Method and device for generating flood risk map and nonvolatile storage medium

Abstract

The invention discloses a method and device for generating a flood risk map and a nonvolatile storage medium. The method comprises the steps that flood disaster related data of a to-be-detected area in a detection time period is acquired, and the flood disaster related data at least comprises a plurality of submerging point locations; geographic disaster data of each submerged point location are determined in the flood disaster related data, and the geographic disaster data are used for describing geographic features and flood disaster features of the submerged point locations; processing and analyzing the geographic disaster data by adopting a flood disaster prediction model to obtain a flood disaster grade prediction value of each submerged point location; and generating a flood risk map of the to-be-detected area according to the plurality of flood disaster grade predicted values. The technical problem that the accuracy of the obtained prediction result is low when the flood risk of the power grid is predicted by performing statistical analysis on the time sequence data obtained by long-term measurement of the power grid is solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular, to a method and device for generating a flood risk map, and a non-volatile storage medium. Background Art

[0002] As an important infrastructure supporting social and economic development, the stable operation of the power grid is of vital importance. However, frequent flood disasters pose a serious threat to the safety of the power grid. Therefore, the technology of monitoring the flood risk of the power grid has emerged. In the related technology, the flood risk of the power grid is predicted by statistical analysis of the time series data obtained by long-term measurement of the power grid, but the prediction result has the problem of low accuracy.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method and device for generating a flood risk map, and a non-volatile storage medium, so as to at least solve the technical problem of low accuracy of prediction results obtained by predicting the flood risk of a power grid by statistically analyzing time series data obtained by long-term measurement of the power grid.

[0005] According to one aspect of an embodiment of the present application, a method for generating a flood risk map is provided, comprising: obtaining flood disaster related data of a to-be-detected area within a detection period, wherein the flood disaster related data includes at least: a plurality of inundation points; determining geographical disaster data of each inundation point in the flood disaster related data, wherein the geographical disaster data is used to describe the geographical characteristics and flood disaster characteristics of the inundation point; processing and analyzing the geographical disaster data using a flood disaster prediction model to obtain a flood disaster level prediction value for each inundation point, wherein the flood disaster prediction model is a neural network model trained using a particle swarm optimization algorithm; generating a flood risk map of the to-be-detected area according to the plurality of flood disaster level prediction values, wherein, in the flood risk map, areas corresponding to flood disaster level prediction values ​​belonging to different numerical ranges are displayed as different colors in the flood risk map.

[0006] Optionally, the flood disaster related data also include: a first type of data describing topography, a second type of data describing climate characteristics, a third type of data describing soil types, a fourth type of data describing vegetation coverage, the frequency of flood disasters, the intensity of flood disasters, and the scope of flood disaster impact; determining the geographical disaster data of each inundation point in the flood disaster related data, including: for each inundation point, determining the contribution density and spatial coordinates of the inundation point, wherein the contribution density is used to indicate the inundation range of the inundation point; generating a density distribution map based on the flood disaster related data and the contribution density of each inundation point, and determining the spatial coordinates used to describe the inundation range based on the density distribution map. The data are geographical disaster data with flood disaster characteristics at different points, wherein the density distribution map shows the frequency of flood disasters, the intensity of flood disasters and the impact range of flood disasters in different inundation ranges, and the frequency of flood disasters, the intensity of flood disasters and the impact range of flood disasters in each inundation range are the geographical disaster data with flood disaster characteristics at the inundation points corresponding to the inundation range; the first type of data, the second type of data, the third type of data and the fourth type of data associated with the inundation points are determined according to the spatial coordinates, wherein the first type of data, the second type of data, the third type of data and the fourth type of data associated with each inundation point are the geographical disaster data used to describe the geographical characteristics of the inundation points.

[0007] Optionally, a flood disaster prediction model is used to process and analyze the geographic disaster data to obtain a flood risk prediction value for each inundation point, including: for different types of geographic disaster data, determining multiple characteristic factors related to the formation of flood disasters, the development of flood disasters, and the degree of impact of flood disasters in the geographic disaster data; generating a corresponding characteristic map for each characteristic factor, wherein the characteristic map is used to display the spatial distribution of physical information represented by the characteristic factor in the area to be detected; and using a flood disaster prediction model to process and analyze multiple characteristic maps to obtain a flood risk prediction value for each inundation point.

[0008] Optionally, the flood disaster prediction model is trained by the following method: obtaining historical flood disaster data of the area to be detected, determining target data representing the altitude in the historical flood disaster data, and extracting a training set from the historical flood disaster data based on the target data, wherein the training set includes: flood disaster-related data, flood disaster level; using the training set and the particle swarm optimization algorithm to iteratively train the neural network model until the number of iterations reaches a preset number, stopping the iterative training, and obtaining the flood disaster prediction model.

[0009] Optionally, extracting a training set from historical flood disaster data according to target data includes: determining multiple value intervals according to the value of the target data, wherein each value interval corresponds to a different value range; determining multiple data sets according to the multiple value intervals, wherein each data set contains the following data: target data whose value belongs to the value interval, target inundation points corresponding to the target data, and geographical disaster data associated with the inundation points; for each data set, normalizing the data in the data set and determining the variance of the normalized data; determining a first data volume of the data set and determining a ratio of the first data volume to a second volume, wherein the second volume is the volume of historical flood disaster data; determining a target volume according to a third volume, variance and ratio of the data set, wherein the target volume is the data volume of the training set; extracting the target volume of data from the historical flood disaster data as a training set.

