Flood risk monitoring method and device, storage medium and electronic equipment

Abstract

The invention discloses a flood risk monitoring method and device, a storage medium and electronic equipment. Comprising the following steps: acquiring a first rainfall data set, a first geographical environment data set and first power grid data of a target area in a current time period; according to a data screening rule, screening out at least one piece of first target geographical environment data from the first geographical environment data set, wherein the correlation value of the first target geographical environment data and the flood submerging prediction range is not lower than a preset correlation threshold value; analyzing the first rainfall data set and each first target geographical environment data by using a flood inundation prediction model to obtain a first flood inundation prediction range of the target area in a future time period; and according to the first flood inundation prediction range and the first power grid data, determining a risk level of failure of each power grid device in the target area in the future time period due to flood inundation. According to the method, the technical problems of large calculation amount, long time consumption and low precision when a related urban flood inundation model predicts the flood inundation range are solved.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and more specifically, to a flood risk monitoring method and device, a storage medium, and an electronic device. Background Art

[0002] As an important pillar industry for national economic and social development, the development of the power industry is not only related to people's daily lives, but also affects the stability and development of the country. With the continuous expansion and extension of the scale of the power grid, the issue of power grid security has become increasingly prominent. However, flood disasters seriously threaten the safe operation of the power system due to their rapid occurrence and high frequency. In particular, sudden rainfall events are one of the main causes of floods. Therefore, predicting the flood inundation range under rainfall scenarios can timely discover the rain-inundated areas, effectively reduce the losses caused by flood disasters, and ensure the safety of the power grid.

[0003] At present, the key to reducing flood risks and reducing power grid damage caused by floods is to build an efficient urban flood inundation model, which can effectively reduce the risk of flood disasters by accurately predicting the flood inundation range under rainfall scenarios. To this end, relevant researchers have conducted relevant research, and physics-driven hydrological and hydrodynamic models have been applied to flood inundation prediction. However, these physics-driven models have high requirements for the accuracy of basic data, high calculation costs, and long time consumption. It is difficult to effectively respond to sudden heavy rainfall events, which reduces their application value in flood inundation.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a flood risk monitoring method and device, a storage medium, and an electronic device to at least solve the technical problems of large amount of calculation, long time consumption, and low accuracy when the relevant urban flood inundation model predicts the flood inundation range.

[0006] According to one aspect of an embodiment of the present application, a flood risk monitoring method is provided, comprising: obtaining a first rainfall data set, a first geographical environment data set, and a first power grid data of a target area in a current time period, wherein the first rainfall data set at least includes the rainfall of the target area at each moment in the current time period, the first geographical environment data set at least includes the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data at least includes the distribution data and water resistance data of all power grid equipment in the target area; screening out at least one first target geographical environment data having a correlation value with a flood inundation prediction range that is not less than a preset correlation threshold from the first geographical environment data set according to a preset data screening rule; analyzing the first rainfall data set and each first target geographical environment data using a pre-trained flood inundation prediction model to obtain a first flood inundation prediction range of the target area in a future time period, wherein the first flood inundation prediction range is used to reflect the distribution of water depth inundated by floods in the target area in the future time period; and determining the risk level of failure of each power grid equipment in the target area due to flood inundation in the future time period based on the first flood inundation prediction range and the first power grid data.

[0007] Optionally, the process of determining the data screening rules includes: obtaining multiple groups of historical data, wherein each group of historical data includes: taking multiple categories of geographical environment data in a second geographical environment data set of a test area within a first historical time period as influencing factors, taking a second flood inundation prediction range of the test area within a second historical time period as a target variable, and the first historical time period is earlier than the second historical time period; determining the first marginal probability distribution of each category of influencing factors, the second marginal probability distribution of the target variable, and the joint probability distribution between each category of influencing factors and the target variable based on the multiple groups of historical data; determining the correlation value between each category of influencing factors and the target variable based on the first marginal probability distribution of each category of influencing factors, the second marginal probability distribution of the target variable, and the joint probability distribution between each category of influencing factors and the target variable; and determining the data corresponding to the influencing factors whose correlation values ​​are not lower than the correlation threshold as model input data as the data screening rules.

[0008] Optionally, the training process of the flood inundation prediction model includes: constructing an initial learning model; obtaining a training sample set and a sample label set, wherein the training sample set includes a second rainfall data set of multiple test areas as training samples within a first historical time period and at least one second target geographical environment data, and the sample label set includes a second flood inundation prediction range of each test area within the second historical time period as a first sample label, and the second target geographical environment is data whose correlation with the flood inundation prediction range is higher than a preset correlation threshold and is screened out from the second geographical environment data set of the test area within the first historical time period according to data screening rules; and the initial learning model is iteratively trained using the training sample set and the sample label set to obtain a flood inundation prediction model.

