Urban inland inundation prediction model construction method and urban inland inundation prediction method and device

Abstract

The invention provides a construction method of an urban inland inundation prediction model and an urban inland inundation prediction method and device, and relates to the technical field of data processing. The construction method of the urban inland inundation prediction model comprises the following steps: constructing an urban inland inundation process model coupled with an emergency drainage mode based on regional topographic data, hydro meteorological data and flood prevention response data; inputting the rainfall data under different scenes into the urban waterlogging process model to obtain waterlogging feature data; performing correlation analysis on the rainfall data and the waterlogging characteristic data, and determining rainfall parameters related to the flood risk from the rainfall data; and constructing sample data according to the rainfall parameters and the waterlogging feature data, and training the neural network model based on the sample data to obtain an urban waterlogging prediction model. According to the technical scheme, the prediction precision of the urban inland inundation prediction model can be improved.

Description

Background Art

[0002] With the acceleration of global climate change and urbanization, urban waterlogging is becoming more and more frequent, becoming one of the main challenges facing many cities. Under heavy rainfall conditions, the load on urban drainage systems increases rapidly, often leading to waterlogging on roads, traffic disruptions, and even serious threats to people's lives and property. In order to address this problem, relevant technologies use prediction models to make accurate warnings before heavy rains arrive, thereby providing a basis for disaster prevention, mitigation, and emergency response.

[0003] However, most of the existing urban waterlogging prediction methods rely on historical rainfall data. By reviewing historical rainfall events and analyzing their correlation with waterlogging, a prediction model is constructed. However, in the face of climate change and the rapid development of urban infrastructure, this prediction method based on historical data often ignores factors such as terrain differences in different areas within the city and drainage system layout. Simply relying on historical rainfall data cannot accurately predict the location and depth of waterlogging. In addition, most of the existing prediction models are based on static analysis, ignoring the impact of emergency drainage measures on the waterlogging process, resulting in a lag or deviation in the judgment of the development trend of waterlogging. Therefore, there is still room for improvement in the urban waterlogging prediction model in related technologies.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute relevant technology known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the embodiments of the present disclosure is to provide a method for constructing an urban waterlogging prediction model, an urban waterlogging prediction method, a device for constructing an urban waterlogging prediction model, an urban waterlogging prediction device, an electronic device and a computer-readable storage medium, thereby improving the prediction accuracy of the urban waterlogging prediction model at least to a certain extent.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to a first aspect of an embodiment of the present disclosure, a method for constructing an urban waterlogging prediction model is provided, the method comprising: constructing an urban waterlogging process model coupled with an emergency drainage mode based on regional terrain data, hydrological and meteorological data, and flood control response data; inputting rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data; performing correlation analysis on the rainfall data and the waterlogging characteristic data, and determining rainfall parameters related to flood risk from the rainfall data; constructing sample data based on the rainfall parameters and the waterlogging characteristic data, and training a neural network model based on the sample data to obtain the urban waterlogging prediction model.

[0008] In some embodiments of the present disclosure, based on the aforementioned solution, the urban waterlogging process model coupled with the emergency drainage mode is constructed based on regional terrain data, hydrological and meteorological data, and flood control response data, including: Constructing a two-dimensional surface hydrodynamic model based on the regional topographic data and the hydrological and meteorological data; Based on the flood control response data, the two-dimensional surface hydrodynamic model is coupled with temporary drainage of flood-prone areas, road flood control drainage vehicles, engineering scheduling, and flood control retaining walls to obtain the urban waterlogging process model; The two-dimensional surface hydrodynamic model is based on To build, q Indicates flow rate ，F express x The flux vector in the direction, G express y The flux vector in the direction, S represents the source term vector, t Indicates time, x Represents the spatial coordinate in the east-west direction, y The spatial coordinate representing the north-south direction; in, q according to to determine; F according to To confirm, G according to To confirm, S according to to determine; h Indicates water depth. u Indicates that water is flowing x Flow rate in direction, v Indicates that water is flowing y Flow rate in direction, g represents the acceleration due to gravity, represents the friction source term, represents the bottom slope source term, i represents the net rain source term generated by rainfall and infiltration, represents the river bottom elevation, Represents the surface roughness coefficient.

[0009] In some embodiments of the present disclosure, based on the aforementioned solution, the process of coupling the two-dimensional surface hydrodynamic model with temporary drainage of the flood-prone area based on the flood control response data includes: Determine the pumping efficiency of a portable pump installed at a flood-prone point according to the flood control response data, convert the pumping efficiency of the portable pump into a grid drainage volume in the two-dimensional surface hydrodynamic model, and couple based on a grid drainage equivalent substitution method; according to: ; Determine the start-up and shutdown conditions of the portable pump, wherein: Indicates i The depth of water in a flood-prone area Indicates i How long does water last at a flood-prone spot? Indicates the water depth threshold is enabled. Indicates the threshold for opening the water accumulation duration. Indicates the closing water depth threshold; according to: ; Determine the grid depth change, where: represents the change in grid water depth, represents the computational flow of the grid cell, l represents the side length of the grid cell, Indicates the model calculation time step; The water depth and flow state of the two-dimensional surface hydrodynamic model are updated according to the operating state of the portable pump and the change in the grid water depth.

[0010] In some embodiments of the present disclosure, based on the aforementioned solution, the process of coupling the two-dimensional surface hydrodynamic model with a road flood control drainage vehicle based on the flood control response data includes: Determine the operating conditions of the flood control drainage vehicle and the change in grid water depth according to the flood control response data; The mobile path of the flood control and drainage vehicle is planned according to: ; Determine the operating time of the flood control and drainage vehicle, wherein: T Indicates the operation time of the flood control and drainage vehicle. Z Indicates the main road. C Indicates secondary roads. represents the length of the main road, Indicates the length of the secondary road. represents the average speed of vehicles on the main roads. Indicates the average speed of vehicles on secondary roads; The operation progress of the flood control and drainage vehicle is determined based on the mobile path planning, and the water depth and flow state of the two-dimensional surface hydrodynamic model are updated according to the operation progress of the flood control and drainage vehicle and the change in the grid water depth.

[0011] In some embodiments of the present disclosure, based on the aforementioned solution, the process of coupling the two-dimensional surface hydrodynamic model with engineering scheduling based on the flood control response data includes: According to the water conservancy information exchange area, the flood control and drainage projects are divided into underground flood control and drainage projects and surface flood control and drainage projects, and the underground flood control and drainage projects and the surface flood control and drainage projects are connected by drainage pipe networks; By marking the grid cells of the flood control and drainage project, based on the water volume exchange between the two-dimensional surface hydrodynamic model and the pipe network nodes, the coupling of the two-dimensional surface hydrodynamic process, the one-dimensional hydrodynamic process of the rainwater pipe network and the underground flood control and drainage project is realized; Based on the inner boundary processing method, the surface flood control and drainage project is coupled with the two-dimensional surface hydrodynamic model; according to: ; Determine the flow rate through the gate, where represents the gate flow of a single grid, represents the comprehensive flow coefficient, B Indicates the grid width, e Indicates the gate opening, represents the hydraulic head on each grid; The water depth and flow state of the two-dimensional surface hydrodynamic model are updated according to the lock flow and water depth data.

