target area, and multiple evaluation functions for evaluating the layout performance of the green infrastructure; an initialization module, configured to initialize the layout location and layout area of ​​the green infrastructure in the target area based on the regional dataset to obtain an initial layout scheme; an input module, configured to input the initial layout scheme into the evaluation functions to obtain an evaluation value of the initial layout scheme, the evaluation value including at least a flood resilience value for evaluating the impact of the initial layout scheme on flood prevention in the target area, a perceived preference value for user satisfaction with the initial layout scheme, and a cost value for the cost incurred by the initial layout scheme; an adjustment module, configured to adjust the initial layout scheme according to the flood resilience value, perceived preference value, and cost value until a predetermined termination condition is reached to obtain multiple layout schemes and their corresponding evaluation values; and a layout module, configured to lay out the green infrastructure based on the layout requirements and the evaluation values ​​corresponding to the multiple layout schemes.

[0014] According to embodiments of the present invention, a regional dataset, a set of physical attribute parameters, a preference dataset, and multiple evaluation functions are acquired. Based on the regional dataset, the layout location and area of ​​green infrastructure are initialized to obtain an initial layout scheme. Based on the initial layout scheme, target data is queried from the regional dataset, the set of physical attribute parameters, and the preference dataset, and the initial layout scheme and target data are input into the evaluation functions to obtain the evaluation value of the initial layout scheme. The initial layout scheme is adjusted according to the evaluation value to obtain multiple layout schemes and their evaluation values. Based on the layout requirements and the evaluation values ​​corresponding to the multiple layout schemes, the green infrastructure is laid out. Since user preference data for green infrastructure is acquired during the layout process, and the perceived preference value, flood resilience value, and cost value generated based on this preference data are used as targets to jointly adjust the layout scheme, achieving synergistic optimization of urban flooding, cost, and satisfaction, the problem of low implementation efficiency of green infrastructure layout due to neglecting user wishes can be effectively avoided, thereby improving layout efficiency and user experience. Attached Figure Description

[0015] The above-described features, other objects, and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0016] Figure 1 An application scenario diagram of a green infrastructure layout method according to an embodiment of the present invention is shown.

[0017] Figure 2A flowchart illustrating a method for laying out green infrastructure according to an embodiment of the present invention is shown.

[0018] Figure 3 A schematic diagram of a Pareto optimal solution according to an embodiment of the present invention is shown.

[0019] Figure 4 A spatial distribution diagram of the target layout scheme according to an embodiment of the present invention is shown.

[0020] Figure 5 A flowchart of a method for laying out green infrastructure according to another embodiment of the present invention is shown.

[0021] Figure 6 It shows Figure 5 A flowchart for generating the Pareto optimal solution set for green infrastructure.

[0022] Figure 7 A structural block diagram of a green infrastructure layout device according to an embodiment of the present invention is shown.

[0023] Figure 8 A block diagram of an electronic device suitable for implementing a layout method for green infrastructure according to an embodiment of the present invention is shown. Detailed Implementation

[0024] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the invention for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0027] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0028] In the technical solution of this invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0029] With global climate change and rapid urbanization, urban flooding has impacted urban safety and residents' quality of life. Traditional urban drainage systems (gray infrastructure) often present costly solutions and struggle to cope with increasingly frequent rainfall events. As a nature-based solution, green infrastructure, due to its ability to effectively reduce peak runoff, control total runoff, and purify water, can significantly alleviate pressure on urban drainage systems and reduce urban flooding risks, and is widely used in sponge city construction. However, current urban drainage system management practices primarily focus on hydrological benefits and costs in the planning and optimization of green infrastructure, often neglecting the social perception dimension. This technology-driven planning approach may lead to public resistance or poor utilization efficiency during the implementation and maintenance phases of green infrastructure projects. As the importance of a people-centered approach in urban infrastructure planning becomes increasingly prominent, incorporating social perception factors into green infrastructure layout decisions is expected to improve the feasibility and sustainability of solutions. Therefore, a method is urgently needed to integrate quantitative evaluation of preference data in green infrastructure layout optimization, achieving a balanced approach that considers both technical performance and user acceptance.

[0030] In view of this, embodiments of the present invention provide a method for laying out green infrastructure, which combines hydraulic simulation, perceptual preference quantification analysis and multi-objective intelligent optimization algorithm to lay out green infrastructure, thereby improving layout efficiency and user experience.

[0031] Figure 1 An application scenario diagram of a green infrastructure layout method according to an embodiment of the present invention is shown.

[0032] like Figure 1As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0033] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, such as sending a layout request for green infrastructure and receiving a layout plan for green infrastructure. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as layout applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0034] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0035] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0036] It should be noted that the green infrastructure layout method provided in this embodiment of the invention can generally be executed by server 105. Correspondingly, the green infrastructure layout device provided in this embodiment of the invention can generally be located in server 105. The green infrastructure layout method provided in this embodiment of the invention can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the green infrastructure layout device provided in this embodiment of the invention can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0037] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0038] The following will be based on Figure 1 The described scene, through Figures 2-6 The layout method of green infrastructure according to embodiments of the present invention will be described in detail.

[0039] Figure 2 A flowchart illustrating a method for laying out green infrastructure according to an embodiment of the present invention is shown.

[0040] like Figure 2 As shown, the green infrastructure layout method of this embodiment includes operations S210 to S250.

[0041] In operation S210, the regional dataset of the target area, the set of physical attribute parameters of the green infrastructure to be laid in the target area, the user preference dataset of the target area for green infrastructure, and multiple evaluation functions for evaluating the layout performance of green infrastructure are obtained.

[0042] In operation S220, based on the regional dataset, the layout location and area of ​​green infrastructure in the target area are initialized to obtain the initial layout scheme.

[0043] In operation S230, based on the initial layout scheme, target data is queried from the regional dataset, physical attribute parameter set, and preference dataset. The initial layout scheme and target data are then input into the evaluation function to obtain the evaluation value of the initial layout scheme. The evaluation value includes at least the flood resilience value used to evaluate the impact of the initial layout scheme on the flood prevention of the target area, the perceived preference value of the user's satisfaction with the initial layout scheme, and the cost value of the cost incurred by the initial layout scheme.

[0044] In operation S240, the initial layout scheme is adjusted based on the waterlogging resilience value, perceived preference value, and cost value until the predetermined termination condition is met, resulting in multiple layout schemes and their corresponding evaluation values.

[0045] When operating S250, green infrastructure is deployed based on layout requirements and the evaluation values ​​corresponding to multiple layout schemes.

[0046] In some embodiments, the target area may be areas that require green infrastructure layout planning, such as cities, streets, and watersheds. The target area may include multiple sub-catchments, which can be areas demarcated by topography and drainage flow direction, serving as the basic spatial unit for green infrastructure layout analysis.

