Flood propagation time prediction method and device and electronic equipment

Abstract

The invention provides a flood propagation time prediction method and device and electronic equipment, and the method comprises the steps: obtaining the geographic space data and hydrological data of a to-be-predicted drainage basin based on a digital twinborn system of the to-be-predicted drainage basin; according to the geographic space data, determining an overlook area and a drainage basin reference surface elevation of the drainage basin to be predicted; according to the overlook area and the drainage basin reference surface elevation, determining the size information of the drainage basin surface of the drainage basin to be predicted; and according to the hydrological data and the size information, predicting the time required for the flood to flow through the surface of the drainage basin. According to the method, the geospatial data and the hydrological data are integrated, and the size information of the drainage basin is accurately calculated by using the digital twinborn system, so that the flood propagation time is accurately predicted, and the timeliness and the precision of flood early warning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins, and in particular to a method, device and electronic device for predicting flood propagation time. Background Art

[0002] In flood warning and disaster management, accurately predicting the flood propagation time is crucial. However, traditional flood simulation and prediction models often have difficulty providing fast and accurate propagation time predictions due to reasons such as lack of real-time data, computational power limitations, and terrain complexity. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device and electronic device for predicting flood propagation time, so as to alleviate the technical problem that traditional flood simulation and prediction models often have difficulty providing fast and accurate propagation time predictions due to reasons such as lack of real-time data, computational power limitations, and terrain complexity, and improve the accuracy of flood propagation time.

[0004] In a first aspect, an embodiment of the present invention provides a method for predicting flood propagation time, including: obtaining the geospatial data and hydrological data of the to-be-predicted basin based on the digital twin system of the to-be-predicted basin; determining the top view area and the elevation of the basin reference surface of the to-be-predicted basin according to the geospatial data; determining the size information of the basin surface of the to-be-predicted basin according to the top view area and the elevation of the basin reference surface; predicting the time required for the flood to flow through the basin surface according to the hydrological data and the size information.

[0005] In a preferred embodiment of the present invention, the step of determining the size information of the basin surface of the to-be-predicted basin according to the top view area and the elevation of the basin reference surface includes: dividing the to-be-predicted basin into multiple sub-basins based on preset parameters; calculating the sub-basin top view area and the sub-basin reference surface elevation of each sub-basin according to the top view area and the elevation of the basin reference surface; calculating the basin basin area ratio and the basin basin elevation ratio of each sub-basin according to the sub-basin top view area, the sub-basin reference surface elevation, the top view area and the elevation of the basin reference surface; constructing a polynomial function of a preset order according to the basin basin elevation ratio, the basin basin area ratio, and the preset coefficient of the basin basin area ratio; determining the size information of the basin surface of the to-be-predicted basin according to the polynomial function.

[0006] In a preferred embodiment of the present invention, the step of constructing a polynomial function of a preset order according to the above-mentioned basin elevation ratio, the above-mentioned basin area ratio, and the preset coefficient of the above-mentioned basin area ratio includes: using the above-mentioned basin elevation ratio as the dependent variable of the above-mentioned polynomial function, and using the above-mentioned basin area ratio as the independent variable of the above-mentioned polynomial function to construct the above-mentioned polynomial function of the preset order; wherein, the above-mentioned polynomial function is represented by the following formula:

[0007] wherein, y represents the above-mentioned dependent variable, x is the above-mentioned independent variable, c 1 to c d are the above-mentioned preset coefficients, d is the above-mentioned preset order, is a preset regularization term.

[0008] In a preferred embodiment of the present invention, the step of determining the size information of the basin surface of the above-mentioned basin to be predicted according to the above-mentioned polynomial function includes: calculating the first derivative of the above-mentioned polynomial function to obtain the curve slope formula of the basin; determining the size information of the basin surface of the above-mentioned basin to be predicted according to the above-mentioned curve slope formula.

