Method, system and device for evaluating risk of dike breach flood and storage medium

Abstract

The application discloses a dike breach flood risk assessment method, system, device and storage medium, based on a dike breach mechanism model and data-driven dike breach flood risk assessment, using a dike breach mechanism model to provide a data basis for a machine learning-based dike breach prediction model, using a dike breach prediction model to predict the probability of dike breach, using a pseudo-random number generator to determine whether each sub-dike section occurs breach, updating the boundary conditions of the dike breach mechanism model according to the breach discrimination results of each sub-dike section, and finally obtaining the grid water level and grid flow rate of each flood area grid in the preset future period after multiple cycles, so as to determine the flood risk level of each flood area grid. The application provides a data basis for drawing a dike breach flood risk map, improves the accuracy and reliability of dike breach flood risk assessment, and can be widely applied in the field of artificial intelligence technology.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and particularly relates to a dike breach flood risk assessment method, system, device and storage medium. BACKGROUND

[0002] Under the background of global climate change and intensified human activities, the frequency and intensity of natural disasters are showing a significant upward trend. Among them, dike breach flood, due to its suddenness and destructive power, has become one of the important factors threatening human life and property safety. Dike breach flood not only can instantly destroy homes and cause casualties, but also can cause great impact on society and economy, including damage to infrastructure, reduction of crop yield, water pollution and other long-term effects. In addition, the accelerating urbanization process makes more and more population and assets concentrated in the riverbanks and low-lying areas, further increasing the risk and potential loss of flood disasters.

[0003] In the face of increasingly severe flood threats, a scientific and reasonable risk management strategy is particularly important. Compiling a flood risk map as a core link of preventive measures aims to systematically assess the probability of flood occurrence and the possible damage degree in a specific area, providing decision support for local governments and helping them to develop effective flood control planning and emergency response plans. Flood risk map can not only identify sensitive areas vulnerable to flood, but also provide basis for land use planning, building design standards, evacuation route planning and other aspects, so as to reduce the possibility of future disasters and their negative impacts.

[0004] Dike breach flood simulation is an indispensable part of flood management and risk assessment, which helps to understand the mechanism of flood occurrence, predict the development process of flood and assess its potential impact range. At present, the main simulation method of dike breach flood is based on mechanism model, each method has its characteristics and limitations.

[0005] Based on mechanism model, dike breach flood numerical simulation usually uses fluid mechanics principles to predict the behavior of flood under certain conditions based on known hydrological data and historical flood event records. The advantage of this simulation method is that the calculation process is relatively simple and clear, and it is effective in dealing with deterministic input conditions. However, there are several defects as follows:

[0006] 1) Single assumption: Deterministic simulation often assumes that input parameters (such as rainfall, soil moisture, etc.) are constant and unchanging, while in reality these parameters have great uncertainty, especially in the face of frequent extreme weather events. This assumption may lead to a large deviation between the simulation results and the actual situation.

[0007] 2) Lack of uncertainty handling: Deterministic simulation struggles to accurately reflect the probabilistic nature of flood occurrence due to the neglect of randomness and complexity in natural processes, limiting its prediction accuracy and reliability.

[0008] 3) Poor adaptability: As the environment changes and socio-economic development occurs, the original hydrological conditions will change, and deterministic simulation may not be able to update model parameters in a timely manner to adapt to new situations.

[0009] In summary, the existing embankment breach flood risk assessment scheme has the defect of insufficient accuracy. SUMMARY

[0010] The purpose of the present application is to at least partially solve one of the technical problems existing in the prior art.

[0011] To this end, one purpose of an embodiment of the present application is to provide a method for assessing the risk of embankment breach floods, which improves the accuracy and reliability of embankment breach flood risk assessment.

[0012] Another purpose of an embodiment of the present application is to provide a system for assessing the risk of embankment breach floods.

[0013] In order to achieve the above technical purpose, the technical solution adopted by an embodiment of the present application comprises:

[0014] In a first aspect, an embodiment of the present application provides a method for assessing the risk of embankment breach floods, comprising the following steps:

[0015] Obtaining basic embankment data of a target embankment area, and establishing an embankment breach mechanism model according to the basic embankment data, wherein the embankment breach mechanism model comprises a one-dimensional river water dynamics model and a two-dimensional floodplain water dynamics model;

[0016] Dividing the target embankment area into a plurality of sub-embankment sections and a plurality of floodplain grids, and obtaining import and export water level and flow data of the target embankment area;

[0017] Using the import and export water level and flow data as boundary conditions, performing embankment breach flood simulation on the target embankment area through the embankment breach mechanism model to obtain river water levels and river flow velocities of each sub-embankment section;

[0018] Inputting the river water levels and the river flow velocities into a pre-trained embankment breach prediction model of the target embankment area to obtain breach occurrence probabilities of each sub-embankment section, and determining whether each sub-embankment section has breached through a pseudo-random number generator;

[0019] update the boundary conditions according to the breach identification results of each sub-embankment section, and return to the step of simulating the embankment breach flood in the target embankment region through the embankment breach mechanism model until a preset simulation number is reached, to obtain the grid water level and grid flow velocity of each floodplain grid in a preset future period;

[0020] determine the flood risk level of each floodplain grid according to the grid water level and the grid flow velocity.

