Flood reservoir flow prediction method and device and related equipment

Abstract

The invention provides a flood reservoir flow prediction method and device and related equipment, and relates to the technical field of disaster prevention and mitigation, and the method comprises the steps: obtaining a plurality of training data pairs corresponding to a target water conservancy facility, the plurality of training data pairs respectively corresponding to a plurality of floods experienced by the target water conservancy facility in a historical period, the training data pair comprises rainfall data indicating the rainfall of the corresponding flood and storage data indicating the storage flow of the target water conservancy facility in the corresponding flood; the in-storage data is data obtained through flood regulation calculation back calculation under the condition of water balance based on the out-storage data of the corresponding flood and the storage capacity data of the corresponding flood; performing data analysis on the plurality of training data pairs to obtain a target mapping relation; and according to the target mapping relationship and the rainfall of the current flood, predicting reservoir flow information of the current flood in the target water conservancy facility. According to the invention, more accurate storage flow information can be predicted.

Description

Technical Field

[0001] The present disclosure relates to the technical field of disaster prevention and reduction, and in particular to a method and device for predicting flood inflow into a reservoir and related equipment. Background Art

[0002] Rapid rehearsal of reservoir inflow flood is crucial to reducing the impact of flood disasters. Currently, reservoir flood forecasting mainly uses hydrological models to calculate runoff and obtain the flood inflow flow into the reservoir.

[0003] It was found in the application that, on the one hand, the hydrological model simplifies and generalizes the real water environment, which makes the inflow calculated based on the hydrological model and the actual inflow differ greatly; on the other hand, the calibration of the model parameters of the hydrological model depends on the monitoring data collected by the flow monitoring station. At present, due to the limitations of construction costs and subsequent maintenance costs, the deployment scale of the flow monitoring stations corresponding to most reservoirs is relatively limited, which makes the calibration of the model parameters in actual production more difficult and has a certain degree of distortion.

[0004] That is to say, the accuracy of flood inflow predicted based on relevant technologies is poor. Summary of the invention

[0005] The purpose of the present disclosure is to provide a flood inflow prediction method, device and related equipment to solve the problem that the accuracy of flood inflow prediction by related technologies is poor.

[0006] In a first aspect, the present application provides a method for predicting flood inflow, the method comprising: Acquire a plurality of training data pairs corresponding to a target water conservancy facility, wherein the plurality of training data pairs respectively correspond to a plurality of floods experienced by the target water conservancy facility in a historical period, and the training data pairs include: rainfall data indicating the rainfall amount corresponding to the flood and inflow data indicating the inflow flow of the target water conservancy facility in the corresponding flood, the inflow data being data obtained by back-calculating flood control calculations based on the outflow data corresponding to the flood and the reservoir capacity data corresponding to the flood under water balance conditions, the outflow data being used to indicate the outflow flow of the target water conservancy facility in the corresponding flood, and the reservoir capacity data being used to indicate the water storage capacity of the target water conservancy facility in the corresponding flood; Performing data analysis on the plurality of training data pairs to obtain a target mapping relationship, wherein the target mapping relationship is used to simulate a mapping relationship between flood rainfall and flood inflow of the target water conservancy facility; According to the target mapping relationship and the rainfall of the current flood, the inflow flow information of the current flood in the target water conservancy facility is predicted.

[0007] In a second aspect, the present application provides a flood inflow prediction device, the device comprising: A data acquisition module, used for acquiring a plurality of training data pairs corresponding to a target water conservancy facility, wherein the plurality of training data pairs respectively correspond to a plurality of floods experienced by the target water conservancy facility in a historical period, and the training data pairs include: rainfall data indicating the rainfall amount corresponding to the flood and inflow data indicating the inflow flow of the target water conservancy facility in the corresponding flood, the inflow data being data obtained by back-calculating flood control calculations based on the outflow data corresponding to the flood and the reservoir capacity data corresponding to the flood under water balance conditions, the outflow data being used to indicate the outflow flow of the target water conservancy facility in the corresponding flood, and the reservoir capacity data being used to indicate the water storage capacity of the target water conservancy facility in the corresponding flood; A data analysis module, used for performing data analysis on the plurality of training data pairs to obtain a target mapping relationship, wherein the target mapping relationship is used to simulate a mapping relationship between flood rainfall and flood inflow of the target water conservancy facility; The prediction module is used to predict the inflow flow information of the current flood in the target water conservancy facility according to the target mapping relationship and the rainfall of the current flood.