[0047] A regional dataset can be a set of basic data describing the geographical features of a target urban area. A regional dataset may include a data elevation model to represent topographic relief, a drainage network topology to represent the direction of drainage pipes and the location of inspection wells, land use type identifiers to represent different land use types, and the buildable impermeable area of ​​each sub-catchment and the total area of ​​the sub-catchment to represent the upper limit of the renovation area.

[0048] Green infrastructure can be a type of engineering facility that controls rainwater runoff at its source by simulating natural hydrological processes. In embodiments of the present invention, green infrastructure may include green roofs created by planting on building roofs, rain gardens that use plants and soil to retain and purify rainwater, and bioretention ponds that store and infiltrate rainwater through plant, soil, and microbial systems.

[0049] For example, if City A is selected as the target area, the total area of ​​the target area is approximately 1.15 km². 2 The proportion of impermeable surface area that can be constructed in the target area is as high as 80% of the total area. The target area contains 154 drainage network nodes, divided into 159 sub-catchments. The types of green infrastructure selected include rain gardens, green roofs, and bioretention ponds.

[0050] The physical attribute parameter set can be data describing the inherent properties of various green infrastructures. This set can include the permeability, water storage depth, Manning coefficient, and overall life-cycle layout cost of different green infrastructures. Permeability describes the rate at which rainwater infiltrates the green infrastructure per unit time; water storage depth describes the maximum depth to which rainwater can be stored on the surface of the green infrastructure; the Manning coefficient reflects the impediment effect of the surface roughness of the green infrastructure on water flow; and the overall life-cycle layout cost can include the construction cost, operating cost, maintenance cost, and demolition cost of the green infrastructure.

[0051] The preference dataset can include data on users in the target area's acceptance or preference for different types of green infrastructure. The preference data in the preference dataset can be calculated using logistic regression analysis based on user information obtained from questionnaires (such as demographic characteristics, building age, etc.) and historical flooding data, with the user's permission, and then processed through normalization standards.

[0052] The evaluation function can be a function used to evaluate the performance of green infrastructure layout, which can transform the input layout scheme into an evaluation value. In this embodiment of the invention, the evaluation function may include a flood resilience function for evaluating the impact of green infrastructure on flood prevention in the target area, a cost function for evaluating the layout cost required for green infrastructure, and a perceived preference function for evaluating user satisfaction with the layout of green infrastructure.

[0053] Optimizing the layout scheme requires generating an initial layout plan first. This process can be based on a regional dataset, where the location and area of ​​green infrastructure within the target area are initialized. For example, based on land use type identifiers and predetermined layout area conditions in the regional dataset, the location and area of ​​green infrastructure in each sub-catchment are allocated to obtain the initial layout plan. This initial layout plan can then serve as the starting population for multi-objective genetic algorithms, such as the Non-dominated Sorting Genetic Algorithm II (NSGA-II).

[0054] Based on this initial layout scheme, target data can be queried from the aforementioned regional dataset, physical attribute parameter set, and preference dataset. For example, based on the facility layout area and type of green infrastructure for each type in each sub-catchment in the initial layout scheme, target data can be queried from the regional dataset, physical attribute parameter set, and preference dataset. For instance, if the initial layout scheme is to lay rain gardens in sub-catchment 1, the target data that can be queried includes the drainage network topology of sub-catchment 1, the buildable impermeable area of ​​sub-catchment 1, physical attribute data related to rain gardens, at least one preference data for rain gardens, and the layout cost of rain gardens, etc.

[0055] The target data and initial layout plan can be input into evaluation functions, such as the flood resilience function, perceived preference function, and cost function. This yields a flood resilience value (assessing the impact of the initial layout plan on flood prevention in the target area), a perceived preference value (reflecting user satisfaction with the initial layout plan), and a cost value (reflecting the costs incurred by the initial layout plan). A higher flood resilience value reflects the ability to withstand heavy rain and flooding after the implementation of green infrastructure; a higher perceived preference value reflects the social acceptance of the plan; and a lower cost value reflects the cost of the plan.

[0056] Based on the waterlogging resilience value, perceived preference value, and cost value, the layout area and allocation method of the initial layout scheme can be adjusted until a predetermined number of adjustments is reached or the evaluation function converges, resulting in multiple layout schemes and their corresponding evaluation values.

[0057] Layout requirements can be prioritized by decision-makers (such as regional planning departments) based on actual needs. For example, flood prevention is prioritized, followed by user satisfaction, and finally cost. Based on this requirement, a matching target assessment value can be determined from the evaluation values ​​corresponding to multiple layout schemes. If a target assessment value perfectly matches the priority in the layout requirements (i.e., among multiple assessment values, the flood prevention assessment value is the highest, the perceived preference value is the highest, and the cost value is the lowest), the target layout scheme corresponding to this target assessment value is selected for the green infrastructure layout. If no target assessment value perfectly matches the priority in the layout requirements, a target layout scheme corresponding to the priority of flood prevention followed by user satisfaction (i.e., among multiple assessment values, the flood prevention assessment value is the highest, the perceived preference value is the highest, and the cost value is not the lowest) can be selected for the green infrastructure layout. If no target assessment value matches the priority of flood prevention followed by user satisfaction, then the highest flood prevention assessment value can be selected, and the target layout scheme corresponding to this highest flood prevention assessment value can be used for the green infrastructure layout.

[0058] According to embodiments of the present invention, a regional dataset, a set of physical attribute parameters, a preference dataset, and multiple evaluation functions are acquired. Based on the regional dataset, the layout location and area of ​​green infrastructure are initialized to obtain an initial layout scheme. Based on the initial layout scheme, target data is queried from the regional dataset, the set of physical attribute parameters, and the preference dataset, and the initial layout scheme and target data are input into the evaluation functions to obtain the evaluation value of the initial layout scheme. The initial layout scheme is adjusted according to the evaluation value to obtain multiple layout schemes and their evaluation values. Based on the layout requirements and the evaluation values ​​corresponding to the multiple layout schemes, the green infrastructure is laid out. Since user preference data for green infrastructure is acquired during the layout process, and the perceived preference value, flood resilience value, and cost value generated based on this preference data are used as targets to jointly adjust the layout scheme, achieving synergistic optimization of urban flooding, cost, and satisfaction, the problem of low implementation efficiency of green infrastructure layout due to neglecting user wishes can be effectively avoided, thereby improving layout efficiency and user experience.

[0059] In some embodiments, the acquisition of the regional dataset, physical attribute parameter set, preference dataset, and evaluation function can be based on instructions. For example, in response to a dataset generation instruction for a target region, the geographic location information of the target region contained in the instruction can be identified. Based on this geographic location information, the regional dataset, physical attribute parameter set, and preference dataset can be obtained from the database, and a target region base database can be constructed based on these datasets.