[0021] Further, in an embodiment of the present application, the one-dimensional river channel hydrodynamic model is:

[0022]

[0023] wherein t and x respectively represent time and distance, U1 is a vector composed of conservative variables, F is a flux, S1 is a source term, A represents a water cross-section area, Q represents a flow, I1 and I2 respectively represent a hydrostatic pressure term and a side pressure term, g represents a gravitational acceleration, S0 is a bed slope term, S f is a friction term.

[0024] Further, in an embodiment of the present application, the two-dimensional floodplain hydrodynamic model is:

[0025]

[0026] wherein t represents time, U2 is a vector composed of conservative variables, E and G are fluxes in x and y directions respectively, S2 is a source term, h represents a water level, u and v respectively represent water velocities in x and y directions along the water level, q e is a mass source term per unit area, g represents a gravitational acceleration, S 0x and S 0y are bed slope terms in x and y directions respectively, S fx and S fy are friction slopes in x and y directions respectively, and n represents a Manning roughness coefficient.

[0027] Further, in an embodiment of the present application, the one-dimensional river channel hydrodynamic model and the two-dimensional floodplain hydrodynamic model are coupled through a Riemann solver, the Riemann solver is used to solve a breach flow according to water levels and flow velocities on both sides of an embankment, and the breach flow is obtained through the following formula:

[0028] Q b = W b F Riemann (h L ,h R ,u L ,u R )

[0029] wherein Q brepresents breach flow, W b represents breach width, F Riemann represents the Riemann solver, h represents water level, u represents flow rate, and subscripts L and R respectively refer to river and surface two-dimensional units.

[0030] Further, in an embodiment of the present application, the dike breach prediction model is trained by the following steps:

[0031] obtaining dike sample data of a plurality of historical periods of the target dike area and corresponding dike danger states, and determining dike danger labels of each dike sample data according to the dike danger states;

[0032] constructing a training data set according to the dike sample data and the dike danger labels;

[0033] inputting the training data set into a pre-constructed machine learning model to obtain a trained dike breach prediction model;

[0034] wherein the machine learning model is one of a random forest model, a support vector machine model, and a neural network model.

[0035] Further, in an embodiment of the present application, the determination of whether each sub-dike section breaches by the pseudo-random number generator specifically includes:

[0036] generating a random number in the interval [0, 1] by the pseudo-random number generator;

[0037] when the random number is less than the breach occurrence probability, determining that the corresponding sub-dike section breaches;

[0038] when the random number is greater than or equal to the breach occurrence probability, determining that the corresponding sub-dike section does not breach.

[0039] Further, in an embodiment of the present application, the determination of the flood risk level of each flood area grid according to the grid water level and the grid flow rate specifically includes:

[0040] determining a first flood risk value of each flood area grid according to the grid water level and a preset water level threshold;

[0041] determining a second flood risk value of each flood area grid according to the grid flow rate and a preset flow rate threshold;

[0042] weighting and summing the first flood risk value and the second flood risk value according to a preset weighting coefficient to obtain a target flood risk value of each flood area grid, and determining the flood risk level according to the target flood risk value.

[0043] In a second aspect, an embodiment of the present application provides a levee breach flood risk assessment system, comprising:

[0044] A levee breach mechanism model establishing module is configured to acquire basic levee data of a target levee region, and establish a levee breach mechanism model according to the basic levee data, wherein the levee breach mechanism model comprises a one-dimensional river channel hydrodynamic model and a two-dimensional floodplain hydrodynamic model;

[0045] A data acquisition module is configured to divide the target levee region into a plurality of sub-levee sections and a plurality of floodplain grids, and acquire import and export water level and flow data of the target levee region;

[0046] A levee breach flood simulation module is configured to take the import and export water level and flow data as boundary conditions, and simulate levee breach flood of the target levee region by using the levee breach mechanism model, so as to obtain river channel water levels and river channel flow velocities of each sub-levee section;

[0047] A levee breach occurrence discrimination module is configured to input the river channel water levels and the river channel flow velocities into a pre-trained levee breach prediction model of the target levee region, so as to obtain levee breach occurrence probabilities of each sub-levee section, and discriminate whether levee breach occurs in each sub-levee section by using a pseudo-random number generator;

[0048] A grid water level and flow velocity determination module is configured to update boundary conditions according to levee breach discrimination results of each sub-levee section, and return to the step of simulating levee breach flood of the target levee region by using the levee breach mechanism model, until a preset simulation number is reached, so as to obtain grid water levels and grid flow velocities of each floodplain grid in a preset future period;

[0049] A flood risk grade determination module is configured to determine flood risk grades of each floodplain grid according to the grid water levels and the grid flow velocities.

