Forecasting method and system for small reservoir

Abstract

The invention discloses a forecasting method and system for a small reservoir, and belongs to the technical field of reservoir rainstorm resistance. The method comprises the following steps: for a target small reservoir, preprocessing system database data and historical result data of the target small reservoir to obtain target data; according to the target data, constructing a flood forecasting model, acquiring meteorological grid forecast rainfall data of the target small reservoir and the basin where the target small reservoir is located in real time, and inputting the meteorological grid forecast rainfall data into the flood forecasting model; calculating the water level change of the target small reservoir in the future preset time in real time by using the flood forecasting model according to the meteorological grid forecast rainfall data; according to the water level change, the flood time and the flood peak water level of the target small reservoir are determined, and based on the flood time and the flood peak water level, real-time disaster forecast is given out for the target small reservoir. The method is beneficial for solving the problem of automatic and rapid forecasting of a large number of widely existing small reservoirs.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir anti - rainstorm, and more specifically, to a forecasting method and system for small reservoirs. Background Art

[0002] Currently, in Liaoning Province, the anti - rainstorm capacity is calculated based on rainfall - runoff. Through the runoff coefficient and the principle of water balance, the anti - rainstorm capacity is inversely deduced from the reservoir capacity. However, the two key calculation parameters used in this method do not originate from the reservoir itself. Among them, the antecedent precipitation amount Pa (soil saturation) is obtained by transplanting from representative stations, and the rainfall - runoff relationship curve is obtained by referring to the rainfall - runoff relationship of large reservoirs or hydrological regions without data. Although the calculation process is simple and rapid, the accuracy is insufficient and the error is relatively large.

[0003] In view of the above problems, traditional forecasting models are relatively applicable to large reservoirs in large basins because they consider many factors and the calculation is relatively complex. However, it is difficult to achieve fast and efficient forecasting for a large number of small reservoirs. Summary of the Invention

[0004] In view of the above problems, the present invention proposes a forecasting method for small reservoirs, including:

[0005] For a target small reservoir, obtain the system database data and historical result data of the target small reservoir, and pre - process the system database data and historical result data of the target small reservoir to obtain target data;

[0006] According to the target data, construct a flood forecasting model, and real - time obtain the meteorological grid forecast rainfall data of the basin where the target small reservoir is located, and input it into the flood forecasting model;

[0007] Use the flood forecasting model to calculate the water level change of the target small reservoir within a preset future time according to the meteorological grid forecast rainfall data;

[0008] Determine the flood occurrence time and peak flood level of the target small reservoir through the water level change, and issue a real - time disaster forecast for the target small reservoir based on the flood occurrence time and peak flood level.

[0009] Optionally, the system database data includes: real - time monitoring data for the target small reservoir;

[0010] The real - time monitoring data includes: real - time rainfall and water situation data of the basin where the target small reservoir is located and basin meteorological grid data.

[0011] Optionally, the historical result data includes:

[0012] Reservoir characteristic data, reservoir sub-basin data and historical water level data of the target small reservoir.

[0013] Optionally, preprocessing the system database data and historical achievement data of the target small reservoir to obtain target data includes:

[0014] After cleaning, deduplicating, and completing the system database data and historical achievement data of the target small reservoir, the system database data and historical achievement data to be processed are generated; grid calculation is performed on the system database data to be processed to generate rainfall information data of the target small reservoir; feature extraction is performed on the historical achievement data to be processed to generate feature data; and the rainfall information data and feature data are used as target data;

[0015] The characteristic data includes:

[0016] Reservoir capacity relationship curve, discharge relationship curve, reservoir basin shape characteristic data and inflow and outflow data.

[0017] Optionally, constructing a flood forecasting model based on the target data includes:

[0018] Based on a preset distributed forecast model and according to the watershed data divided for the target small reservoir, a distributed forecast model applicable to the target small reservoir is constructed;

[0019] Based on the target data, the model parameters of the distributed forecast model are adjusted to generate a flood forecast model suitable for the target small reservoir.

[0020] Optionally, the method further includes: issuing a real-time disaster forecast based on the target small reservoir, and generating a decision on the disaster in real time to respond to the occurrence of the disaster.