[0009] Optionally, obtaining a training sample set and a sample label set includes: obtaining multiple test areas; for each test area, using a preset rainfall measurement method to obtain a second precipitation data set of the test area within a first historical time period, and using a preset terrain measurement method to obtain a second geographical environment data set of the test area within the first historical time period; screening out at least one second target geographical environment data having a correlation with a flood and inundation prediction range higher than a preset correlation threshold from the second geographical environment data set of the test area within the first historical time period according to a data screening rule, and using the second precipitation data set and each second target geographical environment data as training samples; forming a training sample set with the obtained multiple training samples; for each test area, calling a preset simulation software to analyze the second precipitation data set and the second geographical environment data set of the test area within the first historical time period to obtain a second flood and inundation prediction range of the test area within the second historical time period, and using the second flood and inundation prediction range as a sample label; and forming a sample label set with the obtained multiple sample labels.

[0010] Optionally, the initial learning model is iteratively trained using a training sample set and a sample label set to obtain a flood inundation prediction model, including: for each training batch in the iterative training process, each training sample of the training batch is input into the initial learning model to obtain each flood inundation prediction range output by the initial learning model, a target loss function is constructed using the flood inundation prediction range and the corresponding sample labels, and the model parameters of the initial learning model are adjusted according to the target loss function.

[0011] Optionally, the risk level of failure of each power grid equipment in the target area due to flooding in a future time period is determined based on the first flood inundation prediction range and the first power grid data, including: determining the sub-area where each power grid equipment in the target area is located based on the first power grid data, and determining the degree of inundation of each sub-area based on the first flood inundation prediction range, wherein the degree of inundation includes: mild inundation, moderate inundation, and severe inundation; determining the risk level of each power grid equipment due to flooding in a future time period based on the sub-area where each power grid equipment is located and the degree of inundation of each sub-area.

[0012] Optionally, the risk level of each power grid device failing due to flooding in a future time period is determined based on the sub-area where each power grid device is located and the degree of flooding in each sub-area, including: when the degree of flooding in the sub-area where the power grid device is located is light flooding, determining that the risk level of the power grid device failing due to flooding in a future time period is a low risk level; when the degree of flooding in the sub-area where the power grid device is located is moderate flooding or severe flooding, judging whether the water resistance data of the power grid device is lower than a preset water resistance threshold based on the first power grid data; when the water resistance data of the power grid device is not lower than the water resistance threshold, determining that the risk level of the power grid device failing due to flooding in a future time period is a medium risk level; when the water resistance data of the power grid device is lower than the water resistance threshold, determining that the risk level of the power grid device failing due to flooding in a future time period is a high risk level.

[0013] According to another aspect of the embodiment of the present application, a flood risk monitoring device is also provided, including: an acquisition module, used to acquire a first rainfall data set, a first geographical environment data set and a first power grid data of a target area in a current time period, wherein the first rainfall data set at least includes the rainfall of the target area at each moment in the current time period, the first geographical environment data set at least includes the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data at least includes the distribution data and water resistance data of all power grid equipment in the target area; a screening module, used to screen out at least one first target geographical environment data whose correlation value with the flood inundation prediction range is not less than a preset correlation threshold from the first geographical environment data set according to a preset data screening rule; a prediction module, used to analyze the first rainfall data set and each first target geographical environment data using a pre-trained flood inundation prediction model to obtain a first flood inundation prediction range of the target area in a future time period, wherein the first flood inundation prediction range is used to reflect the distribution of water depth inundated by floods in the target area in the future time period; a determination module, used to determine the risk level of each power grid equipment in the target area failing due to flood inundation in the future time period based on the first flood inundation prediction range and the first power grid data.

[0014] According to another aspect of an embodiment of the present application, a non-volatile storage medium is further provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned flood risk monitoring method by running the computer program.

[0015] According to another aspect of an embodiment of the present application, an electronic device is further provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned flood risk monitoring method through the computer program.

[0016] In the embodiment of the present application, a data screening mechanism is used to screen out key geographical environment data whose correlation value with the flood and waterlogging prediction range is not less than a preset correlation threshold from the collected geographical environment data set, and the screened key geographical environment data and the collected rainfall data set are used as the input of the flood and waterlogging prediction model to effectively eliminate redundant information, so that the model can more accurately capture the key driving factors of flood events, and improve the accuracy and efficiency of model prediction. Then, the pre-trained flood and waterlogging prediction model is used to analyze the real-time rainfall data and key geographical environment parameters, so as to quickly generate the first flood and waterlogging prediction range, and combine with the first power grid data to scientifically and reasonably determine the potential risk level of power grid equipment caused by flood disasters in a specific future time period, providing strong technical support for power grid flood prevention and disaster reduction. Thereby solving the technical problems of large amount of calculation, long time consumption and low precision when the relevant urban flood and waterlogging model predicts the flood and waterlogging range. 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 an optional computer terminal (or mobile device) for implementing a flood risk monitoring method according to an embodiment of the present application;

[0019] Figure 2 is a flow chart of an optional flood risk monitoring method according to an embodiment of the present application;

[0020] Figure 3 is a schematic structural diagram of an optional flood risk monitoring device according to an embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of the structure of an optional electronic device 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 addition, the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0025] Example 1

[0026] According to an embodiment of the present application, an embodiment of a flood risk monitoring method 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.