[0012] In some embodiments of the present disclosure, based on the aforementioned scheme, the sample data is constructed according to the rainfall parameters and the waterlogging characteristic data, and the neural network model is trained based on the sample data to obtain the urban waterlogging prediction model, including: the sample data is constructed according to the rainfall parameters and the waterlogging characteristic data, and the neural network model is trained based on the sample data to obtain the initial model for urban waterlogging prediction; the prediction accuracy of the initial model for urban waterlogging prediction is determined, and the prediction accuracy is used as the objective function, and the initial model for urban waterlogging prediction is optimized based on the particle swarm optimization algorithm that integrates the Sky Eagle optimization operator and the Cauchy-Gaussian mutation operator to obtain the urban waterlogging prediction model.

[0013] In some embodiments of the present disclosure, based on the aforementioned scheme, the prediction accuracy is used as the objective function, and the initial model for urban waterlogging prediction is optimized based on a particle swarm optimization algorithm that integrates the Sky Eagle optimization operator and the Cauchy-Gauss mutation operator to obtain the urban waterlogging prediction model, including: representing each particle as a solution of the initial model for urban waterlogging prediction, and taking the prediction accuracy as the objective function, updating the speed and position of the particle based on the basic iteration rule of the particle swarm optimization algorithm; using the Sky Eagle optimization operator to improve the global search capability of the particle swarm optimization algorithm, searching the global optimal area in advance, and optimizing the movement of the particles using the Levy flight distribution function; using the particle swarm optimization algorithm to accelerate the iterative search, and in response to the optimal solution of the particle swarm not changing after a preset number of iterations, mutating the particles based on the Cauchy-Gauss mutation operator to jump out of the local optimal solution; when the iteration termination condition is met, the optimization of the initial model for urban waterlogging prediction is completed to obtain the urban waterlogging prediction model.

[0014] In some embodiments of the present disclosure, based on the above solution, the use of the Sky Eagle optimization operator to improve the global search capability of the particle swarm optimization algorithm includes: according to: ; Improve the global search capability of the particle swarm optimization algorithm, wherein, Indicated in t At the +1 iteration, the particle position is updated using the Eagle optimization operator. represents the search shrinkage factor, Indicated in t The position of the global optimal solution in the iteration, Indicates the moving position when tracking the target. Indicated in t The particle position at the iteration, Represents a function that generates a random number between 0 and 1. Indicates the flight speed when tracking the target. represents the Levy flight distribution function.

[0015] According to a second aspect of an embodiment of the present disclosure, a method for predicting urban waterlogging is provided, the method comprising: obtaining real-time rainfall parameter data; inputting the real-time rainfall parameter data into an urban waterlogging prediction model to obtain a prediction result of waterlogging characteristic data corresponding to the current city; wherein the urban waterlogging prediction model is obtained according to the method for constructing an urban waterlogging prediction model as described above.

[0016] According to a third aspect of an embodiment of the present disclosure, a device for constructing an urban waterlogging prediction model is provided, the device comprising: a waterlogging model construction module, for constructing an urban waterlogging process model coupled with an emergency drainage mode based on regional terrain data, hydrological and meteorological data, and flood control response data; a waterlogging feature determination module, for inputting rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging feature data; a correlation analysis module, for performing correlation analysis on the rainfall data and the waterlogging feature data, and determining rainfall parameters related to flood risk from the rainfall data; and a prediction model construction module, for constructing sample data based on the rainfall parameters and the waterlogging feature data, and training a neural network model based on the sample data to obtain the urban waterlogging prediction model.

[0017] According to a fourth aspect of an embodiment of the present disclosure, a device for predicting urban waterlogging is provided, the device comprising: a data acquisition module for acquiring real-time rainfall parameter data; a waterlogging prediction module for inputting the real-time rainfall parameter data into an urban waterlogging prediction model to obtain a prediction result of waterlogging characteristic data corresponding to the current city; wherein the urban waterlogging prediction model is obtained according to the above-mentioned method for constructing an urban waterlogging prediction model.

[0018] According to a fifth aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method for constructing the urban waterlogging prediction model or the method for predicting urban waterlogging is implemented.

[0019] According to a sixth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for constructing the urban waterlogging prediction model or the method for predicting urban waterlogging is implemented.

[0020] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects: The construction method of the urban waterlogging prediction model in the exemplary embodiment of the present disclosure, on the one hand, constructs an urban waterlogging process model coupled with an emergency drainage mode based on regional terrain data, hydrological and meteorological data and flood control response data, which can accurately simulate the dynamic changes of water flow under different terrain conditions, meteorological conditions and emergency response measures, so that the urban waterlogging process model can fully reflect the dynamic changes of the urban waterlogging process; on the other hand, by inputting different rainfall scenario data, not only can the urban waterlogging process model simulate the waterlogging situation under various rainfall conditions, but also enable the model to flexibly respond to real-time rainfall data, so that the prediction results can timely reflect the current meteorological changes and improve the timeliness of the prediction; on the other hand, through correlation analysis, the rainfall parameters most relevant to the flood risk can be identified, unnecessary data interference can be reduced, and the effectiveness of model training can be improved; in addition, the neural network model is trained by sample data constructed by rainfall parameters and waterlogging feature data, so that the trained urban waterlogging prediction model has strong adaptability and generalization ability. Furthermore, the prediction accuracy of the urban waterlogging prediction model is improved to a certain extent, so that the model can more accurately predict the complex waterlogging process, leaving sufficient lead time for emergency response, and reducing the losses and impacts caused by waterlogging.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0023] Figure 1 A flowchart of a method for constructing an urban waterlogging prediction model according to some embodiments of the present disclosure is schematically shown.

[0024] Figure 2 A schematic diagram of a generalized method of a hand pump according to some embodiments of the present disclosure is schematically shown.

[0025] Figure 3 A schematic diagram of a generalized method for a road flood control and drainage vehicle according to some embodiments of the present disclosure is schematically shown.

[0026] Figure 4 A schematic diagram of a coupling method for an emergency flood control retaining wall according to some embodiments of the present disclosure is schematically shown.

[0027] Figure 5The flowchart of the particle swarm optimization algorithm according to some embodiments of the present disclosure is schematically shown.

[0028] Figure 6 A block diagram of a device for constructing an urban waterlogging prediction model according to some embodiments of the present disclosure is schematically shown.

[0029] Figure 7 A block diagram of a device for predicting urban waterlogging according to some embodiments of the present disclosure is schematically shown.

[0030] Figure 8 A schematic diagram of the structure of a computer system of an electronic device according to some embodiments of the present disclosure is schematically shown.

[0031] Fig. 9 A schematic diagram of a computer-readable storage medium according to some embodiments of the present disclosure is schematically shown.

[0032] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this specification. Instead, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.

[0034] The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this specification. The singular forms "a", "the" and "the" used in this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0035] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this specification, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0036] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete and will fully convey the concept of the example embodiments to those skilled in the art.