[0010] Optionally, the neural network model is iteratively trained using a training set and a particle swarm optimization algorithm, wherein each iterative training includes: determining a set consisting of multiple model parameters of the model to be trained as particles to be optimized, wherein the model to be trained in the next iterative training is the model output by the previous iterative training, and when the iterative training is performed for the first time, the model to be trained is a neural network model; using a particle swarm optimization algorithm to update the particles to be optimized until the number of iterations reaches a preset number, and outputting target particles, wherein the target particles contain multiple updated values ​​of multiple model parameters; and adjusting the numerical value of each model parameter of the neural network model to a corresponding updated value to obtain a flood disaster prediction model.

[0011] Optionally, the model output by each iterative training is determined by the following method: using the model to be trained to analyze and process the flood disaster related data in the training set to obtain a first prediction result, wherein the first prediction result is the flood disaster level prediction value output by the model to be trained; using the updated model to analyze and process the flood disaster related data in the training set to obtain a second prediction result, wherein the updated model is the model to be trained after adjusting the model parameters, and the second prediction result is the flood disaster level prediction value output by the updated model; determining a first error value between the first prediction result and the flood risk level in the training set, and determining a second error value between the second prediction result and the flood risk level in the training set; when the first error value is less than the second error value, output the model to be trained; when the first error value is greater than or equal to the second error value, output the updated model.

[0012] According to another aspect of an embodiment of the present application, a device for generating a flood risk map is also provided, including: an acquisition module, used to acquire flood disaster-related data of a to-be-detected area within a detection period, wherein the flood disaster-related data includes at least: a plurality of inundation points; a determination module, used to determine the geographical disaster data of each inundation point in the flood disaster-related data, wherein the geographical disaster data is used to describe the geographical characteristics and flood disaster characteristics of the inundation point; an analysis module, used to process and analyze the geographical disaster data using a flood disaster prediction model to obtain a flood disaster level prediction value for each inundation point, wherein the flood disaster prediction model is a neural network model trained using a particle optimization algorithm; a generation module, used to generate a flood risk map of the to-be-detected area based on a plurality of flood disaster level prediction values, wherein, in the flood risk map, areas corresponding to flood disaster level prediction values ​​belonging to different numerical ranges are displayed as different colors in the flood risk map.

[0013] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, in which a computer program is stored, wherein the method for generating a flood risk map is executed by running the computer program on a device where the non-volatile storage medium is located.

[0014] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned method for generating a flood risk map through the computer program.

[0015] According to another aspect of an embodiment of the present application, a computer program product is also provided, including computer instructions, which implement the steps of the above-mentioned method for generating a flood risk map when the computer instructions are executed by a processor.

[0016] In an embodiment of the present application, data related to flood disasters in a detection area within a detection period are obtained, wherein the flood disaster related data include at least: multiple inundation points; geographical disaster data of each inundation point is determined in the flood disaster related data, wherein the geographical disaster data is used to describe the geographical characteristics and flood disaster characteristics of the inundation point; a flood disaster prediction model is used to process and analyze the geographical disaster data to obtain a flood disaster level prediction value for each inundation point, wherein the flood disaster prediction model is a neural network model trained by a particle swarm optimization algorithm; a flood risk map of the area to be detected is generated according to the multiple flood disaster level prediction values, wherein in the flood risk map, the flood disaster levels that do not belong to the flood risk map are not included in the flood risk map. The areas corresponding to the predicted values ​​of flood disaster levels in the same numerical range are displayed in different colors in the flood risk map. The flood risk of the area to be detected is predicted by processing and analyzing multiple flooding points in the distribution network area using a neural network model based on the particle swarm optimization algorithm. Among them, the neural network model based on the particle optimization algorithm searches for the global optimal solution when predicting the flood risk, thereby achieving the purpose of avoiding the result being the local optimal solution, thereby achieving the technical effect of improving the accuracy of the prediction results, and further solving the technical problem of low accuracy of the prediction results obtained by predicting the flood risk of the power grid through statistical analysis of the time series data obtained by long-term measurement of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing a method for generating a flood risk map according to an embodiment of the present application;

[0019] Figure 2 is a flowchart of steps of a method for generating a flood risk map according to an embodiment of the present application;

[0020] Figure 3 is a structural diagram of a device for generating a flood risk map according to an embodiment of the present application;

[0021] Figure 4 It is a flood risk map of region A in different years output by a device for generating a flood risk map according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] In the related art, a convolutional neural network model is used to predict the flood risk of the distribution network based on input data. The convolutional neural network is prone to fall into local optimality and slow convergence during training, resulting in inaccurate prediction results obtained using the convolutional neural network model. In addition, the convolution operation of the convolutional neural network will cause information loss and degradation, especially in images with weak texture types. It is difficult to learn high-order semantic information, which limits the application of convolutional neural networks in complex system risk assessment. Therefore, the method for predicting flood risk in the related art still has the problem of not being universal. In order to solve this problem, a relevant solution is provided in the embodiment of the present application, which is described in detail below.

[0025] According to an embodiment of the present application, a method embodiment for generating a flood risk map is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a method for generating a flood risk map. Figure 1As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0028] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the method for generating a flood risk map in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the method for generating a flood risk map is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0029] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0031] The embodiment of the present application provides a method for generating a flood risk map that can be run in the above-mentioned operating environment. Figure 2 is a flowchart of the steps of the method for generating a flood risk map according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0032] Step S202, obtaining flood disaster related data of the area to be detected within a detection period, wherein the flood disaster related data at least includes: a plurality of flooded points.