[0027] 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 (or mobile device) for implementing a flood risk monitoring method. Figure 1As shown, the computer terminal 10 (or mobile device 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.

[0028] 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 (or mobile device). 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).

[0029] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the flood risk monitoring method 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 flood risk monitoring method of the above-mentioned application 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.

[0030] 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.

[0031] 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 (or mobile device).

[0032] In the above operating environment, Figure 2 is a flow chart of an optional flood risk monitoring method according to an embodiment of the present application, such as Figure 2 As shown, the method at least includes steps S202-S206, wherein:

[0033] Step S202, obtaining a first rainfall data set, a first geographical environment data set and a first power grid data of a target area in a current time period.

[0034] In the technical solution provided in step S202, the above-mentioned target area refers to a specific geographical area, such as a city or an area covered by a power grid. The first rainfall data set includes information such as the rainfall amount, duration, distribution characteristics, intensity, etc. of the target area at each moment in the current time period, wherein the rainfall amount refers to the total amount of rain falling on a unit area of ​​the ground within a certain period of time, usually measured in millimeters (mm). As an important meteorological parameter, it is usually used to describe the intensity and measurement of precipitation. In an embodiment of the present application, a rainstorm intensity formula can usually be used to calculate the rainfall intensity of the target area at each moment in the current time period, thereby reflecting the rainfall of the target area at each moment in the current time period. For example, the rainstorm intensity formula shown below can be used:

[0035]

[0036] Where q represents the intensity of the rainstorm, which indicates the depth of rainfall per unit time, usually in millimeters per hour (mm / h); A1 represents the correction coefficient of the rain area, which takes into account the impact of the size of the rainfall area on the intensity of rainfall; C represents the regional coefficient, which reflects the hydrological and climatic characteristics of a specific area, so different regions will have different C values; p represents the recurrence period, in years, which represents the average interval of occurrence of rainstorms of a certain intensity in a statistical sense. For example, a rainstorm with a return period of 20 years means that a rainstorm of this intensity will occur once or more in an average of 20 years; t represents the duration of rainfall, that is, the time of continuous rainfall, usually in minutes (min) or hours (h), which affects the calculation of the intensity of the rainstorm; b and n represent empirical parameters, which are used to adjust the impact of duration (t) on the intensity of the rainstorm.

[0037] The first geographic environment data set includes at least the terrain data and geographic element distribution data of the target area in the current time period, which can provide a comprehensive geographic environment background and provide basic data support for subsequent flood inundation range prediction and power grid risk assessment. Among them, the terrain data can be obtained through digital terrain model (Digital Elevation Model, DEM) data, where the digital terrain model is to record the altitude information of each point on the surface through high-precision measurement technology such as satellite images, aerial photogrammetry, topography or LIDAR (Light Detection and Ranging), and present the undulating changes of the terrain in the form of a regular grid. Therefore, the terrain data obtained through the digital terrain model in the embodiment of the present application include but are not limited to: the slope aspect of the target area (indicating the descending direction of a point on the ground, that is, the slope direction of the point, usually expressed in degrees, 0 degrees means east, 90 degrees means south, 180 degrees means west, and 270 degrees means north), Curvature (describing the degree of curvature of the terrain surface, directly affecting the convergence and dispersion of water), Flow direction in D8 mode (specifies that the water of each pixel will flow to one of its eight neighboring pixels, and this mode is used to determine the path and direction of the water flow), Flow accumulation in D8 mode (indicating the total area of ​​the upstream area that flows into each pixel, usually used to identify watersheds and potential high-risk areas for floods), Flow direction in DINF (Deterministic Infinite) mode, Flow accumulation in DINF mode, Shaded Relief (indicates the undulation and structure of the terrain), roughness (describes the irregularity of the terrain surface), slope (indicates the inclination angle of a point on the ground), Topographic Position Index (measures the terrain position of a point relative to its neighborhood, used to identify mountain tops, ridges, valleys and plains), Terrain Ruggedness Index (quantifies the complexity and irregularity of the terrain), terrain amplitude (also known as terrain amplitude, describing the degree of terrain change), etc. In addition, geographic element distribution data can be obtained through a geographic information system (GIS), which records the boundary information of different regions, the distribution of roads, buildings, rivers, lakes and other geographical elements.Therefore, the geographical element distribution data obtained by the geographic information system in the embodiment of the present application includes but is not limited to: land use type, water body distribution, vegetation coverage, road network and other information in the target area.