[0050] In a third aspect, an embodiment of the present application provides a levee breach flood risk assessment device, comprising:

[0051] At least one processor;

[0052] At least one memory for storing at least one program;

[0053] When the at least one program is executed by the at least one processor, the at least one processor implements the levee breach flood risk assessment method described above.

[0054] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, wherein a processor executable program is stored, and the processor executable program is used to execute the levee breach flood risk assessment method described above when executed by a processor.

[0055] The advantages and beneficial effects of the present application will be partially given in the following description, partially will become apparent from the following description, or will be understood by the practice of the present application:

[0056] The embodiment of the present application obtains the basic embankment data of the target embankment area, establishes an embankment breach mechanism model according to the basic embankment data, the embankment breach mechanism model including a river one-dimensional water power model and a flood area two-dimensional water power model, divides the target embankment area into multiple sub-embankment sections and multiple flood area grids, and obtains the import and export water level and flow data of the target embankment area, takes the import and export water level and flow data as boundary conditions, simulates the embankment breach flood of the target embankment area through the embankment breach mechanism model, obtains the river water level and river flow velocity of each sub-embankment section, inputs the river water level and river flow velocity into the pre-trained embankment breach prediction model of the target embankment area, obtains the breach occurrence probability of each sub-embankment section, and discriminates whether each sub-embankment section occurs breach through a pseudo-random number generator, updates the boundary conditions according to the breach discrimination results of each sub-embankment section, and returns to the step of simulating the embankment breach flood of the target embankment area through the embankment breach mechanism model until a preset simulation number is reached, obtains the grid water level and grid flow velocity of each flood area grid in a preset future period, and determines the flood risk level of each flood area grid according to the grid water level and grid flow velocity. The embodiment of the present application performs embankment breach flood risk assessment based on the embankment breach mechanism model and data driving, uses the embankment breach mechanism model to provide a data basis for the machine learning-based embankment breach prediction model, uses the embankment breach prediction model to predict the probability of embankment breach, uses the pseudo-random number generator to determine whether each sub-embankment section occurs breach, updates the boundary conditions of the embankment breach mechanism model according to the breach discrimination results of each sub-embankment section, and finally obtains the grid water level and grid flow velocity of each flood area grid in a preset future period after multiple cycles, so that the flood risk level of each flood area grid can be determined, thereby providing a data basis for drawing an embankment breach flood risk map and improving the accuracy and reliability of embankment breach flood risk assessment. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following introduces the drawings needed to be used in the embodiments of the present application as follows, and it should be understood that the drawings in the following introduction are only for the convenience of clearly expressing part of the embodiments in the technical solutions of the present application, and for those skilled in the art, other drawings can also be obtained without paying creative labor on the premise.

[0058] Figure 1 The step flow chart of the embankment breach flood risk assessment method provided by the embodiment of the present application;

[0059] Figure 2 The comparative schematic diagram before and after the embankment breach provided by the embodiment of the present application;

[0060] Figure 3 A schematic diagram of the result of the dike breach flood simulation provided for the embodiment of the present application;

[0061] Figure 4 A structural block diagram of a dike breach flood risk assessment system provided for the embodiment of the present application;

[0062] Figure 5 A structural block diagram of a dike breach flood risk assessment device provided for the embodiment of the present application. DETAILED DESCRIPTION

[0063] The embodiments of the present application will be described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application. For the step numbers in the following embodiments, they are only set for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0064] In the description of the present application, the meaning of multiple is two or more, and if the first, the second is described, it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the sequence of indicated technical features. In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art.

[0065] In recent years, with the development of big data technology and machine learning algorithms, data-driven methods have gradually become one of the effective ways to solve complex system problems. In the field of dike breach flood simulation, data-driven methods also show their unique advantages, especially in dealing with nonlinear relationships, high-dimensional data and uncertainties. Data-driven methods provide new ideas and tools for dike breach flood simulation, which helps to improve the accuracy and reliability of the flood warning system, and has important significance for disaster prevention and reduction. In summary, the integration of mechanism models and data-driven methods to simulate dike breach flood processes and identify flood risks more flexibly and comprehensively is the future development trend. This not only improves people's ability to resist flood disasters, but also helps to promote the development of water resources management towards precision and intelligence.