[0009] In a preferred embodiment of the present invention, the step of determining the size information of the basin surface of the above-mentioned basin to be predicted according to the above-mentioned curve slope formula includes: determining the curve distance between preset points in the above-mentioned basin to be predicted according to the above-mentioned curve slope formula; the step of predicting the time required for flood water to flow through the above-mentioned basin surface according to the above-mentioned hydrological data and the above-mentioned size information includes: predicting the time required for flood water to flow through the above-mentioned basin surface according to the above-mentioned hydrological data and the above-mentioned curve distance.

[0010] In a preferred embodiment of the present invention, after the step of using the above-mentioned basin elevation ratio as the dependent variable of the above-mentioned polynomial function and using the above-mentioned basin area ratio as the independent variable of the above-mentioned polynomial function to construct the above-mentioned polynomial function of the preset order, the above-mentioned method includes: performing a comparison and optimization process on the above-mentioned preset coefficients and the above-mentioned preset order by the least squares method to obtain a target coefficient and a target order; the step of constructing a polynomial function of a preset order according to the above-mentioned basin elevation ratio, the above-mentioned basin area ratio, and the preset coefficient of the above-mentioned basin area ratio includes: constructing a polynomial function of the above-mentioned target order according to the above-mentioned target coefficients of the above-mentioned basin elevation ratio, the above-mentioned basin area ratio, and the above-mentioned basin area ratio.

[0011] In a preferred embodiment of the present invention, the step of performing a comparison and optimization process on the above-mentioned preset coefficients and the above-mentioned preset order by the least squares method to obtain a target coefficient and a target order includes: Step 1, constructing the eigenvector of the above-mentioned polynomial function:

[0012] Among them, represents the eigenvector, n is the number of sub-watersheds, and d is the above-mentioned preset order, is the d-th power of the n-th sub-watershed, is the elevation ratio of the basin of the n-th sub-watershed; Step 2, construct a coefficient vector according to the above eigenvector; Among them, Q is the above coefficient vector; Step 3, substitute the above coefficient vector into the above polynomial function to obtain the function to be fitted; Step 4, fit the above function to be fitted to obtain the fitting result; Step 5, according to the above fitting result, determine the minimum residual sum of squares of the above polynomial function; Step 6, according to the above minimum residual sum of squares, determine whether the above fitting result meets the preset requirements; Step 7, if not, adjust the above preset order according to the preset order step size to obtain an updated polynomial function; Step 8, according to the above updated polynomial function, determine the updated fitting result corresponding to the updated polynomial function and the minimum residual sum of squares corresponding to the above updated fitting result until the minimum residual sum of squares corresponding to the above updated fitting result meets the above preset requirements; Step 9, calculate the goodness-of-fit index of the above updated polynomial function; Step 10, determine whether the above goodness-of-fit index is less than a preset threshold; Step 11, if the above goodness-of-fit index is less than the above preset threshold, determine the adjusted order as the target order; if the above goodness-of-fit index is greater than or equal to the above preset threshold, repeat the above steps 7 to the above step 10 until the above goodness-of-fit index is less than the above preset threshold; Step 12, according to the above updated polynomial function of the above target order, determine the above target coefficient.

[0013] In a preferred embodiment of the present invention, the step of determining the above target coefficient according to the above updated polynomial function of the above target order includes: Step S1, construct a likelihood function and a log-likelihood function through the above updated polynomial function; Step S2, solve the maximum likelihood function according to the above log-likelihood function to obtain a solution result; Step S3, determine whether the above solution result meets the preset convergence condition; Step S4, if it does not meet the preset convergence condition, adjust the above preset coefficient based on the preset coefficient step size, and repeat the above steps S1 to the above step S3 until the solution result meets the above convergence condition, and determine the coefficient of the above updated polynomial function corresponding to the above solution result as the above target coefficient.

[0014] In a second aspect, an embodiment of the present invention provides a flood propagation time prediction device, including: a data acquisition module, configured to acquire the geospatial data and hydrological data of the to-be-predicted basin based on the digital twin system of the to-be-predicted basin; a determination module, configured to determine the top view area and the elevation of the basin reference plane of the to-be-predicted basin according to the geospatial data; a surface determination module, configured to determine the size information of the basin surface of the to-be-predicted basin according to the top view area and the elevation of the basin reference plane; and a prediction module, configured to predict the time required for the flood to flow through the basin surface according to the hydrological data and the size information.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes a processor and a memory, and the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the flood propagation time prediction method.

