Construction Method of Urban Waterlogging Prediction Model, Urban Waterlogging Prediction Method and Device

Abstract

The present disclosure provides a method for constructing an urban waterlogging prediction model, an urban waterlogging prediction method and device, relating to the technical field of data processing. The method for constructing an urban waterlogging prediction model includes: constructing an urban waterlogging process model with a coupled emergency drainage mode based on regional terrain data, hydrometeorological data and flood control response data; inputting rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data; performing a correlation analysis on the rainfall data and the waterlogging characteristic data to determine rainfall parameters related to flood risk from the rainfall data; 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 urban waterlogging prediction model. The technical solution in the present disclosure can improve the prediction accuracy of the urban waterlogging prediction model.

Description

Background Art

[0002] With the acceleration of global climate change and urbanization, urban waterlogging has become increasingly frequent, becoming one of the major challenges faced by many cities. Under strong rainfall weather conditions, the load on the urban drainage system increases rapidly, often resulting in road flooding, traffic disruptions, and even posing a serious threat to people's lives and property. To address this issue, in related technologies, prediction models are designed to make accurate early warnings before heavy rain arrives, thus providing a basis for disaster prevention, mitigation, and emergency response.

[0003] However, most existing urban waterlogging prediction methods rely on historical rainfall data. By reviewing historical rainfall events and analyzing their correlation with the occurrence of waterlogging, prediction models are constructed. However, this historical data-based prediction method often ignores factors such as terrain differences in different areas within the city and the layout of the drainage system in the face of the real environment of climate change and the rapid development of urban infrastructure. Simply relying on historical rainfall data cannot accurately predict the occurrence location and water accumulation depth of waterlogging. In addition, most 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 urban waterlogging prediction models in related technologies.

[0004] It should be noted that the information disclosed in the above Background Art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute relevant technologies known to those of ordinary skill in the art. 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 at least to a certain extent improving the prediction accuracy of the urban waterlogging prediction model.

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

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

[0008] In some embodiments of the present disclosure, based on the foregoing solution, the constructing an urban waterlogging process model with a coupled emergency drainage mode based on regional terrain data, hydrometeorological data, and flood control response data includes:

[0009] Constructing a two-dimensional surface water dynamic model based on the regional terrain data and the hydrometeorological data;

[0010] Performing coupling of temporary drainage in flood-prone areas, coupling of flood control drainage vehicles on roads, coupling of engineering scheduling, and coupling of flood control water retaining walls on the two-dimensional surface water dynamic model based on the flood control response data to obtain the urban waterlogging process model;

[0011] The two-dimensional surface water dynamic model is constructed according to for construction, q represents the flow rate ，F represents x the flux vector in the G direction, y represents S the flux vector in the t direction, x represents the spatial coordinate in the east-west direction, y represents the spatial coordinate in the north-south direction;

[0012] Wherein, q is determined according to ; F is determined according to ; G is determined according to ; S is determined according to ; h represents the water depth, u represents the flow velocity of the water flow in the x direction, v represents the flow velocity of the water flow in the y direction, g represents the gravitational acceleration, represents the frictional resistance source term Represents the bottom slope source term, i Represents the net rainfall source term generated by rainfall and infiltration, Represents the river bottom elevation, Represents the surface roughness coefficient.

[0013] In some embodiments of the present disclosure, based on the foregoing solution, the process of coupling the temporary drainage of waterlogging-prone areas to the two-dimensional surface water dynamic model based on the flood control response data includes:

[0014] Determine the pumping efficiency of the portable pump set at the waterlogging-prone point according to the flood control response data, convert the pumping efficiency of the portable pump into the grid drainage volume in the two-dimensional surface water dynamic model, and perform coupling based on the grid drainage equivalent substitution method;

[0015] According to:

[0016] ;

[0017] Determine the opening operation and closing conditions of the portable pump, where, Represents the water depth at the i th waterlogging-prone point, Represents the water accumulation duration at the i th waterlogging-prone point, Represents the opening water depth threshold, Represents the opening water accumulation duration threshold, Represents the closing water depth threshold;

[0018] According to:

[0019] ;

[0020] Determine the grid water depth change amount, where, Represents the grid water depth change amount, Represents the calculated flow rate of the grid cell, l Represents the side length of the grid cell, Represents the model calculation time step;

[0021] Update the water depth and flow rate states of the two-dimensional surface water dynamic model according to the operating state of the portable pump and the grid water depth change amount.

[0022] In some embodiments of the present disclosure, based on the foregoing solution, the process of coupling the road flood control drainage vehicle to the two-dimensional surface water dynamic model based on the flood control response data includes:

[0023] Determine the operating conditions of the flood control drainage vehicle and the grid water depth change amount according to the flood control response data;

[0024] Plan the moving path of the flood control drainage vehicle, according to:

[0025] ;

[0026] Determine the operation time of the flood control and drainage vehicle, where T represents the operation time of the flood control and drainage vehicle, Z represents the arterial road, C represents the secondary arterial road, represents the length of the arterial road, represents the length of the secondary arterial road, represents the average passing vehicle speed of the arterial road, represents the average passing vehicle speed of the secondary arterial road;

[0027] Based on the determined mobile path planning, determine the operation progress of the flood control and drainage vehicle, and update the water depth and flow state of the two-dimensional surface water dynamic model according to the operation progress of the flood control and drainage vehicle and the grid water depth change amount.

[0028] In some embodiments of the present disclosure, based on the foregoing solution, the process of performing engineering scheduling coupling on the two-dimensional surface water dynamic model based on the flood control response data includes:

[0029] According to the water conservancy information exchange area, divide the flood control and drainage projects into underground flood control and drainage projects and surface flood control and drainage projects, and connect the drainage pipe networks of the underground flood control and drainage projects and the surface flood control and drainage projects;

[0030] By marking the grid cells of the flood control and drainage projects, based on the water volume exchange between the two-dimensional surface water dynamic model and the pipe network nodes, realize the coupling of the two-dimensional surface water dynamic process, the one-dimensional water dynamic process of the rainwater pipe network, and the underground flood control and drainage projects;

[0031] Based on the inner boundary treatment method, couple the surface flood control and drainage project with the two-dimensional surface water dynamic model;

[0032] According to:

[0033] ;

[0034] Determine the flow rate through the sluice, where represents the flow rate through the sluice of a single grid, represents the comprehensive flow coefficient, B represents the grid width, e represents the sluice opening, represents the water head on each grid;

[0035] Update the water depth and flow state of the two-dimensional surface water dynamic model according to the flow rate through the sluice and the water depth data.

[0036] In some embodiments of the present disclosure, based on the foregoing solution, 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 the urban waterlogging prediction model includes: 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 urban waterlogging prediction model; determining the prediction accuracy of the initial urban waterlogging prediction model, using the prediction accuracy as an objective function, and optimizing the initial urban waterlogging prediction model based on a particle swarm optimization algorithm that combines an eagle optimization operator and a Cauchy-Gaussian mutation operator to obtain the urban waterlogging prediction model.