[0021] Optionally, the method further includes: determining the rainstorm resistance capacity of the target small reservoir based on the flood forecast model and rainfall data;

[0022] Establishing a flood forecast results database and a rainstorm resistance capability results database for the target small reservoir, and uploading the forecast data and rainstorm resistance capability data output by the flood forecast model to the flood forecast results database and the rainstorm resistance capability results database respectively;

[0023] The model parameters of the flood forecast model are optimized based on the comparison results of the data in the flood forecast results database and the rainstorm resistance capability results database with the actual data.

[0024] Optionally, the method further includes:

[0025] Based on the characteristic data of the small reservoir basin, the runoff generation and concentration characteristic data, and the natural outflow characteristic data, and according to the meteorological grid forecast rainfall data, the water level change of the target small reservoir within a preset future time is calculated in real time.

[0026] Optionally, the runoff generation and concentration characteristic data is used to calculate the net water volume and the confluent water volume of the small reservoir.

[0027] On the other hand, the present invention also provides a forecasting system for a small reservoir, including:

[0028] A data acquisition unit, configured to obtain the system database data and historical result data of the target small reservoir for the target small reservoir, and preprocess the system database data and historical result data of the target small reservoir to obtain target data;

[0029] A modeling unit, configured to construct a flood forecasting model according to the target data, and in real time obtain the meteorological grid forecast rainfall data of the basin where the target small reservoir is located, and input it into the flood forecasting model;

[0030] A calculation unit, configured to use the flood forecasting model to calculate in real time the water level change of the target small reservoir within a preset future time according to the meteorological grid forecast rainfall data;

[0031] A forecasting unit, configured to determine the flood occurrence time and peak flood level of the target small reservoir through the water level change, and issue a real-time disaster forecast for the target small reservoir based on the flood occurrence time and peak flood level.

[0032] On the other hand, the present invention also provides a computing device, including: one or more processors;

[0033] The processor is configured to execute one or more programs;

[0034] When the one or more programs are executed by the one or more processors, the method as described above is implemented.

[0035] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the method as described above is implemented.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] The present invention provides a forecasting method for small reservoirs, including: for a target small reservoir, obtaining the system database data and historical achievement data of the target small reservoir, and preprocessing the system database data and historical achievement data of the target small reservoir to obtain target data; according to the target data, constructing a flood forecasting model, and real-time obtaining the meteorological grid forecast rainfall data of the basin where the target small reservoir is located, and inputting it into the flood forecasting model; using the flood forecasting model to calculate in real time the water level change of the target small reservoir within a preset future time according to the meteorological grid forecast rainfall data; through the water level change, determining the flood occurrence time and flood peak water level of the target small reservoir, and based on the flood occurrence time and flood peak water level, issuing a real-time disaster forecast for the target small reservoir. The present invention is beneficial to solving the problem of automatic and rapid forecasting of a large number of existing small reservoirs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flowchart of the method of the present invention;

[0039] Figure 2 It is a structure diagram of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] Now, exemplary embodiments of the present invention will be introduced with reference to the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely, and to fully convey the scope of the present invention to those skilled in the art. The terms in the exemplary embodiments shown in the drawings are not limitations on the present invention. In the drawings, the same unit / element uses the same reference numeral.

[0041] Unless otherwise specified, the terms (including scientific and technical terms) used herein have the ordinary meaning understood by those skilled in the art. In addition, it can be understood that the terms defined in the commonly used dictionary should be understood as having a meaning consistent with the context of their related fields, and should not be understood as idealized or overly formal meanings.

[0042] Embodiment 1:

[0043] The present invention proposes a forecasting method for small reservoirs, as Figure 1 shown, including:

[0044] Step 1: For a target small reservoir, obtain the system database data and historical achievement data of the target small reservoir, and preprocess the system database data and historical achievement data of the target small reservoir to obtain target data;

[0045] Step 2: Based on the target data, construct a flood forecasting model, and obtain the meteorological grid forecast rainfall data of the basin where the target small reservoir is located in real time, and input it into the flood forecasting model;

[0046] Step 3: Using the flood forecasting model, calculate the water level change of the target small reservoir within a preset future time according to the meteorological grid forecast rainfall data;

[0047] Step 4: Determine the flood occurrence time and peak flood level of the target small reservoir through the water level change, and issue a real-time disaster forecast for the target small reservoir based on the flood occurrence time and peak flood level.

[0048] Among them, the system database data includes: real-time monitoring data for the target small reservoir;

[0049] The real-time monitoring data includes: real-time rainfall and water regime data and basin meteorological grid data of the basin where the target small reservoir is located.