[0037] Furthermore, the drawings are only schematic illustrations and are not necessarily drawn to scale. The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0038] With the acceleration of global climate change and urbanization, urban waterlogging is becoming more and more frequent, becoming one of the major challenges facing many cities around the world. Under heavy rainfall or extreme weather conditions, the load on urban drainage systems increases rapidly, often leading to waterlogging on roads, traffic disruptions, and even serious threats to people's lives and property. In order to address this problem, we can use waterlogging prediction models to make accurate warnings before heavy rains arrive, thereby providing a basis for disaster prevention, mitigation, and emergency response.

[0039] In related technologies, urban waterlogging prediction methods mostly rely on historical rainfall data, and build prediction models by reviewing historical rainfall events and analyzing their correlation with waterlogging. However, this prediction method based on historical data has obvious limitations and shortcomings in the face of climate change and the rapid development of urban infrastructure: First, most of the existing methods are based on macro rainfall data, ignoring factors such as topographic differences and drainage system layout in different areas of the city, and the spatial resolution is insufficient. In a complex urban environment, there are significant differences in surface drainage capacity and pipe network capacity in different areas. Simply relying on historical rainfall data cannot accurately predict the location and depth of waterlogging. Secondly, traditional waterlogging prediction models are mostly static analyses, ignoring the impact of emergency drainage measures (such as drainage vehicle scheduling and activation of temporary drainage facilities) on the waterlogging process. In actual disaster prevention management, urban emergency management departments often take a variety of measures to alleviate the impact of waterlogging. Existing prediction models cannot dynamically incorporate these measures into the simulation of waterlogging processes, resulting in lags or deviations in the judgment of waterlogging development trends. In addition, urban waterlogging is a highly complex nonlinear problem, which is affected by multiple factors such as topography, drainage pipe network, and rainfall intensity. Existing models have limited ability to deal with these nonlinear problems, and often fall into local optimal solutions, thus failing to obtain global optimal solutions. Therefore, the relevant urban waterlogging prediction models based on historical rainfall data show problems such as insufficient accuracy, low spatial resolution, and poor real-time performance when facing complex urban environments and dynamic emergency responses.

[0040] In order to solve all or part of the technical problems in the above-mentioned related technologies, in an exemplary embodiment of the present disclosure, a method for constructing an urban waterlogging prediction model is firstly proposed. Figure 1 The following is a schematic diagram of a method for constructing an urban flood prediction model according to some embodiments of the present disclosure. Figure 1 As shown, the method for constructing the urban waterlogging prediction model may include the following steps: Step S110, constructing an urban waterlogging process model coupled with an emergency drainage mode based on regional terrain data, hydrological and meteorological data, and flood control response data; Step S120, inputting rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data; Step S130, performing correlation analysis on the rainfall data and the waterlogging characteristic data, and determining rainfall parameters related to flood risk from the rainfall data; Step S140, constructing sample data according to rainfall parameters and urban waterlogging characteristic data, and training a neural network model based on the sample data to obtain an urban waterlogging prediction model.

[0041] Specifically, firstly, an urban waterlogging process model coupled with an emergency drainage mode is constructed based on regional terrain data, hydrological and meteorological data, and flood control response data, fully considering the impact of terrain characteristics, rainfall characteristics, and emergency drainage measures on the waterlogging process; then, rainfall data under different scenarios are input into the urban waterlogging process model, and various waterlogging characteristic data are obtained through simulation. These characteristic data include waterlogging depth, waterlogging area, flow rate, etc., which are used to reflect the waterlogging situation under different rainfall conditions; then, a correlation analysis is conducted between rainfall data and waterlogging characteristic data, and key rainfall parameters related to flood risks are screened out, such as peak rainfall time, peak rainfall, accumulated rainfall, etc. These parameters will be used as inputs to the model; finally, sample data are constructed based on the screened rainfall parameters and the extracted waterlogging characteristic data, and the neural network model is trained based on these sample data. After training, an optimized urban waterlogging prediction model is obtained, which can accurately predict the development trend of waterlogging in future rainfall events and provide support for urban emergency response and disaster prevention and mitigation.

[0042] Next, the method for constructing the urban waterlogging prediction model in the above exemplary embodiment will be further described.

[0043] In step S110, an urban waterlogging process model coupled with an emergency drainage mode is constructed based on regional terrain data, hydrological and meteorological data, and flood control response data.

[0044] Among them, regional terrain data can represent spatial data describing the surface morphology in the urban area, covering the terrain's elevation, slope, depression area, slope aspect and other features. It can be presented in the form of a digital elevation model or a topographic map. By using regional terrain data, the direction and velocity of water flow under different rainfall conditions can be determined, and areas prone to waterlogging can be identified, providing basic support for the simulation of waterlogging processes. Hydrometeorological data can represent meteorological information related to the water cycle, such as rainfall, humidity, and wind speed, usually including rainfall, rainfall intensity, peak time, peak rainfall, and rainfall distribution, which can be used to simulate rainfall events under different scenarios. Flood control response data can represent the measures and resource information taken in response to heavy rain or waterlogging events in waterlogging emergency management, including emergency drainage equipment (such as pumping stations, temporary drainage pumps), flood control projects (such as river sluices and dams, drainage vehicle scheduling) and historical emergency response data, etc. These data help simulate the dynamic impact of different emergency response measures on waterlogging processes. The emergency drainage mode can represent the drainage strategy and operation mode adopted by the drainage system and emergency facilities of the city when waterlogging occurs, including flood control emergency plans, temporary drainage and water retaining equipment data of flood-prone points, construction location of flood control and drainage projects and emergency operation data, road flood control drainage vehicle data and location, etc. The urban waterlogging process model can represent the mathematical model of the occurrence, development and retreat process of urban waterlogging under rainstorm conditions by integrating regional topographic data, hydrological and meteorological data and flood control response data. Among them, by combining regional topography, hydrological and meteorological data and flood control emergency response data, the urban waterlogging process model can accurately simulate the dynamic development of waterlogging, and dynamically adjust the prediction results according to the emergency drainage measures under different scenarios, ensuring that the model can not only reflect the natural development process of waterlogging, but also simulate the mitigation effect of emergency responses such as drainage equipment and drainage vehicle scheduling on waterlogging, thereby improving the fitting ability of complex waterlogging scenarios.

[0045] In some embodiments, an urban waterlogging process model coupled with an emergency drainage mode is constructed based on regional terrain data, hydrological and meteorological data, and flood control response data, specifically including the following steps: constructing a two-dimensional surface hydrodynamic model based on regional terrain data and hydrological and meteorological data; coupling the two-dimensional surface hydrodynamic model with temporary drainage of flood-prone areas, coupling with road flood control drainage vehicles, coupling with engineering scheduling, and coupling with flood control retaining walls based on the flood control response data to obtain an urban waterlogging process model.