[0066] Reference Figure 1 The embodiment of the present application provides a dike breach flood risk assessment method, which specifically comprises the following steps:

[0067] S101, acquire the basic embankment data of the target embankment region, and establish an embankment breach mechanism model according to the basic embankment data, wherein the embankment breach mechanism model comprises a river one-dimensional water dynamic model and a flood area two-dimensional water dynamic model;

[0068] S102, divide the target embankment region into a plurality of sub-embankment sections and a plurality of flood area grids, and acquire import and export water level and flow data of the target embankment region;

[0069] S103, use the import and export water level and flow data as boundary conditions, and simulate embankment breach flood of the target embankment region through the embankment breach mechanism model to obtain river water level and river flow rate of each sub-embankment section;

[0070] S104, input the river water level and river flow rate into a pre-trained embankment breach prediction model of the target embankment region to obtain a breach occurrence probability of each sub-embankment section, and determine whether each sub-embankment section breaches through a pseudo-random number generator;

[0071] S105, update the boundary conditions according to the breach determination result of each sub-embankment section, and return to the step of simulating embankment breach flood of the target embankment region through the embankment breach mechanism model until a preset simulation number is reached, to obtain grid water level and grid flow rate of each flood area grid in a preset future period;

[0072] S106, determine the flood risk level of each flood area grid according to the grid water level and the grid flow rate.

[0073] Specifically, the embodiment of the present application performs embankment breach flood risk assessment based on an embankment breach mechanism model and data driving, uses the embankment breach mechanism model to provide a data basis for an embankment breach prediction model based on machine learning, uses the embankment breach prediction model to predict the probability of embankment breach, uses a pseudo-random number generator to determine whether each sub-embankment section breaches, updates the boundary conditions of the embankment breach mechanism model according to the breach determination result of each sub-embankment section, and finally obtains the grid water level and the grid flow rate of each flood area grid in a preset future period after multiple cycles, so as to determine the flood risk level of each flood area grid, thereby providing a data basis for drawing an embankment breach flood risk map and improving the accuracy and reliability of embankment breach flood risk assessment.

[0074] In some optional embodiments, the river one-dimensional water dynamic model uses a Godunov format finite volume method to solve one-dimensional Saint-Venant equation sets to simulate water level and flow of each section in the river. The flood area two-dimensional water dynamic model uses a Godunov format finite volume method to solve two-dimensional shallow water equations to simulate water level and flow in the two-dimensional grid of the flood area. The one-dimensional model and the two-dimensional model are coupled by using an improved Riemann solver.

[0075] Further as an optional implementation, the river one-dimensional water dynamic model is:

[0076]

[0077] where t and x represent time and distance respectively, U1 is a vector of conservative variables, F is a flux, S1 is a source term, A represents cross-sectional area of water, Q represents flow rate, I1 and I2 represent static pressure term and side pressure term respectively, g represents gravitational acceleration, S0 is a bottom slope term, S f is a friction term.

[0078] Specifically, the one-dimensional river water dynamic model control equation is Saint-Venant equation set, and for natural river shallow water equation with irregular cross-section characteristics, the conservation form is as follows:

[0079]

[0080] In the formula, t and x represent time and distance respectively; U1 is a vector of conservative variables, F is a flux, S1 is a source term. The specific form of each vector is as follows:

[0081]

[0082] In the formula, A is cross-sectional area of water; Q is flow rate; I1 and I2 are static pressure term and side pressure term respectively; g is gravitational acceleration; S0 is a bottom slope term, S f is a friction term = n 2 Q|Q| / (A 2 R 43 ).

[0083] Further as an optional implementation, the two-dimensional water dynamic model of flood area is as follows:

[0084]

[0085] where t represents time, U2 is a vector of conservative variables, E and G are fluxes in x and y directions respectively, S2 is a source term, h represents water level, u and v represent water flow velocities in x and y directions respectively, q e is a mass source term per unit area, g represents gravitational acceleration, S 0x and S 0y are bottom slope terms in x and y directions respectively, S fx and S fy are friction slopes in x and y directions respectively, and n represents Manning roughness coefficient.

[0086] Specifically, the two-dimensional water dynamic model control equation of flood area is composed of mass conservation equation and momentum conservation equations in x and y directions, and the conservation form is as follows:

[0087]

[0088] wherein: U2 is a vector of conservative variables; E and G are fluxes in x and y directions; S2 is a source term, mainly including mass source term S e and bottom slope term S b , friction term S f , and momentum source term, the specific form of the above vector is:

[0089]

[0090] wherein: h is water level; u and v are flow velocities in x and y directions averaged along water level; q e is mass source term per unit area, mainly including rainfall, infiltration, rainwater outlet flow, overflow, etc.; g is gravitational acceleration; bottom slope terms S 0x and S 0y reflect terrain changes in x and y directions; S fx and S fy are friction slopes in x and y directions, which are calculated by Manning formula here:

[0091]

[0092] wherein: n is Manning roughness coefficient.