[0060] Based on the data in this base database, a multi-objective optimization model framework based on both physical and preference perception can be constructed. This framework can include a physical perception module, a preference perception module, and a cost module. The physical perception module includes running a hydraulic model (e.g., a Storm Water Management Model, SWMM) and a flooding assessment function, calculating the total volume of rainfall received by each sub-catchment and the total volume of overflow from pipe network nodes based on the design rainfall sequence, generating a flooding resilience index. The preference perception module includes a preference perception function, used to calculate the overall preference perception index based on the product of the layout area of ​​various green infrastructures in each sub-catchment and preference data. The cost module includes a cost function based on life-cycle cost analysis to calculate the total life-cycle layout cost of various green infrastructures.

[0061] In some embodiments, the preference data in the preference dataset can be obtained by: acquiring user information; constructing a logistic regression model for various types of green infrastructure based on the user information and the probability of the user selecting various types of green infrastructure; processing the logistic regression model for various types of green infrastructure to obtain the user's initial preference data for various types of green infrastructure; and normalizing the initial preference data to obtain the preference data.

[0062] In some embodiments, with the user's permission, user information may be obtained through questionnaires, such as the age of the house, the user's perception of the risk of flooding, the user's evaluation of different types of green infrastructure, and historical flooding data.

[0063] Based on user information and the probability of users choosing various types of green infrastructure, a logistic regression model for various types of green infrastructure can be constructed. This logistic regression model can be shown in formulas (1) and (2).

[0064] (1)

[0065] (2)

[0066] in, Let P be the probability that a user chooses the k-th type of green infrastructure, and 1-P be the probability that a user does not choose the k-th type of green infrastructure. Independent variables influencing the choice can include the age of the user's home, their familiarity with areas prone to flooding, and their perceived risk of flooding. , , ..., For regression coefficients, It is a constant; For users to the first Standardized preference data for green infrastructure, The regression coefficients corresponding to the k-th type of green infrastructure can be obtained.

[0067] In one example, based on the regression results, the standardized preference data for various types of green infrastructure can be calculated as follows: rain garden: 1.112; green roof: 1.104; bioretention pond: 1.085.

[0068] In some embodiments, based on the constructed multi-objective optimization model framework with dual physical and preference perception, the deployable area of ​​green infrastructure in each catchment area of ​​the target region can be used as a control variable. The first optimization objective is to maximize the urban flood resilience value, the second optimization objective is to maximize the perception preference value, and the third optimization objective is to minimize the cost value over the entire life cycle. The layout area constraints of different types of green infrastructure in each catchment area are embedded to construct an urban green infrastructure layout optimization model. The NSGA-II genetic algorithm is coupled and, according to the preset population size and number of iterations, drives the physical perception module, perception preference module, and cost module to perform large-scale parallel computation. Under the premise of satisfying spatial constraints, the Pareto optimal solution set for the layout of green infrastructure is generated. The Pareto optimal solution set can be multiple layout schemes with their own advantages and disadvantages.

[0069] According to an embodiment of the present invention, user information and historical flooding data are transformed into quantitative facility preference data through a logistic regression model, and then normalization is performed to eliminate dimensional differences, so that subjective user intentions are transformed into objective data, providing objective support for the quantitative evaluation of perceived preference values ​​and avoiding the subjectivity and arbitrariness of manual determination.

[0070] In some embodiments, optimizing the layout scheme requires first generating an initial layout scheme. In one example, the process of initializing the layout location and area of ​​green infrastructure in the target area based on a regional dataset to obtain an initial layout scheme may include the following operations: allocating the layout location and area of ​​green infrastructure in each sub-catchment based on land use type identifiers and predetermined layout area conditions to obtain an initial layout scheme.

[0071] Green infrastructure can include green roofs, rain gardens, and bioretention ponds. The process of allocating the location and area of ​​green infrastructure in each sub-catchment based on land use type identification and predetermined layout area conditions to obtain an initial layout plan may include the following operations: placing green roofs within building sub-areas identified as buildings, with the green roof area not exceeding the total roof area of ​​the buildings in the building sub-area; placing rain gardens and bioretention ponds within ground sub-areas identified as impermeable surfaces or roadside green spaces; and ensuring that the total layout area of ​​all green infrastructure within each sub-catchment does not exceed the sub-catchment's renovation area threshold.

[0072] In one embodiment, the initialization of the population in the NSGA-II genetic algorithm can be used to randomly generate N (N is a positive integer) initial layout schemes for green infrastructure. Each initial layout scheme can define the proportion of the layout area of ​​rain gardens, green roofs, and bioretention ponds in the total area of ​​each sub-catchment. During the initialization of the population, the following spatial constraints can be set: green roofs can only be arranged in sub-areas where the land use type is identified as buildings, and their area cannot exceed the total roof area of ​​buildings in that sub-area; rain gardens and bioretention ponds can only be arranged in sub-areas where the land use type is identified as impermeable ground or roadside green space; the sum of the total areas of all types of green infrastructure in each sub-catchment cannot exceed the maximum modifiable area threshold of that sub-catchment.

[0073] In one example, the process of generating the initial layout scheme using the NSGA-II genetic algorithm can be described by setting the initial population size to 100, the crossover coefficient to 0.9 (meaning that in each generation of evolution, 90% of the layout schemes are generated through crossover, and the remaining 10% are directly retained as the original layout schemes), the mutation coefficient to 0.1 (meaning that when generating a new layout scheme, each gene in each layout scheme (e.g., the area value of a sub-catchment area) has a 10% probability of being randomly fine-tuned (e.g., the area suddenly increases or decreases by tens of square meters)), and the number of iterations to 100.

[0074] According to embodiments of the present invention, by setting differentiated spatial layout rules for different types of green infrastructure, the feasibility of the initial layout scheme in physical space is ensured, the infeasibility of the initial layout scheme due to facility misalignment or exceeding limits is avoided, the resource consumption of subsequent iterative optimization is reduced, and the optimization efficiency of the layout scheme is improved.

[0075] In some embodiments, the initial layout scheme includes the facility layout area for each type of green infrastructure in each sub-catchment. Once the initial layout scheme is obtained, target data can be queried from a regional dataset, a set of physical attribute parameters, and a preference dataset. This querying process may include the following operations: based on the sub-catchment's identifier, querying the drainage network topology of the sub-catchment, the buildable impermeable area of ​​the sub-catchment, and physical attribute data matching the type of green infrastructure from the regional dataset and the set of physical attribute parameters, as first target data; based on the type of green infrastructure laid out in the sub-catchment, querying at least one preference data matching the type of green infrastructure from the preference dataset, as second target data; and based on the type of green infrastructure, querying the layout cost matching the type of green infrastructure from the set of physical attribute parameters, as third target data.