[0016] The embodiment of the present invention has the following beneficial technical effects: The embodiment of the present invention provides a flood propagation time prediction method, device and electronic device, including: acquiring the geospatial data and hydrological data of the to-be-predicted basin based on the digital twin system of the to-be-predicted basin; determining the top view area and the elevation of the basin reference plane of the to-be-predicted basin according to the geospatial data; determining the size information of the basin surface of the to-be-predicted basin according to the top view area and the elevation of the basin reference plane; and predicting the time required for the flood to flow through the basin surface according to the hydrological data and the size information. By integrating geospatial data and hydrological data and using the digital twin system to accurately calculate the size information of the basin, this method can accurately predict the flood propagation time, improving the timeliness and accuracy of flood warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic flow chart of a flood propagation time prediction method provided by an embodiment of the present invention; Figure 2 It is a schematic flow chart of another flood propagation time prediction method provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of a flood propagation time prediction device provided by an embodiment of the present invention; Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention.

[0019] Icons: 31 - data acquisition module; 32 - determination module; 33 - surface determination module; 34 - prediction module; 41 - memory; 42 - processor; 43 - bus; 44 - communication interface. Detailed implementation manners

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Components of the embodiments of the present invention usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0021] Currently, in flood warning and disaster management, accurately predicting the time of flood propagation is crucial. However, traditional flood simulation and prediction models often have difficulty providing fast and accurate propagation time predictions due to reasons such as lack of real-time data, computational power limitations, and terrain complexity.

[0022] Based on this, the embodiments of the present invention provide a method, device, and electronic device for predicting flood propagation time. This method integrates geospatial data and hydrological data, and uses a digital twin system to accurately calculate the size information of the watershed, thereby achieving accurate prediction of flood propagation time and improving the timeliness and accuracy of flood warning. For the convenience of understanding, the embodiments of the present invention first introduce a method for predicting flood propagation time.

[0023] Embodiment 1 In the embodiments of the present invention, Figure 1 A flowchart of a method for predicting flood propagation time provided by an embodiment of the present invention.

[0024] As Figure 1 can be seen, the method includes: Step S101: Based on the digital twin system of the watershed to be predicted, obtain the geospatial data and hydrological data of the above-mentioned watershed to be predicted.

[0025] In an embodiment of the present invention, the above digital twin system is connected to the hydrological system of the hydrological station and the peripheral geographic information system; the above geospatial data includes: Digital Surface Model (DSM), Digital Elevation Model (DEM), and Digital Orthophoto Map (DOM); the above hydrological data includes: precipitation data, runoff data, groundwater data, and the basin characteristic data of the basin to be predicted.

[0026] Step S102: Determine the top view area and the elevation of the basin reference plane of the basin to be predicted according to the above geospatial data. Here, the basin reference plane refers to the starting horizontal plane for calculating elevation and water level within a certain basin, also known as the base plane, which has four types: absolute base plane (the horizontal plane with the elevation of the average sea level over the years set as zero), assumed base plane (when there is no national benchmark near the measuring station or it is not possible to connect for measurement, the water level base plane assumed for calculating the hydrological process), station base plane (a special assumed fixed base plane where the hydrological measuring station is selected slightly lower than the lowest water level or the lowest point of the riverbed over the years), and frozen base plane (after a certain base plane is first used at the hydrological measuring station, its elevation is fixed). The above basin reference plane elevation is the distance from a certain point on the basin along the plumb direction to the absolute base plane, also known as the absolute elevation.

[0027] Step S103: Determine the size information of the surface of the basin to be predicted according to the above top view area and the elevation of the basin reference plane.

[0028] In this embodiment, it is assumed that there is a certain slope in the basin to be predicted, and when precipitation falls on the basin to be predicted, it slides downward along the slope due to the action of gravity, thus forming a flood.

[0029] Step S104: Predict the time required for the flood to flow through the surface of the basin according to the above hydrological data and the above size information.