[0038] The first power grid data includes at least the distribution data and water resistance data of all power grid equipment in the target area, where the distribution data includes but is not limited to: the location coordinates, type, and spatial distribution of the power grid equipment, which is crucial for understanding the layout of the equipment in the region and the scope to which it may be affected by floods; and the water resistance data reflects the performance indicators of the power grid equipment in a flooded environment, including the equipment's waterproof level, electrical safety performance, mechanical strength, corrosion resistance, and operating history and performance under specific water depth conditions. This information is used to assess the risk of damage and recovery capacity of equipment in flood events.

[0039] Step S204: at least one first target geographical environment data having a correlation value with the flood inundation prediction range not less than a preset correlation threshold is screened out from the first geographical environment data set according to a preset data screening rule.

[0040] In the technical solution provided in step S204, in order to ensure that the model prediction process focuses on the variables that have a significant impact on the prediction results, thereby improving the accuracy and efficiency of the prediction, at least one first target geographic environment data with a correlation value with the flood inundation prediction range that is not less than a preset correlation threshold can be firstly screened out from the first geographic environment data set according to the preset data screening rules, wherein the first target geographic environment data can be terrain data or geographic element distribution data. Through this screening mechanism, redundant information in the collected data can be effectively eliminated, so that the model can more accurately capture the key driving factors of flood events, thereby quickly predicting the potential flood inundation range under rainfall events, and providing timely and effective decision support for power grid risk management and emergency response.

[0041] Step S206, using the pre-trained flood inundation prediction model to analyze the first rainfall data set and each first target geographical environment data, to obtain a first flood inundation prediction range of the target area in a future time period.

[0042] In the technical solution provided in step S206, each rainfall amount and each first target geographical environment data in the first rainfall data set is taken as input, and analyzed using a pre-trained model to obtain a first flood inundation prediction range of the target area in a future time period, wherein the pre-trained model learns the relationship between rainfall intensity, terrain characteristics and flood inundation range based on historical data, and can quickly and accurately predict the water depth distribution of the target area that will be flooded in the future time period, that is, the first flood inundation prediction range, which provides key information for subsequent power grid risk management, helps decision makers identify potential high-risk areas in advance, and formulate corresponding emergency response measures.

[0043] Step S208, determining the risk level of failure of each power grid equipment in the target area due to flooding in a future time period based on the first flooding prediction range and the first power grid data.

[0044] In the technical solution provided in step S208, the first flood inundation prediction range and the first power grid data are comprehensively analyzed to assess the flood impact and the associated failure risk that each power grid device may suffer in the future time period. This process provides a clear risk map for power grid operators, helping them take targeted preventive measures before the disaster occurs to ensure the stable operation of the power grid.

[0045] The above method of this embodiment is further introduced below.

[0046] As an optional implementation, in the technical solution provided in the above step S204, the method may include:

[0047] Step 1: Get multiple sets of historical data.

[0048] Specifically, each set of historical data includes: multiple data in the second geographical environment data set of the test area in the first historical time period as multiple types of influencing factors, and the second flood inundation prediction range of the test area in the second historical time period as the target variable, wherein the second geographical environment data set also includes the terrain data and geographical element distribution data of the test area in the first historical time period. In addition, the first historical time period is earlier than the second historical time period, that is, the second historical time period is after the first historical time period and before the current time period.

[0049] Step 2: Determine the first marginal probability distribution of each type of influencing factor, the second marginal probability distribution of the target variable, and the joint probability distribution between each type of influencing factor and the target variable based on multiple groups of historical data.

[0050] The above marginal probability distribution reflects the frequency or distribution of each type of influencing factor or target variable in the historical data, which can be calculated by directly counting the number of occurrences of each possible value of each type of influencing factor or target variable in the historical data set and then dividing it by the total number of samples. The joint probability distribution reveals the correlation between different types of influencing factors and target variables.

[0051] Step 3: Determine the correlation value between each type of influencing factor and the target variable based on the first marginal probability distribution of each type of influencing factor, the second marginal probability distribution of the target variable, and the joint probability distribution between each type of influencing factor and the target variable.

[0052] Specifically, the correlation value between the influencing factor and the target variable can be expressed by the following formula:

[0053]

[0054] Where p(x) represents the first marginal probability distribution, p(y) represents the second marginal probability distribution, and p(x,y) represents the joint probability distribution.

[0055] Step 4: The data corresponding to the influencing factors whose correlation values ​​are not lower than the correlation threshold are used as model input data to determine the data screening rules.

[0056] For example, if the correlation value reaches above 0.5, it means that this factor may play an important role in the prediction model, and it can be considered as input data closely related to the flood inundation prediction range.

[0057] It should be noted that when the correlation value between the statistics and the flood inundation prediction range is not less than the influencing factor of the preset correlation threshold, the above mutual information method can be used, or the Pearson correlation coefficient can be used. In addition, in order to improve the data quality, the historical data can be pre-processed before executing the second step, including but not limited to: standardization processing, format unification processing, outlier detection and missing data filling.