[0076] In some embodiments, the process of inputting the initial layout scheme and target data into an evaluation function based on the target data queried by the above operations to obtain the evaluation value of the initial layout scheme may include the following operations: based on the facility layout area and the first target data, predicting the total overflow volume of the drainage network nodes in the target area under a rainfall event, and the total rainfall volume received by each sub-catchment; inputting the total overflow volume of the drainage network nodes and the total rainfall volume received by each sub-catchment into an urban flooding resilience function, and outputting an urban flooding resilience value; inputting the facility layout area and the second target data into a perception preference function, and outputting a perception preference value; inputting the facility layout area and the third target data into a cost function, and outputting a cost value.

[0077] In some embodiments, the waterlogging resilience function can be as shown in formula (3), the perceived preference function can be as shown in formula (4), and the cost function can be as shown in formula (5).

[0078] (3)

[0079] in, For the first Urban flooding resilience value under designed rainfall events; This represents the total overflow volume (m³) of all drainage network nodes during this rainfall event. 3 ); This refers to the total rainfall volume (m³) received by each sub-catchment area during this rainfall event. 3 ).

[0080] The total overflow volume of all drainage network nodes and the total rainfall volume received by each sub-catchment during the rainfall event can be predicted based on the facility layout area and the first target data. For example, a hydraulic model can be used, based on the facility layout area in the current layout scheme, combined with the first target data, namely the digital elevation data, drainage network topology, sub-catchment area, land use type identifier, and preset design rainfall sequence in the regional dataset, and by calling the permeability, water storage depth, and Manning coefficient from the physical attribute parameter set, to obtain the prediction through the hydraulic model. For example, a hydraulic model can construct a physical model of the drainage system for a target area based on topographical and drainage network data indicated by land use type identifiers. Then, based on the facility layout area and physical attribute parameters of each sub-catchment, it calculates the surface runoff and infiltration of each sub-catchment during rainfall and inputs these as boundary conditions into the network runoff sub-model within the hydraulic model. A dynamic wave method is then used to simulate the flow and water level changes at each node of the network throughout the rainfall process, recording the overflow exceeding the threshold water level in real time and accumulating the total overflow volume. Simultaneously, the total rainfall volume of each sub-catchment is calculated by multiplying the rainfall depth by the area of ​​the sub-catchment. These two values ​​are then jointly input into a flood resilience function to evaluate the flood prevention effect of the current layout scheme on the target area.

[0081] (4)

[0082] in, Perceived preference value; This represents the total number of sub-catchment areas; The number of types of green infrastructure; For the first The first in the watershed area Green infrastructure facility layout area (m²) 2 ); For the first Preference data for green infrastructure; The primary target data is the data representing the greatest preference across all types of green infrastructure. The second target data may include... and By adjusting the facility layout area, and Inputting the value into formula (4) yields the perceived preference value, which represents the user's level of satisfaction with the current layout scheme.

[0083] (5)

[0084] in, Cost value; For the first Total facility layout area for green infrastructure; , , , The first The unit construction cost, annual unit operating cost, annual unit maintenance cost, and unit demolition cost of green infrastructure; The service life is defined as the design service life. In this embodiment of the invention, the service life of the design for various types of green infrastructure in City A can be determined to be 15 years.

[0085] In one example, based on the type of green infrastructure, the layout cost matching the type of green infrastructure is queried from the set of physical attribute parameters, and the resulting third target data can be shown in Table 1. By inputting the total facility layout area and the third target data into formula (5), the cost value used to evaluate the cost consumption of the layout scheme can be obtained.

[0086] Table 1. Lifecycle Cost of Green Infrastructure

[0087]

[0088] According to embodiments of the present invention, by inputting relevant data of the layout scheme into three evaluation functions respectively, a quantitative and decoupled evaluation of the green infrastructure layout scheme in three dimensions—flood control performance, public acceptance, and cost consumption—can be achieved. This provides clear and comparable quantitative indicators for subsequent multi-objective optimization, overcomes the one-sidedness of single-indicator evaluation in traditional methods, and improves the implementation rate of the layout scheme.

[0089] In some embodiments, the initial layout scheme can be adjusted based on the evaluation value of the initial layout scheme obtained from the above operations. In one example, the adjustment process may include the following operations: adjusting the layout position and layout area of ​​the initial layout scheme to obtain a first candidate layout scheme; inputting the first candidate layout scheme into an evaluation function to obtain an evaluation value of the first candidate layout scheme; determining the layout schemes to be adjusted that need to continue to participate in the adjustment based on the evaluation value of the first candidate layout scheme and the evaluation value of the initial layout scheme; adjusting the layout position and layout area of ​​the layout schemes to be adjusted to obtain a second candidate layout scheme and an evaluation value of the second candidate layout scheme; repeating the operation of determining the layout schemes to be adjusted that need to continue to participate in the adjustment, and repeating the operation of adjusting the layout position and layout area of ​​the layout schemes to be adjusted, based on the evaluation value of the first candidate layout scheme, the evaluation value of the initial layout scheme, and the evaluation value of the second candidate layout scheme, until a predetermined number of adjustments is reached or the evaluation function converges, resulting in multiple layout schemes and their corresponding evaluation values.

[0090] In some embodiments, the process of adjusting the layout location and area of ​​the initial layout scheme can be achieved through genetic operations of a genetic algorithm. For example, offspring populations can be generated using selection, crossover, and mutation operators. Selection can involve choosing layout schemes that need further adjustment, crossover can involve exchanging green infrastructure configuration genes in different sub-catchments, and mutation can involve adjusting the layout area of ​​specific green infrastructure facilities, such as adjusting the rain garden in sub-catchment 1 from 150㎡ to 168㎡, as an example only. By adjusting the initial layout scheme, a first candidate layout scheme can be obtained.

[0091] By inputting the relevant target data of the first candidate layout scheme into the objective function shown in formulas (3) to (5), the evaluation value of the first candidate layout scheme can be obtained.

[0092] By comparing the evaluation values ​​of the first candidate layout scheme with those of the initial layout scheme, the layout schemes that need further adjustment can be determined. For example, by stratifying and ranking the individuals in the population based on the superiority or inferiority of the three evaluation values, the schemes that need further adjustment can be determined based on the ranking results. For instance, if the initial layout scheme has all three evaluation values ​​better than the first candidate layout scheme—that is, the initial layout scheme has higher waterlogging resilience and perceived preference values, and lower costs—then the initial layout scheme dominates the first candidate layout scheme. In this case, the first candidate layout scheme can be eliminated, and the initial layout scheme can continue to be used as the parent scheme for the next generation. Similarly, if the first candidate layout scheme has all three evaluation values ​​better than the initial layout scheme, the initial layout scheme can be eliminated, and the first candidate layout scheme can continue to be used as the parent scheme for the next generation. If the initial layout scheme and the first candidate layout scheme do not dominate each other, for example, if the waterlogging resilience value of the initial layout scheme is higher than that of the first candidate layout scheme, and the perceived preference value and cost of the initial layout scheme are lower than those of the first candidate layout scheme, then both schemes can participate in the adjustment, and one layout scheme can be adjusted at a time.