[0030] Therefore, after determining the size information of the surface of the basin to be predicted and the hydrological data, the time required for the flood to flow through the surface of the basin can be calculated according to Newton's second law.

[0031] An embodiment of the present invention provides a method for predicting flood propagation time, including: based on the digital twin system of the basin to be predicted, obtaining the geospatial data and hydrological data of the basin to be predicted; determining the top view area and the elevation of the basin reference plane of the basin to be predicted according to the geospatial data; determining the size information of the basin surface of the basin to be predicted according to the top view area and the elevation of the basin reference plane; predicting the time required for the flood to flow through the basin surface according to the hydrological data and the size information. This method integrates geospatial data and hydrological data, and uses the digital twin system to accurately calculate the size information of the basin, so as to achieve accurate prediction of flood propagation time and improve the timeliness and accuracy of flood warning.

[0032] Embodiment 2 Based on the above embodiment, Figure 2 It is a schematic flowchart of another method for predicting flood propagation time provided by an embodiment of the present invention.

[0033] As Figure 2 can be seen, this method includes: Step S201: Based on the digital twin system of the basin to be predicted, obtain the geospatial data and hydrological data of the basin to be predicted.

[0034] Step S202: Determine the top view area and the elevation of the basin reference plane of the basin to be predicted according to the geospatial data.

[0035] Step S203: Divide the basin to be predicted into multiple sub-basins based on preset parameters.

[0036] Step S204: Calculate the sub-basin top view area and the sub-basin reference plane elevation of each sub-basin according to the top view area and the elevation of the basin reference plane.

[0037] Step S205: Calculate the basin basin area ratio and the basin basin elevation ratio of each sub-basin according to the sub-basin top view area, the sub-basin reference plane elevation, the top view area and the elevation of the basin reference plane.

[0038] In this embodiment, divide the sub-basin top view area of the sub-basin by the basin basin area to obtain the basin basin area ratio of each sub-basin; divide the sub-basin reference plane elevation of the sub-basin by the elevation of the basin reference plane to obtain the basin basin elevation ratio of each sub-basin.

[0039] Step S206: Construct a polynomial function of a preset order according to the preset coefficient of the basin basin elevation ratio, the basin basin area ratio, and the basin basin area ratio.

[0040] In actual operation, the steps of constructing a polynomial function of a preset order according to the above-mentioned elevation ratio of the river basin, the above-mentioned area ratio of the river basin, and the preset coefficient of the above-mentioned area ratio of the river basin include: Taking the above-mentioned elevation ratio of the river basin as the dependent variable of the above-mentioned polynomial function and taking the above-mentioned area ratio of the river basin as the independent variable of the above-mentioned polynomial function, and constructing the above-mentioned polynomial function of the preset order; Among them, the above-mentioned polynomial function is represented by the following formula:

[0041] Among them, y represents the above-mentioned dependent variable, x is the above-mentioned independent variable, c 1 to c d are the above-mentioned preset coefficients, d is the above-mentioned preset order, is a preset regularization term.

[0042] Further, after the step of taking the above-mentioned elevation ratio of the river basin as the dependent variable of the above-mentioned polynomial function and taking the above-mentioned area ratio of the river basin as the independent variable of the above-mentioned polynomial function, and constructing the above-mentioned polynomial function of the preset order, the above method includes: By using the least squares method, comparing and optimizing the above-mentioned preset coefficients and the above-mentioned preset order to obtain the target coefficients and the target order; The steps of constructing a polynomial function of a preset order according to the above-mentioned elevation ratio of the river basin, the above-mentioned area ratio of the river basin, and the preset coefficient of the above-mentioned area ratio of the river basin include: Constructing a polynomial function of the above-mentioned target order according to the above-mentioned elevation ratio of the river basin, the above-mentioned area ratio of the river basin, and the above-mentioned target coefficients of the above-mentioned area ratio of the river basin.