[0008] In a third aspect, the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method described in the first aspect.

[0009] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] In a fifth aspect, the present application provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0011] In the present application, the outflow flow and storage capacity data of the target water conservancy facility in the experienced flood are statistically analyzed, and the inflow flow of the target water conservancy facility in the experienced flood is back-calculated under the condition of water balance, and the inflow flow of the current flood is predicted accordingly, so as to replace the related technology of using hydrological models to estimate the inflow flow. This can not only circumvent the various limitations of the hydrological model in the application process, but also make the predicted inflow flow of the current flood more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flow chart of a flood inflow prediction method provided by an embodiment of the present disclosure; Figure 2It is a schematic diagram of a reservoir runoff generation and convergence process provided by an embodiment of the present disclosure; Figure 3 It is a structural schematic diagram of a flood inflow prediction device provided by an embodiment of the present disclosure; Figure 4 It is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0014] The present disclosure provides a method for predicting flood inflow. Figure 1 As shown, the flood inflow prediction method includes: Step 101: Obtain multiple training data pairs corresponding to target water conservancy facilities.

[0015] Among them, the multiple training data pairs respectively correspond to multiple floods experienced by the target water conservancy facility in historical periods, and the training data pairs include: rainfall data indicating the rainfall of the corresponding flood and inflow data indicating the inflow flow of the target water conservancy facility in the corresponding flood, the inflow data is data obtained by inverse calculation based on the outflow data of the corresponding flood and the reservoir capacity data of the corresponding flood under water balance conditions through flood control calculation, the outflow data is used to indicate the outflow flow of the target water conservancy facility in the corresponding flood, and the reservoir capacity data is used to indicate the water storage capacity of the target water conservancy facility in the corresponding flood.

[0016] Among them, the target water conservancy facilities are water conservancy facilities with flood storage and flood discharge functions, such as reservoirs, sluice gates, hydropower stations, etc.

[0017] Specifically, in the present application, flood refers to a situation where the water level of the main water area connected to the target water conservancy facility is greater than or equal to a preset flood water level.

[0018] The rainfall data can be: the trend of total rainfall over time in the associated area of ​​the target water conservancy facility during the period of occurrence of the corresponding flood, wherein the period of occurrence of the corresponding flood can be understood as the duration when the water level of the main water area caused by the corresponding flood is greater than or equal to the flood water level, and the associated area of ​​the target water conservancy facility can be understood as a circular area with the target water conservancy facility as the center and a preset radius as the coverage radius.

[0019] Similarly, the inflow data can be: the trend of the flood inflow flow of the target water conservancy facility over time during the period of the corresponding flood. The flood inflow flow can be understood as the volume of water flowing into the target water conservancy facility per unit time. For example, the flood inflow flow is 50m 3 / s.

[0020] The outflow data can be: the trend of the flood discharge of the target water conservancy facility over time during the period of the corresponding flood. The flood discharge can be understood as the volume of water flowing out of the target water conservancy facility per unit time. For example, the flood discharge is 60m 3 / s.

[0021] In the application, if there is flow monitoring data in the downstream river, it can be directly quoted. If there is no flow monitoring data, it needs to be calculated based on the actual working conditions of the target water conservancy facility combined with hydraulic formulas. For example: if there is gate control, the flood discharge of the target water conservancy facility at the corresponding time can be determined by monitoring the gate opening (such as 0.5m, 1m, fully open) and the number of gates opened. If there is no gate control, the flood discharge at the corresponding time can be determined by monitoring the water depth on the overflow weir (or by subtracting the weir top elevation from the real-time water level).

[0022] The reservoir capacity data may be: the volume of water stored in the target water conservancy facility during the period of occurrence of the corresponding flood / the trend of the volume of the remaining storable water over time.

[0023] In the application, by monitoring the water storage level of the target water conservancy facility, the volume of the stored water body of the target water conservancy facility at the corresponding time can be calculated using the known water level-area curve and water level-reservoir capacity curve. The volume of the remaining storable water body is the difference between the maximum volume of the target water conservancy facility that can be stored and the current volume of the stored water body.