[0093] By adjusting the layout scheme to be adjusted, a second candidate layout scheme can be obtained. By inputting the relevant target data of the second candidate layout scheme into the evaluation function, the evaluation value of the second candidate layout scheme can be obtained.

[0094] Based on the evaluation values ​​of the first candidate layout scheme, the initial layout scheme, and the second candidate layout scheme, the operation of determining the layout schemes to be adjusted that need to continue to be adjusted is repeated, as is the operation of adjusting the layout position and layout area of ​​the layout schemes to be adjusted, until the predetermined number of adjustments is reached or the evaluation function converges to the convergence threshold, resulting in multiple layout schemes and their corresponding evaluation values. These multiple layout schemes can constitute a Pareto optimal solution.

[0095] Figure 3 A schematic diagram of a Pareto optimal solution according to an embodiment of the present invention is shown.

[0096] like Figure 3 As shown, the perceived preference value and cost value exhibit a linear relationship; the perceived preference value increases linearly with increasing cost. The perceived preference value and flood resilience value exhibit a non-linear positive relationship; the perceived preference value increases at an accelerating rate with improved flood resilience, demonstrating diminishing marginal returns in their influence. Furthermore, the flood resilience value and cost value also exhibit a typical convex function relationship, with increased flood resilience requiring greater cost input.

[0097] According to an embodiment of the present invention, through a multi-round iterative adjustment and evaluation feedback mechanism, the layout scheme is continuously optimized, and a set of Pareto optimal solutions is finally generated, providing decision-makers with multiple feasible options and avoiding the problem that single optimization is prone to getting trapped in local optima or only outputting a single scheme, resulting in no choice.

[0098] In some embodiments, based on the obtained multiple layout schemes and their evaluation values, green infrastructure can be laid out in conjunction with layout requirements, i.e., decision preferences. In one example, layout requirements include preset priority information for flood resilience values, perceived preference values, and cost values; laying out green infrastructure based on layout requirements and the evaluation values ​​corresponding to multiple layout schemes includes: selecting a target evaluation value that matches the preset priority information from the evaluation values ​​corresponding to multiple layout schemes; and laying out the green infrastructure using the target layout scheme that corresponds to the target evaluation value among the multiple layout schemes.

[0099] In some embodiments, the layout requirement can prioritize flood resilience value over perceived preference value over cost value. From the evaluation values ​​of multiple layout schemes, the set of evaluation values ​​with the highest flood resilience value, the highest perceived preference value, and the lowest cost value can be selected as the target evaluation value; alternatively, the set of evaluation values ​​with the highest flood resilience value and the highest perceived preference value can be selected as the target evaluation value; or, the set of evaluation values ​​with the highest flood resilience value can be selected as the target evaluation value. The layout scheme corresponding to this target evaluation value is then used as the target layout scheme, which can be used to lay out green infrastructure.

[0100] In some embodiments, one or more sets of evaluation values ​​can be selected from the evaluation values ​​of multiple layout schemes. These values ​​include a waterlogging resilience value higher than a predetermined waterlogging resilience value, a perceived preference value higher than a predetermined perceived preference value, and a cost value lower than a predetermined cost value. Alternatively, one or more sets of evaluation values ​​can be selected. Alternatively, one set of evaluation values ​​can be selected. The layout scheme corresponding to the target evaluation value is then used as the target layout scheme.

[0101] In some embodiments, when selecting a target layout scheme, different preset weights can be assigned to the three evaluation values ​​of each layout scheme. The total evaluation value of the layout scheme is determined by multiplying the evaluation value by the preset weight. The layout scheme with the highest total evaluation value can be selected, or the layout schemes ranked first by a preset number of total evaluation values ​​can be selected as the target layout scheme.

[0102] Figure 4 A spatial distribution diagram of the target layout scheme according to an embodiment of the present invention is shown.

[0103] like Figure 4 As shown, Figure 4 There are three types of green infrastructure: bioretention ponds, green roofs, and rain gardens. Each curve represents the layout area of ​​a bioretention pond, green roof, or rain garden. Figure 4 The area ratio is the ratio of the sum of the areas of green infrastructure in each sub-catchment to the total urban area. Based on layout requirements and assessments of layout schemes, multiple target layout schemes can be selected. Among these schemes, the area ratio of bioretention ponds ranges from 0.17 to 0.32, the area ratio of green roofs ranges from 0.218 to 0.241, and the area ratio of rain gardens ranges from 0 to 0.08.

[0104] According to an embodiment of the present invention, by introducing the decision-maker's priority preferences as the basis for scheme selection, the final selected layout scheme can be adapted to the specific decision-making orientation and actual needs of different cities or different periods, thereby achieving a flexible match between optimization results and decision-making needs and improving the actual adoption rate and feasibility of the layout scheme.

[0105] Figure 5 A flowchart of a method for laying out green infrastructure according to another embodiment of the present invention is shown.

[0106] like Figure 5 As shown, the layout method of this embodiment may include operations S510 to S540.

[0107] During operation of S510, in response to the command to generate a base database for the catchment area of ​​the target region, the region dataset, physical attribute parameter set, and preference dataset are obtained, and the base database is constructed.

[0108] In operating S520, a multi-objective optimization model framework based on both physical and preference perceptions is constructed using a base database.

[0109] The framework includes a physical perception module, a perception preference module, and a cost module. The physical perception module is configured to run a hydraulic model, calculate the total volume of rainfall received by each sub-catchment and the total volume of overflow from the pipe network nodes based on the design rainfall sequence, and generate an urban flooding resilience index. The perception preference module is configured to calculate the overall perception preference index based on the product of the planned area and preference weight coefficient of various types of green infrastructure in each sub-catchment. The cost module is configured to calculate the total layout cost of construction, operation and maintenance, and demolition of various types of green infrastructure based on the full life cycle cost analysis method.

[0110] By operating the S530 and using a genetic algorithm, a Pareto optimal solution set for green infrastructure is generated under the premise of satisfying spatial constraints.

[0111] Using the deployable area of ​​green infrastructure in each urban catchment area as the control variable, the first optimization objective is to maximize the urban flood resilience value, the second optimization objective is to maximize the perception preference value, and the third optimization objective is to minimize the total life cycle cost. The layout area constraints of different types of green infrastructure in each catchment area are embedded to construct an urban green infrastructure layout optimization model. The model is coupled with the NSGA-II genetic algorithm to drive the physical perception module, social perception module, and economic cost module to perform large-scale parallel computation according to the preset population size and number of iterations. The device includes selection operator units, crossover operator units, and mutation operator units to evolve and generate the Pareto optimal solution set of green infrastructure under the premise of satisfying spatial constraints.

