Waterlogging prediction method, electronic equipment and medium

Abstract

The embodiment of the invention discloses a waterlogging prediction method, electronic equipment and a medium. The method comprises the following steps: for each candidate region, determining a risk index of the candidate region, and determining a target region from the candidate region according to the risk index; for the target area, determining waterlogging prediction correlation parameters required for waterlogging prediction of the target area; and inputting the waterlogging prediction correlation parameters into the loosely coupled rainstorm flood management model and the two-dimensional hydrodynamic model to obtain a waterlogging prediction result of the target area. According to the scheme, the target region with relatively high risk can be selected in a targeted manner according to the risk index of the candidate region, and the waterlogging condition of the target region is accurately predicted by adopting the loosely coupled rainstorm flood management model and the two-dimensional hydrodynamic model for the target region; therefore, waterlogging prediction can be carried out on the area which needs to be detected urgently in time and efficiently.

Description

Technical Field

[0001] The present application relates to the technical field of waterlogging prediction, and in particular to a waterlogging prediction method, electronic equipment and medium. Background Art

[0002] In the past decade, urban waterlogging has been a serious problem. In response to the problem, relevant departments have proposed the requirements of promoting smart water conservancy construction and improving the level of water conservancy informatization. They require full use of advanced technologies to achieve dynamic monitoring of all elements of water conservancy information, and adopt a variety of means to build an integrated monitoring system to achieve dynamic monitoring and comprehensive perception of water and construction information. They also require network coverage and data connectivity for objects that need to be perceived, and realize monitoring and construction of key targets.

[0003] However, in the current waterlogging prediction scheme, waterlogging prediction is carried out for all regions without targeting, resulting in heavy computing pressure and a large waste of computing resources, which reduces the efficiency and real-time performance of waterlogging prediction, making it difficult to generate waterlogging prediction results in a timely and accurate manner for some areas, thus affecting the timely generation and implementation of subsequent flood control plans, and in severe cases causing waterlogging disasters in the region. Summary of the invention

[0004] The embodiments of the present application provide a waterlogging prediction method, electronic device, and medium, which are used to determine a target area according to the risk index of each candidate area, determine a waterlogging prediction result for the target area, and improve the timeliness and pertinence of the waterlogging prediction.

[0005] According to one aspect of the present application, a method for predicting waterlogging is provided, the method comprising:

[0006] For each candidate area, determining a risk index of the candidate area, and determining a target area from the candidate areas according to the risk index;

[0007] For the target area, determining waterlogging prediction associated parameters required for waterlogging prediction in the target area;

[0008] The waterlogging prediction correlation parameters are input into the loosely coupled storm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction results of the target area.

[0009] According to one aspect of the present application, a waterlogging prediction device is provided, the device comprising:

[0010] A target area determination module, used to determine a risk index of each candidate area, and determine a target area from the candidate areas according to the risk index;

[0011] A waterlogging prediction associated parameter determination module, used to determine the waterlogging prediction associated parameters required for waterlogging prediction of the target area;

[0012] The waterlogging prediction result determination module is used to input the waterlogging prediction related parameters into the loosely coupled rainstorm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction results of the target area.

[0013] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] A memory connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the waterlogging prediction method of any embodiment of the present application.

[0017] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the waterlogging prediction method of any embodiment of the present application when executed by a processor.

[0018] The technical solution of the embodiment of the present application determines the risk index of each candidate area, determines the target area from the candidate area according to the risk index; determines the waterlogging prediction associated parameters required for waterlogging prediction of the target area for the target area; inputs the waterlogging prediction associated parameters into the loosely coupled rainstorm and flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area. The above scheme can selectively select the target area with higher risk according to the risk index of the candidate area, and accurately predict the waterlogging situation of the target area using the loosely coupled rainstorm and flood management model and the two-dimensional hydrodynamic model for the target area, thereby more timely and efficiently predicting waterlogging in the area that urgently needs to be tested.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1A flowchart of a method for predicting waterlogging provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of a rainstorm-related model structure provided in an embodiment of the present application;

[0023] Figure 3 A flowchart of a method for predicting waterlogging provided in another embodiment of the present application;

[0024] Figure 4 A schematic diagram of POI area settings provided in another embodiment of the present application;

[0025] Figure 5 A flowchart of a method for predicting waterlogging provided in another embodiment of the present application;

[0026] Figure 6 This is a schematic diagram of a waterlogging alarm process in another embodiment of the present application;

[0027] Figure 7 This is a schematic diagram of loose coupling of models in another embodiment of the present application;

[0028] Figure 8 A schematic diagram of the structure of a waterlogging prediction device provided in an embodiment of the present application;

[0029] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second", "third", "fourth", "actual", "preset", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Figure 1 This is a flow chart of a waterlogging prediction method provided in an embodiment of the present application. The embodiment of the present application can be applied to the case of selecting a target area for waterlogging prediction. The method can be executed by a waterlogging prediction device, which can be implemented in the form of hardware and / or software, and the waterlogging prediction device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] S110 . Determine a risk index of each candidate region, and determine a target region from the candidate regions according to the risk index.

[0034] The candidate area may be an area divided according to the size, ownership, and location of the area. For example, areas such as schools, hospitals, and communities are divided into candidate areas. The risk index reflects the necessity of waterlogging prediction and waterlogging reminder in the candidate area, and reflects the importance of the candidate area. The risk index of the candidate area can be calculated based on various parameters of the candidate area, such as the distance between the location of the candidate area and the drainage facilities, the population density in the candidate area, the rainfall in the candidate area, etc.