[0024] The water balance condition is: in any period of the corresponding flood period, the changed inflow of the target water conservancy facility = the change in storage capacity of the target water conservancy facility + the outflow of the target water conservancy facility, among which the changed inflow of water is the product of the aforementioned flood inflow flow and the corresponding period, and the outflow of water is the product of the flood discharge flow and the corresponding period.

[0025] For example, if the outflow data is set to O(z(t), t), the area data is F(z(t), t), and the storage capacity data is the area data and water level change The product of t(t) and z(t), where t refers to the tth moment in the period of occurrence of the corresponding flood, and z(t) is used to represent the trend of the water level of the target water conservancy facility over time. Then, the above water balance condition can be expressed as:

[0026] In the above formula, I(t) represents the aforementioned storage data. Based on the water balance condition, the storage data can be calculated back as follows:

[0027] Step 102: Perform data analysis on the multiple training data pairs to obtain a target mapping relationship.

[0028] The target mapping relationship is used to simulate the mapping relationship between flood rainfall and flood inflow of the target water conservancy facility.

[0029] In one example, linear fitting or nonlinear fitting may be performed based on the multiple training data pairs to obtain the target mapping relationship.

[0030] In another example, a preset neural network model can also be trained based on the multiple training data to obtain a prediction model including the target mapping relationship, wherein the model input of the prediction model is rainfall data, and the model output of the prediction model is inflow data. The model training process of the prediction model can be understood as follows: in the training stage, feature extraction is performed on the model input, and the extracted features are subjected to convolution and other processing to obtain model prediction values, and then based on the difference between the model prediction value and the true value of the model input, the model parameters are adjusted in reverse until the preset training termination conditions are met.

[0031] Exemplarily, if the flood rainfall is set to P(t), the target mapping relationship can be expressed as: I(t)=f(P(t)).

[0032] Step 103: predict the inflow information of the current flood in the target water conservancy facility according to the target mapping relationship and the rainfall of the current flood.

[0033] Among them, the rainfall of the current flood can be understood as the trend of the total rainfall in the associated area of ​​the target water conservancy facility changing over time at the time of the current flood.

[0034] In the application, the rainfall of the current flood can be obtained based on meteorological data.

[0035] The inflow flow information of the current flood in the target water conservancy facility can be understood as the trend of the flood inflow flow of the target water conservancy facility changing over time during the period of occurrence of the current flood.

[0036] like Figure 2 As shown, Figure 2 I1(t)~I4(t) can be understood as the inflow of different water areas flowing into the target water conservancy facilities. In related technologies, the runoff of different water areas flowing into the target water conservancy facilities is calculated through hydrological models, and then the flood inflow of the target water conservancy facilities is obtained by summarizing them.

[0037] On the one hand, the hydrological model simplifies and generalizes the real water environment, which makes the inflow calculated based on the hydrological model and the actual inflow differ greatly. On the other hand, the calibration of the model parameters of the hydrological model depends on the monitoring data collected by the flow monitoring station. At present, due to the limitations of construction costs and subsequent maintenance costs, the deployment scale of the flow monitoring stations corresponding to most reservoirs is relatively limited, which makes the calibration of the model parameters in actual production more difficult and there is a certain degree of distortion.

[0038] Based on this, this application uses the statistical outflow flow and storage capacity data of the target water conservancy facilities in the experienced floods, and reversely calculates the inflow flow of the target water conservancy facilities in the experienced floods under the condition of water balance, and predicts the inflow flow of the current flood accordingly, so as to replace the related technology of using hydrological models to estimate the inflow flow. This can not only circumvent the various limitations of the hydrological models in the application process, but also make the predicted inflow flow of the current flood more accurate.

[0039] Exemplarily, flood control calculations can be performed based on the inflow information, thereby generating a flood control dispatch plan for the target water conservancy facility, so as to perform more effective flood control dispatch management on the target water conservancy facility based on the flood control dispatch plan.

[0040] In the application, the latest rainfall of the current flood can be obtained according to the real-time collected meteorological data, and then the process of step 103 is repeated to obtain the inflow flow information matching the latest collected meteorological data through dynamic calculation.