[0093] Further as an optional implementation, the one-dimensional water power model of the river channel and the two-dimensional water power model of the flood area are coupled through a Riemann solver, the Riemann solver is used to solve breach flow according to water levels and flow velocities on both sides of the dike, and the breach flow is obtained by the following formula:

[0094] Q b = W b F Riemann (h L ,h R ,u L ,u R )

[0095] wherein: Q b represents breach flow, W b represents breach width, F Riemann represents the Riemann solver, h represents water level, and u represents flow velocity, and subscripts L and R respectively represent river channel and ground two-dimensional units.

[0096] Specifically, the improved Riemann solver of the embodiment of the present application has the following characteristics: using HLLC, HLL, Roe and other approximate Riemann operators to solve numerical flux according to water levels and flow velocities on both sides of the dike;

[0097] Q b = W b F Riemann (h L ,h R ,uL ,u R )

[0098] wherein Q b is breach flow rate; W b is breach width; F Riemann is Riemann solver, which can be any common Riemann solver; h is water level, and u is flow velocity; subscripts L and R respectively represent riverway and ground surface two-dimensional units.

[0099] As Figure 2 shown is a comparison schematic diagram before and after embankment breach provided by the embodiment of the application, water level h L on the left side of the embankment is set according to breach elevation Z b and riverway water level Z R , equal to max(0, Z R -Z b ); water level h R on the right side of the embankment is set according to water level Z c in the flood area and breach elevation Z b , equal to max(0, Z c -Z b ), if there is water on the left or right side of the interface, flow velocity on the left and right sides of the interface is equal to the flow velocity of the two-dimensional unit in the flood area.

[0100] Breach width and breach bottom elevation can change with time, wherein the calculation formula of breach width change is:

[0101]

[0102] wherein W b is breach width, W0 is initial moment breach width, τ is water flow shear stress, τ c is soil critical shear stress, γ is soil bulk density, and c w is transverse scour coefficient.

[0103] The calculation formula of breach depth change is:

[0104]

[0105] wherein Z b is breach top elevation; Z b0 is initial moment breach elevation, breach top elevation; c z is vertical scour coefficient.

[0106] Further as an optional implementation manner, the embankment breach prediction model is obtained by training through the following steps:

[0107] S201, obtain dike sample data of a plurality of historical periods of a target dike area and corresponding dike danger states, and determine dike danger labels of the dike sample data according to the dike danger states;

[0108] S202, construct a training data set according to the dike sample data and the dike danger labels;

[0109] S203, input the training data set into a pre-constructed machine learning model to obtain a trained dike breach prediction model;

[0110] The machine learning model is one of a random forest model, a support vector machine model, and a neural network model.

[0111] Specifically, the measured data of dike breach of the target dike area is collected, including dike soil type, dike slope, dike width, dike top-to-bottom distance, river curvature, river flow, river topography, danger water level, danger position and the like; the collected basic dike data is processed, and the dike data is divided into two categories of dangerous dike and non-dangerous dike, wherein whether the dike is dangerous, the danger water level, the danger position are dependent variables, i.e. dike danger states, and other data are independent variables, i.e. dike sample data; based on the processed dike data, a dike breach prediction model is trained by using random forest, support vector machine, convolutional neural network and the like.

[0112] Based on the river topography section, flood area DEM and the like data, a dike breach mechanism model is established, and then measured hydrological data is used to verify the calculation accuracy of the model. Then the dike is subdivided into a plurality of sub-dike sections, and the length of each sub-dike section should not exceed 1 / 4 of the length of a single bend section of the river. The river inlet water level and outlet flow process are selected as the boundary conditions of the flood numerical simulation, and the water dynamic model outputs the simulation results every 1h. The dike breach prediction model reads the river water level and river flow rate simulated by the water dynamic model to calculate the probability of dike breach of each non-breach dike section.

[0113] Further as an optional implementation, whether each sub-dike section breaches is determined by a pseudo-random number generator, which specifically includes:

[0114] S1041, a random number in the interval [0, 1] is generated by a pseudo-random number generator;

[0115] S1042, when the random number is less than the dike breach probability, it is determined that the corresponding sub-dike section breaches;

[0116] S1043, when the random number is greater than or equal to the dike breach probability, it is determined that the corresponding sub-dike section does not breach.