[0033] The method provided in the embodiment of the present application can realize flood risk prediction for the power grid area to be tested, and can generate a flood risk map for displaying flood risks in different areas based on the results of flood risk prediction. In the method provided in the embodiment of the present application, the area where the power grid is located (i.e., the area to be tested) is tested during a preset detection period, and data related to flood disasters in the area to be tested are collected. In step S202, when flood risk prediction is to be performed on the area to be tested, flood disaster related data of the area to be tested collected during the preset detection period are obtained, wherein the above-mentioned flood disaster related data at least includes multiple inundation points when flood disasters occur in the area to be tested during the preset detection period, and the flood disaster related data within the detection period may not be all historical flood disaster data generated by the area to be tested before the current moment.

[0034] Step S204, determining the geographical disaster data of each flooded point in the flood disaster related data, wherein the geographical disaster data is used to describe the geographical characteristics and flood disaster characteristics of the flooded point.

[0035] In step S204, for each inundation point, the geographical disaster data related to each inundation point is extracted from all the flood disaster related data obtained in step S202, wherein the geographical disaster data related to each inundation point includes: data describing the geographical characteristics of the inundation point, and data describing the flood disaster characteristics of the inundation point.

[0036] According to an optional embodiment of the present application, the flood disaster related data also includes: a first type of data describing topography, a second type of data describing climate characteristics, a third type of data describing soil types, a fourth type of data describing vegetation coverage, the frequency of flood disasters, the intensity of flood disasters, and the scope of flood disaster impact; determining the geographical disaster data of each inundation point in the flood disaster related data, including: for each inundation point, determining the contribution density and spatial coordinates of the inundation point, wherein the contribution density is used to indicate the inundation range of the inundation point; generating a density distribution map based on the flood disaster related data and the contribution density of each inundation point, and determining based on the density distribution map The geographical disaster data used to describe the flood disaster characteristics of the inundation points, wherein the density distribution map shows the frequency of flood disasters, the intensity of flood disasters and the impact range of flood disasters in different inundation ranges, and the frequency of flood disasters, the intensity of flood disasters and the impact range of flood disasters in each inundation range are the geographical disaster data of the flood disaster characteristics of the inundation points corresponding to the inundation range; the first type of data, the second type of data, the third type of data and the fourth type of data associated with the inundation points are determined according to the spatial coordinates, wherein the first type of data, the second type of data, the third type of data and the fourth type of data associated with each inundation point are the geographical disaster data used to describe the geographical characteristics of the inundation points.

[0037] As mentioned in step S204, the geological disaster data related to each inundation point includes data for describing the geographical features of the inundation point and data for describing the flood disaster characteristics of each inundation point. Among them, the data for describing the geographical features of each inundation point includes: data for describing the topography and landform (i.e., the first type of data), data for describing the climate characteristics (i.e., the second type of data), and data for describing the soil type (i.e., the third type of data); the data for describing the flood disaster characteristics of each inundation point includes: the flood disaster occurrence frequency in the area to be detected, the flood disaster intensity in the area to be detected, and the flood disaster influence range in the area to be detected; the above data for describing the geographical features of the inundation point and the data for describing the flood disaster characteristics of the inundation point are all included in the flood disaster related data obtained in step S202. In this embodiment, when determining the geological disaster data related to each inundation point, it is first necessary to determine the contribution density and spatial coordinates of each inundation point. Among them, the contribution density of the inundation point is data for indicating the inundation range of the inundation point, and the spatial coordinates of the inundation point are the coordinates of the inundation point in the world coordinate system, and the spatial coordinates are composed of the longitude and latitude of the inundation point, which are used to indicate the position of the inundation point in the world coordinate system; further, according to the flood disaster related data obtained in step S202 and the contribution density of each inundation point, a density distribution map for describing the flood disaster situation in the area to be detected is constructed. Among them, the geological disaster data in the area to be detected is displayed in the density distribution map. For example, in the inundation range corresponding to each inundation point, at least the flood disaster occurrence frequency, flood disaster intensity, and flood disaster influence range of the inundation point and other geological disaster data for describing the flood disaster characteristics of the inundation point are displayed; in addition, the geological disaster data for describing the geographical features of each inundation point can also be displayed in the density distribution map. For example, after determining the spatial coordinates of each inundation point, the data for describing the topography and landform (i.e., the first type of data), the data for describing the climate characteristics (i.e., the second type of data), the data for describing the soil type (i.e., the third type of data), and the data for describing the vegetation coverage (i.e., the fourth type of data) associated with the spatial coordinates are displayed in the inundation range corresponding to the inundation point. In this embodiment, the contribution density of each inundation point is calculated according to the formula: (contribution density) dist i <radius, where i = 1,..., n represents the inundation point, pop i represents the flood disaster occurrence frequency of the inundation point i, dist i represents the frequency between the inundation point and the center point of the grid. The center point of the grid is the center point of the entire density distribution map; radius represents the bandwidth radius, which is determined according to the inundation range corresponding to the inundation point when analyzing each inundation point; Where n is the total number of flooded points involved in the calculation, SD is the standard distance, Among them, (x i ,y i , z i ) is the spatial coordinate of the flooded point i, is the average value of the coordinates of all flooded points, n is the total number of flooded points; D m The mean distance representing the average center is the median of multiple distance values ​​obtained by calculating the distances from all data points (flooded points) to the average center.

[0038] Step S206, using a flood disaster prediction model to process and analyze the geographical disaster data to obtain a flood disaster level prediction value for each inundation point, wherein the flood disaster prediction model is a neural network model trained using a particle swarm optimization algorithm.