[0037] In some embodiments of the present disclosure, based on the foregoing solution, using the prediction accuracy as an objective function and optimizing the initial urban waterlogging prediction model based on a particle swarm optimization algorithm that combines an eagle optimization operator and a Cauchy-Gaussian mutation operator to obtain the urban waterlogging prediction model includes: representing each particle as a solution of the initial urban waterlogging prediction model, using the prediction accuracy as an objective function, and updating the velocity and position of the particle based on the basic iteration rule of the particle swarm optimization algorithm; using the eagle optimization operator to improve the global search ability of the particle swarm optimization algorithm, searching the global optimal region in advance, and simultaneously optimizing the movement of the particle using the Levy flight distribution function; using the particle swarm optimization algorithm to accelerate iterative search, and in response to the optimal solution not changing after a preset number of iterations of the particle swarm, mutating the particle based on the Cauchy-Gaussian mutation operator to jump out of the local optimal solution; when the iteration termination condition is met, completing the optimization of the initial urban waterlogging prediction model to obtain the urban waterlogging prediction model.

[0038] In some embodiments of the present disclosure, based on the foregoing solution, using the eagle optimization operator to improve the global search ability of the particle swarm optimization algorithm includes:

[0039] According to:

[0040] ;

[0041] Improving the global search ability of the particle swarm optimization algorithm, where represents the position of the particle updated by using the eagle optimization operator at the t +1-th iteration, represents the search contraction factor, represents the position of the global optimal solution in the t -th iteration, represents the moving position when tracking the target, represents the position of the particle at the t -th iteration, A function representing a random number between 0 and 1, represents the flight speed when tracking the target, represents the Levy flight distribution function.

[0042] According to a second aspect of the embodiments of the present disclosure, a method for predicting urban waterlogging is provided. The method includes: 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 construction method of the urban waterlogging prediction model as described above.

[0043] According to a third aspect of the embodiments of the present disclosure, a device for constructing an urban waterlogging prediction model is provided. The device includes: a waterlogging model construction module for constructing an urban waterlogging process model with a coupled emergency drainage mode based on regional terrain data, hydro-meteorological data, and flood control response data; a waterlogging characteristic determination module for inputting rainfall data in different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data; a correlation analysis module for performing a correlation analysis on the rainfall data and the waterlogging characteristic data to determine rainfall parameters related to flood risk from the rainfall data; a prediction model construction module for 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 the urban waterlogging prediction model.

[0044] According to a fourth aspect of the embodiments of the present disclosure, an urban waterlogging prediction device is provided. The device includes: 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 construction method of the above urban waterlogging prediction model.

[0045] According to a fifth aspect of the embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory, where computer-readable instructions are stored on the memory, and when the computer-readable instructions are executed by the processor, the construction method of the above urban waterlogging prediction model or the urban waterlogging prediction method is implemented.

[0046] According to a sixth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the construction method of the urban waterlogging prediction model or the urban waterlogging prediction method as described above is implemented.

[0047] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:

[0048] In the construction method of the urban waterlogging prediction model in the exemplary embodiments of the present disclosure, on the one hand, an urban waterlogging process model coupled with an emergency drainage mode is constructed based on regional terrain data, hydrometeorological 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, enabling the urban waterlogging process model to comprehensively 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 conditions under various rainfall conditions, but also the model can flexibly respond to real-time rainfall data, enabling the prediction results to timely reflect the current meteorological changes and improving the timeliness of prediction; on the one hand, through correlation analysis, rainfall parameters most relevant to flood risk can be identified, reducing unnecessary data interference and improving the effectiveness of model training; in addition, the neural network model is trained with sample data constructed from rainfall parameters and waterlogging characteristic data, making the trained urban waterlogging prediction model have strong adaptability and generalization ability. Furthermore, to a certain extent, the prediction accuracy of the urban waterlogging prediction model is improved, enabling the model to more accurately predict complex waterlogging processes, leaving sufficient lead time for emergency response, and reducing the losses and impacts caused by waterlogging.

[0049] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Brief Description of the Drawings

[0050] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0051] Figure 1 The flowchart schematically shows a method for constructing an urban waterlogging prediction model according to some embodiments of the present disclosure.

[0052] Figure 2 The schematic diagram schematically shows a method for generalizing a hand pump according to some embodiments of the present disclosure.

[0053] Figure 3 The schematic diagram schematically shows a method for generalizing a road flood control drainage vehicle according to some embodiments of the present disclosure.

[0054] Figure 4 The schematic diagram schematically shows a method for coupling an emergency flood control water retaining wall according to some embodiments of the present disclosure.

[0055] Figure 5Schematically shows a flowchart of a particle swarm optimization algorithm according to some embodiments of the present disclosure.

[0056] Figure 6 Schematically shows a block diagram of a device for constructing an urban waterlogging prediction model according to some embodiments of the present disclosure.

[0057] Figure 7 Schematically shows a block diagram of an urban waterlogging prediction device according to some embodiments of the present disclosure.

[0058] Figure 8 Schematically shows a structural diagram of a computer system of an electronic device according to some embodiments of the present disclosure.

[0059] Figure 9 Schematically shows a diagram of a computer-readable storage medium according to some embodiments of the present disclosure.

[0060] In the drawings, the same or corresponding reference numerals denote the same or corresponding parts. Detailed Description of Specific Embodiments

[0061] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. On the contrary, they are merely examples of devices and methods consistent with some aspects of this specification as detailed in the appended claims.

[0062] 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 "said" used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0063] It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, such 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 "when" or "while" or "in response to a determination".

[0064] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various 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 thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

[0065] In addition, 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 independent entities. That is, these functional entities can be implemented in the form of software, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0066] With the acceleration of global climate change and urbanization, the phenomenon of urban waterlogging has become increasingly frequent, becoming one of the major challenges faced by many cities around the world. Under heavy rainfall or extreme weather conditions, the load on the urban drainage system increases rapidly, often leading to road flooding, traffic interruptions, and even posing a serious threat to people's lives and property safety. To address this issue, an urban waterlogging prediction model can be used to make accurate early warnings before heavy rain arrives, thereby providing a basis for disaster prevention, mitigation, and emergency response.

[0067] In related technologies, most urban waterlogging prediction methods rely on historical rainfall data. By reviewing historical rainfall events and analyzing their correlation with the occurrence of waterlogging, a prediction model is constructed. However, this prediction method based on historical data shows obvious limitations and deficiencies when facing the real environment of climate change and the rapid development of urban infrastructure:

[0068] First, most existing methods are based on macroscopic rainfall data, ignoring factors such as topographic differences and drainage system layouts in different areas within the city, resulting in insufficient spatial resolution. In a complex urban environment, there are significant differences in surface drainage capabilities and pipe network capacities in different areas. Simply relying on historical rainfall data cannot accurately predict the occurrence locations and waterlogging depths of waterlogging. Second, traditional waterlogging prediction models are mostly static analyses, ignoring the impact of emergency drainage measures (such as the scheduling of drainage trucks and the activation of temporary drainage facilities) on the waterlogging process. In actual disaster prevention management, urban emergency management departments often take various measures to mitigate the impact of waterlogging. Existing prediction models cannot dynamically incorporate these measures into the simulation of the waterlogging process, leading to lags or deviations in the judgment of the waterlogging development trend. Additionally, urban waterlogging is a highly complex non-linear problem, affected by multiple factors such as topography, drainage pipe networks, and rainfall intensity. Existing models have limited capabilities in dealing with these non-linear problems and often fall into local optimal solutions, thus unable to obtain the global optimal solution. Therefore, relevant urban waterlogging prediction models based on historical rainfall data exhibit problems such as insufficient accuracy, low spatial resolution, and poor real-time performance when facing complex urban environments and dynamic emergency responses.