[0043] Among them, the steps of comparing and optimizing the above-mentioned preset coefficients and the above-mentioned preset order by using the least squares method to obtain the target coefficients and the target order include: Step 1, constructing the eigenvector of the above-mentioned polynomial function:

[0044] Among them, represents the eigenvector, n is the number of sub-basins, d is the above-mentioned preset order, is the d-th power of the n-th sub-basin, is the elevation ratio of the river basin of the n-th sub-basin.

[0045] Step 2, constructing a coefficient vector according to the above-mentioned eigenvector;

[0046] Among them, Q is the above-mentioned coefficient vector.

[0047] Step 3: Substitute the above coefficient vector into the above polynomial function to obtain the function to be fitted.

[0048] In this embodiment, substitute the above coefficient vector into the above polynomial function, represent the above dependent variable as y, and represent the above independent variable as x to obtain the above function to be fitted.

[0049] Step 4: Fit the above function to be fitted to obtain a fitting result.

[0050] Step 5: Determine the minimum residual sum of squares of the above polynomial function according to the above fitting result.

[0051] In this embodiment, the minimum residual sum of squares is used to determine the fitting effect. The smaller the value of the minimum residual sum of squares, the better the polynomial fitting effect.

[0052] Step 6: Determine whether the above fitting result meets the preset requirements according to the above minimum residual sum of squares.

[0053] Step 7: If not, adjust the above preset order according to the preset order step size to obtain an updated polynomial function.

[0054] In this embodiment, the preset order adjustment step size is 1 order.

[0055] For example: on the basis of , add one term, then the updated polynomial function is .

[0056] Step 8: Determine the updated fitting result corresponding to the updated polynomial function and the minimum residual sum of squares corresponding to the above updated fitting result according to the above updated polynomial function until the minimum residual sum of squares corresponding to the above updated fitting result meets the above preset requirements.

[0057] Step 9: Calculate the goodness-of-fit index of the above updated polynomial function.

[0058] Step 10: Determine whether the above goodness-of-fit index is less than a preset threshold.

[0059] Step 11: If the above goodness-of-fit index is less than the above preset threshold, determine the adjusted order as the target order; if the above goodness-of-fit index is greater than or equal to the above preset threshold, repeat the above steps 7 to the above step 10 until the above goodness-of-fit index is less than the above preset threshold.

[0060] Step 12: Determine the above target coefficient according to the above updated polynomial function of the above target order.

[0061] Further, the step of determining the above-mentioned target coefficient according to the above-mentioned updated polynomial function of the above-mentioned target order includes: Step S1, construct a likelihood function and a log-likelihood function through the above-mentioned updated polynomial function; Step S2, solve the maximum likelihood function according to the above-mentioned log-likelihood function to obtain a solution result; Step S3, determine whether the above-mentioned solution result satisfies a preset convergence condition; Step S4, if it does not satisfy the preset convergence condition, adjust the above-mentioned preset coefficient based on a preset coefficient step size, and repeat the above-mentioned steps S1 to the above-mentioned step S3 until the solution result satisfies the above-mentioned convergence condition, and determine the coefficient of the above-mentioned updated polynomial function corresponding to the above-mentioned solution result as the above-mentioned target coefficient.

[0062] In this embodiment, it is assumed that the above-mentioned updated polynomial function is , The above-mentioned likelihood function is ; The above-mentioned log-likelihood function is ; Among them, the above-mentioned represents the mean square error, the above-mentioned y i represents the i-th dependent variable, the above-mentioned xi represents the i-th independent variable, represents the likelihood function, represents the log-likelihood function.

[0063] Then, take the partial derivative of each parameter of the above-mentioned log-likelihood function and set it to zero:

[0064] Among them, represents the gradient of the negative log-likelihood function with respect to the parameter .

[0065] Then, then iteratively update the parameters:

[0066] Among them, represents the parameter value after the (t + 1)-th iteration, represents the parameter value after the t-th iteration, is the learning rate, and its value is a constant, is the negative log-likelihood function.

[0067] Finally, check the convergence condition. After each iteration, check whether the convergence condition is satisfied. Set the convergence condition as the range of the gradient being less than a preset threshold. If the convergence condition is satisfied, stop the iteration; otherwise, return to continue updating and iterating the parameters. That is, judge Whether it is less than the above preset threshold value. If the convergence condition is met, stop the iteration; otherwise, return to continue updating the iteration parameters.