[0039] In step S206, the flood disaster prediction model generated by particle swarm optimization algorithm training is used to process and analyze the inundation points, the data describing the geographical characteristics of the inundation points, and the data describing the flood disaster characteristics of the inundation points, so as to obtain the prediction result (i.e., the flood disaster level prediction value) for each inundation point output by the flood disaster prediction model, wherein the prediction result for each inundation point is used to indicate the flood disaster level of the inundation point.

[0040] In step S206, the flood disaster prediction model may be loaded into the memory, for example, the raw data of the flood disaster prediction model may be loaded from the non-volatile memory into the volatile memory, so that the processor runs the flood disaster prediction model. The raw data of the flood disaster prediction model refers to unprocessed data, and generally includes parameters and structural data of the flood disaster prediction model. The structural data may be a calculation relationship based on the parameters, such as a forward propagation calculation relationship between intermediate layers and neurons. Specifically, the structural data may include code related to the structure of the flood disaster prediction model, such as code for executing related calculations between intermediate layers and neurons.

[0041] In one embodiment, an area for loading the flood disaster prediction model can be divided in the memory, which can include a structure data storage area and a parameter storage area. The structure data storage area is used to store structure-related codes, and the parameters referenced by it can point to the address of a specific parameter in the parameter storage area through a pointer. During the training process of the flood disaster prediction model, it may be necessary to frequently update the parameters, and the parameter values ​​in the parameter storage area can be updated.

[0042] Optionally, a flood disaster prediction model is used to process and analyze the geographic disaster data to obtain a flood risk prediction value for each inundation point, including: for different types of geographic disaster data, determining multiple characteristic factors related to the formation of flood disasters, the development of flood disasters, and the degree of impact of flood disasters in the geographic disaster data; generating a corresponding characteristic map for each characteristic factor, wherein the characteristic map is used to display the spatial distribution of physical information represented by the characteristic factor in the area to be detected; and using a flood disaster prediction model to process and analyze multiple characteristic maps to obtain a flood risk prediction value for each inundation point.

[0043] In this embodiment, after the flood disaster data is associated with the inundation points in step S204, a flood risk prediction model is used to predict the flood risk of each inundation point. Specifically, multiple characteristic factors are determined in the flood disaster data. For example, a characteristic factor is generated for each type of geographical disaster data. For example, the types of geographical disaster data include geographical disaster data describing geographical characteristics and geographical disaster data describing flood characteristics. In this embodiment, characteristic factors related to the formation of flood disasters, characteristic factors related to the development of flood disasters, and characteristic factors related to the degree of impact of flood disasters are respectively determined in the geographical disaster data describing geographical characteristics; and characteristic factors related to the formation of flood disasters, characteristic factors related to the development of flood disasters, and characteristic factors related to the degree of impact of flood disasters are determined in the geographical disaster data describing flood characteristics. Furthermore, the flood disaster model processes and analyzes the multiple characteristic factors generated above, determines the spatial distribution of the physical information represented by each characteristic factor (such as topography, soil distribution, vegetation coverage, etc.) in the area to be detected, and generates a characteristic map that can display the spatial distribution, wherein a characteristic map is generated for each characteristic factor. Finally, the flood risk prediction model is used to process and analyze the multiple characteristic maps generated above to obtain the flood risk prediction value of each inundated point. In this embodiment, the flood disaster data obtained in step S202 may also include: meteorological data, terrain data, soil and vegetation data, land use data, socio-economic data, historical disaster data, basic geographic data, and other data closely related to power grid flood disasters; As can be seen from the above, the flood disaster related data are not measured at the same scale, so when constructing the feature map, in order to keep the ground resolution of each data consistent, the grid thematic map (i.e., each feature map) should be scaled uniformly, for example, the scales of all flood disaster related data can be unified by interpolation processing; for example, P = f (x, y) P is the pixel point to be interpolated, and multiple known points located in the reference grid with point P are used, such as Q 11 =(x1, y1), Q 12 =(x1, y2), Q 21=(x2, y1), Q 22 = (x2, y1) to interpolate point P, where point P and point Q 11 , Q 12 , Q 21 and Q 22 A rectangular / square grid is formed. When performing the difference processing, the difference in the X direction of point P is performed according to the following formula: Perform the difference in the Y direction for point P according to the following formula: Finally, according to the following formula, the pixel point f(x, y) of point P on the feature map is determined based on the difference result of point P in the X direction and the difference result in the Y direction:

[0044]

[0045] According to an optional embodiment of the present application, the flood disaster prediction model is trained by the following method: obtaining historical flood disaster data of the area to be detected, determining target data representing the altitude in the historical flood disaster data, and extracting a training set from the historical flood disaster data based on the target data, wherein the training set includes: flood disaster-related data, flood disaster level; using the training set and the particle swarm optimization algorithm to iteratively train the neural network model until the number of iterations reaches a preset number, stopping the iterative training, and obtaining the flood disaster prediction model.

[0046] The flood risk prediction model used in the embodiment of the present application is obtained by training the neural network model using the particle swarm optimization algorithm, wherein, when training the neural network model, the training data is extracted from the historical flood disaster data of the area to be detected, and the above-mentioned historical flood disaster data is the relevant data of all flood disasters that occurred in the area to be detected before the current moment. When extracting the training data, the data representing the altitude (i.e., the target data) is determined in the historical flood disaster data, and the altitude is used as a priori feature. The training data is extracted from the historical flood disaster data using the priori feature to obtain a training set composed of training data, wherein, since the flood disaster level will be determined after the flood disaster occurs, the historical flood disaster data not only contains flood disaster data but also contains multiple flood disaster levels, and each flood disaster level is mutually related to the relevant data of the flood disaster indicated by it. The purpose of training the flood risk prediction model is to use it to predict the flood risk level, therefore, the extracted training data contains not only flood disaster data but also flood disaster levels. After extracting the training set, the particle swarm optimization algorithm and the training set can be used to iteratively train the basic neural network model.