[0050] Among them, the historical achievement data includes:

[0051] Reservoir characteristic data, reservoir sub-basin data and historical water level data of the target small reservoir.

[0052] Among them, preprocessing the system database data and historical achievement data of the target small reservoir to obtain target data includes:

[0053] After cleaning, de-duplicating and complementing the system database data and historical achievement data of the target small reservoir, generate the to-be-processed system database data and to-be-processed historical achievement data. For the to-be-processed system database data, perform grid calculation to generate the rainfall information data of the target small reservoir. For the to-be-processed historical achievement data, perform feature extraction to generate feature data. Use the rainfall information data and feature data as target data;

[0054] The feature data includes:

[0055] Storage capacity relationship curve, discharge relationship curve, reservoir basin shape characteristic data and inflow and outflow discharge data.

[0056] Among them, constructing a flood forecasting model according to the target data includes:

[0057] Based on a preset distributed forecasting model, construct a distributed forecasting model applicable to the target small reservoir according to the basin data divided for the target small reservoir;

[0058] And based on the target data, adjust the model parameters of the distributed forecasting model to generate a flood forecasting model applicable to the target small reservoir.

[0059] Among them, the method further includes: issuing a real-time disaster forecast according to the target small reservoir, and generating a decision on the disaster in real time to cope with the occurrence of the disaster.

[0060] Among them, the method further includes: based on the flood forecasting model, determine the rainstorm resistance ability of the target small reservoir according to rainfall data;

[0061] Establish a flood forecasting result library and a rainstorm resistance ability result library for the target small reservoir, and upload the flood forecasting model, the forecast data output, and the rainstorm resistance ability data to the flood forecasting result library and the rainstorm resistance ability result library respectively;

[0062] Optimize the model parameters of the flood forecasting model based on the comparison results between the data existing in the flood forecasting result library and the rainstorm resistance ability result library and the actual data.

[0063] Among them, the method further includes:

[0064] Based on the small reservoir basin characteristic data, runoff generation and concentration characteristic data, and natural outflow characteristic data, calculate the water level change of the target small reservoir within a preset future time according to the meteorological grid forecast rainfall data.

[0065] Among them, the runoff generation and concentration characteristic data is used to calculate the net water volume and the converged water volume of the small reservoir.

[0066] The following explains the data sources, thematic database construction, reservoir inflow forecasting calculation services, etc. used in the present invention:

[0067] Data sources:

[0068] The data sources mainly include system database data and historical result data.

[0069] The database data is mainly connected to the real-time monitoring information of the small reservoir, such as real-time rainfall and water conditions, and basin meteorological grid data, providing a reliable rainfall data source for model calculation and analysis.

[0070] The historical result data mainly includes the basic information of the reservoir and historical data.

[0071] (1) Collect reservoir characteristic data:

[0072] It should collect storage capacity relationship curves, discharge relationship curves, other characteristic value information, etc.

[0073] (2) Extract the small reservoir sub-basin:

[0074] Due to different shapes of the reservoir basin, it is necessary to extract the upstream and downstream sub-basins to cope with different distributions of rainfall centers.

[0075] (3) Historical data processing:

[0076] 1) Conduct a gridded analysis of historical rainfall in Liaoning Province, and combine it with the boundaries of the reservoir sub-basins to calculate historical rainfall information;

[0077] 2) Based on the historical water level monitoring data of the reservoir and the outflow discharge, calculate the historical inflow discharge information.

[0078] (4) Construction of reservoir forecasting schemes and parameter calibration:

[0079] 1) Use the distributed Xin'anjiang model and combine it with the division of the reservoir sub-basins to construct a forecasting scheme;

[0080] 2) Use the processed historical data for model parameter calibration.

[0081] Construction of a special topic database:

[0082] Construct a flood forecasting result library and a rainstorm resistance capacity result library to provide data storage, analysis, and calculation. Provide a standard library table structure for the business analysis and calculation of small reservoirs and the data call of subsequent business platforms.

[0083] Reservoir inflow forecasting calculation service:

[0084] The system integrates multiple models such as the distributed Xin'anjiang model, rainfall-runoff correlation diagram, Muskingum method, and geomorphic unit hydrograph, and has functions such as automatic timed forecasting, manual intervention interactive forecasting, and real-time correction, providing "forecasting and early warning" services for disaster prevention and mitigation. Connect to grid rainfall meteorological data and support the output of forecasting result data. It mainly includes meteorological precipitation numerical forecasting, forecasting model construction, forecasting scheme management, flood forecasting management, etc.