[0046] Specifically, the two-dimensional surface hydrodynamic model can represent a mathematical model used to simulate the movement of surface water flow on a two-dimensional plane, and is used to describe the flow process of water flow under different terrain conditions. It can use regional terrain data and hydrological and meteorological data as input to calculate hydrodynamic parameters such as water accumulation depth, flow velocity, and flow rate to reflect the risk of urban waterlogging under rainfall scenarios. Temporary drainage coupling in flood-prone areas refers to the introduction of temporary drainage equipment, such as portable pumps and temporary drainage pumps, in high-risk areas of waterlogging, combining them with the two-dimensional surface hydrodynamic model to dynamically simulate the impact of the operation of these drainage equipment on the depth of waterlogging. Road flood control drainage vehicle coupling can represent the combination of the scheduling and operation process of urban flood control drainage vehicles during waterlogging with the two-dimensional surface hydrodynamic model, dynamically simulating the movement of drainage vehicles on the road, drainage operations and their impact on waterlogging, including modeling of drainage vehicle scheduling, movement paths and drainage capacity. Engineering scheduling coupling refers to combining the operation and scheduling process of underground or surface flood control and drainage projects, such as rainwater drainage pumping stations, underground storage reservoirs, river dams, etc., with the hydrodynamic model to simulate the role of these engineering facilities in drainage, storage, and gate operation and their impact on the waterlogging process. Flood control retaining wall coupling can mean combining temporary or fixed retaining wall structures with the hydrodynamic model to simulate the use of retaining walls during rainfall, calculate the retaining wall's blocking effect on water flow and its impact on water level changes in the waterlogged area.

[0047] In the embodiment of the present disclosure, the two-dimensional surface hydrodynamic model uses the two-dimensional shallow water equation as the control equation, which ignores the kinematic viscosity term, turbulent diffusion term, wind stress and Coriolis force, and only considers the friction and bottom slope source terms. To build, q Indicates flow rate ，F express x The flux vector in the direction, G express y The flux vector in the direction, S represents the source term vector, t Indicates time, x Represents the spatial coordinate in the east-west direction, y A spatial coordinate representing the north-south direction.

[0048] Furthermore, the flow q according to to determine; x Direction flux vector F according to To confirm, y Direction flux vector G according to To determine, the source vector S according to to determine; h Indicates water depth.u Indicates that water is flowing x Flow rate in direction, v Indicates that water is flowing y Flow rate in direction, g represents the acceleration due to gravity, represents the friction source term, represents the bottom slope source term, i represents the net rain source term generated by rainfall and infiltration, represents the river bottom elevation, represents the surface roughness coefficient, , n represents the Manning coefficient.

[0049] In some embodiments, the process of coupling temporary drainage of flood-prone areas to a two-dimensional surface hydrodynamic model based on flood control response data comprises the following steps: First, the pumping efficiency of the portable pumps installed at the flood-prone points is determined based on the flood control response data, and the pumping efficiency of the portable pumps is converted into the grid drainage in the two-dimensional surface hydrodynamic model, and coupled based on the grid drainage equivalent substitution method. Among them, the grid drainage equivalent substitution method can represent the technical method used to simulate the impact of drainage facilities on water flow and water accumulation in the hydrodynamic model. By converting the actual drainage capacity and effect of the drainage facilities into grid parameters in the model, the hydrodynamic model can effectively reflect the regulatory effect of drainage measures on waterlogging under different scenarios. Specifically, a temporary portable pump can be selected as an emergency drainage device, and its drainage capacity parameters can be established, including flow rate, opening conditions and working efficiency. Then, the grid drainage equivalent substitution method is applied to convert the drainage effect of the portable pump into the water flow input in the two-dimensional surface hydrodynamic model. By adjusting the hydrodynamic parameters in the model, the dynamic discharge of accumulated water by the portable pump can be achieved. Among them, the schematic diagram of the portable pump generalization method can be shown as follows Figure 2 As shown, it includes a surface infiltration unit and a hand pump drainage generalization unit.

[0050] Then, the start and stop conditions of the portable pump are determined according to the following formula (1): (1) in, Indicates i The depth of water in a flood-prone area Indicates i How long does water last at a flood-prone spot? Indicates the water depth threshold is enabled. Indicates the threshold for opening the water accumulation duration. Indicates the closing water depth threshold. and Set to 15, Set to 5.

[0051] Next, the grid water depth change is determined according to the following formula (2): (2) in, represents the change in grid water depth, represents the computational flow of the grid cell, l represents the side length of the grid cell, Indicates the model calculation time step.

[0052] Finally, the water depth and flow state of the two-dimensional surface hydrodynamic model are updated according to the operating status of the portable pump and the change of grid water depth.

[0053] In some embodiments, the process of coupling a two-dimensional surface hydrodynamic model with a road flood control drainage vehicle based on flood control response data includes the following steps: First, the operating conditions of the flood control drainage vehicle and the change in grid water depth are determined based on the flood control response data.

[0054] Then, taking the road flood control drainage vehicle as the research object, the focus is on analyzing the movement of the flood control drainage vehicle during waterlogging and its shortest path planning when the road is closed due to waterlogging. The generalization method of the road flood control drainage vehicle is as follows: Figure 3 When the time t = j , the flood control drainage vehicle performs drainage operations at the first intersection, and the change in grid water depth is the same as the drainage effect of the portable pump. After completing the drainage operation at the first intersection, the system will sort the water depth and waterlogging area of ​​key roads to identify the nearest flooded roads that need to be drained. Then, for the path planning of the flood control drainage vehicle, the Dijkstra algorithm is used to calculate the shortest driving path of the flood control drainage vehicle during the waterlogging process. In this process, the time required for the drainage vehicle to reach the drainage operation site will be determined based on the road length and the average vehicle speed. When the time t = j+k When , the flood control drainage vehicle arrives at the nearest flooded road that needs to be drained and starts to drain water. Among them, the mobile path planning of the flood control drainage vehicle can be determined according to the following formula (3): (3) in, T Indicates the operation time of the flood control and drainage vehicle. Z Indicates the main road. C Indicates secondary roads. represents the length of the main road, Indicates the length of the secondary road. represents the average speed of vehicles on the main roads. Indicates the average vehicle speed on secondary roads.

[0055] Finally, the operation progress of the flood control and drainage vehicle is determined based on the mobile path planning, where the operation start condition of the flood control and drainage vehicle can be That is, when the water depth is not less than 50 cm, the flood control drainage vehicle is turned on, and when the water depth is less than 5 cm, the flood control drainage vehicle is turned off. According to the operation progress of the flood control drainage vehicle and the change of grid water depth, the water depth and flow status of the two-dimensional surface hydrodynamic model are updated.

[0056] In some embodiments, the process of coupling the two-dimensional surface hydrodynamic model with engineering scheduling based on flood control response data includes the following steps: First, according to the water conservancy information exchange area, flood control and drainage projects are divided into underground flood control and drainage projects and surface flood control and drainage projects, and the underground flood control and drainage projects and surface flood control and drainage projects are connected by drainage pipe networks. Among them, the water conservancy information exchange area can represent the area where water volume and water level information is exchanged between different water bodies and drainage facilities in urban drainage and flood control management. In this area, the operation status of water flow, rainfall and drainage facilities is dynamically monitored and dispatched through data sharing. Underground flood control and drainage projects can represent flood control and drainage facilities set up underground, including rainwater drainage pumping stations, underground storage reservoirs, drainage pipe networks, etc. Surface flood control and drainage projects can represent flood control and drainage facilities set up on the ground, including river dams, drainage pumping stations, etc.