[0068] Step S207: Determine the size information of the basin surface of the to-be-predicted basin according to the above polynomial function.

[0069] In one implementation, the step of determining the size information of the basin surface of the to-be-predicted basin according to the above polynomial function includes: calculating the first derivative of the above polynomial function to obtain the curve slope formula of the basin; determining the size information of the basin surface of the to-be-predicted basin according to the above curve slope formula.

[0070] Further, the step of determining the size information of the basin surface of the to-be-predicted basin according to the above curve slope formula includes: determining the curve distance between preset points in the to-be-predicted basin according to the above curve slope formula; the step of predicting the time required for the flood to flow through the above basin surface according to the above hydrological data and the above size information includes: predicting the time required for the flood to flow through the above basin surface according to the above hydrological data and the above curve distance.

[0071] Here, assume that the above polynomial function is , and the first derivative of calculating the above polynomial function is: , and this first derivative is the curve slope formula. Among them, is equal to the tangent value of the current slope inclination angle of the basin surface.

[0072] Further, any two points can be taken on the curve corresponding to the above curve slope formula to obtain a curve segment, and then calculate the time for the water flow data in the hydrological data to flow through the above curve segment due to gravity to predict the time required for the flood to flow through the above basin surface.

[0073] Further, that is, the above polynomial function is the relationship function between the elevation ratio of the above basin and the area ratio of the above basin, and the above curve slope formula is the first derivative of the above relationship function.

[0074] Step S208: Predict the time required for the flood to flow through the above basin surface according to the above hydrological data and the above size information.

[0075] An embodiment of the present invention provides a method for predicting flood propagation time, including: based on the digital twin system of the basin to be predicted, obtaining the geospatial data and hydrological data of the basin to be predicted; determining the top view area and the elevation of the basin reference plane of the basin to be predicted according to the geospatial data; dividing the basin to be predicted into multiple sub-basins based on preset parameters; calculating the sub-basin top view area and the sub-basin reference plane elevation of each sub-basin according to the top view area and the elevation of the basin reference plane; calculating the basin area ratio and the basin elevation ratio of each sub-basin according to the sub-basin top view area, the sub-basin reference plane elevation, the top view area and the elevation of the basin reference plane; constructing a polynomial function of a preset order according to the basin elevation ratio, the basin area ratio and the preset coefficient of the basin area ratio; determining the size information of the basin surface of the basin to be predicted according to the polynomial function; predicting the time required for the flood to flow through the basin surface according to the hydrological data and the size information. This method integrates geospatial data and hydrological data through a digital twin system, divides the basin into sub-regions, and uses a polynomial function for modeling, accurately calculating the size and elevation information of each sub-basin, so as to achieve high-precision prediction of flood propagation time, significantly improving the accuracy and reliability of flood warning.

[0076] Embodiment 3 Based on the above embodiment, Figure 3 It is a schematic structural diagram of a device for predicting flood propagation time provided by an embodiment of the present invention.

[0077] As can be Figure 3 seen, the device includes: A data acquisition module 31, configured to obtain the geospatial data and hydrological data of the basin to be predicted based on the digital twin system of the basin to be predicted.

[0078] A determination module 32, configured to determine the top view area and the elevation of the basin reference plane of the basin to be predicted according to the geospatial data.

[0079] A surface determination module 33, configured to determine the size information of the basin surface of the basin to be predicted according to the top view area and the elevation of the basin reference plane.

[0080] A prediction module 34, configured to predict the time required for the flood to flow through the basin surface according to the hydrological data and the size information.

[0081] Among them, the data acquisition module 31, the determination module 32, the surface determination module 33 and the prediction module 34 are connected in sequence.

[0082] The flood propagation time prediction device provided by the embodiment of the present invention has the same technical features as the flood propagation time prediction method provided by the above embodiment, so it can also solve the same technical problems and achieve the same technical effects. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the foregoing method embodiment, and will not be elaborated herein.