[0047] Optionally, extracting a training set from historical flood disaster data according to target data includes: determining multiple value intervals according to the value of the target data, wherein each value interval corresponds to a different value range; determining multiple data sets according to the multiple value intervals, wherein each data set contains the following data: target data whose value belongs to the value interval, target inundation points corresponding to the target data, and geographical disaster data associated with the inundation points; for each data set, normalizing the data in the data set and determining the variance of the normalized data; determining a first data volume of the data set and determining a ratio of the first data volume to a second volume, wherein the second volume is the volume of historical flood disaster data; determining a target volume according to a third volume, variance and ratio of the data set, wherein the target volume is the data volume of the training set; extracting the target volume of data from the historical flood disaster data as a training set.

[0048] As mentioned in the previous embodiment, the altitude is used as a priori feature, and the training data is extracted from the historical flood disaster data using the priori feature. In this embodiment, when extracting the training data, the historical flood disaster data is first divided into a data set according to the data representing the altitude (i.e., the target data); specifically, a plurality of numerical intervals representing different numerical ranges are determined according to the value of the data representing the altitude (i.e., the target data), wherein the number of numerical intervals may be predefined; next, the data representing the altitude (i.e., the target data) is classified into different numerical intervals according to the numerical value, and other flood disaster data associated with the target data is classified into the same numerical interval as the target data; wherein , each altitude data (i.e., target data) is at least associated with a (target) flooding point. When determining other flood disaster data associated with the target data, the associated (target) flooding point can be determined first, and then the geographical disaster data associated with the (target) flooding point can be determined. Therefore, a data set actually contains multiple data of different dimensions, such as the flooding point, the altitude of the flooding point, and the geographical disaster data of the flooding point (topography, vegetation coverage, soil permeability, flood disaster frequency, flood disaster impact range); in order to speed up the convergence speed of the neural network model during the training process and eliminate the influence of the dimension, different data sets are also normalized to unify the dimension of the data. In this embodiment, the training data are extracted from the multiple data sets generated above according to the following formula: Among them, i represents the i-th data set, n i represents the amount of data extracted from the i-th data set, N i represents the data volume of the ith data set (i.e., the first data volume), f represents the extraction ratio (i.e., the ratio of the data volume of each data set (i.e., the first volume) to the total data volume of historical flood disaster data (i.e., the second data volume)), L represents the total number of data sets, Si represents the variance of data set i, N j represents the amount of data in the Jth data set, S i represents the variance estimate of data set i, in, is a variance calculated based on the data contained in the ith data set. In this embodiment, the amount of data n to be extracted from each data set is determined by the above method. i The data extracted from each data set are grouped into a training set; the data in the entire training set is divided into training data and test data in a ratio of 7:3. The training data is used to iteratively train the neural network model, and the test data is used to evaluate the trained neural network model; for example, considering both the factors that promote the formation of floods and the factors that reduce the impact of floods, select indicators that jointly determine the probability of floods in the power grid area (i.e., the area to be detected), and combine the actual situation of the power grid area. The annual average rainfall, watershed density, slope, distance from the water body, Normalized Difference Vegetation Index (NDVI) and soil permeability are selected as risk assessment indicators, and population density, cultivated land density, building density, road density, and power grid facility density are selected as vulnerability assessment indicators.

[0049] According to some optional embodiments of the present application, a neural network model is iteratively trained using a training set and a particle swarm optimization algorithm, wherein each iterative training includes: determining a set consisting of multiple model parameters of a model to be trained as a particle to be optimized, wherein the model to be trained in the next iterative training is a model output by the previous iterative training, and when the iterative training is performed for the first time, the model to be trained is a neural network model; using a particle swarm optimization algorithm to update the particles to be optimized until the number of iterations reaches a preset number, and outputting target particles, wherein the target particles contain multiple updated values ​​of multiple model parameters; adjusting the numerical value of each model parameter of the neural network model to a corresponding updated value, and obtaining a flood disaster prediction model.