[0057] Next, by marking the grid cells of the flood control and drainage project, based on the water volume exchange between the two-dimensional surface hydrodynamic model and the pipe network nodes, the coupling of the two-dimensional surface hydrodynamic process, the one-dimensional hydrodynamic process of the rainwater pipe network and the underground flood control and drainage project is realized. Specifically, the specific location of the flood control and drainage project in the model is determined, and the relevant grid cells are marked for subsequent water flow calculations. The vertical water volume exchange mechanism is used to dynamically transfer the water volume between the surface water flow and the rainwater pipe network, so that the two-dimensional hydrodynamic process and the one-dimensional pipe network hydrodynamic process can be effectively coupled, thereby realizing the overall operation optimization of the underground flood control and drainage project.

[0058] Secondly, based on the inner boundary processing method, the surface flood control and drainage project is coupled with the two-dimensional surface hydrodynamic model. The inner boundary processing method is used to enhance the coupling effect, and the flux calculation using the HLLC Riemann solver in the marked grid cell is stopped to avoid unnecessary calculation interference. Instead, the weir flow formula or the discharge of the pump is directly given to accurately calculate the change in water depth in the same time step of the grid cell.

[0059] Then, the flow rate through the gate is determined according to the following formula (4): (4) in, represents the gate flow of a single grid, represents the comprehensive flow coefficient, , B Indicates the grid width, e Indicates the gate opening, Represents the hydraulic head on each grid Finally, the water depth and flow state of the two-dimensional surface hydrodynamic model are updated according to the flow and water depth data.

[0060] In some embodiments, the process of coupling a two-dimensional surface hydrodynamic model with a flood control retaining wall based on flood control response data comprises the following steps: First, analyze the vulnerable buildings and key protective buildings during flood disasters, identify the potential risks of these areas in heavy rain or floods, and determine the locations where emergency flood control retaining walls need to be constructed.

[0061] Next, through Figure 4 The positions marked in the schematic diagram of the coupling method for emergency flood control retaining walls determine the terrain grid numbers where retaining walls need to be added, such as 534, 504, 210, and 30. Among them, vulnerable buildings and key protective buildings are protected by emergency flood control retaining walls, while emergency flood control retaining walls are not required for natural water bodies and low-risk buildings. In the two-dimensional surface hydrodynamic model, the corresponding positions of protective buildings and retaining walls are associated with terrain data to ensure that retaining walls can be accurately located in the correct grid units.

[0062] Then, during the operation of the 2D surface hydrodynamic model, the retaining wall grid is raised to a preset height by reconstructing the terrain grid where the retaining wall is located. Specifically, the terrain grid in the model is adjusted in the area where the retaining wall is located to simulate the effect of an actual retaining wall. This increase in height can effectively prevent water from entering the vulnerable area.

[0063] In addition, the retaining wall is dynamically controlled according to the water depth. When the water depth in the grid exceeds 5 cm, the retaining wall will automatically rise to ensure timely protection when the flood reaches a certain level. At the same time, when the rainfall and drainage events stop, the retaining wall automatically closes, allowing the system to return to normal drainage.

[0064] Next reference Figure 1 In step S120, rainfall data under different scenarios are input into the urban waterlogging process model to obtain waterlogging characteristic data.

[0065] Among them, waterlogging characteristic data can represent a series of key parameters and data used to describe the occurrence, development and impact range of waterlogging in the process of simulating or predicting urban waterlogging. These data usually reflect information such as waterlogging depth, waterlogging area, water flow velocity, flow direction, etc. in urban areas under different rainfall scenarios.

[0066] Specifically, the process of obtaining waterlogging characteristic data includes: First, based on historical rainstorm data, typical rainfall scenarios with different rainfall amounts and types are designed as a supplement. The rainfall scenarios need to cover rainfall patterns under various extreme weather conditions, such as short-term heavy rainfall, continuous rainfall, and intermittent rainfall, etc., to ensure that rainfall patterns of different intensities and durations are covered, so as to provide diverse input conditions for the urban waterlogging process.

[0067] Then, the designed rainfall data under different scenarios are input into the urban waterlogging process model to simulate the waterlogging process in various areas of the city under different rainfall scenarios, including dynamic changes in water accumulation depth, flow velocity and water flow direction.

[0068] Then, the simulation results are processed into regional grids using GIS (Geographic Information System) technology. By dividing the urban area into multiple grid cells, the system can analyze the waterlogging characteristics of each area in a more refined manner, including the depth, area and flow state of water in each grid. This grid processing facilitates the subsequent data extraction and analysis.

[0069] Finally, the extracted grid water depth data under each scenario are integrated to generate waterlogging characteristic data.

[0070] Next reference Figure 1 In step S130, a correlation analysis is performed on the rainfall data and the waterlogging characteristic data, and rainfall parameters related to flood risk are determined from the rainfall data.

[0071] Among them, rainfall parameters can represent a set of key variables used to describe rainfall characteristics and behaviors, which play a vital role in waterlogging risk prediction.

[0072] Specifically, according to the needs of urban waterlogging prediction, a set of rainfall and waterlogging characteristic parameters that may be related to flood risk are initially selected. Rainfall data may include peak rainfall time, peak rainfall, cumulative rainfall, and maximum 2-hour rainfall. Waterlogging characteristic data may include the amount of water accumulated at the maximum waterlogging moment and the total amount of water accumulated.

[0073] Next, rainfall data and waterlogging characteristic data under different scenarios are collected to construct a data set for correlation analysis. The data set should include multiple rainfall events or scenarios, and the above-mentioned preliminary rainfall characteristic parameters and waterlogging characteristic parameters are recorded in each scenario.

[0074] Then, the Pearson correlation coefficient is used to perform correlation analysis on the rainfall characteristic parameters and the waterlogging characteristic parameters. The Pearson correlation coefficient is a statistical method to measure the linear relationship between two variables. The coefficient ranges from -1 to 1, where 1 indicates a complete positive correlation, -1 indicates a complete negative correlation, and 0 indicates no linear correlation. Specifically, the Pearson correlation coefficient of each preliminary rainfall parameter (such as peak rainfall time, cumulative rainfall, etc.) and the waterlogging characteristic (such as waterlogging depth, waterlogging area) is calculated. By analyzing the size of these coefficients, it is determined which rainfall parameters are highly correlated with the waterlogging characteristics. The calculation formula of the Pearson correlation coefficient is shown in formula (5): (5) in, represents the Pearson correlation coefficient, Representation parameters a and b The covariance of Representation parameters a The variance of Representation parameters b The variance of . , , Representation parameters a The mathematical expectation of Representation parameters b The mathematical expectation of Representation parameters ab The mathematical expectation of .

[0075] Finally, according to the results of the correlation analysis, a correlation threshold (such as 0.5 or 0.7) is set to screen out rainfall parameters with higher correlation, and use them as key features for subsequent urban waterlogging prediction model training and optimization.

[0076] Next reference Figure 1 In step S140, sample data is constructed according to rainfall parameters and urban waterlogging characteristic data, and a neural network model is trained based on the sample data to obtain an urban waterlogging prediction model.