[0035] Specifically, the risk index of each candidate area can be determined, and the target area can be determined from the candidate areas according to the risk index, so as to carry out timely waterlogging prediction and early warning reminders for the target area in a targeted manner, thereby improving the safety of the target area. Other candidate areas are generally areas with lower risk indexes and lower waterlogging risks. Waterlogging prediction can be temporarily not carried out for the candidate areas, or the frequency of waterlogging prediction for other candidate areas can be reduced, thereby reducing unnecessary waste of resources and improving the timeliness and efficiency of waterlogging prediction in the target area.

[0036] S120: For the target area, determine waterlogging prediction associated parameters required for waterlogging prediction of the target area.

[0037] Among them, the waterlogging prediction associated parameters are parameters used for waterlogging prediction of the target area, such as rainfall, temperature, humidity, road information, pipeline information, river channel information, interception wells, pump stations, gate station information, etc. Exemplarily, for the target area, waterlogging prediction of the target area requires the waterlogging prediction associated parameters used for waterlogging prediction in the target area, so as to facilitate waterlogging prediction of the target area.

[0038] The parameters associated with waterlogging prediction can be directly detected and obtained through the detection device set at the front end, and can be obtained from the Internet. For example, the water level, temperature, humidity, etc. of the target area can be obtained through the detection device set at the front end, such as water level sensor, temperature sensor, humidity sensor, etc. Information such as road information, pipeline information, rainfall, etc. can be obtained from the Internet, that is, network data related to the target area can be obtained.

[0039] S130, inputting the waterlogging prediction associated parameters into the loosely coupled rainstorm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area.

[0040] Among them, the Storm Flood Management Model (SWMM model) is a dynamic precipitation-runoff simulation model, which is mainly used to simulate a single precipitation event or long-term water quantity and water quality simulation in the city. Its runoff module comprehensively handles the precipitation, runoff and pollution load occurring in each sub-basin. Its confluence module transmits water through pipe networks, channels, water storage and treatment facilities, water pumps, regulating gates, etc. The model can track and simulate the water quality and quantity of runoff generated by each sub-basin at any time at different time steps, as well as the flow, water depth and water quality of water in each pipe and river. The Storm Flood Management Model is widely used in the planning, analysis and design of storm floods, combined sewers, sewage pipes and other drainage systems in urban areas, and is also widely used in other non-urban areas. The two-dimensional hydrodynamic model (LISFLOOD-FP model) is mainly used to simulate flooding and inundation in river, coastal and estuary floodplains. The model uses a two-dimensional finite difference method to predict on a grid based on a DEM raster, and can predict the time evolution of water depth (inundation) using limited CPU. The LISFLOOD-FP model can simulate unsteady hydrodynamic processes by solving a first-order inertial model based on shallow water equations. By specifying appropriate boundary conditions, the model can perform flood inundation predictions on a grid based on a DEM raster. In practical applications, the LISFLOOD-FP model can adapt well to the simulation of waterlogging in the study area, and the simulation results are basically consistent with the measured data. Loosely coupled is a concept in computer science that describes the relationship between two or more components, modules, or systems. When these components can perform their tasks independently without having a direct impact on each other, the coupling between them is considered loose. Loose coupling means that there are fewer interactions between components and they are easier to modify and replace. In software design, loose coupling is generally considered a better practice because it improves the maintainability and scalability of the code. If the parts of a system are independent of each other, then when one part needs to be changed or updated, there will be less interference with other parts. This helps improve development efficiency because developers can more easily make changes to each part without worrying about affecting other parts.

[0041] In the embodiment of this application, the SWMM model is used to realize the two-dimensional runoff and pipe network hydrodynamic simulation of the urban land surface. It realizes effective simulation of rainfall, surface runoff, drainage pipe network runoff and water quality, and is widely used in urban drainage pipe network planning and design, waterlogging prediction and warning, and water quality simulation, with high versatility and good simulation ability.

[0042] The SWMM model mainly includes four calculation modules and one service module. The calculation modules are runoff module (Runoff), transport module (Transport), extended transport module (Extran) and storage / treatment module (Storage / Treatment). SWMM simulates different rainfall runoff processes through these calculation modules. The service module is mainly used for post-calculation processing and provides users with statistics, drawing and other services.

[0043] In the specific simulation process, the study area is first divided into multiple sub-catchments, and the surface runoff and confluence calculations are completed for each sub-catchment. The surface runoff is collected by the slope confluence to the pipeline or river for confluence calculation, and then superimposed and calculated to the outlet of the drainage area. The relevant model structure is as follows Figure 2 As shown, it reflects the basic process of rain flood formation.

[0044] The SWMM model supports the calculation of surface runoff and drainage pipe network systems, but it is insufficient in the calculation of surface inundation. Therefore, in order to realize the two-dimensional surface runoff process under surface inundation and the one-dimensional river flood evolution simulation, the LISFLOOD-FP model is selected to simulate urban drainage facilities and ground inundation as well as scenario analysis.

[0045] The LISFLOOD-FP model is a semi-open source two-dimensional hydrodynamic model developed by Paul Bates and Ad De Roo of the University of Bristol in the United Kingdom in 2001. The LISFLOOD-FP model is of average difficulty to build, can simulate waterlogging, and has high computational efficiency. LISFLOOD-FP is widely used abroad, and many researchers use it for research on water flow calculations in rivers and plains. The model provides a variety of solvers to adapt to different simulation requirements and data conditions. However, there are few studies on the LISFLOOD-FP model in China, and researchers often use it to couple with the SWMM model to complete the simulation of urban waterlogging.

[0046] The FISFLOOD-FP model is mainly used for hydrodynamic simulation of one-dimensional river channels and two-dimensional floodplains. Based on the principles of continuity equation and momentum equation, there are two corresponding solution methods.