[0069] To solve all or part of the above technical problems in the related art, in the exemplary embodiments of the present disclosure, a method for constructing an urban waterlogging prediction model is first proposed. Figure 1 A schematic flowchart of a method for constructing an urban waterlogging prediction model according to some embodiments of the present disclosure is schematically shown. Refer to Figure 1 As shown, the method for constructing the urban waterlogging prediction model may include the following steps:

[0070] Step S110, constructing an urban waterlogging process model with a coupled emergency drainage mode based on regional topographic data, hydro-meteorological data, and flood control response data;

[0071] Step S120, inputting rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data;

[0072] Step S130, performing a correlation analysis on the rainfall data and the waterlogging characteristic data to determine rainfall parameters related to flood risk from the rainfall data;

[0073] Step S140, 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 urban waterlogging prediction model.

[0074] Specifically, first, a urban waterlogging process model coupled with an emergency drainage mode is constructed based on regional terrain data, hydro-meteorological data, and flood control response data, fully considering the impacts of terrain features, 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, including water depth, waterlogging area, flow velocity, etc., which are used to reflect the waterlogging situation under different rainfall conditions; subsequently, a correlation analysis is performed on the rainfall data and the waterlogging characteristic data to screen out key rainfall parameters related to flood risk, such as rain peak time, peak rainfall, cumulative rainfall, etc., and these parameters will be used as the input of the model; finally, sample data are constructed based on the screened rainfall parameters and the extracted waterlogging characteristic data, and a 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.

[0075] Next, the construction method of the urban waterlogging prediction model in the above exemplary embodiment will be further described.

[0076] In step S110, a urban waterlogging process model coupled with an emergency drainage mode is constructed based on regional terrain data, hydro-meteorological data, and flood control response data.

[0077] Among them, the regional terrain data can represent spatial data describing the surface morphology within the urban area, covering features such as terrain elevation, slope, depression areas, and aspect. It can be presented in the form of a digital elevation model or a topographic map. By using the regional terrain data, the flow direction and velocity of water under different rainfall conditions can be determined, and areas prone to waterlogging can be identified, providing basic support for the simulation of the waterlogging process. The hydrometeorological data can represent meteorological information related to the water cycle, such as rainfall, humidity, wind speed, etc., usually including rainfall amount, rainfall intensity, rain peak time, peak rainfall amount, and rainfall distribution. It can be used to simulate rainfall events under different scenarios. The flood control response data can represent the measures and resource information taken in the waterlogging emergency management to respond to rainstorms or waterlogging events, specifically including emergency drainage equipment (such as pumping stations, temporary drainage pumps), flood control projects (such as river sluices, drainage vehicle dispatching), and historical emergency response data, etc. These data help simulate the dynamic impact of different emergency response measures on the waterlogging process. The emergency drainage mode can represent the drainage strategies and operation methods adopted based on the urban drainage system and emergency facilities during a waterlogging event, including flood control emergency plans, information on temporary drainage and water blocking equipment at waterlogging-prone points, construction locations and emergency operation information of flood control and drainage projects, information and locations of road flood control drainage vehicles, etc. The urban waterlogging process model can represent a mathematical model that comprehensively combines regional terrain data, hydrometeorological data, and flood control response data to dynamically simulate the occurrence, development, and recession process of urban waterlogging under rainstorm conditions. Among them, by combining regional terrain, hydrometeorological, 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 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 dispatching on waterlogging, thereby improving the fitting ability for complex waterlogging scenarios.

[0078] In some embodiments, a urban waterlogging process model coupled with an emergency drainage mode is constructed based on regional terrain data, hydrometeorological data, and flood control response data, specifically including the following steps: constructing a two-dimensional surface water dynamic model based on the regional terrain data and hydrometeorological data; performing coupling of temporary drainage in waterlogging-prone areas, coupling of road flood control drainage vehicles, coupling of project dispatching, and coupling of flood control water retaining walls on the two-dimensional surface water dynamic model based on the flood control response data to obtain the urban waterlogging process model.

[0079] Specifically, a two-dimensional surface water hydrodynamic model can represent a mathematical model used to simulate the movement of surface water flow on a two-dimensional plane, which is used to describe the flow process of water under different topographic conditions. It can use regional topographic data and hydrometeorological data as inputs to calculate hydrodynamic parameters such as waterlogging depth, flow velocity, and flow rate, so as to reflect the urban waterlogging risk under rainfall scenarios. The coupling of temporary drainage in flood-prone areas refers to the combination of a two-dimensional surface water hydrodynamic model with temporary drainage equipment such as hand pumps and temporary drainage pumps introduced in high-risk waterlogging areas to dynamically simulate the impact of the operation of these drainage devices on the waterlogging depth. The coupling of road flood control drainage vehicles can represent the combination of the scheduling and operation process of urban flood control drainage vehicles during waterlogging with a two-dimensional surface water hydrodynamic model to dynamically simulate the movement, drainage operation of drainage vehicles on roads and their impact on waterlogging, including the modeling of drainage vehicle scheduling, movement paths and their drainage capabilities. The coupling of engineering scheduling refers to the combination of the operation scheduling process of underground or surface flood control and drainage projects such as rainwater drainage pumping stations, underground storage tanks, river sluice dams, etc. with a hydrodynamic model to simulate the role of these engineering facilities in drainage, storage and gate operation and their impact on the waterlogging process. The coupling of flood control water retaining walls can represent the combination of temporary or fixed water retaining wall structures with a hydrodynamic model to simulate the use of water retaining walls during rainfall, calculate the blocking effect of water retaining walls on water flow and their impact on the water level change in waterlogging areas.

[0080] In the embodiments of the present disclosure, the two-dimensional surface water hydrodynamic model uses the two-dimensional shallow water equation as the control equation, and the control equation ignores the kinematic viscosity term, turbulent diffusion term, wind stress and Coriolis force, and only considers the friction and bottom slope source terms. Specifically, the two-dimensional surface water hydrodynamic model is constructed according to for construction, q represents the flow rate ，F represents x the flux vector in the G represents y the flux vector in the S represents the source term vector, t represents time, x represents the spatial coordinate in the east-west direction, y represents the spatial coordinate in the north-south direction.

[0081] Furthermore, the flow rate q is determined according to ; x the flux vector in the F is determined according to ; y the flux vector in the G is determined according to ; the source term vector S is determined according to ; h represents the water depth,u represents the flow velocity of the water flow in the x direction, v represents the flow velocity of the water flow in the y direction, g represents the acceleration due to gravity, represents the frictional resistance source term, represents the bottom slope source term, i represents the net rainfall source term generated by rainfall and infiltration, represents the river bottom elevation, represents the surface roughness coefficient, , n represents the Manning coefficient.