[0077] Among them, the urban waterlogging prediction model can represent a model trained using a neural network model based on regional topography, hydrological and meteorological data, flood control response data, rainfall characteristic parameters and waterlogging characteristic data. It is used to predict the occurrence, development and impact range of waterlogging in urban areas under different rainfall scenarios. The model can simulate key waterlogging characteristics such as waterlogging depth, waterlogging area, flow rate and other key areas in the city during rainfall, providing urban managers with decision support for emergency response and disaster prevention and mitigation.

[0078] In some embodiments, sample data is constructed according to rainfall parameters and waterlogging characteristic data, and a neural network model is trained based on the sample data to obtain an urban waterlogging prediction model, which specifically includes the following steps: sample data is constructed according to rainfall parameters and waterlogging characteristic data, and a neural network model is trained based on the sample data to obtain an initial urban waterlogging prediction model; the prediction accuracy of the initial urban waterlogging prediction model is determined, and the prediction accuracy is used as the objective function. The initial urban waterlogging prediction model is optimized based on a particle swarm optimization algorithm that integrates the Sky Eagle optimization operator and the Cauchy-Gaussian mutation operator to obtain an urban waterlogging prediction model.

[0079] Among them, the Aquila Optimizer (AO) is a global optimization search that simulates the flight strategy and hunting process of the eagle. This operator is mainly used to enhance the global search ability of the algorithm during the optimization process to avoid falling into the local optimal solution. The Cauchy-Gaussian mutation operator is a hybrid mutation strategy that combines the characteristics of the Cauchy distribution and the Gaussian distribution. It is used to introduce randomness into the optimization algorithm to jump out of the local optimal solution. The particle swarm optimization algorithm (PSO) is an optimization algorithm that simulates group behavior. It performs global optimization based on the movement of particles in the search space. Each particle represents a candidate solution. The particle continuously updates its speed and position according to its own historical best position and the global best position of the group. The particle swarm optimization algorithm quickly converges to the global optimal solution through information sharing between particles. The prediction accuracy of the model can be analyzed based on evaluation indicators such as the mean absolute percentage error MAPE and the coefficient of determination R2. The initial model of urban waterlogging prediction is optimized based on the particle swarm optimization algorithm that integrates the Sky Eagle optimization operator and the Cauchy-Gauss mutation operator, which improves the performance of the initial model of urban waterlogging prediction in global search and local optimization and enhances the generalization ability of the model.

[0080] The PSO algorithm exhibits good search capabilities and fast convergence speed when solving nonlinear problems. Therefore, it is very suitable for optimizing urban waterlogging prediction models with high timeliness requirements. However, the global search capability of the PSO algorithm is limited, and it is easy to fall into the local optimal trap during the evolutionary iteration process. In order to solve this problem, the algorithm introduces the Sky Eagle optimization operator in the early stage of the iteration to enhance the global search capability; in the later stage of the iteration, the Cauchy-Gauss mutation operator is introduced to help the algorithm jump out of possible local optimal solutions, thereby improving the optimization effect and prediction accuracy of the model. In some embodiments, with prediction accuracy as the objective function, the initial model of urban waterlogging prediction is optimized based on the particle swarm optimization algorithm that integrates the Sky Eagle optimization operator and the Cauchy-Gauss mutation operator to obtain an urban waterlogging prediction model. The flow chart of the particle swarm optimization algorithm can be shown as follows. Figure 5 As shown, the specific steps include: First, the basic framework of the PSO algorithm was constructed to initialize the population, calculate and update the fitness. Each particle was represented as a solution of the initial model of urban flood prediction, and the prediction accuracy was used as the objective function. Based on the basic iterative rules of the particle swarm optimization algorithm, the particle speed and position were updated.

[0081] Then, the Sky Eagle optimization operator is used to improve the global search capability of the particle swarm optimization algorithm, search the global optimal area in advance, and use the Levy flight distribution function to optimize the movement of particles. Specifically, in the early stage of the algorithm, when hour, T Represents the maximum number of iterations. The global search capability of the particle swarm optimization algorithm is improved according to the following formula (6): (6) in, Indicated in t At +1 iteration, the particle position is updated using the SkyEagle optimization operator. represents the search shrinkage factor, Indicated in t The position of the global optimal solution in the iteration, Indicates the moving position when tracking the target. Indicated in t The particle position at the iteration, Represents a function that generates a random number between 0 and 1. Indicates the flight speed when tracking the target. represents the Levy flight distribution function, ,in, s is a fixed constant of 0.01, u and v It follows a Gaussian distribution A random number, is a constant of 1.5.

[0082] Next, the particle swarm optimization algorithm is used to accelerate the iterative search. In response to the optimal solution of the particle swarm not changing after a preset number of iterations, the particles are mutated based on the Cauchy-Gauss mutation operator to jump out of the local optimal solution.

[0083] Specifically, in the later stage of the algorithm, when When the PSO algorithm is used to accelerate the iterative search, t In the iteration, the particle's velocity and position will be updated, where the particle's velocity update process can be expressed by the following formula (7): (7) in, Indicates t +1 The update speed of the particle at iteration 1, Indicates the inertia weight, which is used to control the influence of the current velocity of the particle on the next velocity. Indicates t The current velocity of the particle at iteration , represents the individual learning factor, represents a random number generated in the range [0,1]. represents the individual optimal solution of the particle, Indicates t The position of the particle at the iteration, represents the social learning factor, represents another random number generated in the range [0,1], represents the global optimal solution for all particles, i.e. t The best position found by all particles during the search process at iteration .

[0084] The particle position update process can be expressed by the following formula (8): (8) in, Indicates t +1 The updated position of the particle at iteration 1.

[0085] The Cauchy-Gauss mutation strategy is introduced to improve the global search ability of the algorithm. If the optimal solution of the particle swarm does not change after 5 iterations, the Cauchy-Gauss (CG) operator is used to mutate the current best individual. The mutation process using the CG operator can be expressed by the following formula (9): (9) in, represents the position of the particle after mutation, represents the adaptive parameter of the Cauchy distribution, represents the adaptive parameter of the Gaussian distribution, represents a random factor that follows a Cauchy distribution, represents a random factor that follows a Gaussian distribution.

[0086] Finally, when the iteration termination condition is met, the optimization of the initial model for urban waterlogging prediction is completed, and the urban waterlogging prediction model is obtained.

[0087] The construction method of the urban waterlogging prediction model in the above-mentioned example embodiment, on the one hand, constructs an urban waterlogging process model coupled with an emergency drainage mode based on regional terrain data, hydrological and meteorological data, and flood control response data, which can accurately simulate the dynamic changes of water flow under different terrain conditions, meteorological conditions, and emergency response measures, so that the urban waterlogging process model can fully reflect the dynamic changes of the urban waterlogging process; on the other hand, by inputting different rainfall scenario data, not only can the urban waterlogging process model simulate the waterlogging situation under various rainfall conditions, but also enable the model to flexibly respond to real-time rainfall data, so that the prediction results can timely reflect the current meteorological changes and improve the timeliness of the prediction; on the other hand, through correlation analysis, the rainfall parameters most relevant to the flood risk can be identified, unnecessary data interference can be reduced, and the effectiveness of model training can be improved; in addition, the neural network model is trained by sample data constructed by rainfall parameters and waterlogging feature data, so that the trained urban waterlogging prediction model has strong adaptability and generalization ability. Furthermore, the prediction accuracy of the urban waterlogging prediction model is improved to a certain extent, so that the model can more accurately predict the complex waterlogging process, leaving sufficient lead time for emergency response, and reducing the losses and impacts caused by waterlogging.