[0041] In one embodiment, the step of obtaining a plurality of training data pairs corresponding to the target water conservancy facilities includes: Get flood information for current floods; The flood information is retrieved from the historical database corresponding to the target water conservancy facility to obtain the plurality of training data pairs, wherein the training data pairs meet a preset condition, and the preset condition includes at least one of the following: The difference between the rainfall date associated with the training data pair and the rainfall date carried in the flood information is less than or equal to a preset date difference threshold; The ratio of the rainfall intensity associated with the training data pair to the rainfall intensity carried in the flood information is within a first preset fluctuation range; The ratio of the rainfall associated with the training data pair to the rainfall carried in the flood information is within a second preset fluctuation range.

[0042] In this embodiment, by selecting historical data with a rainfall date close to the current flood, a rainfall intensity close to the current flood, and a rainfall amount close to the current flood to construct a training data pair, the target mapping relationship obtained by subsequent analysis can be made more accurate, thereby making the predicted inflow flow information more accurate.

[0043] The ratio of the rainfall intensity associated with the training data pair and the rainfall intensity carried in the flood information is within the first preset fluctuation range, specifically: the ratio of the rainfall intensity associated with the training data pair and the rainfall intensity carried in the flood information is greater than or equal to the minimum value of the first preset fluctuation range, and the ratio of the rainfall intensity associated with the training data pair and the rainfall intensity carried in the flood information is less than or equal to the maximum value of the first preset fluctuation range.

[0044] Similarly, the ratio of the rainfall associated with the training data pair and the rainfall carried in the flood information is within the second preset fluctuation range, specifically: the ratio of the rainfall associated with the training data pair and the rainfall carried in the flood information is greater than or equal to the minimum value of the second preset fluctuation range, and the ratio of the rainfall associated with the training data pair and the rainfall carried in the flood information is less than or equal to the maximum value of the second preset fluctuation range.

[0045] The above-mentioned date difference threshold, the first preset fluctuation range, and the second preset fluctuation range can be adaptively set according to actual needs, and this application does not limit this.

[0046] It should be noted that the dates referred to in this application are Chinese lunar calendar dates. This setting can filter out training data pairs that are more compatible with the current flood meteorological conditions.

[0047] In the application, in the process of obtaining multiple training data pairs, the date difference threshold, the first preset fluctuation range, and the second preset fluctuation range can be dynamically adjusted to ensure that the number of the obtained multiple training data pairs is greater than or equal to the preset number threshold.

[0048] For example, the process of obtaining the multiple training data pairs may be: 1. Find training samples with similar time: Take the lunar calendar date corresponding to the occurrence time of the current flood as the base date, and find historical data within X time periods before and after the base date (X can be set to one month) in the historical database to form training sample 1 (which can be understood as the aforementioned training data pair); 2. Find training samples with similar rainfall intensity: Take the rainfall intensity of the current flood as the benchmark rainfall intensity, and find historical data with a corresponding rainfall intensity of Y times the benchmark rainfall intensity (Y can be set to 0.8~1.2) in the historical database, and form training sample 2 (which can be understood as the aforementioned training data pair); 3. Find similar rainfall training samples: Take the rainfall of the current flood as the benchmark rainfall, and find historical data with corresponding rainfall C times the benchmark rainfall (C can be set to 0.8~1.2) in the historical database, and form training sample 3 (which can be understood as the aforementioned training data pair); 4. Merge and remove duplicates from training samples 1, 2, and 3, and detect whether the number of samples in the resulting sample set is greater than or equal to the quantity threshold (e.g., 20-50). If the number of samples is less than the quantity threshold, adjust the aforementioned X / Y / C to obtain more training samples until the number of samples in the resulting sample set is greater than or equal to the quantity threshold.

[0049] In one embodiment, predicting the inflow information of the current flood in the target water conservancy facility according to the target mapping relationship and the rainfall of the current flood includes: According to the target mapping relationship and the rainfall of the current flood, predict the inflow flow data of the current flood in the target water conservancy facility; When the current flood meets the preset extreme rainfall conditions, the inflow flow data is corrected based on the correction coefficient, and the inflow flow information is formed according to the corrected inflow flow data, and the correction coefficient is greater than 1; When the current flood does not meet the preset extreme rainfall condition, the inflow flow information is formed according to the inflow flow data.