[0117] Specifically, the random number generator is used to determine whether the dike breaches. The process of dike danger determination can be written as:

[0118] Random(x)∈[0,1]

[0119] if x<P,Occur=Ture

[0120] if x≥P,Occur=False

[0121] where Random is a pseudo-random number generator, x is a random number, P is the probability of an event, and Occur is whether the event will occur. It is assumed that the initial breach width is 1 m, and the breach height is a random number from the water level to the levee foot elevation.

[0122] After determining whether each sub-levee section is breached, the levee breach mechanism model reads the breach conditions of each sub-levee section, re-performs numerical simulation with the breach conditions of the sub-levee section as boundary conditions, obtains the hydrodynamic conditions of the river channel and the floodplain at the next time, and outputs the hydrodynamic simulation results, and then again performs levee breach determination. The Monte Carlo simulation idea is adopted to perform multiple levee breach flood simulation and levee breach determination, and finally the levee breach flood simulation results of the last output are obtained, including the hydrodynamic simulation results of the floodplain grid, i.e., the grid water level and the grid flow rate. As shown in FIG. 6, the results of the levee breach flood simulation provided by the embodiment of the present application are shown. Figure 3

[0123] Further as an optional implementation, the flood risk level of each floodplain grid is determined according to the grid water level and the grid flow rate, which specifically includes:

[0124] S1061, determining a first flood risk value of each floodplain grid according to the grid water level and a preset water level threshold;

[0125] S1062, determining a second flood risk value of each floodplain grid according to the grid flow rate and a preset flow rate threshold;

[0126] S1063, performing weighted summation on the first flood risk value and the second flood risk value according to a preset weighting coefficient to obtain a target flood risk value of each floodplain grid, and determining a flood risk level according to the target flood risk value.

[0127] Specifically, the grid water level and the network flow rate are compared with the corresponding threshold conditions respectively to obtain the first flood risk value and the second flood risk value, and then the weighted summation is performed according to the preset weighting coefficient, so that the target flood risk value of each floodplain grid is obtained, and then the flood risk level is determined according to the target flood risk value.

[0128] ​The method steps of the embodiments of the present application are described above. It can be recognized that the embodiments of the present application perform dike breach flood risk assessment based on a dike breach mechanism model and data driving, use the dike breach mechanism model to provide a data basis for a machine learning-based dike breach prediction model, use the dike breach prediction model to predict the probability of dike breach, use a pseudo-random number generator to determine whether each sub-dike section breaches, update the boundary conditions of the dike breach mechanism model according to the breach determination results of each sub-dike section, and after a plurality of cycles, finally obtain the grid water level and grid flow rate of each floodplain grid in a preset future period, so as to determine the flood risk level of each floodplain grid, provide a data basis for drawing a dike breach flood risk map, and improve the accuracy and reliability of dike breach flood risk assessment.

[0129] Reference Figure 4 The embodiments of the present application provide a dike breach flood risk assessment system, comprising:

[0130] A dike breach mechanism model establishment module is configured to obtain basic dike data of a target dike area, and establish a dike breach mechanism model according to the basic dike data, wherein the dike breach mechanism model comprises a river one-dimensional hydrodynamic model and a floodplain two-dimensional hydrodynamic model.

[0131] A data acquisition module is configured to divide the target dike area into a plurality of sub-dike sections and a plurality of floodplain grids, and acquire import and export water level and flow data of the target dike area.

[0132] A dike breach flood simulation module is configured to use the import and export water level and flow data as boundary conditions, and simulate dike breach flood of the target dike area by the dike breach mechanism model to obtain river water level and river flow rate of each sub-dike section.

[0133] A breach occurrence determination module is configured to input the river water level and river flow rate into a pre-trained dike breach prediction model of the target dike area to obtain a dike breach probability of each sub-dike section, and determine whether each sub-dike section breaches by a pseudo-random number generator.

[0134] A grid water level and flow rate determination module is configured to update the boundary conditions according to the breach determination results of each sub-dike section, and return to the step of simulating dike breach flood of the target dike area by the dike breach mechanism model until a preset simulation number is reached, to obtain grid water level and grid flow rate of each floodplain grid in a preset future period.

[0135] A flood risk level determination module is configured to determine a flood risk level of each floodplain grid according to the grid water level and grid flow rate.

[0136] The contents in the method embodiments are applicable to the system embodiments, the system embodiments specifically implement the same functions as the method embodiments, and achieve the same beneficial effects as the method embodiments.

[0137] With reference to Figure 5 The embodiment of the present application provides a levee flood risk assessment device, which comprises:

[0138] at least one processor;

[0139] at least one memory for storing at least one program;

[0140] When the at least one program is executed by the at least one processor, the at least one processor implements the levee flood risk assessment method.

[0141] The contents in the method embodiments are applicable to the device embodiments, the device embodiments specifically implement the same functions as the method embodiments, and achieve the same beneficial effects as the method embodiments.