[0088] Furthermore, by constructing a two-dimensional surface hydrodynamic model, the water flow dynamics during urban waterlogging are simulated. Combined with emergency measures such as temporary drainage in flood-prone areas, road flood control drainage vehicles, and engineering scheduling, the model can dynamically respond to various emergency drainage measures, improving the accuracy of waterlogging predictions. By using flux vectors and source term vectors for modeling, the model can more accurately describe the movement of water under complex terrain, enhancing the accuracy of predictions and detail processing capabilities; by converting the pumping efficiency of the portable pump into the grid drainage volume in the two-dimensional hydrodynamic model, the impact of temporary drainage measures on waterlogging is simulated, and the dynamic response capability of the model is improved. The start-up and shutdown conditions of the portable pump are judged by the thresholds of water depth and water accumulation time, making the model more intelligent and able to accurately reflect the water level changes in the actual drainage process; through path planning and dynamic calculation of grid water depth changes, the model can make real-time adjustments to the operation of the drainage vehicle and adjust it according to the road. The waterlogging situation optimizes the scheduling of drainage vehicles, reduces the impact of waterlogging on road traffic, and improves the efficiency of urban flood control and drainage systems; by connecting underground flood control and drainage projects with surface flood control and drainage projects through drainage pipe networks, and realizing the coupling of surface two-dimensional hydrodynamic processes with underground drainage pipe networks through water exchange, the synergy of flood control and drainage systems is improved. The model can dynamically simulate the scheduling and operation of underground and surface drainage projects, effectively improving the accuracy of drainage prediction; by using rainfall parameters and waterlogging feature data to construct training samples and train the neural network model, the model can capture complex nonlinear relationships and significantly improve the accuracy of waterlogging prediction; the introduction of the Eagle optimization operator and the Cauchy-Gauss mutation operator in the particle swarm optimization algorithm improves the global search ability and local optimization ability, and prevents the model from falling into the local optimal solution. The particle motion is optimized by the Levy flight distribution function, which improves the search efficiency of the model and accelerates the convergence speed of model training, thereby optimizing the waterlogging prediction model and improving the accuracy and stability of the prediction. The Eagle optimization operator enhances the global search ability of the particle swarm optimization algorithm, enabling it to find the global optimal solution more effectively in the early stage. Combined with the optimization of particle motion using the Levy flight distribution function, the search efficiency of the model in complex high-dimensional search space is further improved, thereby improving the optimization effect of the model and the accuracy of waterlogging prediction.

[0089] Furthermore, in the embodiments of the present disclosure, a method for predicting urban waterlogging is also provided, which specifically includes the following steps: obtaining real-time rainfall parameter data; inputting the real-time rainfall parameter data into an urban waterlogging prediction model to obtain a prediction result of the waterlogging characteristic data corresponding to the current city; wherein the urban waterlogging prediction model is obtained according to the method for constructing the urban waterlogging prediction model in the above-mentioned embodiments.

[0090] It should be noted that, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0091] Next, in the embodiment of the present disclosure, a device for constructing an urban waterlogging prediction model is also provided. Figure 6 As shown in , the construction device 600 of the urban waterlogging prediction model can be composed of a waterlogging model construction module 601, a waterlogging feature determination module 602, a correlation analysis module 603 and a prediction model construction module 604. Among them: the waterlogging model construction module 601 can be used to construct an urban waterlogging process model coupled with an emergency drainage mode based on regional terrain data, hydrological and meteorological data and flood control response data; the waterlogging feature determination module 602 can be used to input rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging feature data; the correlation analysis module 603 can be used to perform correlation analysis on rainfall data and waterlogging feature data, and determine rainfall parameters related to flood risk from rainfall data; the prediction model construction module 604 can be used to construct sample data according to rainfall parameters and waterlogging feature data, and train a neural network model based on the sample data to obtain an urban waterlogging prediction model.

[0092] In the embodiment of the present disclosure, a device for predicting urban waterlogging is also provided. Figure 7 As shown in , the urban waterlogging prediction device 700 may be composed of a data acquisition module 701 and a waterlogging prediction module 702. The data acquisition module 701 may be used to acquire real-time rainfall parameter data; the waterlogging prediction module 702 may be used to input the real-time rainfall parameter data into an urban waterlogging prediction model to obtain a prediction result of waterlogging characteristic data corresponding to the current city; the urban waterlogging prediction model is obtained according to the above-mentioned urban waterlogging prediction model construction method.

[0093] It should be noted that the specific details of each part of the above-mentioned urban waterlogging prediction model construction device have been described in detail in the implementation method of the urban waterlogging prediction model construction method part. The undisclosed details can be found in the implementation method part, and will not be repeated here.

[0094] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above-mentioned method for constructing the urban waterlogging prediction model is also provided.

[0095] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware embodiments, complete software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0096] Refer to the following Figure 8 800 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0097] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include but are not limited to: the at least one processing unit 810, the at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.

[0098] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0099] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 821 and / or a cache memory unit 822 , and may further include a read-only memory unit (ROM) 823 .

[0100] The storage unit 820 may also include a program / utility 824 having a set (at least one) of program modules 825, such program modules 825 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0101] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0102] The electronic device 800 may also communicate with one or more external devices 870 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface 850. In addition, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 through a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0103] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0104] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0105] refer to Fig. 9 As shown, a program product 900 for implementing the method for constructing the urban waterlogging prediction model according to an embodiment of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus, or a device.

[0106] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0107] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0108] Program code for performing operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0109] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0110] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for constructing an urban waterlogging prediction model, characterized in that: include: Based on regional topographic data, hydrological and meteorological data, and flood control response data, an urban waterlogging process model coupled with emergency drainage mode was constructed; Inputting rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data; Performing correlation analysis on the rainfall data and the waterlogging characteristic data, and determining rainfall parameters related to flood risk from the rainfall data; Sample data is constructed according to the rainfall parameters and the urban waterlogging characteristic data, and a neural network model is trained based on the sample data to obtain the urban waterlogging prediction model.

2. The method for constructing an urban waterlogging prediction model according to claim 1, characterized in that: The urban waterlogging process model coupled with the emergency drainage mode is constructed based on regional terrain data, hydrological and meteorological data, and flood control response data, including: Constructing a two-dimensional surface hydrodynamic model based on the regional topographic data and the hydrological and meteorological data; Based on the flood control response data, the two-dimensional surface hydrodynamic model is coupled with temporary drainage of flood-prone areas, road flood control drainage vehicles, engineering scheduling, and flood control retaining walls to obtain the urban waterlogging process model; The two-dimensional surface hydrodynamic model is based on To build, q Indicates flow rate ，F express x The flux vector in the direction, G express y The flux vector in the direction, S represents the source term vector, t Indicates time, x represents the spatial coordinate in the east-west direction, y The spatial coordinate representing the north-south direction; in, q according to to determine; F according to To confirm, G according to To confirm, S according to to determine; h Indicates water depth. u Indicates that water is flowing x Flow rate in direction, v Indicates that water is flowing y Flow rate in direction, g represents the acceleration due to gravity, represents the friction source term, represents the bottom slope source term, i represents the net rain source term generated by rainfall and infiltration, represents the river bottom elevation, Represents the surface roughness coefficient.