[0047] For the hydrodynamic simulation of a one-dimensional river channel, the LISFLOOD-FP model uses a simplified one-dimensional Saint-Venant equation based on either a kinematic wave or a diffusion wave model:

[0048]

[0049] S0=S f ;

[0050] Where Q is the flow rate, A is the cross-sectional area, t is the time, and q is the lateral flow rate. In formula (2.2), S0 is the riverbed slope, S f is the friction drop.

[0051] For the hydrodynamic simulation of the two-dimensional floodplain, the flow balance calculation is performed on a single unit grid based on the water exchange balance between adjacent grids:

[0052]

[0053] Where V is the total flow of the unit grid, t is the time, Q up , Q down , Q left and Q right are the flow rates of the upstream, downstream, left and right grid cells adjacent to it; Q ij is the flow rate between the i-th grid and the j-th grid, A ij and R ij are the cross-sectional area and hydraulic radius at the junction of adjacent grid cells i and j, S ij is the water surface slope between adjacent grid cells i and j, and n is the Manning coefficient.

[0054] In an embodiment of the present application, the storm flood management model and the two-dimensional hydrodynamic model can be loosely coupled to achieve the synergy of the two models without affecting each other, and then the internal prediction related parameters are input into the loosely coupled storm flood management model and the two-dimensional hydrodynamic model to realize the waterlogging prediction of the target area and obtain the internal waterlogging prediction result.

[0055] The technical solution of the embodiment of the present application determines the risk index of each candidate area, determines the target area from the candidate area according to the risk index; determines the waterlogging prediction associated parameters required for waterlogging prediction of the target area for the target area; inputs the waterlogging prediction associated parameters into the loosely coupled rainstorm and flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area. The above scheme can selectively select the target area with higher risk according to the risk index of the candidate area, and accurately predict the waterlogging situation of the target area using the loosely coupled rainstorm and flood management model and the two-dimensional hydrodynamic model for the target area, thereby more timely and efficiently predicting waterlogging in the area that urgently needs to be tested.

[0056] Figure 3 This is a flow chart of a method for predicting waterlogging provided by another embodiment of the present application. The present embodiment is optimized based on the above embodiment. For solutions not described in detail in the present embodiment, please refer to the above embodiment. Figure 3 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0057] S210. For each candidate area, obtaining risk impact parameters in the candidate area in real time; wherein the risk impact parameters include at least one of predicted water depth, population density or regional sensitivity, rainfall intensity, emergency response time, robustness index of basic equipment, and geographical environment factors.

[0058] Exemplarily, for each candidate area, a risk impact parameter that affects the waterlogging risk of the candidate area may be obtained and used to calculate the risk index of the candidate area.

[0059] S220. Make the risk index positively correlated with at least one of the predicted water depth, population density or regional sensitivity, and rainfall intensity, and negatively correlated with at least one of the emergency response time, the robustness index of basic equipment, and geographical environment factors, to determine the risk index of the candidate area.

[0060] Exemplarily, the predicted water depth, population density or regional sensitivity or rainfall intensity are all positively correlated with the risk of waterlogging, so the risk index of the candidate area is positively correlated with at least one of the predicted water depth, population density or regional sensitivity and rainfall intensity, that is, when only one of the predicted water depth, population density or regional sensitivity and rainfall intensity is different, the larger the value of the item, the greater the risk index of the candidate area. The emergency response time, the robustness index of basic equipment and geographical environmental factors are all negatively correlated with the risk of waterlogging, so the risk index of the candidate area is negatively correlated with at least one of the emergency response time, the robustness index of basic equipment and geographical environmental factors, that is, when only one of the emergency response time, the robustness index of basic equipment and geographical environmental factors is different, the larger the value of the item, the smaller the risk index of the candidate area, and the risk index of the candidate area is determined accordingly.

[0061] In the embodiment of the present application, the risk index is positively correlated with at least one of the predicted water depth, population density or regional sensitivity, and rainfall intensity, and negatively correlated with at least one of the emergency response time, the robustness index of basic equipment, and the geographical environment factor, and the risk index of the candidate area is determined, including:

[0062] The risk index of the candidate area is determined according to the risk impact parameter based on the following formula:

[0063]

[0064] Among them: RI POIis the risk index of the candidate area. H is the predicted water depth, in meters. D is the population density or regional sensitivity. P is the rainfall intensity, in millimeters per hour. E is the emergency response time, in hours. S is the robustness index of the infrastructure, such as the capacity of the drainage system. F is the geographical environment factor, including topography and / or soil permeability; α, β, κ, δ, ∈, φ are adjustment parameters used to represent the nonlinear and weighted relationship of each risk influencing parameter, γ is the primary adjustment coefficient, and θ is the secondary adjustment coefficient.

[0065] For a general candidate region A:

[0066] Setting parameters: (α=1), (β=1), (κ=0.8), (δ=0.5), (∈=

[0067] 0.5), (φ=0.4), (γ=1) and (θ=1).

[0068] For high-risk areas, such as schools, hospitals, parks, etc.:

[0069] Setting parameters: (α = 0.8), (β = 1.2), (κ = 1), (δ = 0.7), (∈ =

[0070] 0.3), (φ=0.6), (γ=1.2) and (θ=1.1).

[0071] The system dynamically calculates the risk index based on the real-time data of each target area, and automatically updates and releases warning information based on predetermined risk level standards.

[0072] Specifically, in the service function of waterlogging prediction, the detailed functions are as follows: (wherein POI is the area of ​​interest, that is, the target area in the embodiment of the present application). The key POI setting sub-tab mainly displays the content related to POI setting. Figure 4 As shown, the current POI list can be displayed. Users can click Delete POI area to clear the POI list. Click Add POI Area to add a new POI area. Open the Add POI Area window, click the "Select in Map" button, and start drawing a POI rectangular area by left-clicking two points on the map. Right-click the mouse to automatically display the rectangular area range in the IJ range input box in the window. Click the Clear button to clear the rectangular area drawn on the map and the range displayed in the input box for easy redrawing. Then enter the watershed risk level, name, and POI risk level, and click the Confirm button to complete the addition of the POI area. Click the Cancel button to clear the rectangular area drawn on the map and close the pop-up window. As shown in the figure. It should be noted that if the current POI changes, the plan needs to be re-run to generate results for the new conditions.