[0085] Meteorological precipitation numerical forecasting:

[0086] Connect to the meteorological precipitation numerical forecasting function within the small reservoir basin, develop data synchronization software, and achieve synchronization with the 3km grid numerical forecasting results of the meteorological bureau.

[0087] Forecasting model construction:

[0088] The selection of flood forecasting models mainly focuses on the construction of the Xin'anjiang model and the rainfall-runoff model.

[0089] Classify according to the models incorporated into the system, separate the models, interfaces, data, and services, and use object-oriented technology to standardize the input and output interfaces of various models and formulate a unified encapsulation technology standard.

[0090] Forecasting scheme management:

[0091] The scenario prediction is used for the operation staff to construct single-node scenarios for reservoirs. It includes parts such as establishing a prediction scenario from a non-prediction scenario, establishing a new scenario for a station with an existing prediction scenario, and calibrating parameters of an existing prediction scenario, and provides functions such as scenario construction and prediction scenario management.

[0092] (1) Scenario construction: The scenario construction is completed through processes such as selecting a prediction station, selecting the inflow, delineating the catchment area, selecting a prediction model, selecting a river station, and selecting a rain gauge station.

[0093] (2) Prediction scenario management:

[0094] Functions such as editing the scenario, editing parameters, editing the scenario description, copying the scenario, exporting rain gauge stations, exporting the basin shp file, deleting the scenario, and copying basin coordinates are realized.

[0095] The selection of flood prediction models mainly focuses on the construction of the Xin'anjiang model and the construction of rainfall-runoff models.

[0096] According to the models incorporated into the system, the models, interfaces, data, and services are separated. The input and output interfaces of various models are standardized using object-oriented technology, and a unified encapsulation technology standard is formulated.

[0097] Inflow prediction for reservoirs:

[0098] It supports the inflow prediction for reservoirs at stations with existing prediction scenarios. During the prediction process, the model parameters are calibrated and adjusted. Functions such as setting the forecast period, operational prediction, and prediction data management are provided.

[0099] (1) Forecast period setting: The forecast period can be set according to the calibration situation, combined with the measured data, to improve the prediction accuracy and ensure that the forecast period is 8 - 12 hours or more.

[0100] (2) Operational prediction: The prediction is carried out based on the measured rainfall information and the future rainfall prediction information. It supports the operation staff to adjust parameters and conduct trial calculations on-site, perform analysis of individual floods, and at the same time, relevant parameters can be preset, and the scenarios for automatic prediction can be selected to predict the flood flow process.

[0101] (3) Prediction data management: Comprehensively manage the prediction scenarios, provide convenient query services, and provide a reference basis for adjusting important parameters of flood prediction.

[0102] Analysis of the rainstorm resistance ability of small reservoirs:

[0103] Determine an appropriate calculation method for the rainstorm resistance ability, effectively access the forecast information, provide services such as site selection and information query. The rainstorm resistance ability analysis makes full use of the short-term forecast rainfall data of the sites and the short-term flood forecast result information, uses the trial calculation method and combines parameter analysis to conduct the forecast operation of the reservoir sites, completes the result statistics of the rainstorm resistance ability, generates relevant operation plans through the result accuracy evaluation, provides data interfaces for subsequent model applications and reservoir joint operation, and supports reservoir operation decision-making and operation safety.

[0104] It mainly includes content such as forecast information access, site selection, information query, rainstorm resistance ability analysis, result statistics, accuracy evaluation, etc.

[0105] The advantages of the present invention are as follows:

[0106] The present invention is used for quickly and continuously rolling forecasting a large number of small reservoirs during the actual disaster prevention and mitigation process. Combining the basin characteristics, runoff generation and concentration characteristics, and natural outflow characteristics of small reservoirs, using the meteorological grid forecast rainfall data as the forecast input, and rolling calculating the water level change process of small reservoirs within the next 72 hours. Through this process, analyze the flood occurrence time and peak water level of small reservoirs, and combine the flood control indicators of small reservoirs to achieve disaster prevention and mitigation of small reservoirs.

[0107] Strong pertinence, focusing on analyzing the factors that have a greater impact on the runoff generation and concentration of small reservoirs as key parameters.

[0108] Simplify the calculation process and improve the calculation efficiency to meet the rapid forecasting of a large number of small reservoirs.

[0109] Utilize the front-end and back-end separation design to achieve rapid forecasting and result display.