[0050] In the context of global warming, the global average annual temperature is rising year by year, the frequency of extreme weather is increasing year by year, and the extreme degree of extreme weather is also gradually increasing. Based on this, this embodiment introduces the determination of extreme rainfall conditions. When the current flood meets the extreme rainfall conditions, the predicted inflow flow data is corrected and amplified to adapt to the context of global warming, so as to make the predicted inflow flow information more accurate.

[0051] In one embodiment, the data correction of the inflow flow data based on the correction coefficient includes: The product of the correction coefficient and the inflow flow data is determined as the corrected inflow flow data.

[0052] Further, when the rainfall amount of the current flood is greater than the rainfall threshold and / or the rainfall intensity of the current flood is greater than the rainfall intensity threshold, it is determined that the current flood meets the preset extreme rainfall condition; When the rainfall of the current flood is less than or equal to the rainfall threshold, and the rainfall intensity of the current flood is less than or equal to the rainfall intensity threshold, it is determined that the current flood does not meet the preset extreme rainfall condition.

[0053] In this embodiment, by setting the rainfall threshold and the rainfall intensity threshold, it is convenient to determine whether the flood meets the extreme rainfall conditions.

[0054] In one embodiment, before predicting the inflow data of the current flood in the target water conservancy facility based on the target mapping relationship and the rainfall of the current flood, the method further includes: Obtaining a first average temperature of a target monitoring area in a time period that has occurred in a current meteorological monitoring cycle, and obtaining a second average temperature of the target monitoring area in a corresponding time period in a historical meteorological monitoring cycle; The correction coefficient is determined according to the ratio of the first average temperature to the second average temperature, wherein the larger the ratio of the first average temperature to the second average temperature is, the larger the correction coefficient is.

[0055] In this embodiment, the meteorological conditions of the environment in which the target water conservancy facility is located can be monitored on an annual basis. At this time, a meteorological monitoring cycle is one year. In this case, the historical meteorological monitoring cycle can be understood as a set base year, such as 2000, 1995, etc.

[0056] For example, if the current flood occurrence time is set to July 20, then the occurrence period in the current meteorological monitoring cycle can be understood as January 1-July 20 of the current year, and the corresponding period in the historical meteorological monitoring cycle can be understood as January 1-July 20 of the base year.

[0057] In this embodiment, the average temperature in the meteorological monitoring period is used as a reference, and the correction coefficient is determined by the difference in average temperature between the current meteorological monitoring period and the historical meteorological monitoring period, which can avoid interference from human factors and make the determined correction coefficient more accurate and reliable.

[0058] Among them, the ratio of the first average temperature to the second average temperature can be directly determined as the correction coefficient, or the ratio of the first average temperature to the second average temperature can be converted according to the average temperature-rainfall mapping relationship to obtain the correction coefficient, wherein the average temperature-rainfall mapping relationship is used to represent the correlation between the average temperature and rainfall (such as rainfall intensity, rainfall amount, etc.).

[0059] In general, the present application obtains the flood outflow and storage capacity changes of the target water conservancy facility in the historical period, and inversely calculates the historical inflow of the corresponding flood through water balance, and predicts the inflow of the current flood based on this, so as to replace the scheme of predicting the inflow of the current flood through the hydrological model in the related technology. It can not only overcome the errors and uncertainties in calculation accuracy caused by various generalizations when using hydrological models for flood forecasting, but also overcome the problem that it is difficult to verify and apply the hydrological model without reservoir flow monitoring stations, thereby improving the flexibility of the scheme application and expanding the scope of application of the scheme of the present application; and the flood inflow obtained by inverse calculation of the actual historical data can truly reflect the comprehensive influence of various factors in the rainfall-flow generation-confluence process of the water conservancy facility, and the inflow information predicted thereby can maintain a high timeliness and accuracy.