[0073] S230: Compare the risk index of each candidate area with a preset risk index threshold.

[0074] For example, a preset risk index threshold may be pre-set to indicate a boundary value between a high risk and a low risk, and the risk index of each candidate area is compared with the preset risk index threshold to select a target area with a higher risk.

[0075] S240: If there is a risk index exceeding the preset risk index threshold, the candidate area corresponding to the risk index is used as the target area.

[0076] Exemplarily, if there is a risk index exceeding a preset risk index threshold, it is determined that the candidate area has a greater risk of waterlogging, and the selected area exceeding the preset risk index threshold is used as the target area.

[0077] S250: For the target area, determine waterlogging prediction associated parameters required for waterlogging prediction of the target area.

[0078] S260, inputting the waterlogging prediction associated parameters into the loosely coupled storm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area.

[0079] The embodiment of the present application provides a method for predicting waterlogging, which obtains risk impact parameters in the candidate area in real time; wherein the risk impact parameters include at least one of the predicted water depth, population density or regional sensitivity, rainfall intensity, emergency response time, robustness index of basic equipment and geographical environment factors; the risk index is positively correlated with at least one of the predicted water depth, population density or regional sensitivity and rainfall intensity, and negatively correlated with at least one of the emergency response time, robustness index of basic equipment and geographical environment factors, and the risk index of the candidate area is determined. For the target area, the waterlogging prediction associated parameters required for waterlogging prediction of the target area are determined; the waterlogging prediction associated parameters are input into the loosely coupled rainstorm and flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area. The above scheme can accurately calculate the risk index of each candidate area according to the risk impact parameters related to the risk index, select the area with higher risk as the target area in a targeted manner, and further perform waterlogging prediction and early warning, thereby effectively improving the timeliness and efficiency of waterlogging prediction in the target area with higher risk, and avoiding unnecessary waste of resources.

[0080] Figure 5 This is a flowchart of a method for predicting waterlogging provided by another embodiment of the present application. The present embodiment is optimized based on the above embodiment. For solutions not described in detail in the present embodiment, please refer to the above embodiment. Figure 5 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0081] S310 . Determine a risk index of each candidate region, and determine a target region from the candidate regions according to the risk index.

[0082] S320: For the target area, determine waterlogging prediction associated parameters required for waterlogging prediction of the target area.

[0083] S330. Construct a storm and flood management model according to the generalized data of the pipe network water system, the hydrodynamic module, and the boundary conditions; divide the target area into at least two sub-catchment areas based on the storm and flood management model; calculate the surface runoff and surface confluence of each sub-catchment area; and collect the surface confluence through the slope confluence to the pipe or river for confluence calculation; after superposition, calculate to the outlet of the drainage area to obtain the simulated overflow result; wherein, the generalized data of the pipe network water system includes pipe network river network extraction data, terrain correction data, and condition correction data; and the boundary conditions include precipitation, upstream flow, downstream water level, sewage outlet and pipe network inflow data, and dam, sluice station and pump control data.

[0084] For example, Figure 6 As shown in the figure, for the target area, a storm flood management model, that is, a SWMM model, is constructed according to the generalized data of the pipe network water system, the hydrodynamic module, and the boundary conditions. Based on the storm flood management model, the target area is divided into at least two sub-catchments, and the surface runoff and surface confluence of each sub-catchment are calculated. The surface confluence flows through the slope confluence and is collected into the pipe or river for confluence calculation. After superposition, it is calculated to the outlet of the drainage area to obtain the simulated overflow result.

[0085] S340, inputting the simulated overflow result, the actual elevation data, the roughness data and the maximum elevation data of the target area into a two-dimensional hydrodynamic model to obtain a waterlogging prediction result of the target area.

[0086] For example, the simulated overflow results obtained by the SWMM model are obtained, and then combined with the actual elevation data, roughness data, and maximum elevation data of the target area and input into the two-dimensional hydrodynamic model, such as Figure 7 As shown in the flowchart in , the waterlogging prediction results of the target area are obtained.

[0087] In the embodiment of the present application, before inputting the waterlogging prediction associated parameters into the loosely coupled rainstorm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area, the method further includes:

[0088] The storm flood management model and the two-dimensional hydrodynamic model are independently packaged and connected by calling an executable program or a dynamic link library;

[0089] The waterlogging prediction parameters are input into the loosely coupled stormwater flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction results of the target area, including:

[0090] The backend service creates a process, uses a command line to call an executable program, and calls the storm flood management model to simulate and obtain a simulated overflow result;

[0091] The two-dimensional hydrodynamic model is called, and the simulated overflow result is input into the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area.

[0092] For example, the SWMM model and the LISFLOOD-FP model are two separately packaged models. After encapsulation, the two models can be called through the system call logic to call the executable program to achieve loose coupling. In the actual application process, the backend service creates a process, uses the command line to call the executable program, calls the storm flood management model to simulate the overflow volume, calls the two-dimensional hydrodynamic model, inputs the simulated overflow volume results into the two-dimensional hydrodynamic model, and obtains the waterlogging prediction results of the target area. Figure 7 As shown, the coupling model adopted by the present invention is based on a loose coupling approach. In the loose coupling of the water environment model, the main principle is to encapsulate different water environment models independently, and then connect them by calling executable programs or dynamic link libraries. The loose coupling approach adopted in this article is that after the SWMM model and the LISFLOOD-FP model are encapsulated, the back-end service creates a process, inputs data, and uses the command line to call the executable program to implement the scheduling of the model. In the specific operation process of the model, future rainfall is first predicted and forecasted, and then input into the SWMM model to obtain the overflow of the pipe network, which is then input into the LISFLOOD-FP model, and finally the risk of waterlogging caused by the overflow is evaluated.