[0082] In some embodiments, the process of coupling the temporary drainage of flood-prone areas to the two-dimensional surface water hydrodynamic model based on flood control response data includes the following steps:

[0083] First, determine the pumping efficiency of the portable pump set at the flood-prone point according to the flood control response data, convert the pumping efficiency of the portable pump into the grid drainage volume in the two-dimensional surface water hydrodynamic model, and perform coupling based on the grid drainage equivalent substitution method. Among them, the grid drainage equivalent substitution method can represent the technical method used in the hydrodynamic model to simulate the impact of drainage facilities on water flow and waterlogging. 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 in different scenarios. Specifically, a temporary portable pump can be selected as the emergency drainage equipment, and its drainage capacity parameters, including flow rate, opening conditions, and working efficiency, can be established. Then, applying the grid drainage equivalent substitution method, convert the drainage effect of the portable pump into the water flow input in the two-dimensional surface water hydrodynamic model, and adjust the hydrodynamic parameters in the model to achieve the dynamic discharge of waterlogging by the portable pump. Among them, the schematic diagram of the portable pump generalization method can be as Figure 2 shown, which includes a subsurface infiltration unit and a portable pump drainage generalization unit.

[0084] Then, determine the opening operation and closing conditions of the portable pump according to the following formula (1):

[0085] (1)

[0086] Among them, represents the water depth at the i th flood-prone point, represents the waterlogging duration at the i th flood-prone point, represents the opening water depth threshold, represents the opening waterlogging duration threshold, represents the closing water depth threshold. Exemplarily, and Set to 15, and Set to 5.

[0087] Next, determine the change in grid water depth according to the following formula (2):

[0088] (2)

[0089] Wherein, represents the change in grid water depth, represents the calculated flow rate of the grid cell, l represents the side length of the grid cell, represents the time step of the model calculation.

[0090] Finally, update the water depth and flow rate states of the two-dimensional surface water hydrodynamic model according to the operating state of the portable pump and the change in grid water depth.

[0091] In some embodiments, the process of coupling the two-dimensional surface water hydrodynamic model with a road flood control and drainage vehicle based on flood control response data includes the following steps:

[0092] First, determine the operating conditions of the flood control and drainage vehicle and the change in grid water depth according to the flood control response data.

[0093] Then, taking the road flood control and drainage vehicle as the research object, focus on analyzing the movement of the flood control and drainage vehicle during the waterlogging process and its shortest path planning when the road is closed due to waterlogging. The generalization method of the road flood control and drainage vehicle is as Figure 3 shown. When time t = j , the flood control and drainage vehicle conducts 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 operations at the first intersection, the system will sort the water depth and waterlogging area of the key roads to identify the nearest waterlogged road that needs drainage. Then, for the path planning of the flood control and drainage vehicle, the Dijkstra algorithm is used to calculate the shortest driving path of the flood control and drainage vehicle during the waterlogging process. During this process, the time required for the drainage vehicle to reach the drainage operation location will be determined according to the road length and the average vehicle speed. When time t = j + k , the flood control and drainage vehicle reaches the nearest waterlogged road that needs drainage and starts to conduct drainage. Among them, for the moving path planning of the flood control and drainage vehicle, the operating time of the flood control and drainage vehicle can be determined according to the following formula (3):

[0094] (3)

[0095] Wherein, T represents the operating time of the flood control and drainage vehicle, Z represents the main road, C represents the secondary arterial road, represents the length of the arterial road, represents the length of the secondary arterial road, represents the average passing vehicle speed of the arterial road, represents the average passing vehicle speed of the secondary arterial road.

[0096] Finally, based on the mobile path planning, the operation progress of the flood control and drainage vehicle is determined. Among them, 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 and drainage vehicle starts, and when the water depth is less than 5 cm, the flood control and drainage vehicle closes. According to the operation progress of the flood control and drainage vehicle and the change amount of the grid water depth, the water depth and flow state of the two-dimensional surface water dynamic model are updated.

[0097] In some embodiments, the process of coupling the two-dimensional surface water dynamic model based on flood control response data for engineering scheduling includes the following steps:

[0098] First, 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 drainage pipe networks of the underground flood control and drainage projects and the surface flood control and drainage projects are connected. Among them, the water conservancy information exchange area can represent the area where water volume and water level information are exchanged between different water bodies and drainage facilities in urban drainage and flood control management. In this area, the operation states of water flow, rainfall, and drainage facilities are dynamically monitored and scheduled through data sharing. The underground flood control and drainage project can represent the flood control and drainage facilities set underground, including rainwater drainage pump stations, underground storage reservoirs, drainage pipe networks, etc. The surface flood control and drainage project can represent the flood control and drainage facilities set on the ground, including river sluice dams, drainage pump stations, etc.

[0099] Next, by marking the grid cells of the flood control and drainage projects, based on the water volume exchange between the two-dimensional surface water dynamic model and the pipe network nodes, the coupling of the two-dimensional surface water dynamic process, the one-dimensional water dynamic process of the rainwater pipe network, and the underground flood control and drainage project is realized. Specifically, determine the specific location of the flood control and drainage project in the model, and mark the relevant grid cells for subsequent water flow calculation. Adopt a vertical water volume exchange mechanism to dynamically transfer the water volume between the surface water flow and the rainwater pipe network, so that the two-dimensional water dynamic process and the one-dimensional pipe network water dynamic process can be effectively coupled, and then the overall operation optimization of the underground flood control and drainage project is realized.

[0100] Secondly, based on the internal boundary treatment method, the surface flood control and drainage project is coupled with the two-dimensional surface water dynamic model. Use the internal boundary treatment method to enhance the coupling effect, stop using the HLLC Riemann solver for flux calculation in the marked grid cells to avoid unnecessary calculation interference, but adopt the weir flow formula or directly specify the drainage flow of the pump to accurately calculate the change amount of the water depth in the grid cells within the same time step.

[0101] Then, the flow rate passing through the sluice is determined according to the following formula (4):

[0102] (4)

[0103] Wherein, represents the flow rate passing through the sluice of a single grid, represents the comprehensive flow coefficient, , B represents the grid width, e represents the opening of the gate, represents the water head on each grid

[0104] Finally, the water depth and flow rate states of the two-dimensional surface water hydrodynamic model are updated according to the flow rate passing through the sluice and the water depth data.

[0105] In some embodiments, the process of coupling the flood control retaining wall to the two-dimensional surface water hydrodynamic model based on flood control response data includes the following steps:

[0106] First, analyze the vulnerable buildings and key protected buildings during the flood disaster process, identify the potential risks of these areas in rainstorms or floods, and determine the locations where emergency flood control retaining walls need to be constructed.

[0107] Next, through Figure 4 the positions marked in the schematic diagram of the emergency flood control retaining wall coupling method, determine the terrain grid numbers where the retaining walls need to be added, such as 534, 504, 210, and 30. Among them, vulnerable buildings and key protected buildings are protected by emergency flood control retaining walls, while for natural water bodies and low-risk buildings, emergency flood control retaining walls do not need to be added. In the two-dimensional surface water hydrodynamic model, the corresponding positions of the protected buildings and the retaining walls will be associated with the terrain data to ensure that the retaining walls can be accurately positioned to the correct grid cells.

[0108] Then, during the operation of the two-dimensional surface water hydrodynamic model, reconstruct the terrain grid where the retaining wall is located and raise the retaining wall grid by a preset height. Specifically, the terrain grid in the model is adjusted in the area where the retaining wall is located to simulate the function of the actual retaining wall. This increase in height can effectively prevent water flow from entering the vulnerable area.