[0083] Embodiment 4 This embodiment provides an electronic device, including a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of the flood propagation time prediction method.

[0084] This embodiment provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of the flood propagation time prediction method are implemented.

[0085] See Figure 4 The structural schematic diagram of an electronic device shown in the figure. The electronic device includes: a memory 41 and a processor 42. A computer program that can run on the processor 42 is stored in the memory 41. When the processor executes the computer program, the steps provided by the above flood propagation time prediction method are implemented.

[0086] As Figure 4 shown in the figure, the device further includes: a bus 43 and a communication interface 44. The processor 42, the communication interface 44, and the memory 41 are connected through the bus 43. The processor 42 is used to execute the executable module stored in the memory 41, such as a computer program.

[0087] Among them, the memory 41 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 44 (which can be wired or wireless), a communication connection between the system network element and at least one other network element is realized, and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0088] The bus 43 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 4 only a bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0089] Among them, the memory 41 is used to store programs. After receiving an execution instruction, the processor 42 executes the program. The methods executed by the flood propagation time prediction device disclosed in any embodiment of the present invention can be applied to or implemented by the processor 42. The processor 42 may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method can be completed through the integrated logic circuit in the hardware of the processor 42 or instructions in the form of software. The above-mentioned processor 42 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by the hardware decoding processor, or completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 41, and the processor 42 reads the information in the memory 41 and combines its hardware to complete the steps of the above method.

[0090] Furthermore, an embodiment of the present invention also provides a machine-readable storage medium. The machine-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by the processor 42, the machine-executable instructions cause the processor 42 to implement the above-mentioned flood propagation time prediction method.

[0091] The electronic device and the computer-readable storage medium provided by the embodiments of the present invention have the same technical features, so they can also solve the same technical problems and achieve the same technical effects.

[0092] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "coupled" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0093] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

Claims

1. A flood propagation time prediction method, characterized in that: include: Based on the digital twin system of the watershed to be predicted, obtaining the geospatial data and hydrological data of the watershed to be predicted; Determine the overhead area and the base elevation of the watershed to be predicted according to the geospatial data; Determine the size information of the watershed surface of the watershed to be predicted according to the overhead area and the watershed reference plane elevation; The time required for the flood to flow through the surface of the basin is predicted based on the hydrological data and the size information.

2. The flood propagation time prediction method according to claim 1, characterized in that: The step of determining the size information of the surface of the watershed to be predicted according to the overhead area and the watershed reference plane elevation comprises: Based on preset parameters, the watershed to be predicted is divided into a plurality of sub-watersheds; Calculate the sub-basin overhead area and sub-basin reference plane elevation of each of the sub-basins according to the overhead area and the basin reference plane elevation; Calculate the drainage basin area ratio and drainage basin elevation ratio of each of the sub-watersheds according to the sub-watershed overhead area, the sub-watershed reference plane elevation, the overhead area and the watershed reference plane elevation; Constructing a polynomial function of a preset order according to the watershed-basin elevation ratio, the watershed-basin area ratio, and a preset coefficient of the watershed-basin area ratio; According to the polynomial function, the size information of the watershed surface of the watershed to be predicted is determined.

3. The flood propagation time prediction method according to claim 2, characterized in that: The step of constructing a polynomial function of a preset order according to the watershed-basin elevation ratio, the watershed-basin area ratio, and a preset coefficient of the watershed-basin area ratio comprises: Taking the watershed basin elevation ratio as the dependent variable of the polynomial function, taking the watershed basin area ratio as the independent variable of the polynomial function, constructing the polynomial function of the preset order; Wherein, the polynomial function is expressed by the following formula: Among them, y represents the dependent variable, x is the independent variable, c1 to c d is the preset coefficient, d is the preset order, is the preset regularization term.

4. The flood propagation time prediction method according to claim 3, characterized in that: The step of determining the size information of the watershed surface of the watershed to be predicted according to the polynomial function comprises: Calculating the first-order derivative of the polynomial function to obtain a curve slope formula of the watershed; According to the curve slope formula, the size information of the watershed surface of the watershed to be predicted is determined.