[0093] In the embodiment of the present application, the precipitation prediction process includes:

[0094] Obtaining meteorological data within a preset time before the current moment, and inputting the meteorological data into a precipitation prediction model to obtain an initial predicted precipitation;

[0095] Get weather forecast data from weather forecast data;

[0096] The initial predicted precipitation is corrected according to the weather forecast data to obtain a final precipitation.

[0097] For example, the neural network model can be trained in advance based on historical meteorological data to obtain a precipitation prediction model. In actual application, meteorological data within a preset time before the current moment is obtained, and the meteorological data is input into the precipitation prediction model to obtain an initial predicted precipitation. Then, weather forecast data in the weather forecast is obtained, and the initial predicted precipitation is corrected based on the weather forecast data to obtain the final precipitation.

[0098] Specifically, the precipitation prediction model performs time series prediction based on historical meteorological data to obtain hourly rainfall and temperature for the next 1-24 hours. Then, based on the weather forecast data for the next 24 hours released by the meteorological department, the time series prediction results of rainfall and temperature are corrected to obtain the rainfall (mm) and temperature (degrees Celsius) in the basin within the next 24 hours.

[0099] The precipitation prediction model can be based on the LSTM-seq2seq deep learning model to learn the multivariate nonlinear relationship between historical meteorological data, weather forecast data, and future meteorological data. The developed precipitation prediction model can quickly and dynamically simulate the changes in rainfall and temperature based on historical meteorological data and weather forecast data, and realize the rapid, accurate and continuous prediction of hourly rainfall (mm) and hourly temperature (℃) in the basin in the next 24 hours.

[0100] The Seq2Seq model, also known as the Encoder-Decoder model, can be understood as an N×M model. The model consists of two parts: the Encoder is used to encode the sequence information, encoding the sequence information of any length into a vector c. The Decoder is a decoder. After the decoder obtains the context information vector c, it can decode the information and output it as a sequence. The encoder and decoder of LSTM-seq2seq are composed of several LSTM models, and have the long-term memory ability of the LSTM model and the continuous sequence prediction ability of the seq2seq model. In this model, the input sequence is the historical hourly rainfall (mm / h), temperature (℃), humidity, and wind speed (m / s), and the output is the hourly rainfall (mm / h) and temperature (℃) for the next 24 hours.

[0101] Main process:

[0102] Step 1: Time Series Forecasting

[0103] The historical 7-day hourly meteorological data of the weather station stored in the database, including hourly rainfall (mm / h), temperature (℃), humidity, and wind speed (m / s), are read, missing values ​​are processed, outliers are removed, and the data is input into the LSTM-seq2seq deep learning model to obtain the initial forecast values ​​of hourly rainfall and temperature for the next 24 hours.

[0104] Step 2: Get weather forecast data

[0105] According to the weather forecast data interface provided by the meteorological station, obtain the hourly rainfall and temperature forecast values ​​for the next 24 hours.

[0106] Step 3: Optimize and adjust the results

[0107] The initial predicted values ​​of hourly rainfall and temperature for the next 24 hours and weather forecast data are input into the LSTM-seq2seq model to correct and amend the initial prediction results to obtain more accurate predicted values ​​of hourly rainfall (mm) and temperature (℃) in the basin for the next 24 hours.

[0108] In the embodiment of the present application, the construction process of the precipitation prediction model includes:

[0109] Obtain meteorological data in historical time and calculate the difference in precipitation data between two adjacent moments;

[0110] The difference between the meteorological data at the previous moment of two adjacent moments and the precipitation data is used as a training sample and a test sample, and a deep learning model combining a long short-term memory network and a sequence-to-sequence model is trained to obtain a precipitation prediction model.

[0111] Exemplarily, since the function of the precipitation prediction model is to input the current meteorological data to obtain the precipitation at a future moment, the meteorological data in the historical event is obtained during the training stage of the precipitation prediction model, and the difference in precipitation data between two adjacent moments is calculated. The meteorological data of the previous moment of the two adjacent moments is used as sample data, and the difference in precipitation data is used as a label to form training samples and test samples, and the LSTM-seq2seq model is trained to obtain a precipitation prediction model. In the subsequent application process, the current meteorological data is input into the precipitation prediction model to predict the precipitation at the next moment. During the training process, the difference interval of the label data precipitation data can also be extended, so that precipitation data in the future can be predicted.

[0112] The embodiment of the present application provides a method for predicting urban waterlogging, which constructs a storm and flood management model based on the generalized data of the pipe network water system, a hydrodynamic module, and boundary conditions; based on the storm and flood management model, the target area is divided into at least two sub-catchment areas, the surface runoff and surface convergence of each sub-catchment area are calculated, and the surface convergence flows through the slope convergence to the pipeline or river channel for convergence calculation, and then superimposed and calculated to the drainage area outlet to obtain a simulated overflow result; wherein the generalized data of the pipe network water system includes pipe network river network extraction data, terrain correction data, and condition correction data; the boundary conditions include precipitation, upstream flow, downstream water level, sewage outlet and pipe network inflow data, and dam, sluice station and pump control data; the simulated overflow result, the actual elevation data, roughness data, and maximum elevation data of the target area are input into the two-dimensional hydrodynamic model to obtain the urban waterlogging prediction result of the target area. The above scheme can accurately simulate and predict urban waterlogging based on the loosely coupled SWMM model and LISFLOOD-FP model, achieve the goal of urban waterlogging monitoring and early warning, ensure the rapid and timely discovery and treatment of waterlogging hazards, and reduce the economic losses and safety hazards caused by urban waterlogging problems.