[0109] 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, enabling the system to return to the normal drainage state.

[0110] Next, refer to Figure 1, in step S120, rainfall data under different scenarios are input into the urban waterlogging process model to obtain waterlogging characteristic data.

[0111] Among them, the waterlogging characteristic data can represent a series of key parameters and data used to describe the occurrence, development, and influence scope of waterlogging during the simulation or prediction of urban waterlogging. These data usually reflect information such as water accumulation depth, water accumulation area, water flow velocity, and flow direction in the urban area under different rainfall scenarios.

[0112] Specifically, the acquisition process of the waterlogging characteristic data includes:

[0113] First, based on historical rainstorm data, typical rainfall scenarios with different rainfall amounts and rain patterns are designed as supplements. 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 different rainfall patterns with different intensities and durations are covered, so as to provide diverse input conditions for the urban waterlogging process.

[0114] Then, the designed rainfall data under different scenarios are input into the urban waterlogging process model to simulate the waterlogging process in each region of the city under different rainfall scenarios, including dynamic changes such as water accumulation depth, flow velocity, and water flow direction.

[0115] Next, combined with GIS (Geographic Information System) technology, the simulation results are processed by regional grid division. By dividing the urban area into multiple grid units, the system can analyze the waterlogging characteristics of each region more precisely, including the water accumulation depth, area, and water flow state in each grid. This grid division is convenient for subsequent data extraction and analysis.

[0116] Finally, the grid water depth data under each scenario are extracted and integrated to generate waterlogging characteristic data.

[0117] Then refer to Figure 1 , in step S130, a correlation analysis is carried out on the rainfall data and the waterlogging characteristic data to determine the rainfall parameters related to the flood risk from the rainfall data.

[0118] Among them, the rainfall parameters can represent a set of key variables used to describe the characteristics and behaviors of rainfall, and these parameters play a crucial role in flood risk prediction.

[0119] Specifically, according to the needs of urban waterlogging prediction, a group of rainfall and waterlogging characteristic parameters that may be related to the flood risk are initially selected. The rainfall data can include the rain peak time, peak rainfall amount, cumulative rainfall amount, and maximum 2-hour rainfall amount. The waterlogging characteristic data can include the water accumulation amount at the maximum water accumulation moment and the total water accumulation amount, etc.

[0120] Next, collect rainfall data and waterlogging characteristic data under different scenarios to construct a dataset for correlation analysis. This dataset should include multiple rainfall events or scenarios, and record the above-mentioned initially selected rainfall characteristic parameters and waterlogging characteristic parameters for each scenario.

[0121] Then, use the Pearson correlation coefficient to conduct a correlation analysis between the rainfall characteristic parameters and the waterlogging characteristic parameters. The Pearson correlation coefficient is a statistical method for measuring the linear relationship between two variables. The value range of the coefficient is from -1 to 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no linear correlation. Specifically, calculate the Pearson correlation coefficient for each initially selected rainfall parameter (such as rain peak time, cumulative rainfall, etc.) and waterlogging characteristics (such as water accumulation depth, water accumulation area). By analyzing the magnitudes of these coefficients, determine which rainfall parameters are highly correlated with the waterlogging characteristics. Among them, the calculation formula for the Pearson correlation coefficient is shown in Equation (5):

[0122] (5)

[0123] Where, represents the Pearson correlation coefficient, represents the covariance of the parameters a and b ; represents the variance of the parameter a ; represents the variance of the parameter b ; , , represents the mathematical expectation of the parameter a ; represents the mathematical expectation of the parameter b ; represents the mathematical expectation of the parameter ab ;

[0124] Finally, based on the results of the correlation analysis, set a correlation threshold (such as 0.5 or 0.7, etc.), screen out the rainfall parameters with higher correlations, and use them as key features for subsequent training and optimization of the urban waterlogging prediction model.

[0125] Next, refer to Figure 1 , in step S140, construct sample data based on the rainfall parameters and waterlogging characteristic data, and train the neural network model based on the sample data to obtain the urban waterlogging prediction model.

[0126] Among them, the urban waterlogging prediction model can be expressed as a model obtained by training a neural network model based on regional terrain, hydrometeorological data, flood control response data, rainfall characteristic parameters, and waterlogging characteristic data, and is used to predict the occurrence, development, and influence range of urban waterlogging in different rainfall scenarios. This model can simulate key waterlogging characteristics such as water depth, water area, and flow velocity in different urban areas during rainfall, providing decision-making support for urban managers in emergency response and disaster prevention and mitigation.

[0127] In some embodiments, sample data is constructed according to rainfall parameters and waterlogging characteristic data, and the neural network model is trained based on the sample data to obtain an urban waterlogging prediction model. The specific steps are as follows: Sample data is constructed according to rainfall parameters and waterlogging characteristic data, and the neural network model is trained based on the sample data to obtain an initial urban waterlogging prediction model; Determine the prediction accuracy of the initial urban waterlogging prediction model, use the prediction accuracy as the objective function, and optimize the initial urban waterlogging prediction model based on the particle swarm optimization algorithm that combines the Aquila Optimizer (AO) and the Cauchy-Gaussian mutation operator to obtain the urban waterlogging prediction model.

[0128] Among them, the Aquila Optimizer (AO) is a global optimization search method that simulates the flight strategy and hunting process of the Aquila. This operator is mainly used to enhance the global search ability of the algorithm during the optimization process and avoid falling into local optimal solutions. The Cauchy-Gaussian mutation operator is a hybrid mutation strategy that combines the characteristics of the Cauchy distribution and the Gaussian distribution and is used to introduce randomness into the optimization algorithm to jump out of local optimal solutions. The Particle Swarm Optimization (PSO) algorithm is an optimization algorithm that simulates swarm behavior and performs global optimization based on the movement of particles in the search space. Each particle represents a candidate solution, and the particle continuously updates its velocity and position according to its own historical best position and the global best position of the swarm. The PSO algorithm quickly converges to the global optimal solution through information sharing among particles. The prediction accuracy of the model can be analyzed based on evaluation indexes such as the Mean Absolute Percentage Error (MAPE) and the Coefficient of Determination (R2). Optimizing the initial urban waterlogging prediction model based on the particle swarm optimization algorithm that combines the Aquila Optimizer and the Cauchy-Gaussian mutation operator improves the performance of the initial urban waterlogging prediction model in global search and local optimization, and enhances the generalization ability of the model.

[0129] The PSO algorithm exhibits good search ability and fast convergence speed when solving nonlinear problems. Therefore, it is very suitable for optimizing the urban waterlogging process prediction model with high timeliness requirements. However, the global search ability of the PSO algorithm is limited, and it is prone to falling into the local optimal trap during the evolutionary iteration process. To solve this problem, the Tianying optimization operator is introduced at the initial stage of iteration to enhance the global search ability; while in the later stage of iteration, the Cauchy-Gaussian mutation operator is introduced to help the algorithm jump out of the possible local optimal solutions, thereby improving the optimization effect and prediction accuracy of the model. In some embodiments, with the prediction accuracy as the objective function, the particle swarm optimization algorithm integrating the Tianying optimization operator and the Cauchy-Gaussian mutation operator is used to optimize the initial urban waterlogging prediction model to obtain the urban waterlogging prediction model. The flow schematic diagram of the particle swarm optimization algorithm can be as Figure 5 shown, and specifically includes the following steps:

[0130] First, the basic framework of the PSO algorithm is constructed, the population is initialized, and the fitness is calculated and updated. Each particle is represented as a solution of the initial urban waterlogging prediction model. With the prediction accuracy as the objective function, based on the basic iteration rules of the particle swarm optimization algorithm, the velocity and position of the particle are updated.