5. The flood propagation time prediction method according to claim 4, characterized in that: The step of determining the size information of the watershed surface of the watershed to be predicted according to the curve slope formula comprises: According to the curve slope formula, determine the curve distance between the preset points in the watershed to be predicted; The step of predicting the time required for the flood to flow through the surface of the basin based on the hydrological data and the size information comprises: The time required for the flood to flow through the surface of the basin is predicted based on the hydrological data and the curve distance.

6. The flood propagation time prediction method according to claim 3, characterized in that: After the step of constructing the polynomial function of the preset order by taking the watershed-basin elevation ratio as the dependent variable of the polynomial function and taking the watershed-basin area ratio as the independent variable of the polynomial function, the method comprises: By using the least square method, the preset coefficient and the preset order are compared and optimized to obtain the target coefficient and the target order; The step of constructing a polynomial function of a preset order according to the watershed-basin elevation ratio, the watershed-basin area ratio, and a preset coefficient of the watershed-basin area ratio comprises: A polynomial function of the target order is constructed according to the watershed-basin elevation ratio, the watershed-basin area ratio, and the target coefficient of the watershed-basin area ratio.

7. The flood propagation time prediction method according to claim 6, characterized in that: The step of comparing and optimizing the preset coefficients and the preset order by the least square method to obtain the target coefficients and the target order includes: Step 1, construct the characteristic vector of the polynomial function: in, represents the characteristic vector, n is the number of sub-basins, d is the preset order, is the d-th power of the n-th subbasin, is the drainage basin elevation ratio of the nth sub-basin; Step 2, constructing a coefficient vector according to the eigenvector; Wherein, Q is the coefficient vector; Step 3, substituting the coefficient vector into the polynomial function to obtain a function to be fitted; Step 4, fitting the function to be fitted to obtain a fitting result; Step 5, determining the minimized residual sum of squares of the polynomial function according to the fitting result; Step 6, judging whether the fitting result meets the preset requirements according to the minimization of the residual sum of squares; Step 7: If not, adjust the preset order according to the preset order step to obtain an updated polynomial function; Step 8, determining an updated fitting result corresponding to the updated polynomial function and a minimized residual sum of squares corresponding to the updated fitting result according to the updated polynomial function, until the minimized residual sum of squares corresponding to the updated fitting result meets the preset requirement; Step 9, calculating the goodness of fit index of the updated polynomial function; Step 10, determining whether the goodness of fit index is less than a preset threshold; Step 11, if the goodness of fit index is less than the preset threshold, the adjusted order is determined as the target order; if the goodness of fit index is greater than or equal to the preset threshold, repeating steps 7 to 10 until the goodness of fit index is less than the preset threshold; Step 12: Determine the target coefficients according to the updated polynomial function of the target order.

8. The flood propagation time prediction method according to claim 7, characterized in that: The step of determining the target coefficients according to the updated polynomial function of the target order comprises: Step S1, constructing a likelihood function and a log-likelihood function by updating the polynomial function; Step S2, solving the maximum likelihood function according to the log-likelihood function to obtain a solution result; Step S3, determining whether the solution meets a preset convergence condition; In step S4, if the preset convergence condition is not met, the preset coefficient is adjusted based on the preset coefficient step size, and steps S1 to S3 are repeated until the solution result meets the convergence condition, and the coefficient of the updated polynomial function corresponding to the solution result is determined as the target coefficient.

9. A flood propagation time prediction device, characterized in that: include: A data acquisition module, used to acquire geographic spatial data and hydrological data of the watershed to be predicted based on the digital twin system of the watershed to be predicted; A determination module, used to determine the overhead area and the base elevation of the watershed to be predicted according to the geospatial data; A surface determination module, used to determine the size information of the watershed surface of the watershed to be predicted according to the overhead area and the watershed reference plane elevation; A prediction module is used to predict the time required for the flood to flow through the surface of the basin based on the hydrological data and the size information.

10. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the flood propagation time prediction method according to any one of claims 1 to 8.

Images