[0113] The present application provides a specific implementation method, including:

[0114] Construction of meteorological forecast model

[0115] The LSTM-Seq2Seq rainfall prediction model uses five-minute meteorological observation data from meteorological monitoring stations, including the name of the monitoring station, serial number, monitoring time, rainfall, temperature, relative humidity, and wind speed. The units of the last four meteorological elements are: millimeter, degree Celsius, percentage, and meter per second. The model creates a data set based on meteorological data from June 1, 2022 to July 20, 2023, with a total of 100,786 data. Data preprocessing is a very important part of rainfall forecasting. Unpreprocessed meteorological observation data usually contains a large number of elements that are not related to rainfall, which will interfere with the experimental results and thus cannot ensure the reliability of the experimental results. Therefore, in order to make full use of the existing data and give full play to the effectiveness of experimental data, the original data must be preprocessed. Data preprocessing mainly includes the following three steps.

[0116] (1) Data cleaning. Data cleaning refers to deleting invalid information in the data table. For example, information such as the station name and serial port number in the table is meaningless for rainfall prediction and needs to be deleted. On the other hand, if the ground observation station encounters special weather or machine failure and causes missed measurements, it will lead to missing data and data anomalies. However, if the entire sample is deleted just because of a missing value, a large amount of data will be lost. Therefore, in order to improve the training effect of the model, it is necessary to clean the data, fill in the missing values ​​and reduce the noise. Linear interpolation and mean smoothing are used to fill in the missing data. Linear interpolation refers to the use of a first-order polynomial to interpolate the unknown data in the table. Mean smoothing refers to replacing the original data with data near the abnormal data. This method is easy to operate and fast, and can suppress noise well.

[0117] (2) Rainfall data processing. The rainfall data in the original data is the cumulative rainfall of the day recorded every five minutes. It is reset to zero and recorded again after 24:00 every night, so it cannot be directly applied to the forecast. The rainfall data at the next moment is subtracted from the rainfall data at the current moment. Then the calculation results are matched with other meteorological elements at the current moment to construct a new data set.

[0118] (3) Data standardization. Different elements have different dimensional units, and the levels of various indicators often differ greatly. If the original indicator values ​​are used directly for analysis, the role of indicators with higher values ​​in the comprehensive analysis will be highlighted, and the role of indicators with lower values ​​will be relatively weakened. In order to eliminate the adverse effects of these factors and ensure the reliability of the results, it is necessary to standardize these meteorological elements, remove the unit restrictions of the data, and convert them into dimensionless pure values.

[0119] The specific process of model construction is as follows:

[0120] (1) Obtain data from meteorological monitoring stations. To avoid abnormal and irrelevant data from interfering with model training, perform data cleaning, fill in missing values, and delete irrelevant data. Then, calculate 15-minute rainfall data based on the original data and construct a data set using rainfall data as the prediction label.

[0121] (2) Standardize the dataset and divide it into training set and test set in a ratio of 4:1.

[0122] (3) Forward calculation: The rainfall data set is input into the model. The output after passing through the hidden layer can be written as: Y = {Y1, Y2, ...Y n}, if C t-1 ,h t-1 and x t-1 They represent the hidden layer cell state, hidden layer output and input features at time t-1 respectively. The output of the LSTM hidden layer at time t is as follows:

[0123] ht =LSTM(C t-1 ,h t-1 ,x t-1 );

[0124] (4) Back propagation: In this experiment, the mean square error (MSE) is used as the loss function. The error is calculated based on the predicted value and the measured value of the current LSTM rainfall prediction model. The gradient descent method is used to continuously update the weights and bias of the model, so as to achieve iteration and optimization of the model itself.

[0125] (5) When the number of iterations reaches the preset maximum value or the model error reaches the expected value, the training can be stopped. Then the weights and bias of the model are recorded, and the test set data is input into the model to run and verify the model performance.

[0126] SWMM Model Construction

[0127] Based on the existing urban road network information and image layers, the surface of the study area is divided into 460 catchment units. According to the road width, a pipe network is constructed along the center line of the urban road and a total of 380 sub-pipe segments are reasonably divided. In addition, the open channels of the river in the area are determined by satellite remote sensing images, and the open channels of the river are also divided. Finally, the spatial locations of 187 interception wells, 4 pumping stations and 1 gate station are determined and data are marked based on satellite remote sensing images. Then, the area, pipe section and river section length of each sub-catchment unit are calculated by software, and the average slope of each sub-catchment is obtained by combining the digital elevation model data of the study area, and the pipe sections are divided according to the road width. Considering the actual average width of the road in the study area, the pipe sections are divided into 0.8 meters and 1 meter in diameter; finally, the value range of water sensitive parameters is determined based on literature with similar hydrological conditions to the study area, so as to construct the runoff-pipeline network model.

[0128] LISFLOOD-FP model construction

[0129] Based on the existing urban road network information and image layers, the study area is divided into several grids through generalization, and each grid is used as an independent water catchment calculation unit; based on this grid information, the actual elevation data, roughness data, and maximum elevation data in the study area are generated. The actual elevation data reflects the real elevation information in the study area, including surface elevation, house elevation, river channel elevation and other data; the roughness data defines the roughness value of each grid. Roughness defines the flow velocity state of water on the surface, which reflects the influence of the roughness of the surface on the water flow, and is generally determined by empirical formulas. Considering that the study area is mostly an urban surface environment, the roughness of all grids is uniformly taken as 0.06; the maximum elevation data determines the maximum water depth of the study area, which is usually used as a boundary condition to limit the model to ensure that the model does not overfit. In this project, it is generally set to 10 meters. In addition, the urban flooding model requires the calculation results of the runoff-pipeline model as the operating environment conditions. Therefore, it is necessary to analyze the simulation results of the runoff-pipeline model, mainly the flow simulation results of point sources and non-point sources. By analyzing and transforming these conditional files, the external parameter conditions for the model operation are generated to complete the construction of the LISFLOOD-FP model.