[0110] The following takes the Liaoning area as an example to illustrate the forecast:

[0111] Heavy rainfall in Liaoning region is greatly affected by the Northeast Cold Vortex, which is a large-scale upper-air cold vortex active in Northeast China or its vicinity. It is a deep system that can maintain for 3 - 4 days or longer. The low-level and ultra-low-level jets are near the remaining veins of Changbai Mountain in southeastern Liaoning. Due to the climbing and lifting effect and the flow around the trumpet-shaped terrain, a local "cyclonic small circulation" or "airflow convergence area" is formed. Therefore, the objective forecasting technology of artificial intelligence is introduced. Considering the influence of the Northeast Cold Vortex and the precipitation enhancement effect of the terrain characteristics of different river basins in Liaoning Province, the forecasting accuracy of rainfall areas, intensities, and extreme values has been effectively improved. Through the analysis of precipitation climate characteristics in Liaoning Province and the refined verification of numerical model forecasts, three daily precipitation forecasting schemes are established, namely the optimal percentile integration technology based on probability ideas, the multi-model integration technology based on probability matching average, and the area correction technology based on spatial verification. The three schemes are secondarily integrated to obtain the optimal daily precipitation forecast. The multi-model integration and convolutional neural network methods are used for temporal downscaling to obtain the hourly precipitation forecast for the next 72 hours.

[0112] Firstly, it is upgraded from two categories of sunny / rainy and heavy rain in 2021 to 5 magnitudes (0.1mm, 10mm, 25mm, 50mm, 100mm); secondly, according to the precipitation probability formula, 9 probability members of precipitation for each magnitude are obtained; finally, an ensemble forecasting system with 45 members (5×9 = 45 members) is formed.

[0113] Calculation method:

[0114]

[0115] Among them: a: the number of models forecasting precipitation; b: the total number of models, which is 8; QY: the forecasting score index for precipitation of a certain magnitude. Finally, the rainfall amount is deduced:

[0116]

[0117] The probabilities of different rainfall magnitudes are determined through this process. Finally, the priority magnitude is determined based on the score, solving the problem of the optimal falling area. Using the scientific research results of the Northeast Cold Vortex, historical data is used for back-calculation to determine the dispersion index. Then, through the calculation of the flow precipitation rate under different models, the weights are determined. Finally, artificial intelligence technology is studied to achieve the forecast correction under the terrain enhancement effect.

[0118] The establishment of the small reservoir forecasting model is as follows:

[0119] Simplify the construction of the API model. According to the hydrological characteristics of Liaoning region and factors such as the small catchment area of small reservoirs and the significant influence of different area shapes on confluence, determine the key elements that can reflect the characteristics of runoff generation and confluence in small reservoirs, such as the infiltration capacity of the soil in small watersheds (underlying surface), the water-holding capacity of the surface (surface), the number of serial reservoirs (shape), the regulation parameters (shape), the natural discharge capacity of each small reservoir (outflow), the antecedent precipitation amount in different regions (antecedent rain), and the relationship between reservoir water level and storage capacity to form a forecasting model for the integration of runoff generation - confluence - discharge in small reservoirs.

[0120] Dynamically calculate the antecedent precipitation amount Pa of each small reservoir (starting from 100 days ago), using Pa[t + 1] = K * (Pa[t] + P[t]), where Pa[t] is the antecedent precipitation amount at the start of the t-th day (mm), K is the daily recession coefficient of basin storage (related to the monthly average daily evaporation capacity of the basin), and Pa[t] < Im (the maximum storage capacity of the basin, which is a basic characteristic reflecting the water storage capacity of the basin).

[0121] The core of reservoir rainfall intake capacity analysis is to predict the inflow hydrograph of the reservoir based on future rainfall. There is a common problem of missing historical data in small - scale data. Conventional models such as the Xin'anjiang model and the rainfall - runoff correlation diagram model cannot effectively calibrate the parameters. It is necessary to develop a flood forecasting model suitable for small reservoirs. By organizing the basic information of small reservoirs, including the catchment area, basin division, maximum soil water storage capacity, water level - storage capacity curve, and flood discharge capacity curve information of each reservoir. Make full use of these basic data and develop a simple API model in combination with runoff generation, confluence, and discharge.