[0050] In some embodiments, before iterative training of the neural network model using the particle swarm optimization algorithm and the data in the training set, the key parameters required for training such as the number of iterations, individual learning factors and social learning factors are set first; during the iterative training process, at the time of initialization, the initial position and initial speed are randomly assigned to each particle to be optimized, and the speed and position of the particle to be optimized are updated in each iterative training; wherein, in this embodiment, the particle to be optimized is a data set containing multiple model parameters of the neural network model (for example, the weights, biases, learning rates, etc. connecting the neurons in each layer). During the entire training process, during the first iterative training, the neural network model with the model parameters as the initialization parameters is used as the training object, and during the other iterative trainings not including the first, the neural network model after the last iterative training is used as the training object (i.e., the model to be trained). However, the model parameters are not necessarily updated in each iterative training, so it is possible that the training objects of the two iterative trainings are the same. After the number of trainings reaches the set number of iterations (i.e., the preset number of times), the result of the last iterative training is output as the target particle, that is, the updated value of the model parameter output by the last iterative training is output as the target particle. The flood risk prediction model used in the embodiment of the present application can be obtained by adjusting the numerical values ​​of the model parameters of the initial neural network model to the updated values ​​of the model parameters output by the last iterative training. During the training process, in order to facilitate the convolutional neural network to extract features, the input of the network is based on a 128×128 sliding window, and the structure of the entire neural network model is divided into three parts: a feature map module, a multi-scale module, and an upsampling module. In the feature map module, the first layer is a combined image block of size 128×128×13, where the size of the convolution kernel is 3×3 with a stride of 2 pixels, and 1 pixel in other convolutional layers. The maximum pooling layer outputs a spatial neighborhood with a stride of 2 pixels in the 2×2 convolutional layer. Therefore, through this module, the height and width of the output layer are one-eighth of the combined image block. The structure of this module can be concisely described as: (input (128×128×13)-convolution layer 1 (64×64×64)-activation layer 1-convolution layer 2 (64×64×96)-normalization layer 2-activation layer 2-convolution layer 3 (64×64×128)-normalization layer 3-activation layer 3-max pooling layer-convolution layer 4 (32×32×192)-normalization layer 4-activation layer 4-convolution layer 5 (32×32×256)-normalization layer 5-activation layer 5-max pooling layer-convolution layer 6 (16×16×256)-normalization layer 6-activation layer 6-convolution layer 7 (16×16×512)-normalization layer 7-activation layer 7). In the multi-scale module, the output features (16×16×512) of activation layer 7 of the previous module are regarded as the input layer. In order to obtain multi-scale global features in the combined image, average pooling filters of different sizes are set during the training process.Each average pooling layer is followed by a convolutional layer and bilinear interpolation; thus, four parallel feature maps with the same height and width can be obtained. The sizes of the parallel average pooling filters are 16×16, 8×8, 4×4, and 2×2, respectively. For each branch, the stride of the convolution kernel in the convolution layer is 1 pixel, the size of the convolution kernel of the first convolution layer is 1×1, and the size of the other is 3×3; finally, by connecting the four output convolutional layers, a global feature map containing multi-scale information can be obtained. In the upsampling module, both high-level semantics and low-level spatial information are applied. The connection layer and feature layer in the multi-scale module will double the size of the upsampled feature map after bilinear interpolation; this process can be described as: (connection layer (16×16×1024) + activation layer 7 (16×16×512) - convolution layer 1 (16×16×512) - activation layer - upsampling layer 1 (32×32×512) + activation layer 5 (32×32×256) - convolution layer p2 (32×32×256) - normalization layer - activation layer - upsampling layer 2 (64×64×256) + activation layer 3 (64×64×128) - convolution layer 3 (64×64×128) - normalization layer - activation layer - upsampling 3 (128×128×128) - output - convolution (128×128×3)).

[0051] Optionally, the model output by each iterative training is determined by the following method: using the model to be trained to analyze and process the flood disaster related data in the training set to obtain a first prediction result, wherein the first prediction result is the flood disaster level prediction value output by the model to be trained; using the updated model to analyze and process the flood disaster related data in the training set to obtain a second prediction result, wherein the updated model is the model to be trained after adjusting the model parameters, and the second prediction result is the flood disaster level prediction value output by the updated model; determining a first error value between the first prediction result and the flood risk level in the training set, and determining a second error value between the second prediction result and the flood risk level in the training set; when the first error value is less than the second error value, output the model to be trained; when the first error value is greater than or equal to the second error value, output the updated model.

[0052] As mentioned in the previous embodiment, it is not necessary to update the model parameters for each iterative training. Whether the model parameters are updated for each iterative training is determined by the following method in this embodiment: the test data in the training set is used to evaluate the neural network model after each iterative training. The neural network model before iteration (i.e., the model to be trained) uses the inundation points in the test data and the geographical disaster data related to the inundation points as input data, and outputs a flood disaster level prediction value (i.e., the first prediction result) for the input data; the neural network model after iteration (i.e., the updated neural network model) uses the inundation points in the test data and the geographical disaster data related to the inundation points as input data, and outputs a flood disaster level prediction value (i.e., the second prediction result) for the input data; since the trained neural network model is used to predict the flood disaster risk level, the purpose of each training is to improve the accuracy of the prediction results outputted by it. Therefore, during each training, the model parameters of the neural network model with more accurate prediction results are outputted. In this embodiment, in order to determine a neural network model with more accurate prediction results, the flood risk level in the training set is used to determine the error value (i.e., the first error value) of the (first) prediction result output by the neural network model before iteration (i.e., the model to be trained), and the error value (i.e., the second error value) of the (second) prediction result output by the neural network model after iteration (i.e., the updated neural network model). The model parameters of the neural network model with a smaller error value are the result of this iteration; the neural network model whose model parameters are the result of this iteration is the updated model.

[0053] Step S208, generating a flood risk map of the area to be detected based on the multiple flood disaster level prediction values, wherein in the flood risk map, areas corresponding to flood disaster level prediction values ​​belonging to different numerical ranges are displayed in different colors in the flood risk map.

[0054] As mentioned in the above embodiments, the method provided in the embodiments of the present application can also generate a flood risk map for displaying flood risks in different areas based on the results of flood risk prediction. Specifically, after the prediction result of each inundation point (i.e., the flood disaster level prediction value) is obtained in step S206, in step S208, a flood risk map of the area to be detected is generated based on the prediction result of each inundation point; wherein, in this embodiment, multiple numerical ranges are preset, and each numerical range represents a flood disaster level. Therefore, when generating the flood risk map of the area to be detected based on the prediction result of each inundation point, the numerical range to which each prediction result belongs is first determined to determine the flood disaster level corresponding to the prediction result; further, the flood disaster level of each inundation point is determined according to the prediction result corresponding to each inundation point. In the flood risk map, the areas to which inundation points of different flood disaster levels belong are displayed in different colors.