[0130] For the target area, the precipitation is predicted according to the meteorological forecast model, and then the precipitation and other waterlogging prediction related parameters are input into the SWMM model to obtain the simulated overflow results. Then the simulated overflow results, the actual elevation data, roughness data and maximum elevation data of the target area are input into the LISFLOOD-FP model to obtain the waterlogging prediction results of the target area.

[0131] Figure 8 This is a schematic diagram of the structure of a waterlogging prediction device provided in an embodiment of the present application. The device can execute the waterlogging prediction method provided in any embodiment of the present application and has the corresponding functional modules and beneficial effects of the execution method. Figure 8 As shown, the device comprises:

[0132] A target region determination module 410 is used to determine a risk index of each candidate region, and determine a target region from the candidate regions according to the risk index;

[0133] The waterlogging prediction associated parameter determination module 420 is used to determine the waterlogging prediction associated parameters required for waterlogging prediction of the target area.

[0134] The waterlogging prediction result determination module 430 is used to input waterlogging prediction associated parameters into the loosely coupled storm flood management model and the two-dimensional hydrodynamic model to obtain waterlogging prediction results for the target area.

[0135] In the embodiment of the present application, the target area determination module 410 determines the risk index of the candidate area, including:

[0136] Acquiring risk impact parameters in the candidate area in real time; wherein the risk impact parameters include at least one of predicted water depth, population density or regional sensitivity, rainfall intensity, emergency response time, robustness index of basic equipment, and geographical environment factors;

[0137] The risk index is made to be positively correlated with at least one of the predicted water depth, population density or regional sensitivity and rainfall intensity, and negatively correlated with at least one of the emergency response time, the robustness index of basic equipment and geographical environment factors, so as to determine the risk index of the candidate area.

[0138] In the embodiment of the present application, the target area determination module 410 makes the risk index positively correlated with at least one of the predicted water depth, population density or regional sensitivity, and rainfall intensity, and negatively correlated with at least one of the emergency response time, the robustness index of the basic equipment, and the geographical environment factor, and determines the risk index of the candidate area, including:

[0139] The risk index of the candidate area is determined according to the risk impact parameter based on the following formula:

[0140]

[0141] Among them: RI POI is the risk index of the candidate area, H is the predicted water depth, D is the population density or regional sensitivity, P is the rainfall intensity, E is the emergency response time, S is the robustness index of the infrastructure, and F is the geographical environment factor, including topography and / or soil permeability; α, β, κ, δ, ∈, φ are adjustment parameters used to represent the nonlinear and weighted relationship of each risk influencing parameter, γ is the primary adjustment coefficient, and θ is the secondary adjustment coefficient.

[0142] In the embodiment of the present application, the target area determination module 410 determines the target area from the candidate areas according to the risk index, including:

[0143] Compare the risk index of each candidate area with a preset risk index threshold;

[0144] If there is a risk index exceeding the preset risk index threshold, the candidate area corresponding to the risk index is used as the target area.

[0145] In the embodiment of the present application, the waterlogging prediction result determination module 430 inputs the waterlogging prediction associated parameters into the loosely coupled rainstorm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area, including:

[0146] A storm and flood management model is constructed according to the generalized data of the pipe network water system, the hydrodynamic module, and the boundary conditions. Based on the storm and flood management model, the target area is divided into at least two sub-catchment areas, the surface runoff and surface confluence of each sub-catchment area are calculated, and the surface confluence flows through the slope confluence to the pipeline or river channel for confluence calculation, and then superimposed and calculated to the outlet of the drainage area to obtain the simulated overflow result; wherein, the generalized data of the pipe network water system includes pipe network river network extraction data, terrain correction data, and condition correction data; the boundary conditions include precipitation, upstream flow, downstream water level, sewage outlet and pipe network inflow data, and dam, gate station and pump control data;

[0147] The simulated overflow result, the actual elevation data, the roughness data and the maximum elevation data of the target area are input into a two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area.

[0148] In the embodiment of the present application, before the waterlogging prediction result determination module 430 inputs the waterlogging prediction associated parameters into the loosely coupled rainstorm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area, the method further includes:

[0149] The storm flood management model and the two-dimensional hydrodynamic model are independently packaged and connected by calling an executable program or a dynamic link library;

[0150] The waterlogging prediction parameters are input into the loosely coupled stormwater flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction results of the target area, including:

[0151] The backend service creates a process, uses a command line to call an executable program, and calls the storm flood management model to simulate and obtain a simulated overflow result;

[0152] The two-dimensional hydrodynamic model is called, and the simulated overflow result is input into the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area.

[0153] In the embodiment of the present application, the device further includes:

[0154] An initial predicted precipitation determination module is used to obtain meteorological data within a preset time before the current moment, and input the meteorological data into a precipitation prediction model to obtain an initial predicted precipitation;

[0155] A weather forecast data acquisition module is used to acquire weather forecast data from weather forecast data;

[0156] The final precipitation determination module is used to correct the initial predicted precipitation according to the weather forecast data to obtain the final precipitation.

[0157] In the embodiment of the present application, the device further includes:

[0158] The precipitation data difference determination module is used to obtain meteorological data in historical time and calculate the precipitation data difference between two adjacent moments;

[0159] The precipitation prediction model determination module is used to use the difference between the meteorological data at the previous moment of two adjacent moments and the precipitation data as training samples and test samples, train a deep learning model that combines a long short-term memory network and a sequence-to-sequence model, and obtain a precipitation prediction model.