[0131] Then, the Tianying optimization operator is used to improve the global search ability of the particle swarm optimization algorithm, search the global optimal region in advance, and at the same time use the Levy flight distribution function to optimize the movement of the particle. Specifically, in the early stage of the algorithm, when When T represents the maximum number of iterations, the global search ability of the particle swarm optimization algorithm is improved according to the following formula (6):

[0132] (6)

[0133] Among them, represents the position of the particle updated by the Tianying optimization operator at the t +1-th iteration, represents the search contraction factor, represents the position of the global optimal solution in the t -th iteration, represents the moving position when tracking the target, represents the position of the particle at the t -th iteration, represents the function of generating a random number between 0 and 1, represents the flight speed when tracking the target, represents the Levy flight distribution function, , among which, s is the fixed constant 0.01, u and vis a random number that follows a Gaussian distribution , and the constant is 1.5.

[0134] Next, the particle swarm optimization algorithm is used to accelerate the iterative search. In response to the optimal solution not changing after the preset number of iterations of the particle swarm, the particles are mutated based on the Cauchy-Gaussian mutation operator to jump out of the local optimal solution.

[0135] Specifically, in the later stage of the algorithm, when , the iterative search is accelerated through the PSO algorithm. In the t th iteration, the velocity and position of the particles are updated. Among them, the process of updating the velocity of the particles can be represented by the following formula (7):

[0136] (7)

[0137] where represents the updated velocity of the particle at the t +1th iteration, represents the inertia weight, which is used to control the influence degree of the current velocity of the particle on the next velocity, represents the current velocity of the particle at the t th iteration, represents the individual learning factor, represents a random number generated within the range of [0, 1], represents the individual optimal solution of the particle, represents the position of the particle at the t th iteration, represents the social learning factor, represents another random number generated within the range of [0, 1], represents the global optimal solution of all particles, that is, the best position found by all particles during the search at the t th iteration.

[0138] The process of updating the position of the particle can be represented by the following formula (8):

[0139] (8)

[0140] where represents the updated position of the particle at the t +1th iteration.

[0141] The Cauchy-Gaussian mutation strategy is introduced to improve the global search ability of the algorithm. If the optimal solution does not change after 5 iterations of the particle swarm, the Cauchy-Gauss (CG) operator is used to mutate the current best individual. The mutation process using the CG operator can be represented by the following formula (9):

[0142] (9)

[0143] Among them, represents the position of the mutated particle, represents the adaptive parameter of the Cauchy distribution, represents the adaptive parameter of the Gaussian distribution, represents a random factor subject to the Cauchy distribution, represents a random factor subject to the Gaussian distribution.

[0144] 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.

[0145] For the construction method of the urban waterlogging prediction model in the above exemplary embodiments, on the one hand, based on regional terrain data, hydrometeorological data, and flood control response data, a urban waterlogging process model with a coupled emergency drainage mode is constructed, 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 comprehensively 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 conditions under various rainfall conditions, but also the model can flexibly respond to real-time rainfall data, so that the prediction results can timely reflect the current meteorological changes and improve the timeliness of prediction; on the other hand, through correlation analysis, the rainfall parameters most relevant to the flood risk can be identified, reducing unnecessary data interference and improving the effectiveness of model training; in addition, by training the neural network model with the sample data constructed by rainfall parameters and waterlogging characteristic data, the obtained urban waterlogging prediction model has strong adaptability and generalization ability. Furthermore, to a certain extent, the prediction accuracy of the urban waterlogging prediction model is improved, so that the model can more accurately predict complex waterlogging processes, leaving sufficient lead time for emergency response and reducing the losses and impacts caused by waterlogging.

[0146] Furthermore, by constructing a two-dimensional surface water dynamic model, the water flow dynamics during urban waterlogging are simulated. Combining emergency measures such as temporary drainage in flood-prone areas, road flood control drainage vehicles, and engineering dispatching, the model can dynamically respond to various emergency drainage measures, improving the accuracy of waterlogging prediction. Using flux vector and source term vector modeling enables the model to more accurately describe the movement behavior of water flow under complex terrain, enhancing the prediction accuracy and detail processing ability. By converting the pumping efficiency of the portable pump into the grid drainage volume in the two-dimensional water dynamic model, the impact of temporary drainage measures on waterlogging is simulated, improving the dynamic response ability of the model. By judging the start and stop conditions of the portable pump through the thresholds of water depth and waterlogging duration, the model becomes more intelligent and can accurately reflect the water level changes in the actual drainage process. Through path planning and dynamic calculation of the grid water depth change amount, the model can adjust the operation process of the drainage vehicle in real time and optimize the drainage vehicle dispatching according to the waterlogging situation of the road, reducing the impact of waterlogging on road traffic and improving the efficiency of the urban flood control and drainage system. By connecting the underground flood control and drainage project with the surface flood control and drainage project through the drainage pipe network and realizing the coupling of the two-dimensional surface water dynamic process and the one-dimensional water dynamic process of the underground drainage pipe network through water volume exchange, the synergistic effect of the flood control and drainage system is enhanced. The model can dynamically simulate the dispatching operation of underground and surface drainage projects, effectively improving the drainage prediction accuracy. By using rainfall parameter and waterlogging characteristic data to construct training samples and training the neural network model, the model can capture complex non-linear relationships, significantly improving the accuracy of waterlogging prediction. By introducing the Tianying optimization operator and Cauchy-Gaussian mutation operator into the particle swarm optimization algorithm, the global search ability and local optimization ability are improved, preventing the model from falling into local optimal solutions. By optimizing the particle movement through the Levy flight distribution function, the search efficiency of the model is improved, accelerating the convergence speed of model training, thereby optimizing the waterlogging prediction model and improving the prediction accuracy and stability. The Tianying optimization operator enhances the global search ability of the particle swarm optimization algorithm, enabling it to more effectively find the global optimal solution in the initial stage. Combining the optimization of particle movement by the Levy flight distribution function further improves the search efficiency of the model in the complex high-dimensional search space, thereby enhancing the optimization effect of the model and the accuracy of waterlogging prediction.

[0147] 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 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 construction method of the urban waterlogging prediction model in the above embodiments.

[0148] It should be noted that although the steps of the methods in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all the shown steps must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0149] Next, in the embodiments of the present disclosure, a device for constructing an urban waterlogging prediction model is further provided. Referring to Figure 6 as shown, the device 600 for constructing an urban waterlogging prediction model may be composed of an urban waterlogging model construction module 601, an urban waterlogging feature determination module 602, a correlation analysis module 603, and a prediction model construction module 604. Among them: the urban waterlogging model construction module 601 may be used to construct an urban waterlogging process model coupling an emergency drainage mode based on regional terrain data, hydro-meteorological data, and flood control response data; the urban waterlogging feature determination module 602 may be used to input rainfall data in different scenarios into the urban waterlogging process model to obtain urban waterlogging feature data; the correlation analysis module 603 may be used to perform a correlation analysis on the rainfall data and the urban waterlogging feature data to determine rainfall parameters related to flood risk from the rainfall data; the prediction model construction module 604 may be used to construct sample data based on the rainfall parameters and the urban waterlogging feature data, and train a neural network model based on the sample data to obtain an urban waterlogging prediction model.