[0058] As an optional implementation, in the technical solution provided in the above step S204, the training process of the flood inundation prediction model may include:

[0059] Step S1, constructing an initial learning model.

[0060] The types of the above initial learning models include but are not limited to: Random Forest Model, Support Vector Regression (SVR), Deep Neural Networks (DNN), ensemble learning models (such as integrating the prediction results of multiple different models, such as combining the prediction results of Random Forest, SVR and DNN), etc. The selection of the above model types is only used as an example for illustration, and the specific selection needs to be made in combination with the spatiotemporal characteristics of the sample data in the actual application scenario, the prediction accuracy requirements, the availability of computing resources, and the real-time requirements of the model.

[0061] Step S2, obtaining a training sample set and a sample label set.

[0062] Among them, the above-mentioned training sample set includes multiple second rainfall data sets and at least one second target geographical environment data of the test areas as training samples in the first historical time period, the above-mentioned sample label set includes the second flood inundation prediction range of each test area in the second historical time period as the first sample label, and the second target geographical environment is data whose correlation with the flood inundation prediction range is higher than a preset correlation threshold, filtered out from the second geographical environment data set of the test area in the first historical time period according to the data screening rules.

[0063] Optionally, the above step S2 can be implemented by the following steps:

[0064] First, a plurality of test areas are obtained, wherein the test area may be a target area or another area other than the target area.

[0065] For each test area, a preset rainfall measurement method (such as ground rain gauge observation, satellite remote sensing rainfall estimation or radar rainfall measurement technology, etc.) is used to obtain a second precipitation dataset of the test area within the first historical time period, and a preset topographic measurement method is used to obtain a second geographical environment dataset of the test area within the first historical time period; at least one second target geographical environment data having a correlation with the flood inundation prediction range higher than a preset correlation threshold is screened out from the second geographical environment dataset of the test area within the first historical time period according to data screening rules, and the second precipitation dataset and each second target geographical environment data are used as training samples; and the obtained multiple training samples are combined into a training sample set.

[0066] For each test area, the preset simulation software is called to analyze the second precipitation data set and the second geographical environment data set of the test area within the first historical time period to obtain the second flood inundation prediction range of the test area within the second historical time period, and the second flood inundation prediction range is used as the sample label; the obtained multiple sample labels are combined into a sample label set.

[0067] It should be noted that after obtaining multiple sets of sample data, the data needs to be cleaned and preprocessed to remove outliers and missing values ​​to ensure data quality and integrity.

[0068] Step S3, iteratively training the initial learning model using the training sample set and the sample label set to obtain a flood inundation prediction model.

[0069] Optionally, the above step S3 can be implemented by the following steps: for each training batch in the iterative training process, each training sample of the training batch is input into the initial learning model to obtain each flood inundation prediction range output by the initial learning model, and the target loss function is constructed using the flood inundation prediction range and the corresponding sample label, and the model parameters of the initial learning model are adjusted according to the target loss function.

[0070] In addition, in step 220, the flood inundation prediction model may be loaded into the memory, for example, the raw data of the flood inundation prediction model may be loaded from the non-volatile memory into the volatile memory, so that the processor runs the flood inundation prediction model. The raw data of the flood inundation prediction model refers to unprocessed data, and generally includes parameters and structural data of the flood inundation 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 inundation prediction model, such as code for executing related calculations between intermediate layers and neurons.

[0071] In one implementation, an area for loading the flood inundation 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 inundation prediction model, it may be necessary to frequently update the parameters, and the parameter values ​​in the parameter storage area can be updated.

[0072] As an optional implementation, in the technical solution provided in the above step S208, the method may include:

[0073] Step S2081, determining the sub-areas where each power grid device is located in the target area according to the first power grid data, and determining the flooding degree of each sub-area according to the first flood inundation prediction range. The flooding degree includes: slight flooding, moderate flooding, and severe flooding.

[0074] Step S2082, determining the risk level of each power grid device failing due to flooding in a future time period based on the sub-areas where each power grid device is located and the flooding degree of each sub-area.

[0075] In the technical solution provided in the above step S2082, the risk level can be determined by the following methods, including:

[0076] In the case where the flooding degree of the sub-area where the power grid equipment is located is slight flooding, the risk level of failure of the power grid equipment due to flooding in the future period is determined to be a low risk level;

[0077] When the flooding degree of the sub-area where the power grid equipment is located is moderately flooded or severely flooded, judging whether the water resistance data of the power grid equipment is lower than a preset water resistance threshold according to the first power grid data;

[0078] When the water resistance data of the power grid equipment is not lower than the water resistance threshold, the risk level of failure of the power grid equipment due to flooding in the future period is determined to be a medium risk level;

[0079] When the water resistance data of the power grid equipment is lower than the water resistance threshold, the risk level of failure of the power grid equipment due to flooding in the future period is determined to be a high risk level.