3. The method for constructing an urban waterlogging prediction model according to claim 2, characterized in that: The process of coupling the two-dimensional surface hydrodynamic model with temporary drainage of the flood-prone area based on the flood control response data includes: Determine the pumping efficiency of a portable pump installed at a flood-prone point according to the flood control response data, convert the pumping efficiency of the portable pump into a grid drainage volume in the two-dimensional surface hydrodynamic model, and couple based on a grid drainage equivalent substitution method; according to: ； Determine the start-up and shutdown conditions of the portable pump, wherein: Indicates i The depth of water in a flood-prone area Indicates i How long does water last at a flood-prone spot? Indicates the water depth threshold is enabled. Indicates the threshold for opening the water accumulation duration. Indicates the closing water depth threshold; according to: ； Determine the grid depth change, where: represents the change in grid water depth, represents the computational flow of the grid cell, l represents the side length of the grid cell, Indicates the model calculation time step; The water depth and flow state of the two-dimensional surface hydrodynamic model are updated according to the operating state of the portable pump and the change in the grid water depth.

4. The method for constructing an urban waterlogging prediction model according to claim 2, characterized in that: The process of coupling the two-dimensional surface hydrodynamic model with a road flood control drainage vehicle based on the flood control response data includes: Determine the operating conditions of the flood control drainage vehicle and the change in grid water depth according to the flood control response data; The mobile path of the flood control and drainage vehicle is planned according to: ； Determine the operating time of the flood control and drainage vehicle, wherein: T Indicates the operation time of the flood control and drainage vehicle. Z Indicates the main road. C Indicates secondary roads. represents the length of the main road, Indicates the length of the secondary road. represents the average speed of vehicles on the main roads. Indicates the average speed of vehicles on secondary roads; The operation progress of the flood control and drainage vehicle is determined based on the mobile path planning, and the water depth and flow state of the two-dimensional surface hydrodynamic model are updated according to the operation progress of the flood control and drainage vehicle and the change in the grid water depth.

5. The method for constructing an urban waterlogging prediction model according to claim 2, characterized in that: The process of coupling the two-dimensional surface hydrodynamic model with engineering scheduling based on the flood control response data includes: According to the water conservancy information exchange area, the flood control and drainage projects are divided into underground flood control and drainage projects and surface flood control and drainage projects, and the underground flood control and drainage projects and the surface flood control and drainage projects are connected by drainage pipe networks; By marking the grid cells of the flood control and drainage project, based on the water volume exchange between the two-dimensional surface hydrodynamic model and the pipe network nodes, the coupling of the two-dimensional surface hydrodynamic process, the one-dimensional hydrodynamic process of the rainwater pipe network and the underground flood control and drainage project is realized; Based on the inner boundary processing method, the surface flood control and drainage project is coupled with the two-dimensional surface hydrodynamic model; according to: ； Determine the flow rate through the gate, where represents the gate flow of a single grid, represents the comprehensive flow coefficient, B Indicates the grid width, e Indicates the gate opening, represents the hydraulic head on each grid; The water depth and flow state of the two-dimensional surface hydrodynamic model are updated according to the lock flow and water depth data.

6. The method for constructing an urban waterlogging prediction model according to claim 1, characterized in that: The constructing of sample data according to the rainfall parameters and the waterlogging characteristic data, and training a neural network model based on the sample data to obtain the urban waterlogging prediction model includes: The step of constructing sample data according to the rainfall parameters and the waterlogging characteristic data, and training a neural network model based on the sample data to obtain an initial model for urban waterlogging prediction; The prediction accuracy of the initial model for urban waterlogging prediction is determined, and the prediction accuracy is used as the objective function. The initial model for urban waterlogging prediction is optimized based on a particle swarm optimization algorithm that integrates the Sky Eagle optimization operator and the Cauchy-Gaussian mutation operator to obtain the urban waterlogging prediction model.

7. The method for constructing an urban waterlogging prediction model according to claim 6, characterized in that: The method uses the prediction accuracy as the objective function and optimizes the initial model for urban waterlogging prediction based on a particle swarm optimization algorithm that integrates the Sky Eagle optimization operator and the Cauchy-Gauss mutation operator to obtain the urban waterlogging prediction model, including: Representing each particle as a solution of the initial model for urban waterlogging prediction, taking the prediction accuracy as the objective function, and updating the velocity and position of the particle based on the basic iteration rule of the particle swarm optimization algorithm; The Sky Eagle optimization operator is used to improve the global search capability of the particle swarm optimization algorithm, and the global optimal area is searched in advance, and the movement of particles is optimized by using the Levy flight distribution function; The particle swarm optimization algorithm is used to accelerate iterative search, and in response to the optimal solution of the particle swarm not changing after a preset number of iterations, the particles are mutated based on the Cauchy-Gauss mutation operator to jump out of the local optimal solution; When the iteration termination condition is met, the optimization of the initial model for urban waterlogging prediction is completed to obtain the urban waterlogging prediction model.

8. The method for constructing an urban waterlogging prediction model according to claim 7, characterized in that: The method of improving the global search capability of the particle swarm optimization algorithm by using the Sky Eagle optimization operator includes: according to: ； Improve the global search capability of the particle swarm optimization algorithm, wherein, Indicated in t At the +1 iteration, the particle position is updated using the Eagle optimization operator. represents the search shrinkage factor, Indicated in t The position of the global optimal solution in the iteration, Indicates the moving position when tracking the target. Indicated in t The particle position at the iteration, Represents a function that generates a random number between 0 and 1. Indicates the flight speed when tracking the target. represents the Levy flight distribution function.

9. A method for predicting urban waterlogging, characterized in that: include: Get real-time rainfall parameter data; Inputting the real-time rainfall parameter data into the urban waterlogging prediction model to obtain the prediction result of the waterlogging characteristic data corresponding to the current city; Wherein, the urban waterlogging prediction model is obtained according to the method for constructing the urban waterlogging prediction model as described in any one of claims 1-8.

10. A device for constructing an urban waterlogging prediction model, characterized in that: include: The waterlogging model construction module is used to construct an urban waterlogging process model coupled with an emergency drainage mode based on regional terrain data, hydrological and meteorological data, and flood control response data; A waterlogging characteristic determination module, used for inputting rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data; A correlation analysis module, used for performing correlation analysis on the rainfall data and the waterlogging characteristic data, and determining rainfall parameters related to flood risk from the rainfall data; The prediction model building module is used to build sample data according to the rainfall parameters and the urban waterlogging characteristic data, and train the neural network model based on the sample data to obtain the urban waterlogging prediction model.

Images