[0142] The embodiment of the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a program executable by a processor, and the program executable by the processor is used for executing the levee flood risk assessment method when executed by the processor.

[0143] The computer readable storage medium of the embodiment of the present application can execute the levee flood risk assessment method provided by the method embodiments of the present application, can execute the step of any combination of the method embodiments, has the corresponding functions and beneficial effects of the method.

[0144] The embodiment of the present application further discloses a computer program product or a computer program, and the computer program product or the computer program comprises computer instructions stored in a computer readable storage medium. A processor of a computer device can read the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method shown in the embodiment of the present application. Figure 1

[0145] ​In alternative embodiments, the functions / operations in the flow diagrams can occur in sequences other than those depicted. For example, two operations shown in succession can in fact be executed substantially concurrently or the operations can sometimes be executed in the reverse order depending upon the functionality / operations involved. Such variations are contemplated to be within the scope of the present application. Embodiments presented and described in the flow diagrams are examples only and are used to provide an enabling teaching for the present application. The processes disclosed are not limited to the order or specific blocks described. Alternative embodiments are contemplated, in which the order of the blocks is changed and where some blocks are performed in parallel rather than sequentially.

[0146] Moreover, while the present application has been described in the context of functional modules, it is to be understood that one or more of the functions and / or features described above can be integrated within a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It will also be appreciated that detailed discussion of the actual implementation of each module is not necessary for an enabling understanding of the application. Rather, the actual implementation is most readily derived from the description of the functionality of the various functional modules, in conjunction with the understanding of the properties, functions and interrelationships of the various functional modules presented in the context of the device disclosed herein. Therefore, the scope of the application is best understood from the appended claims, in conjunction with the full description and examples provided. It is to be understood that the specific concepts presented are merely illustrative of the application and are not intended to limit the scope of the application as defined by the claims. The scope of the application is defined by the claims and the full extent of equivalents to which such claims are entitled.

[0147] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or part of the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in the embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, etc.

[0148] The logic and / or steps represented in the flow diagrams or otherwise described herein, for example, can be embodied in non-transitory computer- readable media, executed by an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or in conjunction with which the instructions can be executed. In the context of this specification, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0149] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and stored in a computer memory.

[0150] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or combinations thereof, can be used: a discrete logic circuit having logic gates for implementing logic functions upon data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), and / or the like.

[0151] In the above description of the present specification, reference is made to the description of terms such as "one embodiment / one example", "another embodiment / another example", or "certain embodiments / certain examples" and the like, which means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. The illustrative appearances of the above-mentioned terms in the description are not necessarily referred to the same embodiment or example throughout the specification. Moreover, the particular features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0152] While the embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary and are not to be construed as limiting the scope of the application. The scope of the application is defined by the appended claims and their equivalents.

[0153] The above is the specific description of the preferred embodiment of the application, but the application is not limited to the above-mentioned embodiments, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the application.

Claims

1. A method of embankment breach flood risk assessment, characterised in that, The method comprises the following steps: obtaining basic dike data of a target dike area, and establishing a dike breach mechanism model according to the basic dike data, wherein the dike breach mechanism model comprises a river one-dimensional water dynamic model and a flood area two-dimensional water dynamic model; dividing the target dike area into multiple sub-dike sections and multiple flood area grids, and obtaining import and export water level and flow data of the target dike area; taking the import and export water level and flow data as boundary conditions, and performing dike breach flood simulation on the target dike area through the dike breach mechanism model to obtain river water level and river flow velocity of each sub-dike section; inputting the river water level and the river flow velocity into a pre-trained dike breach prediction model of the target dike area to obtain dike breach occurrence probability of each sub-dike section, and determining whether dike breach occurs in each sub-dike section through a pseudo-random number generator; updating the boundary conditions according to the dike breach determination results of each sub-dike section, and returning to the step of performing dike breach flood simulation on the target dike area through the dike breach mechanism model until a preset simulation number is reached, and obtaining grid water level and grid flow velocity of each flood area grid in a preset future period; determining flood risk levels of each flood area grid according to the grid water level and the grid flow velocity; the dike breach prediction model is trained through the following steps: obtaining dike sample data of multiple historical periods of the target dike area and corresponding dike risk states, and determining dike risk labels of each dike sample data according to the dike risk states; constructing a training data set according to the dike sample data and the dike risk labels; inputting the training data set into a pre-constructed machine learning model to obtain a trained dike breach prediction model; wherein the machine learning model is one of a random forest model, a support vector machine model, and a neural network model; the pseudo-random number generator is used to determine whether dike breach occurs in each sub-dike section, which specifically comprises: generating a random number in the interval [0, 1] through the pseudo-random number generator; when the random number is less than the dike breach occurrence probability, it is determined that dike breach occurs in the corresponding sub-dike section; when the random number is greater than or equal to the dike breach occurrence probability, it is determined that dike breach does not occur in the corresponding sub-dike section.