[0080] That is to say, firstly, based on the first power grid data and the first flood inundation prediction range, the flood inundation depth of each power grid device in the target area is identified; then, based on the water resistance data of each power grid device in the target area and the flood inundation depth of each power grid device, the possibility of damage to each power grid device is evaluated, and the possibility of damage to each power grid device is converted into an easy-to-understand risk level, such as "low", "medium", and "high". In particular, in order to facilitate the subsequent inspection of power grid equipment by the power grid operator, the risk level of each power grid device can be marked on the map corresponding to the target area, providing a clear and intuitive risk map for the power grid operator, helping them to take targeted preventive measures before the disaster occurs and ensure the stable operation of the power grid.

[0081] Based on the scheme defined by the above steps S202 to S208, it can be known that in the embodiment, a data screening mechanism is used to screen out key geographical environment data whose correlation value with the flood and waterlogging prediction range is not less than a preset correlation threshold from the collected geographical environment data set, and the screened key geographical environment data and the collected rainfall data set are used as the input of the flood and waterlogging prediction model to effectively eliminate redundant information, so that the model can more accurately capture the key driving factors of flood events, and improve the accuracy and efficiency of model prediction. Then, the pre-trained flood and waterlogging prediction model is used to analyze the real-time rainfall data and key geographical environment parameters, so as to quickly generate the first flood and waterlogging prediction range, and combined with the first power grid data, the potential risk level of power grid equipment caused by flood disasters in a specific future time period is scientifically and reasonably determined, providing strong technical support for power grid flood prevention and disaster reduction. Thereby solving the technical problems of large amount of calculation, long time consumption and low precision when the relevant urban flood and waterlogging model predicts the flood and waterlogging range.

[0082] Example 2

[0083] Based on the first embodiment of the present application, an embodiment of a flood risk monitoring device is also provided, and the flood risk monitoring method of the above embodiment is executed when the device is running. Figure 3 is a schematic structural diagram of an optional flood risk monitoring device according to an embodiment of the present application, such as Figure 3 As shown, the flood risk monitoring device at least includes an acquisition module 32, a screening module 34, a prediction module 36 and a determination module 38, wherein:

[0084] The acquisition module 32 is used to acquire a first rainfall data set, a first geographical environment data set and a first power grid data of the target area in the current time period, wherein the first rainfall data set at least includes the rainfall of the target area at each moment in the current time period, the first geographical environment data set at least includes the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data at least includes the distribution data and water resistance data of all power grid equipment in the target area;

[0085] A screening module 34 is used to screen out at least one first target geographical environment data having a correlation value with the flood inundation prediction range not less than a preset correlation threshold value from the first geographical environment data set according to a preset data screening rule;

[0086] The prediction module 36 is used to analyze the first rainfall data set and each first target geographical environment data by using the pre-trained flood inundation prediction model to obtain a first flood inundation prediction range of the target area in a future time period, wherein the first flood inundation prediction range is used to reflect the distribution of water depth inundated by floods in the target area in the future time period;

[0087] The determination module 38 is used to determine the risk level of failure of each power grid equipment in the target area due to flooding in the future time period based on the first flooding prediction range and the first power grid data.

[0088] It should be noted that the various modules in the above-mentioned flood risk monitoring device 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.

[0089] Example 3

[0090] According to an embodiment of the present application, a non-volatile storage medium is further provided, in which a program is stored, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the flood risk monitoring method in Example 1.

[0091] Optionally, the device where the non-volatile storage medium is located implements the following steps by running the program: obtaining a first rainfall data set, a first geographical environment data set and a first power grid data of the target area in the current time period, wherein the first rainfall data set at least includes the rainfall of the target area at each moment in the current time period, the first geographical environment data set at least includes the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data at least includes the distribution data and water resistance data of all power grid equipment in the target area; screening out at least one first target geographical environment data whose correlation value with the flood inundation prediction range is not less than a preset correlation threshold from the first geographical environment data set according to a preset data screening rule; analyzing the first rainfall data set and each first target geographical environment data using a pre-trained flood inundation prediction model to obtain a first flood inundation prediction range of the target area in the future time period, wherein the first flood inundation prediction range is used to reflect the distribution of water depth inundated by floods in the target area in the future time period; determining the risk level of failure of each power grid equipment in the target area due to floods in the future time period based on the first flood inundation prediction range and the first power grid data.

[0092] According to an embodiment of the present application, a computer program product is also provided, which includes a stored computer program, wherein when the computer program is executed by a processor, the flood risk monitoring method in Example 1 is implemented.