[0112] The S540 is operated to output a Pareto optimal solution set. Based on the layout requirements, a target layout scheme is selected from the Pareto optimal solution set, generating parameters such as the layout area of ​​various green infrastructures in each catchment area.

[0113] Figure 6 It shows Figure 5 A flowchart for generating the Pareto optimal solution set for green infrastructure.

[0114] like Figure 6 As shown, the process of generating the Pareto optimal solution set of green infrastructure by operation S530 may include operations S531 to S535.

[0115] In operation S531, determine the initial layout scheme.

[0116] The population is initialized, and N sets of green infrastructure layout schemes are randomly generated. Each scheme defines the ratio of the layout area of ​​rain gardens, green roofs, and bioretention ponds in each sub-catchment to the total area of ​​the sub-catchment. The population initialization process sets the following spatial constraints: green roofs can only be placed in sub-areas identified as buildings, and their area cannot exceed the total roof area of ​​buildings in that sub-area; rain gardens and bioretention ponds can only be placed in sub-areas identified as impermeable ground or roadside green space; the sum of the total area of ​​all types of green infrastructure in each sub-catchment cannot exceed the maximum modifiable area threshold of that sub-catchment.

[0117] In operation S532, determine the evaluation value.

[0118] The physical perception module, preference perception module, and cost module are invoked to calculate the waterlogging resilience value, perception preference value, and cost value for each group of schemes, respectively.

[0119] When operating S533, identify the layout schemes that need further adjustment.

[0120] The non-dominated sorting and crowding calculation of the genetic algorithm can be used to stratify and sort the individuals in the population according to the superiority or inferiority relationship of three evaluation values: waterlogging resilience value, perceived preference value, and cost value.

[0121] When operating S534, perform genetic operations on the layout scheme to be adjusted.

[0122] The offspring population is generated by selection, crossover, and mutation operators, where the crossover operation exchanges the green infrastructure configuration genes of different sub-catchments, and the mutation operation fine-tunes the area proportion of specific green infrastructure.

[0123] In operation S535, loop iterate, repeating operations S531 to S534 until the predetermined number of adjustments is reached or the evaluation function converges to the convergence threshold.

[0124] The green infrastructure layout method provided in this invention constructs a perceived preference value and uses it as a third optimization objective, equally important as the urban flood resilience value and cost value. The NSGA-II algorithm is used to find the optimal target layout scheme that balances hydrological safety, user satisfaction, and cost feasibility. This target layout scheme comprehensively considers the physical hydrological processes of the urban drainage system, the full life-cycle cost of green infrastructure, and public preference for green infrastructure. It achieves synergistic optimization of urban flood resilience, cost, and user satisfaction, realizing a shift from single-engineering water management to a synergistic governance of a dual system of physical and preference-based approaches. This method has the advantages of improving the social acceptance and long-term operational stability of green infrastructure planning schemes, effectively avoiding difficulties in project implementation or NIMBY (Not In My Backyard) effects caused by ignoring public opinion. It enhances the comprehensive resilience of cities in the face of climate disasters and has significant value in people-centered new urbanization construction and refined management of sponge cities.

[0125] Based on the above-described method for laying out green infrastructure, this invention also provides a device for laying out green infrastructure. The following will be combined with... Figure 7 The device is described in detail.

[0126] Figure 7 A structural block diagram of a green infrastructure layout device according to an embodiment of the present invention is shown.

[0127] like Figure 7 As shown, the green infrastructure layout device 700 of this embodiment includes a first acquisition module 710, an initialization module 720, an input module 730, an adjustment module 740, and a layout module 750.

[0128] The first acquisition module 710 is used to acquire a regional dataset of the target area, a set of physical attribute parameters of the green infrastructure to be laid in the target area, a dataset of user preferences for green infrastructure in the target area, and multiple evaluation functions for evaluating the layout performance of the green infrastructure.

[0129] The initialization module 720 is used to initialize the layout location and area of ​​green infrastructure in the target area based on the regional dataset, so as to obtain the initial layout scheme.

[0130] The input module 730 is used to query target data from the regional dataset, physical attribute parameter set, and preference dataset based on the initial layout scheme, and input the initial layout scheme and target data into the evaluation function to obtain the evaluation value of the initial layout scheme. The evaluation value includes at least the flood resilience value used to evaluate the impact of the initial layout scheme on the flood prevention of the target area, the perceived preference value of the user's satisfaction with the initial layout scheme, and the cost value of the cost consumed by the initial layout scheme.

[0131] The adjustment module 740 is used to adjust the initial layout scheme based on the waterlogging resilience value, perceived preference value, and cost value until the predetermined termination condition is met, thereby obtaining multiple layout schemes and their corresponding evaluation values.

[0132] The layout module 750 is used to lay out green infrastructure based on layout requirements and the evaluation values ​​corresponding to multiple layout schemes.

[0133] In some embodiments, the target area includes multiple sub-catchments, and the regional dataset includes land use type identifiers for the target area. The initialization module 720 may include an allocation unit.

[0134] The allocation unit is used to allocate the location and area of ​​green infrastructure in each sub-catchment based on the land use type identifier and the predetermined layout area conditions, so as to obtain the initial layout scheme.

[0135] In some embodiments, green infrastructure includes green roofs, rain gardens, and bioretention ponds. The allocation unit may include a first allocation subunit, a second allocation subunit, and a third allocation subunit.

[0136] The first allocation sub-unit is used to arrange green roofs within building sub-areas where the land use type is identified as buildings, and the layout area of ​​its green roofs does not exceed the total roof area of ​​the buildings in the building sub-area.

[0137] The second allocation sub-unit is used to arrange rain gardens and bioretention ponds in ground sub-areas where the land use type is identified as impermeable ground or roadside green space.

[0138] The third allocation sub-unit is used for each sub-catchment area, where the total layout area of ​​all green infrastructure within the sub-catchment area does not exceed the sub-catchment area renovation threshold.

[0139] In some embodiments, the initial layout scheme includes the facility layout area of ​​each type of green infrastructure in each sub-catchment. The input module 730 may include a first query unit, a second query unit, and a third query unit.

[0140] The first query unit is used to query the drainage network topology of the sub-catchment, the buildable impermeable area of ​​the sub-catchment, and the physical attribute data that matches the type of green infrastructure from the regional dataset and physical attribute parameter set, based on the identification of the sub-catchment, as the first target data.

[0141] The second query unit is used to query at least one preference data that matches the type of green infrastructure based on the type of green infrastructure deployed in the sub-catchment area, as the second target data.

[0142] The third query unit is used to query the layout cost that matches the type of green infrastructure from the set of physical attribute parameters, based on the type of green infrastructure, as the third target data.