[0060] See also Figure 3 , Figure 3 A flood inflow prediction device is provided in an embodiment of the present disclosure. Figure 3 As shown, the flood inflow flow prediction device 300 includes: The data acquisition module 301 is used to acquire a plurality of training data pairs corresponding to the target water conservancy facility, wherein the plurality of training data pairs respectively correspond to a plurality of floods experienced by the target water conservancy facility in the historical period, and the training data pairs include: rainfall data indicating the rainfall amount corresponding to the flood and inflow data indicating the inflow flow of the target water conservancy facility in the corresponding flood, the inflow data being data obtained by back-calculating flood control calculations based on the outflow data corresponding to the flood and the reservoir capacity data corresponding to the flood under the condition of water balance, the outflow data being used to indicate the outflow flow of the target water conservancy facility in the corresponding flood, and the reservoir capacity data being used to indicate the water storage capacity of the target water conservancy facility in the corresponding flood; A data analysis module 302 is used to perform data analysis on the plurality of training data pairs to obtain a target mapping relationship, wherein the target mapping relationship is used to simulate a mapping relationship between flood rainfall and flood inflow of the target water conservancy facility; The prediction module 303 is used to predict the inflow flow information of the current flood in the target water conservancy facility according to the target mapping relationship and the rainfall of the current flood.

[0061] In one embodiment, the data acquisition module 301 is specifically used for: Get flood information for current floods; The flood information is retrieved from the historical database corresponding to the target water conservancy facility to obtain the plurality of training data pairs, wherein the training data pairs meet a preset condition, and the preset condition includes at least one of the following: The difference between the rainfall date associated with the training data pair and the rainfall date carried in the flood information is less than or equal to a preset date difference threshold; The ratio of the rainfall intensity associated with the training data pair to the rainfall intensity carried in the flood information is within a first preset fluctuation range; The ratio of the rainfall associated with the training data pair to the rainfall carried in the flood information is within a second preset fluctuation range.

[0062] In one embodiment, the prediction module 303 includes: A prediction unit, used for predicting the inflow flow data of the current flood in the target water conservancy facility according to the target mapping relationship and the rainfall of the current flood; a correction unit, configured to correct the inflow flow data based on a correction coefficient when the current flood meets a preset extreme rainfall condition, and form the inflow flow information according to the corrected inflow flow data, wherein the correction coefficient is greater than 1; The uncorrected unit is used to form the inflow information according to the inflow data when the current flood does not meet the preset extreme rainfall condition.

[0063] In one embodiment, the correction unit is specifically used for: When the current flood meets the preset extreme rainfall conditions, the product of the correction coefficient and the inflow flow data is determined as the corrected inflow flow data, and the inflow flow information is formed according to the corrected inflow flow data, and the correction coefficient is greater than 1.

[0064] In one embodiment, when the rainfall amount of the current flood is greater than the rainfall threshold and / or the rainfall intensity of the current flood is greater than the rainfall intensity threshold, it is determined that the current flood meets the preset extreme rainfall condition; When the rainfall of the current flood is less than or equal to the rainfall threshold, and the rainfall intensity of the current flood is less than or equal to the rainfall intensity threshold, it is determined that the current flood does not meet the preset extreme rainfall condition.

[0065] In one embodiment, the prediction module 303 further includes a coefficient determination unit, and the coefficient determination unit is specifically used to: Obtaining a first average temperature of a target monitoring area in a time period that has occurred in a current meteorological monitoring cycle, and obtaining a second average temperature of the target monitoring area in a corresponding time period in a historical meteorological monitoring cycle; The correction coefficient is determined according to the ratio of the first average temperature to the second average temperature, wherein the larger the ratio of the first average temperature to the second average temperature is, the larger the correction coefficient is.

[0066] The flood inflow prediction device 300 provided in the embodiment of the present disclosure can implement each process in the above-mentioned flood inflow prediction method embodiment, and will not be described again here to avoid repetition.

[0067] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0068] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0069] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 to a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0070] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0071] The computing unit 401 may be various general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the flood inflow flow prediction method. For example, in some embodiments, the flood inflow flow prediction method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the flood inflow flow prediction method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute the flood inflow prediction method in any other appropriate manner (eg, by means of firmware).

[0072] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0073] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0074] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0075] As used herein, the term "machine-readable medium" refers to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0076] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0077] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0078] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0079] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0080] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0081] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A flood inflow prediction method, characterized in that: The method comprises: Acquire a plurality of training data pairs corresponding to a target water conservancy facility, wherein the plurality of training data pairs respectively correspond to a plurality of floods experienced by the target water conservancy facility in a historical period, and the training data pairs include: rainfall data indicating the rainfall amount corresponding to the flood and inflow data indicating the inflow flow of the target water conservancy facility in the corresponding flood, the inflow data being data obtained by back-calculating flood control calculations based on the outflow data corresponding to the flood and the reservoir capacity data corresponding to the flood under water balance conditions, the outflow data being used to indicate the outflow flow of the target water conservancy facility in the corresponding flood, and the reservoir capacity data being used to indicate the water storage capacity of the target water conservancy facility in the corresponding flood; Performing data analysis on the plurality of training data pairs to obtain a target mapping relationship, wherein the target mapping relationship is used to simulate a mapping relationship between flood rainfall and flood inflow of the target water conservancy facility; According to the target mapping relationship and the rainfall of the current flood, the inflow flow information of the current flood in the target water conservancy facility is predicted.