2. The method of claim 1, wherein, the river one-dimensional water dynamic model is: where t and x represent time and distance, respectively, U1is a vector of conserved variables, F is a flux, S1is a source term, A represents the cross-sectional area of the flow, Q represents the flow rate, I1and I2represent the hydrostatic pressure term and the side pressure term, respectively, g represents the gravitational acceleration, S0is the bed slope term, and S f is the friction term.

3. The method of claim 1, wherein, the flood area two-dimensional water dynamic model is: where t denotes time, U2 is a vector of conservative variables, E and G are fluxes in x and y directions, S2 is a source term, h denotes water level, u and v denote water velocities averaged along water level in x and y directions, q e is a mass source term per unit area, g denotes gravitational acceleration, S 0x and S 0y are bed slope terms in x and y directions, S fx and S fy are friction slopes in x and y directions, and n denotes Manning roughness coefficient.

4. The method of claim 1, wherein, the river one-dimensional water dynamic model and the flood area two-dimensional water dynamic model are coupled through a Riemann solver, which is used to solve breach flow according to water level and flow velocity on both sides of the dike, and the breach flow is obtained through the following formula: where Q b represents the breach flow, W b represents the breach width, F Riemann represents the Riemann solver, h represents the water level, u represents the flow velocity, and the subscripts L and R represent the river and the ground surface two-dimensional elements, respectively.

5. A method of assessing the risk of embankment breach flooding according to any one of claims 1 to 4, wherein, determining a first flood risk value of each flood area grid according to the grid water level and a preset water level threshold; determining a second flood risk value of each flood area grid according to the grid flow velocity and a preset flow velocity threshold; ​ The first flood risk value and the second flood risk value are weighted and summed according to a preset weighting coefficient to obtain a target flood risk value of each floodplain grid, and a flood risk grade is determined according to the target flood risk value.

6. A system for assessing the risk of levee breach flooding, the system comprising: Comprise: The dike breach mechanism model establishment module is used for acquiring basic dike data of a target dike region, and establishing a dike breach mechanism model according to the basic dike data, wherein the dike breach mechanism model comprises a river one-dimensional water dynamic model and a floodplain two-dimensional water dynamic model; The data acquisition module is used for dividing the target dike region into a plurality of sub-dike sections and a plurality of floodplain grids, and acquiring import and export water level and flow data of the target dike region; The dike breach flood simulation module is used for taking the import and export water level and flow data as boundary conditions, and simulating dike breach flood of the target dike region through the dike breach mechanism model to obtain river water level and river flow velocity of each sub-dike section; The dike breach occurrence discrimination module is used for inputting the river water level and the river flow velocity into a pre-trained dike breach prediction model of the target dike region to obtain dike breach occurrence probability of each sub-dike section, and discriminating whether each sub-dike section occurs dike breach through a pseudo-random number generator; The grid water level and flow velocity determination module is used for updating boundary conditions according to dike breach discrimination results of each sub-dike section, and returning to the step of simulating dike breach flood of the target dike region through the dike breach mechanism model until a preset simulation number is reached to obtain grid water level and grid flow velocity of each floodplain grid in a preset future period; The flood risk grade determination module is used for determining flood risk grade of each floodplain grid according to the grid water level and the grid flow velocity; The dike breach prediction model is obtained by the following steps: Acquire dike sample data and corresponding dike risk states of a plurality of historical periods of the target dike region, and determine dike risk labels of each dike sample data according to the dike risk states; Construct a training data set according to the dike sample data and the dike risk labels; Input the training data set into a pre-constructed machine learning model to obtain a trained dike breach prediction model; The machine learning model is one of a random forest model, a support vector machine model, and a neural network model; The dike breach occurrence discrimination through the pseudo-random number generator specifically comprises: Generating a random number in the interval [0, 1] through the pseudo-random number generator; When the random number is less than the dike breach occurrence probability, it is determined that the corresponding sub-dike section occurs dike breach; When the random number is greater than or equal to the dike breach occurrence probability, it is determined that the corresponding sub-dike section does not occur dike breach.

7. A device for assessing the risk of a breach of a dike by a flood, characterized in that Comprise: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a dike breach flood risk assessment method according to any one of claims 1 to 5.

8. A computer readable storage medium having stored therein a program which is executable by a processor, characterized in that, The program executable by the processor, when executed by the processor, is used to perform a dike breach flood risk assessment method as claimed in any one of claims 1 to 5.

Images