[0055] Through the above steps, it is possible to use the flood disaster prediction model trained by the particle swarm optimization algorithm to predict the flood risk in the detection area. Among them, the flood disaster prediction model trained by the particle swarm optimization algorithm has the advantage of global search, avoids the problem of inaccurate prediction results caused by local search, and improves the accuracy of the prediction results.

[0056] Figure 3 is a structural diagram of a device for generating a flood risk map according to an embodiment of the present application, such as Figure 3 As shown, the device for generating a flood risk map includes: an acquisition module 30, which is used to obtain flood disaster related data of the area to be detected within the detection period, wherein the flood disaster related data at least includes: multiple inundation points; a determination module 32, which is used to determine the geographical disaster data of each inundation point in the flood disaster related data, wherein the geographical disaster data is used to describe the geographical characteristics and flood disaster characteristics of the inundation point; an analysis module 34, which is used to process and analyze the geographical disaster data using a flood disaster prediction model to obtain a flood disaster level prediction value for each inundation point, wherein the flood disaster prediction model is a neural network model trained using a particle optimization algorithm; a generation module 36, which is used to generate a flood risk map of the area to be detected based on multiple flood disaster level prediction values, wherein in the flood risk map, areas corresponding to flood disaster level prediction values ​​belonging to different numerical ranges are displayed in different colors in the flood risk map.

[0057] Figure 4 It is a flood risk map of area A in different years output by a device for generating a flood risk map; in the embodiment of the present application, an acquisition module 30 is used to obtain the average annual precipitation distribution data, digital elevation model, aspect data, slope data, soil geological data, vegetation index, river and lake data, road data, cultivated land and building data, population data and power grid facility data of area A; a determination module 32 is used to process and analyze the above data, thereby determining multiple flooding points, and associating each flooding point with the geographical disaster data of the flooding point; a flood disaster prediction model in an analysis module 34 is used to analyze each flooding point and its associated data, and output a flood disaster level prediction value for each flooding point; and a generation module 36 is used to generate a flood disaster level prediction value according to the flood disaster level prediction value output by the analysis module 34. Figure 4 Flood risk maps for area A in 2011 and 2019 are shown.

[0058] It should be noted that Figure 3 The preferred implementation of the illustrated embodiment can be found in Figure 2 The relevant description of the illustrated embodiment will not be repeated here.

[0059] An embodiment of the present application also provides a non-volatile storage medium, in which a computer program is stored, wherein the above method of generating a flood risk map is executed by running the computer program on a device where the non-volatile storage medium is located.

[0060] The above-mentioned non-volatile storage medium is used to store a program that performs the following functions: obtaining flood disaster-related data of the area to be detected within a detection period, wherein the flood disaster-related data at least includes: multiple inundation points; determining the geographical disaster data of each inundation point in the flood disaster-related data, wherein the geographical disaster data is used to describe the geographical characteristics and flood disaster characteristics of the inundation point; using a flood disaster prediction model to process and analyze the geographical disaster data to obtain a flood disaster level prediction value for each inundation point, wherein the flood disaster prediction model is a neural network model trained using a particle swarm optimization algorithm; generating a flood risk map of the area to be detected based on multiple flood disaster level prediction values, wherein in the flood risk map, areas corresponding to flood disaster level prediction values ​​belonging to different numerical ranges are displayed in different colors in the flood risk map.

[0061] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above method for generating a flood risk map through the computer program.

[0062] The processor in the above-mentioned electronic device is used to run a program that performs the following functions: obtaining flood disaster related data of the area to be detected within a detection period, wherein the flood disaster related data at least includes: multiple inundation points; determining the geographical disaster data of each inundation point in the flood disaster related data, wherein the geographical disaster data is used to describe the geographical characteristics and flood disaster characteristics of the inundation point; using a flood disaster prediction model to process and analyze the geographical disaster data to obtain a flood disaster level prediction value for each inundation point, wherein the flood disaster prediction model is a neural network model trained using a particle swarm optimization algorithm; generating a flood risk map of the area to be detected based on multiple flood disaster level prediction values, wherein in the flood risk map, areas corresponding to flood disaster level prediction values ​​belonging to different numerical ranges are displayed in different colors in the flood risk map.

[0063] An embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the above method for generating a flood risk map.

[0064] It should be noted that the various modules in the above-mentioned device for generating flood risk maps can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0065] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0066] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0067] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0068] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0069] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0070] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0071] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for generating a flood risk map, characterized in that: include: Acquire flood disaster related data of the area to be detected within a detection period, wherein the flood disaster related data at least includes: a plurality of flooded points; Determining geographical disaster data of each of the flooded points in the flood disaster related data, wherein the geographical disaster data is used to describe the geographical features and flood disaster features of the flooded points; The geographical disaster data are processed and analyzed using a flood disaster prediction model to obtain a flood disaster level prediction value for each inundated point, wherein the flood disaster prediction model is a neural network model trained using a particle swarm optimization algorithm; A flood risk map of the area to be detected is generated according to the multiple flood disaster level prediction values, wherein in the flood risk map, areas corresponding to the flood disaster level prediction values ​​belonging to different numerical ranges are displayed in different colors in the flood risk map.