[0160] A waterlogging prediction device provided in an embodiment of the present application can execute a waterlogging prediction method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

[0161] Fig. 9 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0162] like Fig. 9 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0163] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a waterlogging prediction unit 19, such as a network card, a modem, a wireless waterlogging prediction transceiver, etc. The waterlogging prediction unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0164] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the waterlogging prediction method.

[0165] In some embodiments, the waterlogging prediction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the waterlogging prediction unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the waterlogging prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the waterlogging prediction method in any other appropriate manner (e.g., by means of firmware).

[0166] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0167] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable waterlogging prediction device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as an independent software package and partially on a remote machine, or entirely on a remote machine or server.

[0168] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0169] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0170] The systems and techniques described herein may be implemented in a computing system that includes a backend component (e.g., as a data server), or a computing system that includes a middleware component (e.g., an application server), or a computing system that includes a frontend component (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by digital data (e.g., a network) of any form or medium. Examples of networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0171] The computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0172] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the information expected by the technical solution of this application can be achieved, and this document is not limited here.

[0173] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for predicting urban flooding, characterized in that: The method comprises: For each candidate area, determining a risk index of the candidate area, and determining a target area from the candidate areas according to the risk index; For the target area, determining waterlogging prediction associated parameters required for waterlogging prediction in the target area; The waterlogging prediction correlation parameters are input into the loosely coupled storm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction results of the target area.

2. The method according to claim 1, characterized in that Determine the risk index of the candidate area, including: Acquiring risk impact parameters in the candidate area in real time; wherein the risk impact parameters include at least one of predicted water depth, population density or regional sensitivity, rainfall intensity, emergency response time, robustness index of basic equipment, and geographical environment factors; The risk index is made to be positively correlated with at least one of the predicted water depth, population density or regional sensitivity and rainfall intensity, and negatively correlated with at least one of the emergency response time, the robustness index of basic equipment and geographical environment factors, so as to determine the risk index of the candidate area.

3. The method according to claim 2, characterized in that The risk index is made to be positively correlated with at least one of the predicted water depth, population density or regional sensitivity, and rainfall intensity, and negatively correlated with at least one of the emergency response time, the robustness index of basic equipment, and geographical environment factors, and the risk index of the candidate area is determined, including: The risk index of the candidate area is determined according to the risk impact parameter based on the following formula: Among them: RI POI is the risk index of the candidate area, H is the predicted water depth, D is the population density or regional sensitivity, P is the rainfall intensity, E is the emergency response time, S is the robustness index of the infrastructure, and F is the geographical environment factor, including topography and / or soil permeability; α, β, κ, δ, ∈, φ are adjustment parameters used to represent the nonlinear and weighted relationship of each risk influencing parameter, γ is the primary adjustment coefficient, and θ is the secondary adjustment coefficient.

4. The method according to claim 3, characterized in that Determining a target area from the candidate areas according to the risk index includes: Compare the risk index of each candidate area with a preset risk index threshold; If there is a risk index exceeding the preset risk index threshold, the candidate area corresponding to the risk index is used as the target area.

5. The method according to claim 1, characterized in that The waterlogging prediction parameters are input into the loosely coupled stormwater flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction results of the target area, including: A storm and flood management model is constructed according to the generalized data of the pipe network water system, the hydrodynamic module, and the boundary conditions. Based on the storm and flood management model, the target area is divided into at least two sub-catchment areas, the surface runoff and surface confluence of each sub-catchment area are calculated, and the surface confluence flows through the slope confluence to the pipeline or river channel for confluence calculation, and then superimposed and calculated to the outlet of the drainage area to obtain the simulated overflow result; wherein, the generalized data of the pipe network water system includes pipe network river network extraction data, terrain correction data, and condition correction data; the boundary conditions include precipitation, upstream flow, downstream water level, sewage outlet and pipe network inflow data, and dam, gate station and pump control data; The simulated overflow result, the actual elevation data, the roughness data and the maximum elevation data of the target area are input into a two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area.

6. The method according to claim 5, characterized in that Before inputting the waterlogging prediction associated parameters into the loosely coupled storm flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area, the method further includes: The storm flood management model and the two-dimensional hydrodynamic model are independently packaged and connected by calling an executable program or a dynamic link library; The waterlogging prediction parameters are input into the loosely coupled stormwater flood management model and the two-dimensional hydrodynamic model to obtain the waterlogging prediction results of the target area, including: The backend service creates a process, uses a command line to call an executable program, and calls the storm flood management model to simulate and obtain a simulated overflow result; The two-dimensional hydrodynamic model is called, and the simulated overflow result is input into the two-dimensional hydrodynamic model to obtain the waterlogging prediction result of the target area.

7. The method according to claim 5, characterized in that The precipitation prediction process includes: Obtaining meteorological data within a preset time before the current moment, and inputting the meteorological data into a precipitation prediction model to obtain an initial predicted precipitation; Get weather forecast data from weather forecast data; The initial predicted precipitation is corrected according to the weather forecast data to obtain a final precipitation.

8. The method according to claim 6, characterized in that The construction process of the precipitation prediction model includes: Obtain meteorological data in historical time and calculate the difference in precipitation data between two adjacent moments; The difference between the meteorological data at the previous moment of two adjacent moments and the precipitation data is used as a training sample and a test sample, and a deep learning model combining a long short-term memory network and a sequence-to-sequence model is trained to obtain a precipitation prediction model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and A memory connected to the at least one processor for waterlogging prediction; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the waterlogging prediction method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the waterlogging prediction method according to any one of claims 1 to 8 when executed.

Images