[0093] Optionally, the computer program executes the following steps: obtaining a first rainfall data set, a first geographical environment data set and a first power grid data of the target area in the current time period, wherein the first rainfall data set at least includes the rainfall of the target area at each moment in the current time period, the first geographical environment data set at least includes the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data at least includes the distribution data and water resistance data of all power grid equipment in the target area; screening out at least one first target geographical environment data whose correlation value with the flood inundation prediction range is not less than a preset correlation threshold from the first geographical environment data set according to a preset data screening rule; analyzing the first rainfall data set and each first target geographical environment data using a pre-trained flood inundation prediction model to obtain a first flood inundation prediction range of the target area in the future time period, wherein the first flood inundation prediction range is used to reflect the distribution of water depth inundated by floods in the target area in the future time period; determining the risk level of failure of each power grid equipment in the target area due to floods in the future time period based on the first flood inundation prediction range and the first power grid data.

[0094] According to an embodiment of the present application, a processor is also provided, which is used to run a program, wherein the flood risk monitoring method in Example 1 is executed when the program is running.

[0095] Optionally, when the program is running, the following steps are executed: obtaining a first rainfall data set, a first geographical environment data set and a first power grid data of the target area in the current time period, wherein the first rainfall data set at least includes the rainfall of the target area at each moment in the current time period, the first geographical environment data set at least includes the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data at least includes the distribution data and water resistance data of all power grid equipment in the target area; filtering out at least one first target geographical environment data whose correlation value with the flood inundation prediction range is not less than a preset correlation threshold from the first geographical environment data set according to a preset data screening rule; analyzing the first rainfall data set and each first target geographical environment data using a pre-trained flood inundation prediction model to obtain a first flood inundation prediction range of the target area in the future time period, wherein the first flood inundation prediction range is used to reflect the distribution of water depth inundated by floods in the target area in the future time period; determining the risk level of failure of each power grid equipment in the target area due to floods in the future time period based on the first flood inundation prediction range and the first power grid data.

[0096] According to an embodiment of the present application, an electronic device is also provided, wherein: Figure 4 is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application, such as Figure 4As shown, the electronic device includes one or more processors; a memory for storing one or more programs, which, when the one or more programs are executed by the one or more processors, enables the one or more processors to run the programs, wherein the programs are configured to execute the flood risk monitoring method in the above-mentioned embodiment 1 when running.

[0097] Optionally, the processor is configured to execute the following steps through a computer program: obtaining a first rainfall data set, a first geographical environment data set and a first power grid data of the target area in the current time period, wherein the first rainfall data set at least includes the rainfall of the target area at each moment in the current time period, the first geographical environment data set at least includes the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data at least includes the distribution data and water resistance data of all power grid equipment in the target area; screening out at least one first target geographical environment data whose correlation value with the flood inundation prediction range is not less than a preset correlation threshold from the first geographical environment data set according to a preset data screening rule; analyzing the first rainfall data set and each first target geographical environment data using a pre-trained flood inundation prediction model to obtain a first flood inundation prediction range of the target area in the future time period, wherein the first flood inundation prediction range is used to reflect the distribution of water depth in the target area that will be flooded in the future time period; determining the risk level of failure of each power grid equipment in the target area due to flood inundation in the future time period based on the first flood inundation prediction range and the first power grid data.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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 flood risk monitoring method, characterized in that: include: Acquire a first rainfall data set, a first geographical environment data set, and a first power grid data of a target area in a current time period, wherein the first rainfall data set includes at least the rainfall of the target area at each moment in the current time period, the first geographical environment data set includes at least the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data includes at least the distribution data and water resistance data of all power grid equipment in the target area; According to a preset data screening rule, at least one first target geographical environment data having a correlation value with the flood inundation prediction range not less than a preset correlation threshold is screened out from the first geographical environment data set; Analyzing the first rainfall data set and each of the first target geographical environment data using a pre-trained flood inundation prediction model to obtain a first flood inundation prediction range for the target area in a future time period, wherein the first flood inundation prediction range is used to reflect the distribution of water depth in the target area that will be flooded in the future time period; The risk level of failure of each power grid equipment in the target area due to flooding in a future time period is determined based on the first flood inundation prediction range and the first power grid data.

2. The method according to claim 1, characterized in that The process of determining the data screening rules includes: Acquire multiple groups of historical data, wherein each group of the historical data includes: multiple types of geographical environment data in a second geographical environment data set of a test area in a first historical time period as influencing factors, and a second flood inundation prediction range of the test area in a second historical time period as a target variable, and the first historical time period is earlier than the second historical time period; Determine, based on the multiple groups of historical data, a first marginal probability distribution of each type of the influencing factors, a second marginal probability distribution of the target variable, and a joint probability distribution between each type of the influencing factors and the target variable; Determine the correlation value between each category of the influencing factors and the target variable according to the first marginal probability distribution of each category of the influencing factors, the second marginal probability distribution of the target variable, and the joint probability distribution between each category of the influencing factors and the target variable; The data corresponding to the influencing factors whose correlation values ​​are not lower than the correlation threshold are used as model input data to determine the data screening rule.