[0143] In some embodiments, multiple evaluation functions include: a flood resilience function for evaluating the impact of green infrastructure on flood prevention in a target area; a cost function for evaluating the layout costs required for the green infrastructure; and a perceived preference function for evaluating user satisfaction with the layout of the green infrastructure. The input module 730 may further include a prediction unit, a first input unit, a second input unit, and a third input unit.

[0144] The prediction unit is used to predict the total overflow volume of the drainage network nodes in the target area and the total rainfall volume received by each sub-catchment area under a rainfall event, based on the facility layout area and the first target data.

[0145] The first input unit is used to input the total overflow volume of the drainage network nodes and the total rainfall volume received by each sub-catchment area into the waterlogging resilience function and output the waterlogging resilience value.

[0146] The second input unit is used to input the facility layout area and the second target data into the perception preference function and output the perception preference value.

[0147] The third input unit is used to input the facility layout area and the third target data into the cost function and output the cost value.

[0148] In some embodiments, the adjustment module 740 may include a first adjustment unit, a fourth input unit, a determination unit, a second adjustment unit, and an iteration unit.

[0149] The first adjustment unit is used to adjust the layout position and layout area of ​​the initial layout scheme to obtain the first candidate layout scheme.

[0150] The fourth input unit is used to input the first candidate layout scheme into the evaluation function to obtain the evaluation value of the first candidate layout scheme.

[0151] The determining unit is used to determine the layout schemes that need to be adjusted and continue to be adjusted based on the evaluation value of the first candidate layout scheme and the evaluation value of the initial layout scheme.

[0152] The second adjustment unit is used to adjust the layout position and layout area of ​​the target layout scheme to obtain the second candidate layout scheme and the evaluation value of the second candidate layout scheme.

[0153] The iterative unit is used to repeatedly determine the layout schemes that need to be adjusted and to continue to be adjusted based on the evaluation values ​​of the first candidate layout scheme, the initial layout scheme, and the second candidate layout scheme, and to repeatedly adjust the layout position and layout area of ​​the target layout scheme until a predetermined number of adjustments is reached or the evaluation function converges, thereby obtaining multiple layout schemes and their corresponding evaluation values.

[0154] In some embodiments, the layout requirements include preset priority information for flood resilience values, perceived preference values, and cost values. The layout module 750 may include selection units and layout units.

[0155] The selection unit is used to select a target evaluation value that matches the preset priority information from the evaluation values ​​corresponding to multiple layout schemes, based on the preset priority information of the layout requirements.

[0156] The layout unit is used to lay out green infrastructure using the target layout scheme that corresponds to the target evaluation value among multiple layout schemes.

[0157] In some embodiments, the green infrastructure deployment device 700 may further include a second acquisition module, a construction module, a processing module, and a normalization module.

[0158] The preference data in the preference dataset is obtained as follows:

[0159] The second acquisition module is used to acquire user information.

[0160] The module is used to build logistic regression models for various types of green infrastructure based on user information and the probability of users choosing various types of green infrastructure.

[0161] The processing module is used to process the logistic regression models of various types of green infrastructure to obtain the initial preference data of users for various types of green infrastructure.

[0162] The normalization module is used to normalize the initial preference data to obtain the final preference data.

[0163] In some embodiments, the regional dataset includes at least one of the following: digital elevation data, land use type identifiers, drainage network topology, and buildable impermeable area of ​​each sub-catchment; the physical attribute parameter set includes at least one of the following: permeability, water storage depth, Manning coefficient, and layout cost of each type of green infrastructure.

[0164] According to embodiments of the present invention, any plurality of modules among the first acquisition module 710, initialization module 720, input module 730, adjustment module 740, and layout module 750 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules may be combined with at least a portion of the functionality of other modules and implemented in one module. According to embodiments of the present invention, at least one of the first acquisition module 710, initialization module 720, input module 730, adjustment module 740, and layout module 750 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in hardware or firmware, or in any one of software, hardware, and firmware implementations, or in a suitable combination of any of these. Alternatively, at least one of the first acquisition module 710, initialization module 720, input module 730, adjustment module 740 and layout module 750 may be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0165] Figure 8 A block diagram of an electronic device suitable for implementing a layout method for green infrastructure according to an embodiment of the present invention is shown.

[0166] like Figure 8 As shown, an electronic device 800 according to an embodiment of the present invention includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage portion 808 into a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0167] Random access memory (RAM) 803 stores various programs and data required for the operation of electronic device 800. Processor 801, read-only memory (ROM) 802, and RAM 803 are interconnected via bus 804. Processor 801 performs various operations of the method flow according to embodiments of the present invention by executing programs in read-only memory (ROM) 802 and / or RAM 803. It should be noted that programs may also be stored in one or more memories other than read-only memory (ROM) 802 and RAM 803. Processor 801 may also perform various operations of the method flow according to embodiments of the present invention by executing programs stored in one or more memories.

[0168] According to an embodiment of the present invention, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to a bus 804. The electronic device 800 may also include one or more of the following components connected to the input / output (I / O) interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output (I / O) interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 810 as needed so that computer programs read from it can be installed into the storage section 808 as needed.

[0169] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0170] According to embodiments of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of the present invention, a computer-readable storage medium may include read-only memory (ROM) 802 and / or random access memory (RAM) 803 described above and / or one or more memories other than read-only memory (ROM) 802 and random access memory (RAM) 803.

[0171] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of the present invention.

[0172] When the computer program is executed by the processor 801, it performs the functions defined in the system / apparatus of this invention. According to embodiments of the invention, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0173] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 809, and / or installed from a removable medium 811. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0174] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by processor 801, it performs the functions defined in the system of this embodiment of the invention. According to embodiments of the invention, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0175] According to embodiments of the present invention, program code for executing the computer programs provided in the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0176] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0177] Those skilled in the art will understand that the features described in the various embodiments of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, the features described in the various embodiments of the present invention can be combined and / or combined in various ways without departing from the spirit and teachings of the present invention. All such combinations and / or combinations fall within the scope of the present invention.

[0178] The embodiments of the present invention have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of the invention. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of the invention, and all such substitutions and modifications should fall within the scope of the invention.

Claims

1. A method for laying out green infrastructure, characterized in that, The method includes: The system acquires a regional dataset of the target area, a set of physical attribute parameters of the green infrastructure to be deployed in the target area, a dataset of user preferences for the green infrastructure in the target area, and multiple evaluation functions for assessing the deployment performance of the green infrastructure. Based on the regional dataset, the layout location and area of ​​the green infrastructure in the target area are initialized to obtain an initial layout scheme; Based on the initial layout scheme, target data is queried from the regional dataset, physical attribute parameter set, and preference dataset. The initial layout scheme and the target data are then input into the evaluation function to obtain the evaluation value of the initial layout scheme. The evaluation value includes at least the flood resilience value used to evaluate the impact of the initial layout scheme on the flood prevention of the target area, the perceived preference value of the user's satisfaction with the initial layout scheme, and the cost value of the cost consumed by the initial layout scheme. Based on the waterlogging resilience value, the perceived preference value, and the cost value, the initial layout scheme is adjusted until a predetermined termination condition is met, resulting in multiple layout schemes and corresponding evaluation values ​​for the multiple layout schemes. Based on the layout requirements and the evaluation values ​​corresponding to the multiple layout schemes, the green infrastructure is laid out.