[0122] For the runoff - generation process, according to the maximum soil water storage capacity (Im) of each reservoir basin and in combination with the antecedent precipitation amount, adopt a combined method of full - storage runoff generation + excess - infiltration runoff generation. When calculating the net rainfall amount, calculate the full - storage runoff generation amount through the "antecedent precipitation amount" and the maximum Im value of different basins, calculate the excess - infiltration runoff generation amount through the "infiltration coefficient" of different regions and the rainfall intensity per unit time, adjust for the influence of evaporation on the net rainfall amount through the "loss coefficient", and considering the small water volume of small reservoirs and the significant influence of different surface topographies on runoff generation, add the surface water - holding capacity parameter.

[0123] For the confluence process, adopt the Nash unit - hydrograph calculation principle. Considering the characteristics of small reservoirs, the shape of the catchment area has a significant influence on confluence. By adjusting two parameters, namely the "number of serial reservoirs" (longitudinal) and the "reservoir regulation parameter" (lateral), the confluence process of the basin under different shapes can be simulated. Considering that there is a certain water loss during the confluence process, this part of the loss is considered together with the loss in runoff generation.

[0124] During the flood discharge process, the flood discharge curves of individual small reservoirs are adopted. The flood discharge capacity corresponding to the water level calculated according to the instantaneous unit hydrograph of the reservoir at the previous moment is involved in the calculation of the instantaneous unit hydrograph of the next time period. For the first calculation, the flood discharge capacity corresponding to the current water level of the reservoir is used for the calculation.

[0125] The advantage of this model is that it can be expressed by mathematical formulas, with simple parameters and convenient calculation, and it is also easy to be transplanted to small reservoirs lacking actual measured data of rainstorm floods. The disadvantage is that it does not consider the uneven spatial and temporal distribution of rainfall, and there are errors between the calculation results using a single unit hydrograph and the actual flood process. However, for small reservoirs, the catchment area is generally only dozens of square kilometers, or even several square kilometers. Therefore, this model can play a normal role and has certain advantages in the flood forecasting of small reservoirs.

[0126] This model combines machine learning technology, continuously and dynamically corrects parameters according to the increased monitoring records of actual rainfall events, and automatically calibrates and corrects the existing parameters according to the newly occurred rainfall process and applies them to the calculation of flood forecasting, rainwater intake, and early warning for the next rainfall process. The prediction accuracy of the model is continuously improved by intelligent automatic optimization of parameters.

[0127] The present invention also proposes a forecasting system 200 for small reservoirs, as Figure 2 shown, including:

[0128] A data acquisition unit 201, configured to obtain the system database data and historical result data of the target small reservoir for the target small reservoir, and preprocess the system database data and historical result data of the target small reservoir to obtain target data;

[0129] A modeling unit 202, configured to construct a flood forecasting model according to the target data, and real-time obtain the meteorological grid forecast rainfall data of the basin where the target small reservoir is located and input it into the flood forecasting model;

[0130] A calculation unit 203, configured to use the flood forecasting model to calculate in real time the water level change of the target small reservoir within a preset future time according to the meteorological grid forecast rainfall data;

[0131] A forecasting unit 204, configured to determine the flood occurrence time and flood peak water level of the target small reservoir through the water level change, and issue a real-time disaster forecast for the target small reservoir based on the flood occurrence time and flood peak water level.

[0132] The present invention is beneficial to solving the problem of automatic and rapid forecasting of a large number of widely existing small reservoirs.

[0133] Embodiment 2:

[0134] On the other hand, the present invention also proposes a forecasting system for small reservoirs, including:

[0135] A data acquisition unit, configured to acquire the system database data and historical result data of the target small reservoir, and preprocess the system database data and historical result data of the target small reservoir to obtain target data;

[0136] A modeling unit, configured to construct a flood forecasting model based on the target data, and in real time acquire the meteorological grid forecast rainfall data of the basin where the target small reservoir is located and input it into the flood forecasting model;

[0137] A calculation unit, configured to use the flood forecasting model to calculate in real time the water level change of the target small reservoir within a preset future time according to the meteorological grid forecast rainfall data;

[0138] A forecasting unit, configured to determine the flood occurrence time and peak flood level of the target small reservoir through the water level change, and issue a real-time disaster forecast for the target small reservoir based on the flood occurrence time and peak flood level.

[0139] The present invention is conducive to solving the problem of automatic and rapid forecasting of a large number of widely existing small reservoirs.

[0140] Embodiment 3:

[0141] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of the method in the above embodiments.