2. The method according to claim 1, characterized in that The flood disaster related data also include: first-category data describing topography, second-category data describing climate characteristics, third-category data describing soil types, fourth-category data describing vegetation coverage, flood disaster frequency, flood disaster intensity, and flood disaster impact range; Determining the geographical disaster data of each of the flooded points in the flood disaster related data includes: For each of the flooded points, determining the contribution density and spatial coordinates of the flooded point, wherein the contribution density is used to indicate the flooded range of the flooded point; Generate a density distribution map based on the flood disaster related data and the contribution density of each of the inundation points, and determine the geographical disaster data used to describe the flood disaster characteristics of the inundation points based on the density distribution map, wherein the density distribution map shows the frequency of flood disasters, the intensity of flood disasters and the impact range of flood disasters in different inundation ranges, and the frequency of flood disasters, the intensity of flood disasters and the impact range of flood disasters in each of the inundation ranges are the geographical disaster data of the flood disaster characteristics of the inundation points corresponding to the inundation ranges; The first category data, the second category data, the third category data and the fourth category data associated with the flooding point are determined according to the spatial coordinates, wherein the first category data, the second category data, the third category data and the fourth category data associated with each of the flooding points are geographic disaster data for describing the geographic features of the flooding point.

3. The method according to claim 1, characterized in that The flood disaster prediction model is used to process and analyze the geographical disaster data to obtain the flood risk prediction value of each inundation point, including: For different types of geographical disaster data, determining a plurality of characteristic factors related to the formation of flood disasters, the development of flood disasters, and the degree of impact of flood disasters in the geographical disaster data; Generate a corresponding feature map for each of the characteristic factors, wherein the feature map is used to display the spatial distribution of the physical information represented by the characteristic factor in the area to be detected; The flood disaster prediction model is used to process and analyze the multiple characteristic maps to obtain the flood risk prediction value of each inundation point.

4. The method according to claim 1, characterized in that: The flood disaster prediction model is trained by the following method: Acquire historical flood disaster data of the area to be detected, determine target data representing altitude in the historical flood disaster data, and extract a training set from the historical flood disaster data according to the target data, wherein the training set includes: the flood disaster related data and the flood disaster level; The neural network model is iteratively trained using the training set and the particle swarm optimization algorithm until the number of iterations reaches a preset number, and the iterative training is stopped to obtain the flood disaster prediction model.

5. The method according to claim 4, characterized in that Extracting a training set from the historical flood disaster data according to the target data includes: Determine a plurality of value intervals according to the value of the target data, wherein each of the value intervals corresponds to a different value range; Determine multiple data sets according to the multiple numerical intervals, wherein each of the data sets includes the following data: target data whose values ​​belong to the numerical interval, target flooding points corresponding to the target data, and the geographical disaster data associated with the flooding points; For each of the data sets, normalizing the data in the data set, and determining the variance of the data after the normalization; Determine a first data volume of the data set, and determine a ratio of the first data volume to a second volume, wherein the second volume is the volume of the historical flood disaster data; Determining a target quantity according to the third quantity of the data set, the variance, and the ratio, wherein the target quantity is the amount of data in the training set; The target amount of data is extracted from the historical flood disaster data as the training set.

6. The method according to claim 4, characterized in that The neural network model is iteratively trained using the training set and the particle swarm optimization algorithm, wherein each time the iterative training is performed, it includes: Determine a set consisting of multiple model parameters of a to-be-trained model as a particle to be optimized, wherein the to-be-trained model in the next iterative training is the model outputted in the last iterative training, and when the iterative training is performed for the first time, the to-be-trained model is the neural network model; The particle swarm optimization algorithm is used to update the particles to be optimized until the number of iterations reaches the preset number, and a target particle is output, wherein the target particle contains multiple updated values ​​of multiple model parameters; The numerical value of each model parameter of the neural network model is adjusted to the corresponding updated value to obtain the flood disaster prediction model.

7. The method according to claim 6, characterized in that The model output of each iteration training is determined by the following method: Using the model to be trained to analyze and process the flood disaster related data in the training set to obtain a first prediction result, wherein the first prediction result is a flood disaster level prediction value output by the model to be trained; The updated model is used to analyze and process the flood disaster related data in the training set to obtain a second prediction result, wherein the updated model is the model to be trained after the model parameters are adjusted, and the second prediction result is the flood disaster level prediction value output by the updated model; Determining a first error value between the first prediction result and the flood risk level in the training set, and determining a second error value between the second prediction result and the flood risk level in the training set; When the first error value is less than the second error value, outputting the model to be trained; When the first error value is greater than or equal to the second error value, the updated model is output.

8. A device for generating a flood risk map, characterized in that: include: An acquisition module is used to acquire flood disaster related data of the area to be detected within a detection period, wherein the flood disaster related data at least includes: a plurality of flooded points; A determination module, used to determine the geographical disaster data of each of the flooded points in the flood disaster related data, wherein the geographical disaster data is used to describe the geographical features and flood disaster features of the flooded points; An analysis module is used to process and analyze the geographical disaster data using a flood disaster prediction model to obtain a flood disaster level prediction value for each inundation point, wherein the flood disaster prediction model is a neural network model trained using a particle optimization algorithm; A generation module is used to generate a flood risk map of the area to be detected based on multiple flood disaster level prediction values, wherein in the flood risk map, areas corresponding to the flood disaster level prediction values ​​belonging to different numerical ranges are displayed in different colors in the flood risk map.

9. A non-volatile storage medium, characterized in that: A computer program is stored in the non-volatile storage medium, wherein the method for generating a flood risk map as described in any one of claims 1 to 7 is executed by running the computer program on the device where the non-volatile storage medium is located.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method for generating a flood risk map according to any one of claims 1 to 7 through the computer program.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method for generating a flood risk map as described in any one of claims 1 to 7 are implemented.

Images