2. The method according to claim 1, characterized in that, The target area includes multiple sub-catchments, and the regional dataset includes land use type identifiers for the target area. The initial layout scheme is obtained by initializing the location and area of ​​the green infrastructure in the target area based on the regional dataset, including: Based on the land use type identifier and the predetermined layout area conditions, the layout location and layout area of ​​the green infrastructure in each sub-catchment are allocated to obtain the initial layout scheme.

3. The method according to claim 2, characterized in that, The green infrastructure includes green roofs, rain gardens, and bioretention ponds; Based on the land use type identifier and predetermined layout area conditions, the initial layout scheme is obtained by allocating the layout location and area of ​​the green infrastructure in each sub-catchment area, including: The green roof is located within a building sub-area whose land use type is identified as a building, and the layout area of ​​the green roof does not exceed the total roof area of ​​the buildings in the building sub-area. The rain garden and the bioretention pond are located in a ground sub-area where the land use type is identified as impermeable ground or roadside green space; For each sub-catchment area, the total layout area of ​​all green infrastructure within the sub-catchment area shall not exceed the threshold area for renovation of the sub-catchment area.

4. The method according to claim 2, characterized in that, The initial layout plan includes the facility layout area for each type of green infrastructure in each sub-catchment area; The step of querying target data from the region dataset, physical attribute parameter set, and preference dataset based on the initial layout scheme includes: Based on the identifier of the sub-catchment area, the drainage network topology of the sub-catchment area, the buildable impermeable area of ​​the sub-catchment area, and the physical attribute data matching the type of the green infrastructure are queried from the regional dataset and the physical attribute parameter set, as the first target data; Based on the type of green infrastructure deployed in the sub-catchment area, at least one preference data matching the type of green infrastructure is queried from the preference dataset as second target data; Based on the type of green infrastructure, the layout cost that matches the type of green infrastructure is queried from the set of physical attribute parameters, and used as the third target data.

5. The method according to claim 4, characterized in that, The plurality of evaluation functions include: a flood resilience function for evaluating the impact of the green infrastructure on flood prevention in the target area, a cost function for evaluating the layout costs required for the green infrastructure, and a perceived preference function for evaluating the user's satisfaction with the layout of the green infrastructure. The step of inputting the initial layout scheme and the target data into the evaluation function to obtain the evaluation value of the initial layout scheme includes: Based on the facility layout area and the first target data, predict the total overflow volume of the drainage network nodes in the target area under rainfall events, and the total rainfall volume received by each sub-catchment area; The total overflow volume of the drainage network nodes and the total rainfall volume received by each sub-catchment area are input into the waterlogging resilience function, and the waterlogging resilience value is output. The facility layout area and the second target data are input into the perception preference function, and the perception preference value is output. The facility layout area and the third target data are input into the cost function, and the cost value is output.

6. The method according to claim 1, characterized in that, The step of adjusting the initial layout scheme based on the waterlogging resilience value, the perceived preference value, and the cost value until a predetermined termination condition is met, resulting in multiple layout schemes and corresponding evaluation values ​​for the multiple layout schemes, includes: The layout positions and layout areas of the initial layout scheme are adjusted to obtain the first candidate layout scheme; The first candidate layout scheme is input into the evaluation function to obtain the evaluation value of the first candidate layout scheme; Based on the evaluation values ​​of the first candidate layout scheme and the initial layout scheme, determine the layout schemes that need to continue to be adjusted. The layout position and layout area of ​​the layout scheme to be adjusted are adjusted to obtain a second candidate layout scheme and an evaluation value of the second candidate layout scheme; Based on the evaluation values ​​of the first candidate layout scheme, the initial layout scheme, and the second candidate layout scheme, the operation of determining the layout schemes to be adjusted that need to continue to be adjusted is repeated, as well as the operation of adjusting the layout position and layout area of ​​the layout schemes to be adjusted is repeated, until a predetermined number of adjustments is reached or the evaluation function converges, to obtain multiple layout schemes and their corresponding evaluation values.

7. The method according to claim 1, characterized in that, The layout requirements include preset priority information for waterlogging resilience values, perception preference values, and cost values; The green infrastructure is laid out based on layout requirements and the evaluation values ​​corresponding to the multiple layout schemes, including: Based on the preset priority information of the layout requirements, a target evaluation value that matches the preset priority information is selected from the evaluation values ​​corresponding to the multiple layout schemes. The green infrastructure is laid out using the target layout scheme that corresponds to the target evaluation value among the multiple layout schemes.

8. The method according to claim 1, characterized in that, The preference data in the preference dataset is obtained in the following way: Obtain the user information of the user; Based on the user information and the probability of the user selecting various types of green infrastructure, a logistic regression model for various types of green infrastructure is constructed. The logistic regression models of the various types of green infrastructure are processed to obtain the initial preference data of the users for the various types of green infrastructure; The initial preference data is normalized to obtain the preference data.

9. The method according to claim 1, characterized in that, The regional dataset includes at least one of the following: digital elevation data, land use type identification, drainage network topology, and the buildable impermeable area of ​​each sub-catchment. The set of physical property parameters includes at least one of the following: the permeability, water depth, Manning coefficient, and layout cost of various types of green infrastructure.

10. A layout device for green infrastructure, characterized in that, The device includes: The first acquisition module is used to acquire a regional dataset of the target area, a set of physical attribute parameters of the green infrastructure to be laid in the target area, a dataset of user preferences for the green infrastructure in the target area, and multiple evaluation functions for evaluating the layout performance of the green infrastructure. An initialization module is used to initialize the layout location and layout area of ​​the green infrastructure in the target area based on the regional dataset, so as to obtain an initial layout scheme; An input module is used to input the initial layout scheme into the evaluation function to obtain an evaluation value of the initial layout scheme. The evaluation value includes at least a flood resilience value for evaluating the impact of the initial layout scheme on the flood prevention of the target area, a perceived preference value for the user's satisfaction with the initial layout scheme, and a cost value for the cost consumed by the initial layout scheme. The adjustment module is used to adjust the initial layout scheme according to the waterlogging resilience value, the perception preference value and the cost value until a predetermined end condition is reached, so as to obtain multiple layout schemes and the evaluation values ​​corresponding to the multiple layout schemes. The layout module is used to lay out the green infrastructure based on layout requirements and the evaluation values ​​corresponding to the multiple layout schemes.

Images