2. The method according to claim 1, characterized in that The step of obtaining a plurality of training data pairs corresponding to the target water conservancy facilities includes: Get flood information for current floods; The flood information is retrieved from the historical database corresponding to the target water conservancy facility to obtain the plurality of training data pairs, wherein the training data pairs meet a preset condition, and the preset condition includes at least one of the following: The difference between the rainfall date associated with the training data pair and the rainfall date carried in the flood information is less than or equal to a preset date difference threshold; The ratio of the rainfall intensity associated with the training data pair to the rainfall intensity carried in the flood information is within a first preset fluctuation range; The ratio of the rainfall associated with the training data pair to the rainfall carried in the flood information is within a second preset fluctuation range.

3. The method according to claim 1, characterized in that The method of predicting the inflow information of the current flood in the target water conservancy facility according to the target mapping relationship and the rainfall of the current flood includes: According to the target mapping relationship and the rainfall of the current flood, predict the inflow flow data of the current flood in the target water conservancy facility; When the current flood meets the preset extreme rainfall conditions, the inflow flow data is corrected based on the correction coefficient, and the inflow flow information is formed according to the corrected inflow flow data, and the correction coefficient is greater than 1; When the current flood does not meet the preset extreme rainfall condition, the inflow flow information is formed according to the inflow flow data.

4. The method according to claim 3, characterized in that The step of correcting the inflow flow data based on the correction coefficient includes: The product of the correction coefficient and the inflow flow data is determined as the corrected inflow flow data.

5. The method according to claim 3, characterized in that: When the rainfall amount of the current flood is greater than the rainfall threshold and / or the rainfall intensity of the current flood is greater than the rainfall intensity threshold, determining that the current flood meets the preset extreme rainfall condition; When the rainfall of the current flood is less than or equal to the rainfall threshold, and the rainfall intensity of the current flood is less than or equal to the rainfall intensity threshold, it is determined that the current flood does not meet the preset extreme rainfall condition.

6. The method according to claim 3, characterized in that Before predicting the inflow data of the current flood in the target water conservancy facility based on the target mapping relationship and the rainfall of the current flood, the method further includes: Obtaining a first average temperature of a target monitoring area in a time period that has occurred in a current meteorological monitoring cycle, and obtaining a second average temperature of the target monitoring area in a corresponding time period in a historical meteorological monitoring cycle; The correction coefficient is determined according to the ratio of the first average temperature to the second average temperature, wherein the larger the ratio of the first average temperature to the second average temperature is, the larger the correction coefficient is.

7. A flood inflow prediction device, characterized in that: The device comprises: A data acquisition module, used for acquiring a plurality of training data pairs corresponding to a target water conservancy facility, wherein the plurality of training data pairs respectively correspond to a plurality of floods experienced by the target water conservancy facility in a historical period, and the training data pairs include: rainfall data indicating the rainfall amount corresponding to the flood and inflow data indicating the inflow flow of the target water conservancy facility in the corresponding flood, the inflow data being data obtained by back-calculating flood control calculations based on the outflow data corresponding to the flood and the reservoir capacity data corresponding to the flood under water balance conditions, the outflow data being used to indicate the outflow flow of the target water conservancy facility in the corresponding flood, and the reservoir capacity data being used to indicate the water storage capacity of the target water conservancy facility in the corresponding flood; A data analysis module, used for performing data analysis on the plurality of training data pairs to obtain a target mapping relationship, wherein the target mapping relationship is used to simulate a mapping relationship between flood rainfall and flood inflow of the target water conservancy facility; The prediction module is used to predict the inflow flow information of the current flood in the target water conservancy facility according to the target mapping relationship and the rainfall of the current flood.

8. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 6 when executed by the processor.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 6.

Images