[0150] In the embodiments of the present disclosure, an urban waterlogging prediction device is further provided. Referring to Figure 7 as shown, the urban waterlogging prediction device 700 may be composed of a data acquisition module 701 and an urban waterlogging prediction module 702. Among them: the data acquisition module 701 may be used to acquire real-time rainfall parameter data; the urban waterlogging prediction module 702 may be used to input the real-time rainfall parameter data into the urban waterlogging prediction model to obtain a prediction result of the urban waterlogging feature 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.

[0151] It should be noted that the specific details of each part in the above-mentioned device for constructing an urban waterlogging prediction model have been described in detail in the implementation manners of the part of the method for constructing an urban waterlogging prediction model. The details not disclosed can be referred to the implementation manners of the method part, and thus will not be elaborated here.

[0152] In addition, in the exemplary embodiments of the present disclosure, an electronic device capable of implementing the above-mentioned method for constructing an urban waterlogging prediction model is further provided.

[0153] Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, a method, or a program product. Therefore, various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuit", "module", or "system" here.

[0154] Reference is now made to Figure 8 describe the electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The illustrated electronic device 800 is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present disclosure.

[0155] As Figure 8 shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one of the above-mentioned processing units 810, at least one of the above-mentioned storage units 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.

[0156] Among them, the storage unit stores program code, and the program code 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.

[0157] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 821 and / or a cache storage unit 822, and may further include a read-only storage unit (ROM) 823.

[0158] The storage unit 820 may further include a program / utility 824 having a set (at least one) of program modules 825. Such program modules 825 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0159] The bus 830 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0160] The electronic device 800 may also communicate with one or more external devices 870 (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or may communicate with any device (such as a router, a modem, etc.) that enables the electronic device 800 to communicate with one or more other computing devices. Such communication may be carried out through the input / output (I / O) interface 850. Moreover, the electronic device 800 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 860. As shown in the figure, the network adapter 860 communicates with other modules of the electronic device 800 through the bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in combination 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.

[0161] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by the way of software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, and the software product 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, including several 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 embodiments of the present disclosure.

[0162] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium, 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 may also be implemented in the form of a program product, which includes program code. When the program product runs 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.

[0163] Refer to Figure 9 As shown, a program product 900 for implementing the above method for constructing an urban waterlogging prediction model according to an embodiment of the present disclosure is described. It may adopt a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0164] The program product may employ any combination of one or more readable media. The readable media 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, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0165] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0166] The program code for performing the 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 also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed 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.

[0167] Those skilled in the art will readily conceive of 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, which follow the general principles of the present disclosure and include known common general knowledge or conventional technical means in the technical field not disclosed by the present disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0168] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes may be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. A method for constructing an urban waterlogging prediction model, characterized in that, Including: Constructing a two-dimensional surface water hydrodynamic model based on regional terrain data and hydrometeorological data; Carrying out coupling of temporary drainage in waterlogging-prone areas, coupling of flood control drainage vehicles on roads, coupling of project scheduling, and coupling of flood control water retaining walls to the two-dimensional surface water hydrodynamic model based on flood control response data to obtain an urban waterlogging process model; The coupling of flood control drainage vehicles on roads means combining the scheduling and operation process of urban flood control drainage vehicles during waterlogging with the two-dimensional surface water hydrodynamic model to simulate the impact of drainage vehicles on waterlogging accumulation; The coupling of project scheduling refers to combining the operation scheduling process of flood control and drainage projects with the hydrodynamic model; The coupling of flood control water retaining walls means combining the water retaining wall structure with the hydrodynamic model; Inputting rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data; Conducting a correlation analysis on the rainfall data and the waterlogging characteristic data to determine 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; Among them, the two-dimensional surface water hydrodynamic model is constructed according to and q represents the flow rate ，F represents x the flux vector in the G direction, y represents the flux vector in the S direction, t t x represents the spatial coordinate in the east-west direction, y represents the spatial coordinate in the north-south direction; Among them, q It is determined according to ; F It is determined according to ; G It is determined according to ; S It is determined according to ; h represents the water depth, u represents the flow velocity of the water flow in the x direction, v represents the flow velocity of the water flow in the y direction, g represents the acceleration of gravity, represents the frictional resistance source term, represents the bottom slope source term, i represents the net rainfall source term generated by rainfall and infiltration, represents the river bottom elevation, represents the surface roughness coefficient; The process of carrying out coupling of temporary drainage in waterlogging-prone areas to the two-dimensional surface water hydrodynamic model based on the flood control response data includes: Determining the pumping efficiency of the portable pumps set at waterlogging-prone points according to the flood control response data, converting the pumping efficiency of the portable pumps into the grid drainage volume in the two-dimensional surface water hydrodynamic model, and conducting coupling based on the grid drainage equivalent substitution method; According to: ； Determine the opening operation and closing conditions of the hand pump, where represents the water depth of the i th waterlogging-prone point, represents the waterlogging duration of the i th waterlogging-prone point, represents the opening water depth threshold, represents the opening waterlogging duration threshold, represents the closing water depth threshold; According to: ； Determine the change in grid water depth, where, represents the change in grid water depth, represents the calculated flow rate of the grid cell, l represents the side length of the grid cell, represents the time step of the model calculation; Updating the water depth and flow state of the two-dimensional surface water hydrodynamic model according to the operating state of the portable pumps and the change amount of grid water depth.

2. The method for constructing an urban waterlogging prediction model according to claim 1, wherein The process of carrying out coupling of flood control drainage vehicles on roads to the two-dimensional surface water hydrodynamic model based on the flood control response data includes: Determining the operating conditions of the flood control drainage vehicles and the change amount of grid water depth according to the flood control response data; Planning the moving path of the flood control drainage vehicles, according to: ； Determine the operation time of the flood control and drainage vehicle, where, T represents the operation time of the flood control and drainage vehicle, Z represents the arterial road, C represents the secondary arterial road, represents the length of the arterial road, represents the length of the secondary arterial road, represents the average passing vehicle speed of the arterial road, represents the average passing vehicle speed of the secondary arterial road; Determining the operation progress of the flood control drainage vehicles based on the moving path planning, and updating the water depth and flow state of the two-dimensional surface water hydrodynamic model according to the operation progress of the flood control drainage vehicles and the change amount of grid water depth.