[0142] Embodiment 4:

[0143] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a computer device, used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. Moreover, in this storage space, one or more instructions suitable for being loaded and executed by the processor are also stored. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the steps of the method in the above embodiments.

[0144] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes. The solutions in the embodiments of the present invention can be implemented using various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0145] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0146] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the function specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0148] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0149] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A forecasting method for small reservoirs, characterized in that, The method includes: For a target small reservoir, obtain the system database data and historical achievement data of the target small reservoir, and preprocess the system database data and historical achievement data of the target small reservoir to obtain target data; According to the target data, construct a flood forecasting model, and in real time obtain the meteorological grid forecast rainfall data of the basin where the target small reservoir is located, and input it into the flood forecasting model; Using the flood forecasting model, calculate in real time the water level change of the target small reservoir within a preset future time according to the meteorological grid forecast rainfall data; Through the water level change, determine the flood occurrence time and peak flood level of the target small reservoir, and based on the flood occurrence time and peak flood level, issue a real-time disaster forecast for the target small reservoir.

2. The prediction method according to claim 1, characterized in that, The system database data includes: real-time monitoring data for the target small reservoir; The real-time monitoring data includes: real-time rainfall and water regime data and basin meteorological grid data of the basin where the target small reservoir is located.

3. The forecasting method according to claim 1, characterized in that: The historical achievement data includes: Reservoir characteristic data, reservoir sub-basin data and historical water level data of the target small reservoir.

4. The prediction method according to claim 1, wherein The preprocessing of the system database data and historical achievement data of the target small reservoir to obtain target data includes: After cleaning, de-duplicating and complementing the system database data and historical achievement data of the target small reservoir, generate the to-be-processed system database data and to-be-processed historical achievement data. For the to-be-processed system database data, perform grid calculation to generate the rainfall information data of the target small reservoir. For the to-be-processed historical achievement data, perform feature extraction to generate feature data, and use the rainfall information data and feature data as target data; The feature data includes: Storage capacity relationship curve, discharge relationship curve, reservoir basin shape characteristic data and inflow and outflow discharge data.

5. The forecasting method according to claim 1, characterized in that: The constructing of the flood forecasting model according to the target data includes: Based on a preset distributed forecasting model, construct a distributed forecasting model applicable to the target small reservoir according to the basin data divided for the target small reservoir; And based on the target data, adjust the model parameters of the distributed forecasting model to generate a flood forecasting model applicable to the target small reservoir.

6. The forecasting method according to claim 1, characterized in that: The method further includes: according to the real-time disaster forecast issued for the target small reservoir, generate a decision for the disaster in real time to cope with the occurrence of the disaster.

7. The forecasting method according to claim 1, characterized in that: The method further includes: based on the flood forecasting model, determine the rainstorm resistance ability of the target small reservoir according to the rainfall data; Establish a flood forecasting achievement library and a rainstorm resistance ability achievement library for the target small reservoir, and upload the forecast data and rainstorm resistance ability data output by the flood forecasting model to the flood forecasting achievement library and the rainstorm resistance ability achievement library respectively; Use the comparison result between the data existing in the flood forecasting achievement library and the rainstorm resistance ability achievement library and the actual data to optimize the model parameters of the flood forecasting model.

8. The prediction method according to claim 1, characterized in that The method further includes: Based on the characteristic data of the small reservoir basin, the runoff generation and concentration characteristic data, and the natural discharge characteristic data, and according to the meteorological grid forecast rainfall data, the water level change of the target small reservoir within a preset future time is calculated in real time.

9. The prediction method according to claim 1, characterized in that The runoff generation and concentration characteristic data are used to calculate the net water volume and the converging water volume of the small reservoir.

10. A forecasting system for small reservoirs, characterized in that, The system includes: A data acquisition unit, which is used to obtain the system database data and historical result data of the target small reservoir for the target small reservoir, and preprocess the system database data and historical result data of the target small reservoir to obtain target data; A modeling unit, which is used to construct a flood forecast model according to the target data, and real-time obtain the meteorological grid forecast rainfall data of the basin where the target small reservoir is located and input it into the flood forecast model; A calculation unit, which is used to use the flood forecast model to calculate the water level change of the target small reservoir within a preset future time in real time according to the meteorological grid forecast rainfall data; A forecast unit, which is used to determine the flood occurrence time and peak flood level of the target small reservoir through the water level change, and issue a real-time disaster forecast for the target small reservoir based on the flood occurrence time and peak flood level.

Images