3. The method according to claim 1, characterized in that The training process of the flood inundation prediction model includes: Build an initial learning model; Acquire a training sample set and a sample label set, wherein the training sample set includes a plurality of second rainfall data sets in a first historical time period and at least one second target geographical environment data of a test area as training samples, the sample label set includes a second flood inundation prediction range of each test area in the second historical time period as a first sample label, and the second target geographical environment is data whose correlation with the flood inundation prediction range is higher than a preset correlation threshold value, filtered out from the second geographical environment data set of the test area in the first historical time period according to the data screening rule; The initial learning model is iteratively trained using the training sample set and the sample label set to obtain the flood inundation prediction model.

4. The method according to claim 3, characterized in that Get the training sample set and sample label set, including: Get multiple test areas; For each of the test areas, a second precipitation data set of the test area within a first historical time period is obtained using a preset rainfall measurement method, and a second geographical environment data set of the test area within the first historical time period is obtained using a preset terrain measurement method; at least one second target geographical environment data having a correlation with the flood and inundation prediction range higher than a preset correlation threshold is screened out from the second geographical environment data set of the test area within the first historical time period according to the data screening rule, and the second precipitation data set and each of the second target geographical environment data are used as training samples; the obtained multiple training samples form the training sample set; For each of the test areas, a preset simulation software is called to analyze the second precipitation data set and the second geographical environment data set of the test area within the first historical time period to obtain a second flood inundation prediction range for the test area within the second historical time period, and the second flood inundation prediction range is used as a sample label; the obtained multiple sample labels are combined into the sample label set.

5. The method according to claim 3, characterized in that: Iteratively training the initial learning model using the training sample set and the sample label set to obtain the flood inundation prediction model includes: For each training batch in the iterative training process, each training sample of the training batch is input into the initial learning model to obtain each flood inundation prediction range output by the initial learning model, and a target loss function is constructed using the flood inundation prediction range and the corresponding sample labels, and the model parameters of the initial learning model are adjusted according to the target loss function.

6. The method according to claim 1, characterized in that Determining the risk level of failure of each power grid device in the target area due to flooding in a future time period according to the first flooding prediction range and the first power grid data includes: Determine the sub-areas where each power grid device in the target area is located according to the first power grid data, and determine the flooding degree of each sub-area according to the first flood inundation prediction range, wherein the flooding degree includes: slight inundation, moderate inundation, and severe inundation; The risk level of failure of each of the power grid devices due to flooding in a future time period is determined based on the sub-areas where each of the power grid devices is located and the flooding degree of each of the sub-areas.

7. The method according to claim 6, characterized in that Determining the risk level of failure of each of the power grid devices due to flooding in a future time period based on the sub-areas where each of the power grid devices is located and the flooding degree of each of the sub-areas, includes: In the case where the flooding degree of the sub-area where the power grid equipment is located is the slight flooding, determining that the risk level of failure of the power grid equipment due to flooding in the future time period is a low risk level; When the flooding degree of the sub-area where the power grid equipment is located is the moderate flooding or the severe flooding, judging whether the water resistance data of the power grid equipment is lower than a preset water resistance threshold according to the first power grid data; When the water resistance data of the power grid equipment is not lower than the water resistance threshold, determining that the risk level of failure of the power grid equipment due to flooding in the future time period is a medium risk level; When the water resistance data of the power grid equipment is lower than the water resistance threshold, it is determined that the risk level of failure of the power grid equipment due to flooding in the future time period is a high risk level.

8. A flood risk monitoring device, characterized in that: include: An acquisition module, used to acquire a first rainfall data set, a first geographical environment data set and a first power grid data of a target area in a current time period, wherein the first rainfall data set includes at least the rainfall of the target area at each moment in the current time period, the first geographical environment data set includes at least the terrain data and geographical element distribution data of the target area in the current time period, and the first power grid data includes at least the distribution data and water resistance data of all power grid equipment in the target area; A screening module, configured to screen out at least one first target geographical environment data having a correlation value with the flood inundation prediction range not less than a preset correlation threshold value from the first geographical environment data set according to a preset data screening rule; A prediction module, configured to analyze the first rainfall data set and each of the first target geographical environment data using a pre-trained flood prediction model to obtain a first flood prediction range for the target area in a future time period, wherein the first flood prediction range is used to reflect the distribution of water depth in the target area that will be flooded in the future time period; A determination module is used to determine the risk level of failure of each power grid equipment in the target area due to flooding in a future time period based on the first flooding prediction range and the first power grid data.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, wherein the device where the non-volatile storage medium is located executes the flood risk monitoring method according to any one of claims 1 to 7 by running the computer program.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program, when running, executes the flood risk monitoring method described in any one of claims 1 to 7.

Images