3. The method for constructing an urban waterlogging prediction model according to claim 1, wherein The process of carrying out coupling of project scheduling to the two-dimensional surface water hydrodynamic model based on the flood control response data includes: Dividing flood control and drainage projects into underground flood control and drainage projects and surface flood control and drainage projects according to the water conservancy information exchange area, and connecting the drainage pipe networks of the underground flood control and drainage projects and the surface flood control and drainage projects; Realizing the coupling of surface two-dimensional hydrodynamic processes, one-dimensional hydrodynamic processes of rainwater pipe networks, and underground flood control and drainage projects by marking the grid units of flood control and drainage projects and based on the water volume exchange between the two-dimensional surface water hydrodynamic model and the pipe network nodes; Coupling the surface flood control and drainage projects to the two-dimensional surface water hydrodynamic model based on the internal boundary treatment method; According to: ； Determine the flow rate through the sluice, where represents the flow rate through the sluice for a single grid, represents the comprehensive flow coefficient, B represents the grid width, e represents the gate opening, represents the water head on each grid; Updating the water depth and flow state of the two-dimensional surface water hydrodynamic model according to the flow rate through the sluice and water depth data.

4. The method for constructing an urban waterlogging prediction model according to claim 1, wherein 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 the urban waterlogging prediction model, including: 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 urban waterlogging prediction model; Determining the prediction accuracy of the initial urban waterlogging prediction model, taking the prediction accuracy as an objective function, and optimizing the initial urban waterlogging prediction model based on a particle swarm optimization algorithm that combines an eagle optimization operator and a Cauchy-Gaussian mutation operator to obtain the urban waterlogging prediction model.

5. The method for constructing an urban waterlogging prediction model according to claim 4, characterized in that, Taking the prediction accuracy as an objective function, and optimizing the initial urban waterlogging prediction model based on a particle swarm optimization algorithm that combines an eagle optimization operator and a Cauchy-Gaussian mutation operator to obtain the urban waterlogging prediction model, including: Representing each particle as a solution of the initial urban waterlogging prediction model, taking the prediction accuracy as an objective function, and updating the velocity and position of the particle based on the basic iteration rule of the particle swarm optimization algorithm; Using the eagle optimization operator to improve the global search ability of the particle swarm optimization algorithm, searching the global optimal region in advance, and at the same time optimizing the movement of the particle using the Levy flight distribution function; Using the particle swarm optimization algorithm to accelerate iterative search, and in response to the optimal solution not changing after a preset number of iterations of the particle swarm, mutating the particle based on the Cauchy-Gaussian mutation operator to jump out of the local optimal solution; When the iteration termination condition is satisfied, complete the optimization of the initial urban waterlogging prediction model to obtain the urban waterlogging prediction model.

6. The method for constructing the urban waterlogging prediction model according to claim 5, characterized in that, Using the eagle optimization operator to improve the global search ability of the particle swarm optimization algorithm, including: According to: ； Improve the global search ability of the particle swarm optimization algorithm, where represents the position of the particle updated by the eagle optimization operator at the t +1-th iteration, represents the search contraction factor, represents the position of the global optimal solution in the t -th iteration, represents the moving position when tracking the target, represents the position of the particle at the t -th iteration, represents a function that generates a random number between 0 and 1, represents the flight speed when tracking the target, represents the Levy flight distribution function; Using the particle swarm optimization algorithm to accelerate iterative search, and in response to the optimal solution not changing after a preset number of iterations of the particle swarm, mutating the particle based on the Cauchy-Gaussian mutation operator to jump out of the local optimal solution, including: When , the accelerated iterative search is performed by the particle swarm optimization algorithm. In the t -th iteration, the velocity and position of the particle are updated. The process of updating the velocity of the particle is expressed as: Among them, T represents the maximum number of iterations, represents the updated velocity of the particle at the t +1-th iteration, represents the inertia weight, represents the t current velocity of the particle at the -th iteration, represents the individual learning factor, represents a random number generated within the range [0, 1], represents the individual optimal solution of the particle, represents the t position of the particle at the -th iteration, represents the social learning factor, represents another random number generated within the range [0, 1], represents the global optimal solution of all particles; The position update process of the particle is expressed as: Among them, represents t the updated position of the particle at the t +1-th iteration; If the optimal solution does not change after 5 iterations of the particle swarm, use the Cauchy-Gaussian operator to mutate the current best individual, and the mutation process is expressed as: Among them, represents the position of the mutated particle, represents the adaptive parameter of the Cauchy distribution, represents the adaptive parameter of the Gaussian distribution, represents a random factor subject to the Cauchy distribution, represents a random factor subject to the Gaussian distribution.

7. A method for predicting urban waterlogging, characterized in that, Including: Obtaining real-time rainfall parameter data; Inputting the real-time rainfall parameter data into the 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 urban waterlogging prediction model construction method described in any one of claims 1-6.

8. An apparatus for constructing an urban waterlogging prediction model, characterized in that, Including: A waterlogging model construction module, configured to construct a two-dimensional surface water dynamic model based on regional terrain data and hydrometeorological data; perform temporary drainage coupling of waterlogging-prone areas, road flood control drainage vehicle coupling, project scheduling coupling, and flood control retaining wall coupling on the two-dimensional surface water dynamic model based on flood control response data to obtain an urban waterlogging process model; the road flood control drainage vehicle coupling means combining the scheduling and operation process of urban flood control drainage vehicles during waterlogging with the two-dimensional surface water dynamic model to simulate the impact of drainage vehicles on waterlogging accumulation. Engineering scheduling coupling refers to the combination of the operation scheduling process of flood control and drainage projects with the hydrodynamic model; flood control flood wall coupling means the combination of the flood wall structure with the hydrodynamic model; The waterlogging characteristic determination module is used to input rainfall data under different scenarios into the urban waterlogging process model to obtain waterlogging characteristic data; The correlation analysis module is used to perform correlation analysis on the rainfall data and the waterlogging characteristic data, and determine rainfall parameters related to flood risk from the rainfall data; The prediction model construction module is used to construct sample data based on the rainfall parameters and the waterlogging characteristic data, and train a neural network model based on the sample data to obtain the urban waterlogging prediction model; Among them, the two-dimensional surface water hydrodynamic model is constructed according to and q represents the flow rate ，F represents x the flux vector in the G direction, y represents the flux vector in the S direction, t represents the source term vector, x represents the time, y represents the spatial coordinate in the east-west direction; Among them, q According to to determine; F According to to determine, G According to to determine, S According to to determine; h represents the water depth, u represents the flow velocity of the water flow in the x direction, v represents the flow velocity of the water flow in the y direction, g represents the gravitational acceleration, represents the frictional resistance source term, represents the bottom slope source term, i represents the net rainfall source term generated by rainfall and infiltration, represents the river bottom elevation, represents the surface roughness coefficient; The process of coupling the temporary drainage of the flood-prone area to the two-dimensional surface water hydrodynamic model based on the flood control response data includes: Determine the pumping efficiency of the portable pump installed at the flood-prone point according to the flood control response data, convert the pumping efficiency of the portable pump into the grid drainage volume in the two-dimensional surface water hydrodynamic model, and perform coupling based on the grid drainage equivalent substitution method; According to: ； Determine the opening operation and closing conditions of the hand pump, where represents the water depth of the i th waterlogging-prone point, represents the waterlogging duration of the i th waterlogging-prone point, represents the opening water depth threshold, represents the opening waterlogging duration threshold, represents the closing water depth threshold; According to: ； Determine the change in grid water depth, where, represents the change in grid water depth, represents the calculated flow rate of the grid cell, l represents the side length of the grid cell, represents the time step of the model calculation; Update the water depth and flow state of the two-dimensional surface water hydrodynamic model according to the operating state of the portable pump and the change in grid water depth.

Images